Moving workloads to old

Signed-off-by: Jose Santos <josantos@login1.hpcfund>


[ROCm/rocprofiler-compute commit: 989e29cf81]
This commit is contained in:
Jose Santos
2024-02-20 11:01:23 -06:00
committed by Karl W. Schulz
parent 6ac883e20e
commit 79c75edc48
9701 changed files with 4016 additions and 0 deletions
@@ -0,0 +1,168 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,grd,Workgroup_Size,LDS_Per_Workgroup,scr,vgpr,SGPR,fbar,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"__amd_rocclr_fillBuffer.kd",0,0,0,919533,919538,33554432,256,0,0,8,32,6464,0x0,0x7f539a404180,510905,510905,524288,6291456,791255,101484656,12076299622617100,12076299868527949,12076299868855467,12076299868966179
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,919533,919538,32768,256,0,0,24,24,12480,0x0,0x7f539a435100,29103,29103,512,8192,11024,1421636,12076299883226411,12076299883536030,12076299883542910,12076299883550754
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,919533,919538,4194304,256,0,0,24,24,12928,0x7f54a6102900,0x7f539a435140,214348,214348,65536,917504,141051,18053272,12076299883612759,12076299883846109,12076299883977148,12076299883980823
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,919533,919538,4194304,256,0,0,36,24,13632,0x7f54a6102800,0x7f539a435180,393217,393217,65536,1245184,183556,23413388,12076299884057155,12076299884237467,12076299884488185,12076299884558838
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,919533,919538,4194304,256,0,0,28,24,14080,0x7f54a6102700,0x7f539a4351c0,398588,398588,65536,983040,136711,17472264,12076299884591839,12076299884784344,12076299885038582,12076299885110302
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,919533,919538,4194304,256,0,0,24,24,14528,0x7f54a6102600,0x7f539a435200,214801,214801,65536,1048576,159691,20414844,12076299885131732,12076299885331861,12076299885463220,12076299885466665
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,919533,919538,4194304,256,0,0,24,24,14976,0x7f54a6102500,0x7f539a435240,217772,217772,65536,983040,151837,19401912,12076299885514403,12076299885699699,12076299885832498,12076299885835941
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,919533,919538,4194304,256,0,0,24,24,15424,0x7f54a6102400,0x7f539a435280,213089,213089,65536,1048576,146940,18850908,12076299885918775,12076299886104337,12076299886234736,12076299886238199
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,919533,919538,4194304,256,0,0,28,24,16128,0x7f54a6102300,0x7f539a4352c0,392820,392820,65536,1572864,229355,29302276,12076299886293581,12076299886473935,12076299886724174,12076299886768474
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,919533,919538,4194304,256,0,0,28,24,16832,0x7f54a6102a00,0x7f539a435300,392001,392001,65536,1179648,157851,20274332,12076299886793070,12076299886995532,12076299887245771,12076299887287509
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,919533,919538,4194304,256,0,0,24,24,17536,0x7f54a6102900,0x7f539a435340,214059,214059,65536,1114112,163347,20901004,12076299887319879,12076299887507530,12076299887638569,12076299887641777
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,919533,919538,4194304,256,0,0,24,24,18240,0x7f54a6102800,0x7f539a435380,213545,213545,65536,1114112,158333,20302232,12076299887686510,12076299887871688,12076299888002567,12076299888006064
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,919533,919538,4194304,256,0,0,24,24,18944,0x7f54a6102700,0x7f539a4353c0,212651,212651,65536,1179648,178701,22843900,12076299888075042,12076299888246086,12076299888375525,12076299888379017
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,919533,919538,4194304,256,0,0,28,24,19904,0x7f54a6102600,0x7f539a435400,398465,398465,65536,1835008,254566,32610180,12076299888427387,12076299888607044,12076299888860963,12076299888929360
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,919533,919538,4194304,256,0,0,28,24,20608,0x7f54a6102500,0x7f539a435440,397484,397484,65536,1310720,177927,22757004,12076299888953455,12076299889151681,12076299889405280,12076299889475224
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,919533,919538,4194304,256,0,0,24,24,21312,0x7f54a6102400,0x7f539a435480,209321,209321,65536,1245184,181910,23327888,12076299889500501,12076299889689118,12076299889817278,12076299889820717
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,919533,919538,4194304,256,0,0,24,24,22016,0x7f54a6102300,0x7f539a4354c0,213411,213411,65536,1310720,180276,23055180,12076299889872613,12076299890057756,12076299890188476,12076299890191896
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,919533,919538,4194304,256,0,0,24,24,22720,0x7f54a6102a00,0x7f539a435500,220089,220089,65536,1310720,180034,23026544,12076299890256567,12076299890424475,12076299890559354,12076299890562736
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,919533,919538,4194304,256,0,0,28,24,23680,0x7f54a6102900,0x7f539a435540,398091,398091,65536,2097152,286809,36778484,12076299890615644,12076299890793913,12076299891048471,12076299891092440
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,919533,919538,4194304,256,0,0,28,24,24384,0x7f54a6102800,0x7f539a435580,399921,399921,65536,1441792,196270,25189740,12076299891117106,12076299891306070,12076299891561909,12076299891628837
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,919533,919538,4194304,256,0,0,24,24,25088,0x7f54a6102700,0x7f539a4355c0,210100,210100,65536,1376256,190752,24365644,12076299891652300,12076299891837907,12076299891966067,12076299891969560
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,919533,919538,4194304,256,0,0,24,24,25792,0x7f54a6102600,0x7f539a435600,208553,208553,65536,1507328,223099,28554880,12076299892027548,12076299892208945,12076299892336305,12076299892339918
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,919533,919538,4194304,256,0,0,24,24,26496,0x7f54a6102500,0x7f539a435640,212075,212075,65536,1441792,200081,25562192,12076299892403136,12076299892573263,12076299892702383,12076299892705808
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,919533,919538,4194304,256,0,0,28,24,27712,0x7f54a6102400,0x7f539a435680,398945,398945,65536,2359296,321994,41224232,12076299892749179,12076299892932942,12076299893188460,12076299893258766
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,919533,919538,4194304,256,0,0,28,24,28416,0x7f54a6102300,0x7f539a4356c0,394531,394531,65536,1572864,212336,27147804,12076299893282670,12076299893472299,12076299893723817,12076299893791165
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,919533,919538,4194304,256,0,0,24,24,29120,0x7f54a6102a00,0x7f539a435700,215913,215913,65536,1507328,209863,26846108,12076299893815110,12076299894006696,12076299894139015,12076299894142278
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,919533,919538,4194304,256,0,0,24,24,30080,0x7f54a6102900,0x7f539a435740,211651,211651,65536,1703936,230651,29594612,12076299894195176,12076299894374854,12076299894504293,12076299894507787
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,919533,919538,4194304,256,0,0,24,24,30784,0x7f54a6102800,0x7f539a435780,216225,216225,65536,1572864,213205,27280232,12076299894573189,12076299894740452,12076299894873412,12076299894876943
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,919533,919538,4194304,256,0,0,28,24,32000,0x7f54a6102700,0x7f539a4357c0,391100,391100,65536,2621440,361835,46493032,12076299894928780,12076299895117410,12076299895367809,12076299895436623
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,919533,919538,4194304,256,0,0,28,24,32960,0x7f54a6102600,0x7f539a435800,395977,395977,65536,1703936,230470,29523928,12076299895464836,12076299895648928,12076299895902526,12076299895969594
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,919533,919538,4194304,256,0,0,24,24,33920,0x7f54a6102500,0x7f539a435840,211483,211483,65536,1638400,227044,29065240,12076299895996444,12076299896188125,12076299896317404,12076299896321187
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,919533,919538,4194304,256,0,0,24,24,34880,0x7f54a6102400,0x7f539a435880,218505,218505,65536,1900544,268741,34343524,12076299896374006,12076299896548923,12076299896683802,12076299896687218
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,919533,919538,4194304,256,0,0,24,24,35840,0x7f54a6102300,0x7f539a4358c0,278476,278476,65536,1703936,232489,29686064,12076299896750916,12076299896920441,12076299897092280,12076299897096027
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,919533,919538,4194304,256,0,0,28,24,37312,0x7f54a6102a00,0x7f539a435900,400697,400697,65536,2883584,394892,50507760,12076299897149537,12076299897335319,12076299897592437,12076299897661218
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,919533,919538,4194304,256,0,0,28,24,38272,0x7f54a6102900,0x7f539a435940,389276,389276,65536,1835008,245721,31376504,12076299897684311,12076299897872916,12076299898121395,12076299898189369
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,919533,919538,4194304,256,0,0,24,24,39232,0x7f54a6102800,0x7f539a435980,216113,216113,65536,1769472,278643,35676384,12076299898214446,12076299898407633,12076299898540753,12076299898544099
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,919533,919538,4194304,256,0,0,24,24,40192,0x7f54a6102700,0x7f539a4359c0,223708,223708,65536,2097152,328429,42225068,12076299898595925,12076299898772751,12076299898908751,12076299898912052
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,919533,919538,4194304,256,0,0,24,24,41152,0x7f54a6102600,0x7f539a435a00,279257,279257,65536,1835008,248776,31844500,12076299898977955,12076299899151949,12076299899326669,12076299899330370
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,919533,919538,4194304,256,0,0,28,24,42624,0x7f54a6102500,0x7f539a435a40,396443,396443,65536,3145728,432501,55279636,12076299899374973,12076299899558667,12076299899812426,12076299899880893
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,919533,919538,4194304,256,0,0,28,24,43584,0x7f54a6102400,0x7f539a435a80,397537,397537,65536,1966080,269365,34482060,12076299899905459,12076299900098665,12076299900353703,12076299900423141
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,919533,919538,4194304,256,0,0,24,24,44544,0x7f54a6102300,0x7f539a435ac0,214636,214636,65536,1900544,271973,34786028,12076299900445933,12076299900640422,12076299900772101,12076299900775465
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,919533,919538,4194304,256,0,0,24,24,45760,0x7f54a6102a00,0x7f539a435b00,215705,215705,65536,2293760,305665,39246868,12076299900827522,12076299901005220,12076299901138659,12076299901142448
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,919533,919538,4194304,256,0,0,24,24,46720,0x7f54a6102900,0x7f539a435b40,276028,276028,65536,1966080,284612,36382880,12076299901206637,12076299901379298,12076299901551777,12076299901555385
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,919533,919538,4194304,256,0,0,28,24,48448,0x7f54a6102800,0x7f539a435b80,414577,414577,65536,3407872,461566,59220616,12076299901598976,12076299901782816,12076299902049374,12076299902118672
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,919533,919538,4194304,256,0,0,28,24,49408,0x7f54a6102700,0x7f539a435bc0,395507,395507,65536,2097152,276323,35383616,12076299902143187,12076299902331613,12076299902585052,12076299902626285
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,919533,919538,4194304,256,0,0,24,24,50368,0x7f54a6102600,0x7f539a435c00,213993,213993,65536,2031616,292874,37532392,12076299902655550,12076299902832890,12076299902964090,12076299902967529
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,919533,919538,4194304,256,0,0,24,24,51584,0x7f54a6102500,0x7f539a435c40,227012,227012,65536,2490368,335111,42932600,12076299903018795,12076299903201048,12076299903341528,12076299903345021
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,919533,919538,4194304,256,0,0,24,24,52544,0x7f54a6102400,0x7f539a435c80,211969,211969,65536,2097152,290284,37168948,12076299903410232,12076299903577687,12076299903707926,12076299903711522
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,919533,919538,4194304,256,0,0,28,24,54272,0x7f54a6102300,0x7f539a435cc0,405019,405019,65536,3670016,489204,62811988,12076299903766123,12076299903942645,12076299904203283,12076299904274047
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,919533,919538,4194304,256,0,0,28,24,55488,0x7f54a6102a00,0x7f539a435d00,387121,387121,65536,2228224,300500,38430084,12076299904299815,12076299904489682,12076299904738801,12076299904806727
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,919533,919538,4194304,256,0,0,24,24,56704,0x7f54a6102900,0x7f539a435d40,212323,212323,65536,2162688,296477,38039316,12076299904831223,12076299905016239,12076299905145678,12076299905149134
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,919533,919538,4194304,256,0,0,24,24,58176,0x7f54a6102800,0x7f539a435d80,227017,227017,65536,2686976,387552,49471624,12076299905201812,12076299905382957,12076299905524076,12076299905527427
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,919533,919538,4194304,256,0,0,24,24,59392,0x7f54a6102700,0x7f539a435dc0,208539,208539,65536,2228224,306254,39183484,12076299905592618,12076299905760395,12076299905888235,12076299905891694
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,919533,919538,4194304,256,0,0,28,24,61376,0x7f54a6102600,0x7f539a435e00,406425,406425,65536,3932160,532180,67960200,12076299905944893,12076299906131113,12076299906393352,12076299906437829
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,919533,919538,4194304,256,0,0,28,24,62592,0x7f54a6102500,0x7f539a435e40,402036,402036,65536,2359296,313357,40150908,12076299906463286,12076299906646311,12076299906904229,12076299906945743
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,919533,919538,4194304,256,0,0,24,24,63808,0x7f54a6102400,0x7f539a435e80,210913,210913,65536,2293760,340510,43490748,12076299906976740,12076299907159908,12076299907289827,12076299907293609
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,919533,919538,4194304,256,0,0,24,24,65280,0x7f54a6102300,0x7f539a435ec0,222268,222268,65536,2883584,431367,55156600,12076299907346998,12076299907529186,12076299907666785,12076299907670369
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,919533,919538,4194304,256,0,0,24,24,66496,0x7f54a6102a00,0x7f539a435f00,212353,212353,65536,2359296,349015,44610384,12076299907735420,12076299907901504,12076299908032223,12076299908035578
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,919533,919538,4194304,256,0,0,28,24,68480,0x7f54a6102900,0x7f539a435f40,406948,406948,65536,4194304,581524,74373760,12076299908090300,12076299908265662,12076299908527741,12076299908596621
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,919533,919538,4194304,256,0,0,28,24,69696,0x7f54a6102800,0x7f539a435f80,387321,387321,65536,2490368,330981,42359592,12076299908623451,12076299908804699,12076299909054138,12076299909124372
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,919533,919538,4194304,256,0,0,24,24,70912,0x7f54a6102700,0x7f539a435fc0,214035,214035,65536,2424832,354206,45414804,12076299909149408,12076299909335257,12076299909467096,12076299909470314
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,919533,919538,4194304,256,0,0,24,24,72384,0x7f54a6102600,0x7f539a436000,220241,220241,65536,3080192,450511,57638424,12076299909524826,12076299909690295,12076299909827574,12076299909830804
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,919533,919538,4194304,256,0,0,24,24,73600,0x7f54a6102500,0x7f539a436040,214363,214363,65536,2490368,355067,45513180,12076299909894413,12076299910060853,12076299910192532,12076299910196484
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,919533,919538,4194304,256,0,0,28,24,75840,0x7f54a6102400,0x7f539a436080,408577,408577,65536,4456448,579780,74345736,12076299910247970,12076299910427571,12076299910691410,12076299910758899
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,919533,919538,4194304,256,0,0,28,24,77056,0x7f54a6102300,0x7f539a4360c0,394324,394324,65536,2621440,343762,44075296,12076299910782082,12076299910970928,12076299911224687,12076299911292661
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,919533,919538,4194304,256,0,0,24,24,78272,0x7f54a6102a00,0x7f539a436100,213665,213665,65536,2555904,367477,47012136,12076299911317978,12076299911506286,12076299911638445,12076299911641600
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,919533,919538,4194304,256,0,0,24,24,80000,0x7f54a6102900,0x7f539a436140,231796,231796,65536,3276800,477202,60917452,12076299911693586,12076299911867244,12076299912011883,12076299912015815
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,919533,919538,4194304,256,0,0,24,24,81216,0x7f54a6102800,0x7f539a436180,211569,211569,65536,2621440,363595,46544632,12076299912081447,12076299912249162,12076299912379561,12076299912383218
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,919533,919538,4194304,256,0,0,28,24,83456,0x7f54a6102700,0x7f539a4361c0,411667,411667,65536,4718592,656067,84140872,12076299912435525,12076299912608040,12076299912874118,12076299912917100
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,919533,919538,4194304,256,0,0,28,24,84928,0x7f54a6102600,0x7f539a436200,391777,391777,65536,2752512,361371,46213224,12076299912940474,12076299913132997,12076299913385316,12076299913455200
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,919533,919538,4194304,256,0,0,24,24,86400,0x7f54a6102500,0x7f539a436240,219084,219084,65536,2686976,394766,50465020,12076299913480026,12076299913665154,12076299913800354,12076299913803758
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,919533,919538,4194304,256,0,0,24,24,88128,0x7f54a6102400,0x7f539a436280,241329,241329,65536,3473408,556381,71237200,12076299913855885,12076299914037472,12076299914188192,12076299914191569
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,919533,919538,4194304,256,0,0,24,24,89600,0x7f54a6102300,0x7f539a4362c0,212492,212492,65536,2752512,386737,49462240,12076299914270686,12076299914438430,12076299914568990,12076299914572587
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,919533,919538,4194304,256,0,0,28,24,92096,0x7f54a6102a00,0x7f539a436300,413625,413625,65536,4980736,659950,84737104,12076299914624844,12076299914798909,12076299915064507,12076299915115676
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,919533,919538,4194304,256,0,0,28,24,93568,0x7f54a6102900,0x7f539a436340,391372,391372,65536,2883584,385374,49326632,12076299915140793,12076299915326906,12076299915578904,12076299915627608
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,919533,919538,4194304,256,0,0,24,24,95040,0x7f54a6102800,0x7f539a436380,218273,218273,65536,2818048,419903,53706572,12076299915647925,12076299915837143,12076299915972022,12076299915975454
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,919533,919538,4194304,256,0,0,24,24,96768,0x7f54a6102700,0x7f539a4363c0,251587,251587,65536,3670016,530319,67833120,12076299916030316,12076299916209301,12076299916366740,12076299916370618
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,919533,919538,4194304,256,0,0,24,24,98240,0x7f54a6102600,0x7f539a436400,218801,218801,65536,2883584,443148,56649432,12076299916433185,12076299916599219,12076299916734578,12076299916737931
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,919533,919538,4194304,256,0,0,28,24,100736,0x7f54a6102500,0x7f539a436440,404363,404363,65536,5177344,685648,87529560,12076299916788315,12076299916963057,12076299917224656,12076299917275029
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,919533,919538,4194304,256,0,0,28,24,102208,0x7f54a6102400,0x7f539a436480,397073,397073,65536,3014656,398099,50926840,12076299917298503,12076299917487055,12076299917743373,12076299917791469
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,919533,919538,4194304,256,0,0,24,24,103680,0x7f54a6102300,0x7f539a4364c0,223547,223547,65536,2949120,499932,63983460,12076299917814452,12076299918004492,12076299918142411,12076299918145928
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,919533,919538,4194304,256,0,0,24,24,105664,0x7f54a6102a00,0x7f539a436500,264505,264505,65536,3866624,590898,75688444,12076299918198806,12076299918375530,12076299918542569,12076299918545951
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,919533,919538,4194304,256,0,0,24,24,107136,0x7f54a6102900,0x7f539a436540,219499,219499,65536,3014656,407783,52170012,12076299918610331,12076299918775208,12076299918910087,12076299918914416
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,919533,919538,4194304,256,0,0,28,24,109888,0x7f54a6102800,0x7f539a436580,408329,408329,65536,5439488,728725,93307600,12076299918965180,12076299919147526,12076299919409925,12076299919461152
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,919533,919538,4194304,256,0,0,28,24,111360,0x7f54a6102700,0x7f539a4365c0,394907,394907,65536,3145728,420648,53828316,12076299919484686,12076299919670243,12076299919924802,12076299919972953
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,919533,919538,4194304,256,0,0,24,24,112832,0x7f54a6102600,0x7f539a436600,216569,216569,65536,3080192,476862,60953660,12076299919995876,12076299920187361,12076299920321120,12076299920325108
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,919533,919538,4194304,256,0,0,24,24,114816,0x7f54a6102500,0x7f539a436640,277483,277483,65536,4063232,561121,71822404,12076299920371744,12076299920556159,12076299920730558,12076299920734308
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,919533,919538,4194304,256,0,0,24,24,116288,0x7f54a6102400,0x7f539a436680,212657,212657,65536,3145728,427720,54716052,12076299920799579,12076299920963677,12076299921095036,12076299921099006
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,919533,919538,4194304,256,0,0,28,24,119040,0x7f54a6102300,0x7f539a4366c0,400571,400571,65536,5701632,743935,94963868,12076299921150992,12076299921329115,12076299921588633,12076299921637066
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,919533,919538,4194304,256,0,0,28,24,120768,0x7f54a6102a00,0x7f539a436700,395201,395201,65536,3276800,447138,57230528,12076299921661822,12076299921846872,12076299922101911,12076299922150851
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,919533,919538,4194304,256,0,0,24,24,122496,0x7f54a6102900,0x7f539a436740,223844,223844,65536,3211264,482379,61662540,12076299922173773,12076299922362229,12076299922500629,12076299922504287
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,919533,919538,4194304,256,0,0,24,24,124736,0x7f54a6102800,0x7f539a436780,288777,288777,65536,4259840,607340,77619552,12076299922548660,12076299922731187,12076299922914547,12076299922917856
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,919533,919538,4194304,256,0,0,24,24,126464,0x7f54a6102700,0x7f539a4367c0,226412,226412,65536,3276800,535703,68596192,12076299922981244,12076299923153745,12076299923293745,12076299923297732
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,919533,919538,4194304,256,0,0,20,24,127936,0x7f54a6102600,0x7f539a436800,410545,410545,65536,7733248,974305,124912844,12076299923349478,12076299923546063,12076299923812782,12076299923859997
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,919533,919538,4194304,256,0,0,28,24,129664,0x7f54a6102500,0x7f539a436840,402724,402724,65536,3407872,454256,58389876,12076299923882859,12076299924073581,12076299924333739,12076299924382588
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,919533,919538,4194304,256,0,0,24,24,131392,0x7f54a6102400,0x7f539a436880,217577,217577,65536,3342336,456477,58455472,12076299924407815,12076299924597898,12076299924732297,12076299924736025
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,919533,919538,4194304,256,0,0,24,24,133632,0x7f54a6102300,0x7f539a4368c0,302051,302051,65536,4456448,640004,82269060,12076299924792089,12076299924963496,12076299925155015,12076299925203845
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,919533,919538,4194304,256,0,0,24,24,135360,0x7f54a6102a00,0x7f539a436900,215145,215145,65536,3538944,490420,62641808,12076299925240813,12076299925410854,12076299925543973,12076299925547663
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,919533,919538,4194304,256,0,0,20,24,136832,0x7f54a6102900,0x7f539a436940,437076,437076,65536,8978432,1131317,144600808,12076299925593228,12076299925771972,12076299926056770,12076299926103917
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,919533,919538,4194304,256,0,0,28,24,138560,0x7f54a6102800,0x7f539a436980,389345,389345,65536,3670016,479222,61424280,12076299926122672,12076299926315489,12076299926567488,12076299926614336
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,919533,919538,4194304,256,0,0,24,24,140288,0x7f54a6102700,0x7f539a4369c0,219715,219715,65536,3604480,543259,69579764,12076299926638932,12076299926830206,12076299926966046,12076299926969756
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,919533,919538,4194304,256,0,0,24,24,142784,0x7f54a6102600,0x7f539a436a00,330785,330785,65536,4849664,735877,94024956,12076299927026863,12076299927213404,12076299927424123,12076299927471599
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,919533,919538,4194304,256,0,0,24,24,144768,0x7f54a6102500,0x7f539a436a40,219067,219067,65536,3801088,601072,76954544,12076299927509309,12076299927675482,12076299927810841,12076299927814526
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,919533,919538,4194304,256,0,0,20,24,145728,0x7f54a6102400,0x7f539a436a80,470385,470385,65536,14548992,1832714,234663380,12076299927866513,12076299928051800,12076299928359478,12076299928408891
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,919533,919538,4194304,256,0,0,28,24,147712,0x7f54a6102300,0x7f539a436ac0,407483,407483,65536,3932160,522533,67088484,12076299928434649,12076299928618677,12076299928882196,12076299928929148
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,919533,919538,4194304,256,0,0,24,24,149696,0x7f54a6102a00,0x7f539a436b00,216841,216841,65536,3866624,602869,77157604,12076299928951980,12076299929145874,12076299929280274,12076299929284548
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,919533,919538,4194304,256,0,0,24,24,152192,0x7f54a6102900,0x7f539a436b40,356148,356148,65536,5242880,750550,96037116,12076299929336835,12076299929513392,12076299929741071,12076299929788054
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,919533,919538,4194304,256,0,0,24,24,154176,0x7f54a6102800,0x7f539a436b80,221153,221153,65536,4063232,581531,74441840,12076299929823279,12076299929994190,12076299930131789,12076299930135400
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,919533,919538,4194304,256,0,0,20,24,155648,0x7f54a6102700,0x7f539a436bc0,504355,504355,65536,10027008,1259275,161391076,12076299930188228,12076299930365228,12076299930695306,12076299930742458
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,919533,919538,4194304,256,0,0,28,24,157632,0x7f54a6102600,0x7f539a436c00,398585,398585,65536,4194304,600322,76837356,12076299930765611,12076299930949865,12076299931207944,12076299931255491
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,919533,919538,4194304,256,0,0,24,24,159616,0x7f54a6102500,0x7f539a436c40,224748,224748,65536,4128768,582931,74613476,12076299931280878,12076299931469170,12076299931608530,12076299931615480
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,919533,919538,4194304,256,0,0,24,24,162368,0x7f54a6102400,0x7f539a436c80,381473,381473,65536,5636096,774439,99074516,12076299931666515,12076299931843887,12076299932089006,12076299932138602
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,919533,919538,4194304,256,0,0,24,24,164608,0x7f54a6102300,0x7f539a436cc0,219852,219852,65536,4587520,636011,81425624,12076299932175792,12076299932348525,12076299932484204,12076299932487551
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,919533,919538,4194304,256,0,0,20,24,166336,0x7f54a6102a00,0x7f539a436d00,575009,575009,65536,11075584,1395290,178377424,12076299932539177,12076299932714923,12076299933092362,12076299933139863
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,919533,919538,4194304,256,0,0,28,24,168576,0x7f54a6102900,0x7f539a436d40,404540,404540,65536,4718592,639390,82178140,12076299933164709,12076299933360200,12076299933622279,12076299933668666
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,919533,919538,4194304,256,0,0,24,24,170816,0x7f54a6102800,0x7f539a436d80,232913,232913,65536,4653056,733715,94047532,12076299933691589,12076299933886118,12076299934031557,12076299934035287
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,919533,919538,4194304,256,0,0,24,24,174080,0x7f54a6102700,0x7f539a436dc0,438427,438427,65536,6422528,893536,115027880,12076299934088015,12076299934265956,12076299934546115,12076299934570151
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,919533,919538,4194304,256,0,0,24,24,176576,0x7f54a6102600,0x7f539a436e00,223985,223985,65536,5111808,810645,103823888,12076299934628580,12076299934794754,12076299934934433,12076299934937925
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,919533,919538,4194304,256,0,0,20,24,177792,0x7f54a6102500,0x7f539a436e40,647819,647819,65536,15007744,1882223,240987232,12076299934984261,12076299935169472,12076299935595390,12076299935645730
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,919533,919538,4194304,256,0,0,28,24,180288,0x7f54a6102400,0x7f539a436e80,395465,395465,65536,5242880,718781,92425140,12076299935670536,12076299935861149,12076299936117948,12076299936166809
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,919533,919538,4194304,256,0,0,24,24,182784,0x7f54a6102300,0x7f539a436ec0,231915,231915,65536,5177344,862288,110298624,12076299936191294,12076299936379226,12076299936521786,12076299936525275
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,919533,919538,4194304,256,0,0,24,24,186304,0x7f54a6102a00,0x7f539a436f00,531153,531153,65536,7208960,1062588,135960020,12076299936579065,12076299936753305,12076299937096983,12076299937146670
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,919533,919538,4194304,256,0,0,24,24,189312,0x7f54a6102900,0x7f539a436f40,244604,244604,65536,6160384,911662,116689268,12076299937181705,12076299937358422,12076299937510901,12076299937514073
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,919533,919538,4194304,256,0,0,20,24,190784,0x7f54a6102800,0x7f539a436f80,784073,784073,65536,17104896,2144722,274642756,12076299937565298,12076299937740660,12076299938258098,12076299938306686
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,919533,919538,4194304,256,0,0,28,24,193792,0x7f54a6102700,0x7f539a436fc0,459491,459491,65536,6291456,960581,122933792,12076299938335519,12076299938523857,12076299938824815,12076299938871986
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,919533,919538,4194304,256,0,0,24,24,196800,0x7f54a6102600,0x7f539a437000,248777,248777,65536,6225920,963195,123194468,12076299938888657,12076299939095694,12076299939252653,12076299939256160
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,919533,919538,4194304,256,0,0,24,24,201088,0x7f54a6102500,0x7f539a437040,592603,592603,65536,8781824,1248748,158885572,12076299939311473,12076299939490092,12076299939875530,12076299939922749
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,919533,919538,4194304,256,0,0,24,24,204608,0x7f54a6102400,0x7f539a437080,278337,278337,65536,7208960,1042106,133458592,12076299939958085,12076299940132809,12076299940309768,12076299940313405
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,919533,919538,4194304,256,0,0,20,24,206080,0x7f54a6102300,0x7f539a4370c0,924339,924339,65536,19202048,2411222,308188192,12076299940358298,12076299940542247,12076299941152964,12076299941201095
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,919533,919538,4194304,256,0,0,28,24,209600,0x7f54a6102a00,0x7f539a437100,504497,504497,65536,7340032,977946,125177312,12076299941224939,12076299941418083,12076299941749602,12076299941796631
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,919533,919538,4194304,256,0,0,24,24,213120,0x7f54a6102900,0x7f539a437140,282692,282692,65536,7274496,1062869,135987200,12076299941819424,12076299942010560,12076299942189760,12076299942193369
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,919533,919538,4194304,256,0,0,24,24,218176,0x7f54a6102800,0x7f539a437180,698657,698657,65536,10354688,1488537,190776492,12076299942245826,12076299942421598,12076299942878236,12076299942925399
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,919533,919538,4194304,256,0,0,24,24,222208,0x7f54a6102700,0x7f539a4371c0,312723,312723,65536,8257536,1184176,151611196,12076299942961436,12076299943135035,12076299943334394,12076299943383300
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,919533,919538,4194304,256,0,0,20,24,223936,0x7f54a6102600,0x7f539a437200,1066265,1066265,65536,21299200,2669401,341698144,12076299943407475,12076299943595033,12076299944299350,12076299944347582
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,919533,919538,4194304,256,0,0,28,24,227968,0x7f54a6102500,0x7f539a437240,606580,606580,65536,8388608,1172274,150354736,12076299944372919,12076299944560949,12076299944959987,12076299945015463
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,919533,919538,4194304,256,0,0,24,24,232000,0x7f54a6102400,0x7f539a437280,320545,320545,65536,8323072,1287436,164707516,12076299945045129,12076299945260145,12076299945464144,12076299945514651
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,919533,919538,4194304,256,0,0,24,24,237824,0x7f54a6102300,0x7f539a4372c0,803284,803284,65536,11927552,1690594,216700224,12076299945538165,12076299945723343,12076299946249901,12076299946298969
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,919533,919538,4194304,256,0,0,24,24,242368,0x7f54a6102a00,0x7f539a437300,350361,350361,65536,9306112,1410890,180543672,12076299946334164,12076299946504460,12076299946728939,12076299946776927
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,919533,919538,4194304,256,0,0,20,24,243584,0x7f54a6102900,0x7f539a437340,1207459,1207459,65536,29163520,3650494,467433600,12076299946800210,12076299946987497,12076299947787814,12076299947857215
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,919533,919538,4194304,256,0,0,28,24,248128,0x7f54a6102800,0x7f539a437380,635801,635801,65536,9437184,1240813,159316744,12076299947880518,12076299948066852,12076299948486850,12076299948555883
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,919533,919538,4194304,256,0,0,24,24,252672,0x7f54a6102700,0x7f539a4373c0,354308,354308,65536,9371648,1435958,183748864,12076299948580429,12076299948765249,12076299948992768,12076299949039592
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,919533,919538,4194304,256,0,0,24,24,259264,0x7f54a6102600,0x7f539a437400,910449,910449,65536,13500416,1900792,243030416,12076299949064489,12076299949250527,12076299949848604,12076299949915520
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,919533,919538,4194304,256,0,0,24,24,264832,0x7f54a6102500,0x7f539a437440,418508,418508,65536,11403264,1737440,222385492,12076299949952028,12076299950134363,12076299950403962,12076299950472906
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,919533,919538,4194304,256,0,0,20,24,266304,0x7f54a6102400,0x7f539a437480,1487497,1487497,65536,33357824,4175603,534728884,12076299950496259,12076299950682680,12076299951668276,12076299951735442
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,919533,919538,4194304,256,0,0,28,24,271872,0x7f54a6102300,0x7f539a4374c0,803932,803932,65536,11534336,1585432,203111956,12076299951753095,12076299951954514,12076299952486832,12076299952557250
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,919533,919538,4194304,256,0,0,24,24,277440,0x7f54a6102a00,0x7f539a437500,423657,423657,65536,11534336,1744628,223243148,12076299952580894,12076299952773871,12076299953047149,12076299953116068
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,919533,919538,4194304,256,0,0,12,24,279936,0x7f54a6102900,0x7f539a437540,1133852,1133852,65536,19267584,2424400,310155488,12076299953145423,12076299953332268,12076299954075145,12076299954143688
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,919533,919538,4194304,256,0,0,24,24,286528,0x7f54a6102800,0x7f539a437580,489825,489825,65536,13500416,2051702,262603160,12076299954186958,12076299954357063,12076299954674342,12076299954742280
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,919533,919538,4194304,256,0,0,20,24,288000,0x7f54a6102700,0x7f539a4375c0,1770043,1770043,65536,37552128,4700917,601623552,12076299954771234,12076299954958340,12076299956130175,12076299956200400
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,919533,919538,4194304,256,0,0,32,24,294592,0x7f54a6102600,0x7f539a437600,918673,918673,65536,13631488,1853505,237302996,12076299956233161,12076299956412894,12076299957022171,12076299957090504
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,919533,919538,4194304,256,0,0,24,24,301184,0x7f54a6102500,0x7f539a437640,492492,492492,65536,13631488,2101299,269030052,12076299957108227,12076299957312410,12076299957632248,12076299957700478
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,919533,919538,4194304,256,0,0,12,24,304960,0x7f54a6102400,0x7f539a437680,1336121,1336121,65536,21692416,2755337,352715068,12076299957729702,12076299957909687,12076299958788403,12076299958858109
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,919533,919538,4194304,256,0,0,24,24,313600,0x7f54a6102300,0x7f539a4376c0,629595,629595,65536,17694720,2657523,340168852,12076299958895098,12076299959061521,12076299959471600,12076299959540468
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,919533,919538,4194304,256,0,0,20,24,314816,0x7f54a6102a00,0x7f539a437700,2332353,2332353,65536,57475072,7193193,920743084,12076299959563090,12076299959755438,12076299961303271,12076299961372392
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,919533,919538,4194304,256,0,0,20,24,317568,0x7f54a6102900,0x7f539a437740,1202236,1202236,65536,19660800,2472188,316437508,12076299961406285,12076299961593830,12076299962388866,12076299962457359
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,919533,919538,4194304,256,0,0,12,24,320320,0x7f54a6102800,0x7f539a437780,640153,640153,65536,20381696,2572355,329398180,12076299962487775,12076299962673505,12076299963088863,12076299963156267
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,919533,919538,4194304,256,0,0,12,24,324096,0x7f54a6102700,0x7f539a4377c0,1757699,1757699,65536,28704768,3615591,462741080,12076299963183398,12076299963372381,12076299964531576,12076299964599109
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,919533,919538,4194304,256,0,0,12,24,328896,0x7f54a6102600,0x7f539a437800,1201873,1201873,65536,36634624,4670909,597570484,12076299964644974,12076299964814775,12076299965601491,12076299965672544
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,919533,919538,4194304,256,0,0,20,24,330112,0x7f54a6102500,0x7f539a437840,4584116,4584116,65536,105840640,13239672,1694957244,12076299965707038,12076299965893490,12076299968943876,12076299969024754
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,919533,919538,4194304,256,0,0,20,24,332864,0x7f54a6102400,0x7f539a437880,2323753,2323753,65536,38535168,4844852,619388704,12076299969050391,12076299969242114,12076299970786267,12076299970853623
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,919533,919538,4194304,256,0,0,12,24,335616,0x7f54a6102300,0x7f539a4378c0,1203387,1203387,65536,39124992,4926957,630479052,12076299970884630,12076299971076346,12076299971867542,12076299971937918
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,919533,919538,4194304,256,0,0,12,24,339392,0x7f54a6102a00,0x7f539a437900,3442505,3442505,65536,55771136,7005437,897087700,12076299971961672,12076299972158581,12076299974440650,12076299974508375
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,919533,919538,4194304,256,0,0,12,24,344192,0x7f54a6102900,0x7f539a437940,2323300,2323300,65536,72548352,9110641,1166105176,12076299974553378,12076299974721449,12076299976257602,12076299976325552
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,919533,919538,4194304,256,0,0,20,24,345408,0x7f54a6102800,0x7f539a437980,9086817,9086817,65536,210698240,26341194,3373172476,12076299976350268,12076299976542880,12076299982597252,12076299982669983
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,919533,919538,4194304,256,0,0,20,24,348160,0x7f54a6102700,0x7f539a4379c0,4573883,4573883,65536,76283904,9551789,1222432152,12076299982699107,12076299982887171,12076299985928917,12076299985985855
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,919533,919538,4194304,256,0,0,12,24,350912,0x7f54a6102600,0x7f539a437a00,2328849,2328849,65536,77398016,9707252,1242251888,12076299986021972,12076299986298995,12076299987838668,12076299987886678
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,919533,919538,4194304,256,0,0,12,24,0,0x7f54a6102500,0x7f539a437a40,6812940,6812940,65536,110821376,13888106,1777123712,12076299987917555,12076299988114347,12076299992641046,12076299992713007
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid grd Workgroup_Size LDS_Per_Workgroup scr vgpr SGPR fbar sig obj GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 __amd_rocclr_fillBuffer.kd 0 0 0 919533 919538 33554432 256 0 0 8 32 6464 0x0 0x7f539a404180 510905 510905 524288 6291456 791255 101484656 12076299622617100 12076299868527949 12076299868855467 12076299868966179
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 919533 919538 32768 256 0 0 24 24 12480 0x0 0x7f539a435100 29103 29103 512 8192 11024 1421636 12076299883226411 12076299883536030 12076299883542910 12076299883550754
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 4 919533 919538 4194304 256 0 0 24 24 12928 0x7f54a6102900 0x7f539a435140 214348 214348 65536 917504 141051 18053272 12076299883612759 12076299883846109 12076299883977148 12076299883980823
5 3 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 6 919533 919538 4194304 256 0 0 36 24 13632 0x7f54a6102800 0x7f539a435180 393217 393217 65536 1245184 183556 23413388 12076299884057155 12076299884237467 12076299884488185 12076299884558838
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 8 919533 919538 4194304 256 0 0 28 24 14080 0x7f54a6102700 0x7f539a4351c0 398588 398588 65536 983040 136711 17472264 12076299884591839 12076299884784344 12076299885038582 12076299885110302
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 10 919533 919538 4194304 256 0 0 24 24 14528 0x7f54a6102600 0x7f539a435200 214801 214801 65536 1048576 159691 20414844 12076299885131732 12076299885331861 12076299885463220 12076299885466665
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 12 919533 919538 4194304 256 0 0 24 24 14976 0x7f54a6102500 0x7f539a435240 217772 217772 65536 983040 151837 19401912 12076299885514403 12076299885699699 12076299885832498 12076299885835941
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 14 919533 919538 4194304 256 0 0 24 24 15424 0x7f54a6102400 0x7f539a435280 213089 213089 65536 1048576 146940 18850908 12076299885918775 12076299886104337 12076299886234736 12076299886238199
10 8 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 16 919533 919538 4194304 256 0 0 28 24 16128 0x7f54a6102300 0x7f539a4352c0 392820 392820 65536 1572864 229355 29302276 12076299886293581 12076299886473935 12076299886724174 12076299886768474
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 18 919533 919538 4194304 256 0 0 28 24 16832 0x7f54a6102a00 0x7f539a435300 392001 392001 65536 1179648 157851 20274332 12076299886793070 12076299886995532 12076299887245771 12076299887287509
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 20 919533 919538 4194304 256 0 0 24 24 17536 0x7f54a6102900 0x7f539a435340 214059 214059 65536 1114112 163347 20901004 12076299887319879 12076299887507530 12076299887638569 12076299887641777
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 22 919533 919538 4194304 256 0 0 24 24 18240 0x7f54a6102800 0x7f539a435380 213545 213545 65536 1114112 158333 20302232 12076299887686510 12076299887871688 12076299888002567 12076299888006064
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 24 919533 919538 4194304 256 0 0 24 24 18944 0x7f54a6102700 0x7f539a4353c0 212651 212651 65536 1179648 178701 22843900 12076299888075042 12076299888246086 12076299888375525 12076299888379017
15 13 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 26 919533 919538 4194304 256 0 0 28 24 19904 0x7f54a6102600 0x7f539a435400 398465 398465 65536 1835008 254566 32610180 12076299888427387 12076299888607044 12076299888860963 12076299888929360
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 28 919533 919538 4194304 256 0 0 28 24 20608 0x7f54a6102500 0x7f539a435440 397484 397484 65536 1310720 177927 22757004 12076299888953455 12076299889151681 12076299889405280 12076299889475224
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 30 919533 919538 4194304 256 0 0 24 24 21312 0x7f54a6102400 0x7f539a435480 209321 209321 65536 1245184 181910 23327888 12076299889500501 12076299889689118 12076299889817278 12076299889820717
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 32 919533 919538 4194304 256 0 0 24 24 22016 0x7f54a6102300 0x7f539a4354c0 213411 213411 65536 1310720 180276 23055180 12076299889872613 12076299890057756 12076299890188476 12076299890191896
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 34 919533 919538 4194304 256 0 0 24 24 22720 0x7f54a6102a00 0x7f539a435500 220089 220089 65536 1310720 180034 23026544 12076299890256567 12076299890424475 12076299890559354 12076299890562736
20 18 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 36 919533 919538 4194304 256 0 0 28 24 23680 0x7f54a6102900 0x7f539a435540 398091 398091 65536 2097152 286809 36778484 12076299890615644 12076299890793913 12076299891048471 12076299891092440
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 38 919533 919538 4194304 256 0 0 28 24 24384 0x7f54a6102800 0x7f539a435580 399921 399921 65536 1441792 196270 25189740 12076299891117106 12076299891306070 12076299891561909 12076299891628837
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 40 919533 919538 4194304 256 0 0 24 24 25088 0x7f54a6102700 0x7f539a4355c0 210100 210100 65536 1376256 190752 24365644 12076299891652300 12076299891837907 12076299891966067 12076299891969560
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 42 919533 919538 4194304 256 0 0 24 24 25792 0x7f54a6102600 0x7f539a435600 208553 208553 65536 1507328 223099 28554880 12076299892027548 12076299892208945 12076299892336305 12076299892339918
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 44 919533 919538 4194304 256 0 0 24 24 26496 0x7f54a6102500 0x7f539a435640 212075 212075 65536 1441792 200081 25562192 12076299892403136 12076299892573263 12076299892702383 12076299892705808
25 23 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 46 919533 919538 4194304 256 0 0 28 24 27712 0x7f54a6102400 0x7f539a435680 398945 398945 65536 2359296 321994 41224232 12076299892749179 12076299892932942 12076299893188460 12076299893258766
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 48 919533 919538 4194304 256 0 0 28 24 28416 0x7f54a6102300 0x7f539a4356c0 394531 394531 65536 1572864 212336 27147804 12076299893282670 12076299893472299 12076299893723817 12076299893791165
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 50 919533 919538 4194304 256 0 0 24 24 29120 0x7f54a6102a00 0x7f539a435700 215913 215913 65536 1507328 209863 26846108 12076299893815110 12076299894006696 12076299894139015 12076299894142278
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 52 919533 919538 4194304 256 0 0 24 24 30080 0x7f54a6102900 0x7f539a435740 211651 211651 65536 1703936 230651 29594612 12076299894195176 12076299894374854 12076299894504293 12076299894507787
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 54 919533 919538 4194304 256 0 0 24 24 30784 0x7f54a6102800 0x7f539a435780 216225 216225 65536 1572864 213205 27280232 12076299894573189 12076299894740452 12076299894873412 12076299894876943
30 28 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 56 919533 919538 4194304 256 0 0 28 24 32000 0x7f54a6102700 0x7f539a4357c0 391100 391100 65536 2621440 361835 46493032 12076299894928780 12076299895117410 12076299895367809 12076299895436623
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 58 919533 919538 4194304 256 0 0 28 24 32960 0x7f54a6102600 0x7f539a435800 395977 395977 65536 1703936 230470 29523928 12076299895464836 12076299895648928 12076299895902526 12076299895969594
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 60 919533 919538 4194304 256 0 0 24 24 33920 0x7f54a6102500 0x7f539a435840 211483 211483 65536 1638400 227044 29065240 12076299895996444 12076299896188125 12076299896317404 12076299896321187
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 62 919533 919538 4194304 256 0 0 24 24 34880 0x7f54a6102400 0x7f539a435880 218505 218505 65536 1900544 268741 34343524 12076299896374006 12076299896548923 12076299896683802 12076299896687218
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 64 919533 919538 4194304 256 0 0 24 24 35840 0x7f54a6102300 0x7f539a4358c0 278476 278476 65536 1703936 232489 29686064 12076299896750916 12076299896920441 12076299897092280 12076299897096027
35 33 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 66 919533 919538 4194304 256 0 0 28 24 37312 0x7f54a6102a00 0x7f539a435900 400697 400697 65536 2883584 394892 50507760 12076299897149537 12076299897335319 12076299897592437 12076299897661218
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 68 919533 919538 4194304 256 0 0 28 24 38272 0x7f54a6102900 0x7f539a435940 389276 389276 65536 1835008 245721 31376504 12076299897684311 12076299897872916 12076299898121395 12076299898189369
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 70 919533 919538 4194304 256 0 0 24 24 39232 0x7f54a6102800 0x7f539a435980 216113 216113 65536 1769472 278643 35676384 12076299898214446 12076299898407633 12076299898540753 12076299898544099
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 72 919533 919538 4194304 256 0 0 24 24 40192 0x7f54a6102700 0x7f539a4359c0 223708 223708 65536 2097152 328429 42225068 12076299898595925 12076299898772751 12076299898908751 12076299898912052
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 74 919533 919538 4194304 256 0 0 24 24 41152 0x7f54a6102600 0x7f539a435a00 279257 279257 65536 1835008 248776 31844500 12076299898977955 12076299899151949 12076299899326669 12076299899330370
40 38 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 76 919533 919538 4194304 256 0 0 28 24 42624 0x7f54a6102500 0x7f539a435a40 396443 396443 65536 3145728 432501 55279636 12076299899374973 12076299899558667 12076299899812426 12076299899880893
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 78 919533 919538 4194304 256 0 0 28 24 43584 0x7f54a6102400 0x7f539a435a80 397537 397537 65536 1966080 269365 34482060 12076299899905459 12076299900098665 12076299900353703 12076299900423141
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 80 919533 919538 4194304 256 0 0 24 24 44544 0x7f54a6102300 0x7f539a435ac0 214636 214636 65536 1900544 271973 34786028 12076299900445933 12076299900640422 12076299900772101 12076299900775465
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 82 919533 919538 4194304 256 0 0 24 24 45760 0x7f54a6102a00 0x7f539a435b00 215705 215705 65536 2293760 305665 39246868 12076299900827522 12076299901005220 12076299901138659 12076299901142448
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 84 919533 919538 4194304 256 0 0 24 24 46720 0x7f54a6102900 0x7f539a435b40 276028 276028 65536 1966080 284612 36382880 12076299901206637 12076299901379298 12076299901551777 12076299901555385
45 43 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 86 919533 919538 4194304 256 0 0 28 24 48448 0x7f54a6102800 0x7f539a435b80 414577 414577 65536 3407872 461566 59220616 12076299901598976 12076299901782816 12076299902049374 12076299902118672
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 88 919533 919538 4194304 256 0 0 28 24 49408 0x7f54a6102700 0x7f539a435bc0 395507 395507 65536 2097152 276323 35383616 12076299902143187 12076299902331613 12076299902585052 12076299902626285
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 90 919533 919538 4194304 256 0 0 24 24 50368 0x7f54a6102600 0x7f539a435c00 213993 213993 65536 2031616 292874 37532392 12076299902655550 12076299902832890 12076299902964090 12076299902967529
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 92 919533 919538 4194304 256 0 0 24 24 51584 0x7f54a6102500 0x7f539a435c40 227012 227012 65536 2490368 335111 42932600 12076299903018795 12076299903201048 12076299903341528 12076299903345021
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 94 919533 919538 4194304 256 0 0 24 24 52544 0x7f54a6102400 0x7f539a435c80 211969 211969 65536 2097152 290284 37168948 12076299903410232 12076299903577687 12076299903707926 12076299903711522
50 48 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 96 919533 919538 4194304 256 0 0 28 24 54272 0x7f54a6102300 0x7f539a435cc0 405019 405019 65536 3670016 489204 62811988 12076299903766123 12076299903942645 12076299904203283 12076299904274047
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 98 919533 919538 4194304 256 0 0 28 24 55488 0x7f54a6102a00 0x7f539a435d00 387121 387121 65536 2228224 300500 38430084 12076299904299815 12076299904489682 12076299904738801 12076299904806727
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 100 919533 919538 4194304 256 0 0 24 24 56704 0x7f54a6102900 0x7f539a435d40 212323 212323 65536 2162688 296477 38039316 12076299904831223 12076299905016239 12076299905145678 12076299905149134
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 102 919533 919538 4194304 256 0 0 24 24 58176 0x7f54a6102800 0x7f539a435d80 227017 227017 65536 2686976 387552 49471624 12076299905201812 12076299905382957 12076299905524076 12076299905527427
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 104 919533 919538 4194304 256 0 0 24 24 59392 0x7f54a6102700 0x7f539a435dc0 208539 208539 65536 2228224 306254 39183484 12076299905592618 12076299905760395 12076299905888235 12076299905891694
55 53 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 106 919533 919538 4194304 256 0 0 28 24 61376 0x7f54a6102600 0x7f539a435e00 406425 406425 65536 3932160 532180 67960200 12076299905944893 12076299906131113 12076299906393352 12076299906437829
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 108 919533 919538 4194304 256 0 0 28 24 62592 0x7f54a6102500 0x7f539a435e40 402036 402036 65536 2359296 313357 40150908 12076299906463286 12076299906646311 12076299906904229 12076299906945743
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 110 919533 919538 4194304 256 0 0 24 24 63808 0x7f54a6102400 0x7f539a435e80 210913 210913 65536 2293760 340510 43490748 12076299906976740 12076299907159908 12076299907289827 12076299907293609
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 112 919533 919538 4194304 256 0 0 24 24 65280 0x7f54a6102300 0x7f539a435ec0 222268 222268 65536 2883584 431367 55156600 12076299907346998 12076299907529186 12076299907666785 12076299907670369
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 114 919533 919538 4194304 256 0 0 24 24 66496 0x7f54a6102a00 0x7f539a435f00 212353 212353 65536 2359296 349015 44610384 12076299907735420 12076299907901504 12076299908032223 12076299908035578
60 58 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 116 919533 919538 4194304 256 0 0 28 24 68480 0x7f54a6102900 0x7f539a435f40 406948 406948 65536 4194304 581524 74373760 12076299908090300 12076299908265662 12076299908527741 12076299908596621
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 118 919533 919538 4194304 256 0 0 28 24 69696 0x7f54a6102800 0x7f539a435f80 387321 387321 65536 2490368 330981 42359592 12076299908623451 12076299908804699 12076299909054138 12076299909124372
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 120 919533 919538 4194304 256 0 0 24 24 70912 0x7f54a6102700 0x7f539a435fc0 214035 214035 65536 2424832 354206 45414804 12076299909149408 12076299909335257 12076299909467096 12076299909470314
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 122 919533 919538 4194304 256 0 0 24 24 72384 0x7f54a6102600 0x7f539a436000 220241 220241 65536 3080192 450511 57638424 12076299909524826 12076299909690295 12076299909827574 12076299909830804
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 124 919533 919538 4194304 256 0 0 24 24 73600 0x7f54a6102500 0x7f539a436040 214363 214363 65536 2490368 355067 45513180 12076299909894413 12076299910060853 12076299910192532 12076299910196484
65 63 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 126 919533 919538 4194304 256 0 0 28 24 75840 0x7f54a6102400 0x7f539a436080 408577 408577 65536 4456448 579780 74345736 12076299910247970 12076299910427571 12076299910691410 12076299910758899
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 128 919533 919538 4194304 256 0 0 28 24 77056 0x7f54a6102300 0x7f539a4360c0 394324 394324 65536 2621440 343762 44075296 12076299910782082 12076299910970928 12076299911224687 12076299911292661
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 130 919533 919538 4194304 256 0 0 24 24 78272 0x7f54a6102a00 0x7f539a436100 213665 213665 65536 2555904 367477 47012136 12076299911317978 12076299911506286 12076299911638445 12076299911641600
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 132 919533 919538 4194304 256 0 0 24 24 80000 0x7f54a6102900 0x7f539a436140 231796 231796 65536 3276800 477202 60917452 12076299911693586 12076299911867244 12076299912011883 12076299912015815
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 134 919533 919538 4194304 256 0 0 24 24 81216 0x7f54a6102800 0x7f539a436180 211569 211569 65536 2621440 363595 46544632 12076299912081447 12076299912249162 12076299912379561 12076299912383218
70 68 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 136 919533 919538 4194304 256 0 0 28 24 83456 0x7f54a6102700 0x7f539a4361c0 411667 411667 65536 4718592 656067 84140872 12076299912435525 12076299912608040 12076299912874118 12076299912917100
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 138 919533 919538 4194304 256 0 0 28 24 84928 0x7f54a6102600 0x7f539a436200 391777 391777 65536 2752512 361371 46213224 12076299912940474 12076299913132997 12076299913385316 12076299913455200
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 140 919533 919538 4194304 256 0 0 24 24 86400 0x7f54a6102500 0x7f539a436240 219084 219084 65536 2686976 394766 50465020 12076299913480026 12076299913665154 12076299913800354 12076299913803758
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 142 919533 919538 4194304 256 0 0 24 24 88128 0x7f54a6102400 0x7f539a436280 241329 241329 65536 3473408 556381 71237200 12076299913855885 12076299914037472 12076299914188192 12076299914191569
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 144 919533 919538 4194304 256 0 0 24 24 89600 0x7f54a6102300 0x7f539a4362c0 212492 212492 65536 2752512 386737 49462240 12076299914270686 12076299914438430 12076299914568990 12076299914572587
75 73 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 146 919533 919538 4194304 256 0 0 28 24 92096 0x7f54a6102a00 0x7f539a436300 413625 413625 65536 4980736 659950 84737104 12076299914624844 12076299914798909 12076299915064507 12076299915115676
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 148 919533 919538 4194304 256 0 0 28 24 93568 0x7f54a6102900 0x7f539a436340 391372 391372 65536 2883584 385374 49326632 12076299915140793 12076299915326906 12076299915578904 12076299915627608
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 150 919533 919538 4194304 256 0 0 24 24 95040 0x7f54a6102800 0x7f539a436380 218273 218273 65536 2818048 419903 53706572 12076299915647925 12076299915837143 12076299915972022 12076299915975454
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 152 919533 919538 4194304 256 0 0 24 24 96768 0x7f54a6102700 0x7f539a4363c0 251587 251587 65536 3670016 530319 67833120 12076299916030316 12076299916209301 12076299916366740 12076299916370618
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 154 919533 919538 4194304 256 0 0 24 24 98240 0x7f54a6102600 0x7f539a436400 218801 218801 65536 2883584 443148 56649432 12076299916433185 12076299916599219 12076299916734578 12076299916737931
80 78 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 156 919533 919538 4194304 256 0 0 28 24 100736 0x7f54a6102500 0x7f539a436440 404363 404363 65536 5177344 685648 87529560 12076299916788315 12076299916963057 12076299917224656 12076299917275029
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 158 919533 919538 4194304 256 0 0 28 24 102208 0x7f54a6102400 0x7f539a436480 397073 397073 65536 3014656 398099 50926840 12076299917298503 12076299917487055 12076299917743373 12076299917791469
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 160 919533 919538 4194304 256 0 0 24 24 103680 0x7f54a6102300 0x7f539a4364c0 223547 223547 65536 2949120 499932 63983460 12076299917814452 12076299918004492 12076299918142411 12076299918145928
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 162 919533 919538 4194304 256 0 0 24 24 105664 0x7f54a6102a00 0x7f539a436500 264505 264505 65536 3866624 590898 75688444 12076299918198806 12076299918375530 12076299918542569 12076299918545951
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 164 919533 919538 4194304 256 0 0 24 24 107136 0x7f54a6102900 0x7f539a436540 219499 219499 65536 3014656 407783 52170012 12076299918610331 12076299918775208 12076299918910087 12076299918914416
85 83 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 166 919533 919538 4194304 256 0 0 28 24 109888 0x7f54a6102800 0x7f539a436580 408329 408329 65536 5439488 728725 93307600 12076299918965180 12076299919147526 12076299919409925 12076299919461152
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 168 919533 919538 4194304 256 0 0 28 24 111360 0x7f54a6102700 0x7f539a4365c0 394907 394907 65536 3145728 420648 53828316 12076299919484686 12076299919670243 12076299919924802 12076299919972953
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 170 919533 919538 4194304 256 0 0 24 24 112832 0x7f54a6102600 0x7f539a436600 216569 216569 65536 3080192 476862 60953660 12076299919995876 12076299920187361 12076299920321120 12076299920325108
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 172 919533 919538 4194304 256 0 0 24 24 114816 0x7f54a6102500 0x7f539a436640 277483 277483 65536 4063232 561121 71822404 12076299920371744 12076299920556159 12076299920730558 12076299920734308
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 174 919533 919538 4194304 256 0 0 24 24 116288 0x7f54a6102400 0x7f539a436680 212657 212657 65536 3145728 427720 54716052 12076299920799579 12076299920963677 12076299921095036 12076299921099006
90 88 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 176 919533 919538 4194304 256 0 0 28 24 119040 0x7f54a6102300 0x7f539a4366c0 400571 400571 65536 5701632 743935 94963868 12076299921150992 12076299921329115 12076299921588633 12076299921637066
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 178 919533 919538 4194304 256 0 0 28 24 120768 0x7f54a6102a00 0x7f539a436700 395201 395201 65536 3276800 447138 57230528 12076299921661822 12076299921846872 12076299922101911 12076299922150851
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 180 919533 919538 4194304 256 0 0 24 24 122496 0x7f54a6102900 0x7f539a436740 223844 223844 65536 3211264 482379 61662540 12076299922173773 12076299922362229 12076299922500629 12076299922504287
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 182 919533 919538 4194304 256 0 0 24 24 124736 0x7f54a6102800 0x7f539a436780 288777 288777 65536 4259840 607340 77619552 12076299922548660 12076299922731187 12076299922914547 12076299922917856
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 184 919533 919538 4194304 256 0 0 24 24 126464 0x7f54a6102700 0x7f539a4367c0 226412 226412 65536 3276800 535703 68596192 12076299922981244 12076299923153745 12076299923293745 12076299923297732
95 93 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 186 919533 919538 4194304 256 0 0 20 24 127936 0x7f54a6102600 0x7f539a436800 410545 410545 65536 7733248 974305 124912844 12076299923349478 12076299923546063 12076299923812782 12076299923859997
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 188 919533 919538 4194304 256 0 0 28 24 129664 0x7f54a6102500 0x7f539a436840 402724 402724 65536 3407872 454256 58389876 12076299923882859 12076299924073581 12076299924333739 12076299924382588
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 190 919533 919538 4194304 256 0 0 24 24 131392 0x7f54a6102400 0x7f539a436880 217577 217577 65536 3342336 456477 58455472 12076299924407815 12076299924597898 12076299924732297 12076299924736025
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 192 919533 919538 4194304 256 0 0 24 24 133632 0x7f54a6102300 0x7f539a4368c0 302051 302051 65536 4456448 640004 82269060 12076299924792089 12076299924963496 12076299925155015 12076299925203845
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 194 919533 919538 4194304 256 0 0 24 24 135360 0x7f54a6102a00 0x7f539a436900 215145 215145 65536 3538944 490420 62641808 12076299925240813 12076299925410854 12076299925543973 12076299925547663
100 98 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 196 919533 919538 4194304 256 0 0 20 24 136832 0x7f54a6102900 0x7f539a436940 437076 437076 65536 8978432 1131317 144600808 12076299925593228 12076299925771972 12076299926056770 12076299926103917
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 198 919533 919538 4194304 256 0 0 28 24 138560 0x7f54a6102800 0x7f539a436980 389345 389345 65536 3670016 479222 61424280 12076299926122672 12076299926315489 12076299926567488 12076299926614336
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 200 919533 919538 4194304 256 0 0 24 24 140288 0x7f54a6102700 0x7f539a4369c0 219715 219715 65536 3604480 543259 69579764 12076299926638932 12076299926830206 12076299926966046 12076299926969756
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 202 919533 919538 4194304 256 0 0 24 24 142784 0x7f54a6102600 0x7f539a436a00 330785 330785 65536 4849664 735877 94024956 12076299927026863 12076299927213404 12076299927424123 12076299927471599
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 204 919533 919538 4194304 256 0 0 24 24 144768 0x7f54a6102500 0x7f539a436a40 219067 219067 65536 3801088 601072 76954544 12076299927509309 12076299927675482 12076299927810841 12076299927814526
105 103 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 206 919533 919538 4194304 256 0 0 20 24 145728 0x7f54a6102400 0x7f539a436a80 470385 470385 65536 14548992 1832714 234663380 12076299927866513 12076299928051800 12076299928359478 12076299928408891
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 208 919533 919538 4194304 256 0 0 28 24 147712 0x7f54a6102300 0x7f539a436ac0 407483 407483 65536 3932160 522533 67088484 12076299928434649 12076299928618677 12076299928882196 12076299928929148
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 210 919533 919538 4194304 256 0 0 24 24 149696 0x7f54a6102a00 0x7f539a436b00 216841 216841 65536 3866624 602869 77157604 12076299928951980 12076299929145874 12076299929280274 12076299929284548
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 212 919533 919538 4194304 256 0 0 24 24 152192 0x7f54a6102900 0x7f539a436b40 356148 356148 65536 5242880 750550 96037116 12076299929336835 12076299929513392 12076299929741071 12076299929788054
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 214 919533 919538 4194304 256 0 0 24 24 154176 0x7f54a6102800 0x7f539a436b80 221153 221153 65536 4063232 581531 74441840 12076299929823279 12076299929994190 12076299930131789 12076299930135400
110 108 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 216 919533 919538 4194304 256 0 0 20 24 155648 0x7f54a6102700 0x7f539a436bc0 504355 504355 65536 10027008 1259275 161391076 12076299930188228 12076299930365228 12076299930695306 12076299930742458
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 218 919533 919538 4194304 256 0 0 28 24 157632 0x7f54a6102600 0x7f539a436c00 398585 398585 65536 4194304 600322 76837356 12076299930765611 12076299930949865 12076299931207944 12076299931255491
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 220 919533 919538 4194304 256 0 0 24 24 159616 0x7f54a6102500 0x7f539a436c40 224748 224748 65536 4128768 582931 74613476 12076299931280878 12076299931469170 12076299931608530 12076299931615480
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 222 919533 919538 4194304 256 0 0 24 24 162368 0x7f54a6102400 0x7f539a436c80 381473 381473 65536 5636096 774439 99074516 12076299931666515 12076299931843887 12076299932089006 12076299932138602
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 224 919533 919538 4194304 256 0 0 24 24 164608 0x7f54a6102300 0x7f539a436cc0 219852 219852 65536 4587520 636011 81425624 12076299932175792 12076299932348525 12076299932484204 12076299932487551
115 113 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 226 919533 919538 4194304 256 0 0 20 24 166336 0x7f54a6102a00 0x7f539a436d00 575009 575009 65536 11075584 1395290 178377424 12076299932539177 12076299932714923 12076299933092362 12076299933139863
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 228 919533 919538 4194304 256 0 0 28 24 168576 0x7f54a6102900 0x7f539a436d40 404540 404540 65536 4718592 639390 82178140 12076299933164709 12076299933360200 12076299933622279 12076299933668666
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 230 919533 919538 4194304 256 0 0 24 24 170816 0x7f54a6102800 0x7f539a436d80 232913 232913 65536 4653056 733715 94047532 12076299933691589 12076299933886118 12076299934031557 12076299934035287
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 232 919533 919538 4194304 256 0 0 24 24 174080 0x7f54a6102700 0x7f539a436dc0 438427 438427 65536 6422528 893536 115027880 12076299934088015 12076299934265956 12076299934546115 12076299934570151
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 234 919533 919538 4194304 256 0 0 24 24 176576 0x7f54a6102600 0x7f539a436e00 223985 223985 65536 5111808 810645 103823888 12076299934628580 12076299934794754 12076299934934433 12076299934937925
120 118 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 236 919533 919538 4194304 256 0 0 20 24 177792 0x7f54a6102500 0x7f539a436e40 647819 647819 65536 15007744 1882223 240987232 12076299934984261 12076299935169472 12076299935595390 12076299935645730
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 238 919533 919538 4194304 256 0 0 28 24 180288 0x7f54a6102400 0x7f539a436e80 395465 395465 65536 5242880 718781 92425140 12076299935670536 12076299935861149 12076299936117948 12076299936166809
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 240 919533 919538 4194304 256 0 0 24 24 182784 0x7f54a6102300 0x7f539a436ec0 231915 231915 65536 5177344 862288 110298624 12076299936191294 12076299936379226 12076299936521786 12076299936525275
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 242 919533 919538 4194304 256 0 0 24 24 186304 0x7f54a6102a00 0x7f539a436f00 531153 531153 65536 7208960 1062588 135960020 12076299936579065 12076299936753305 12076299937096983 12076299937146670
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 244 919533 919538 4194304 256 0 0 24 24 189312 0x7f54a6102900 0x7f539a436f40 244604 244604 65536 6160384 911662 116689268 12076299937181705 12076299937358422 12076299937510901 12076299937514073
125 123 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 246 919533 919538 4194304 256 0 0 20 24 190784 0x7f54a6102800 0x7f539a436f80 784073 784073 65536 17104896 2144722 274642756 12076299937565298 12076299937740660 12076299938258098 12076299938306686
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 248 919533 919538 4194304 256 0 0 28 24 193792 0x7f54a6102700 0x7f539a436fc0 459491 459491 65536 6291456 960581 122933792 12076299938335519 12076299938523857 12076299938824815 12076299938871986
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 250 919533 919538 4194304 256 0 0 24 24 196800 0x7f54a6102600 0x7f539a437000 248777 248777 65536 6225920 963195 123194468 12076299938888657 12076299939095694 12076299939252653 12076299939256160
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 252 919533 919538 4194304 256 0 0 24 24 201088 0x7f54a6102500 0x7f539a437040 592603 592603 65536 8781824 1248748 158885572 12076299939311473 12076299939490092 12076299939875530 12076299939922749
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 254 919533 919538 4194304 256 0 0 24 24 204608 0x7f54a6102400 0x7f539a437080 278337 278337 65536 7208960 1042106 133458592 12076299939958085 12076299940132809 12076299940309768 12076299940313405
130 128 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 256 919533 919538 4194304 256 0 0 20 24 206080 0x7f54a6102300 0x7f539a4370c0 924339 924339 65536 19202048 2411222 308188192 12076299940358298 12076299940542247 12076299941152964 12076299941201095
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 258 919533 919538 4194304 256 0 0 28 24 209600 0x7f54a6102a00 0x7f539a437100 504497 504497 65536 7340032 977946 125177312 12076299941224939 12076299941418083 12076299941749602 12076299941796631
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 260 919533 919538 4194304 256 0 0 24 24 213120 0x7f54a6102900 0x7f539a437140 282692 282692 65536 7274496 1062869 135987200 12076299941819424 12076299942010560 12076299942189760 12076299942193369
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 262 919533 919538 4194304 256 0 0 24 24 218176 0x7f54a6102800 0x7f539a437180 698657 698657 65536 10354688 1488537 190776492 12076299942245826 12076299942421598 12076299942878236 12076299942925399
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 264 919533 919538 4194304 256 0 0 24 24 222208 0x7f54a6102700 0x7f539a4371c0 312723 312723 65536 8257536 1184176 151611196 12076299942961436 12076299943135035 12076299943334394 12076299943383300
135 133 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 266 919533 919538 4194304 256 0 0 20 24 223936 0x7f54a6102600 0x7f539a437200 1066265 1066265 65536 21299200 2669401 341698144 12076299943407475 12076299943595033 12076299944299350 12076299944347582
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 268 919533 919538 4194304 256 0 0 28 24 227968 0x7f54a6102500 0x7f539a437240 606580 606580 65536 8388608 1172274 150354736 12076299944372919 12076299944560949 12076299944959987 12076299945015463
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 270 919533 919538 4194304 256 0 0 24 24 232000 0x7f54a6102400 0x7f539a437280 320545 320545 65536 8323072 1287436 164707516 12076299945045129 12076299945260145 12076299945464144 12076299945514651
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 272 919533 919538 4194304 256 0 0 24 24 237824 0x7f54a6102300 0x7f539a4372c0 803284 803284 65536 11927552 1690594 216700224 12076299945538165 12076299945723343 12076299946249901 12076299946298969
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 274 919533 919538 4194304 256 0 0 24 24 242368 0x7f54a6102a00 0x7f539a437300 350361 350361 65536 9306112 1410890 180543672 12076299946334164 12076299946504460 12076299946728939 12076299946776927
140 138 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 276 919533 919538 4194304 256 0 0 20 24 243584 0x7f54a6102900 0x7f539a437340 1207459 1207459 65536 29163520 3650494 467433600 12076299946800210 12076299946987497 12076299947787814 12076299947857215
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 278 919533 919538 4194304 256 0 0 28 24 248128 0x7f54a6102800 0x7f539a437380 635801 635801 65536 9437184 1240813 159316744 12076299947880518 12076299948066852 12076299948486850 12076299948555883
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 280 919533 919538 4194304 256 0 0 24 24 252672 0x7f54a6102700 0x7f539a4373c0 354308 354308 65536 9371648 1435958 183748864 12076299948580429 12076299948765249 12076299948992768 12076299949039592
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 282 919533 919538 4194304 256 0 0 24 24 259264 0x7f54a6102600 0x7f539a437400 910449 910449 65536 13500416 1900792 243030416 12076299949064489 12076299949250527 12076299949848604 12076299949915520
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 284 919533 919538 4194304 256 0 0 24 24 264832 0x7f54a6102500 0x7f539a437440 418508 418508 65536 11403264 1737440 222385492 12076299949952028 12076299950134363 12076299950403962 12076299950472906
145 143 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 286 919533 919538 4194304 256 0 0 20 24 266304 0x7f54a6102400 0x7f539a437480 1487497 1487497 65536 33357824 4175603 534728884 12076299950496259 12076299950682680 12076299951668276 12076299951735442
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 288 919533 919538 4194304 256 0 0 28 24 271872 0x7f54a6102300 0x7f539a4374c0 803932 803932 65536 11534336 1585432 203111956 12076299951753095 12076299951954514 12076299952486832 12076299952557250
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 290 919533 919538 4194304 256 0 0 24 24 277440 0x7f54a6102a00 0x7f539a437500 423657 423657 65536 11534336 1744628 223243148 12076299952580894 12076299952773871 12076299953047149 12076299953116068
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 292 919533 919538 4194304 256 0 0 12 24 279936 0x7f54a6102900 0x7f539a437540 1133852 1133852 65536 19267584 2424400 310155488 12076299953145423 12076299953332268 12076299954075145 12076299954143688
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 294 919533 919538 4194304 256 0 0 24 24 286528 0x7f54a6102800 0x7f539a437580 489825 489825 65536 13500416 2051702 262603160 12076299954186958 12076299954357063 12076299954674342 12076299954742280
150 148 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 296 919533 919538 4194304 256 0 0 20 24 288000 0x7f54a6102700 0x7f539a4375c0 1770043 1770043 65536 37552128 4700917 601623552 12076299954771234 12076299954958340 12076299956130175 12076299956200400
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 298 919533 919538 4194304 256 0 0 32 24 294592 0x7f54a6102600 0x7f539a437600 918673 918673 65536 13631488 1853505 237302996 12076299956233161 12076299956412894 12076299957022171 12076299957090504
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 300 919533 919538 4194304 256 0 0 24 24 301184 0x7f54a6102500 0x7f539a437640 492492 492492 65536 13631488 2101299 269030052 12076299957108227 12076299957312410 12076299957632248 12076299957700478
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 302 919533 919538 4194304 256 0 0 12 24 304960 0x7f54a6102400 0x7f539a437680 1336121 1336121 65536 21692416 2755337 352715068 12076299957729702 12076299957909687 12076299958788403 12076299958858109
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 304 919533 919538 4194304 256 0 0 24 24 313600 0x7f54a6102300 0x7f539a4376c0 629595 629595 65536 17694720 2657523 340168852 12076299958895098 12076299959061521 12076299959471600 12076299959540468
155 153 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 306 919533 919538 4194304 256 0 0 20 24 314816 0x7f54a6102a00 0x7f539a437700 2332353 2332353 65536 57475072 7193193 920743084 12076299959563090 12076299959755438 12076299961303271 12076299961372392
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 308 919533 919538 4194304 256 0 0 20 24 317568 0x7f54a6102900 0x7f539a437740 1202236 1202236 65536 19660800 2472188 316437508 12076299961406285 12076299961593830 12076299962388866 12076299962457359
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 310 919533 919538 4194304 256 0 0 12 24 320320 0x7f54a6102800 0x7f539a437780 640153 640153 65536 20381696 2572355 329398180 12076299962487775 12076299962673505 12076299963088863 12076299963156267
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 312 919533 919538 4194304 256 0 0 12 24 324096 0x7f54a6102700 0x7f539a4377c0 1757699 1757699 65536 28704768 3615591 462741080 12076299963183398 12076299963372381 12076299964531576 12076299964599109
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 314 919533 919538 4194304 256 0 0 12 24 328896 0x7f54a6102600 0x7f539a437800 1201873 1201873 65536 36634624 4670909 597570484 12076299964644974 12076299964814775 12076299965601491 12076299965672544
160 158 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 316 919533 919538 4194304 256 0 0 20 24 330112 0x7f54a6102500 0x7f539a437840 4584116 4584116 65536 105840640 13239672 1694957244 12076299965707038 12076299965893490 12076299968943876 12076299969024754
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 318 919533 919538 4194304 256 0 0 20 24 332864 0x7f54a6102400 0x7f539a437880 2323753 2323753 65536 38535168 4844852 619388704 12076299969050391 12076299969242114 12076299970786267 12076299970853623
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 320 919533 919538 4194304 256 0 0 12 24 335616 0x7f54a6102300 0x7f539a4378c0 1203387 1203387 65536 39124992 4926957 630479052 12076299970884630 12076299971076346 12076299971867542 12076299971937918
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 322 919533 919538 4194304 256 0 0 12 24 339392 0x7f54a6102a00 0x7f539a437900 3442505 3442505 65536 55771136 7005437 897087700 12076299971961672 12076299972158581 12076299974440650 12076299974508375
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 324 919533 919538 4194304 256 0 0 12 24 344192 0x7f54a6102900 0x7f539a437940 2323300 2323300 65536 72548352 9110641 1166105176 12076299974553378 12076299974721449 12076299976257602 12076299976325552
165 163 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 326 919533 919538 4194304 256 0 0 20 24 345408 0x7f54a6102800 0x7f539a437980 9086817 9086817 65536 210698240 26341194 3373172476 12076299976350268 12076299976542880 12076299982597252 12076299982669983
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 328 919533 919538 4194304 256 0 0 20 24 348160 0x7f54a6102700 0x7f539a4379c0 4573883 4573883 65536 76283904 9551789 1222432152 12076299982699107 12076299982887171 12076299985928917 12076299985985855
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 330 919533 919538 4194304 256 0 0 12 24 350912 0x7f54a6102600 0x7f539a437a00 2328849 2328849 65536 77398016 9707252 1242251888 12076299986021972 12076299986298995 12076299987838668 12076299987886678
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 332 919533 919538 4194304 256 0 0 12 24 0 0x7f54a6102500 0x7f539a437a40 6812940 6812940 65536 110821376 13888106 1777123712 12076299987917555 12076299988114347 12076299992641046 12076299992713007
@@ -0,0 +1,168 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,grd,Workgroup_Size,LDS_Per_Workgroup,scr,vgpr,SGPR,fbar,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"__amd_rocclr_fillBuffer.kd",0,0,0,921341,921346,33554432,256,0,0,8,32,6464,0x0,0x7f75c7a04180,0,0,0,12076325872059438,12076326117604157,12076326117928636,12076326118038409
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,921341,921346,32768,256,0,0,24,24,12480,0x0,0x7f75c7a35100,0,0,0,12076326132896351,12076326133202573,12076326133209293,12076326133221776
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,921341,921346,4194304,256,0,0,24,24,12928,0x7f76f7c91900,0x7f75c7a35140,0,0,0,12076326133274564,12076326133491052,12076326133626091,12076326133629754
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,921341,921346,4194304,256,0,0,36,24,13632,0x7f76f7c91800,0x7f75c7a35180,0,0,0,12076326133699504,12076326133869611,12076326134124969,12076326134193793
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,921341,921346,4194304,256,0,0,28,24,14080,0x7f76f7c91700,0x7f75c7a351c0,0,0,0,12076326134229669,12076326134417768,12076326134668807,12076326134734778
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,921341,921346,4194304,256,0,0,24,24,14528,0x7f76f7c91600,0x7f75c7a35200,0,0,0,12076326134761488,12076326134943046,12076326135084326,12076326135088125
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,921341,921346,4194304,256,0,0,24,24,14976,0x7f76f7c91500,0x7f75c7a35240,0,0,0,12076326135137296,12076326135308805,12076326135447684,12076326135451039
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,921341,921346,4194304,256,0,0,24,24,15424,0x7f76f7c91400,0x7f75c7a35280,0,0,0,12076326135529615,12076326135693283,12076326135823523,12076326135826828
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,921341,921346,4194304,256,0,0,28,24,16128,0x7f76f7c91300,0x7f75c7a352c0,0,0,0,12076326135877061,12076326136052322,12076326136308321,12076326136350471
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,921341,921346,4194304,256,0,0,28,24,16832,0x7f76f7c91a00,0x7f75c7a35300,0,0,0,12076326136373504,12076326136557760,12076326136809439,12076326136850119
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,921341,921346,4194304,256,0,0,24,24,17536,0x7f76f7c91900,0x7f75c7a35340,0,0,0,12076326136873052,12076326137072958,12076326137201597,12076326137205129
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,921341,921346,4194304,256,0,0,24,24,18240,0x7f76f7c91800,0x7f75c7a35380,0,0,0,12076326137255543,12076326137421276,12076326137559996,12076326137563184
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,921341,921346,4194304,256,0,0,24,24,18944,0x7f76f7c91700,0x7f75c7a353c0,0,0,0,12076326137624148,12076326137790715,12076326137921754,12076326137925097
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,921341,921346,4194304,256,0,0,28,24,19904,0x7f76f7c91600,0x7f75c7a35400,0,0,0,12076326137973447,12076326138156953,12076326138407512,12076326138474969
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,921341,921346,4194304,256,0,0,28,24,20608,0x7f76f7c91500,0x7f75c7a35440,0,0,0,12076326138502099,12076326138682231,12076326138940150,12076326139012418
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,921341,921346,4194304,256,0,0,24,24,21312,0x7f76f7c91400,0x7f75c7a35480,0,0,0,12076326139040530,12076326139219029,12076326139348148,12076326139351418
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,921341,921346,4194304,256,0,0,24,24,22016,0x7f76f7c91300,0x7f75c7a354c0,0,0,0,12076326139399668,12076326139562388,12076326139700147,12076326139703232
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,921341,921346,4194304,256,0,0,24,24,22720,0x7f76f7c91a00,0x7f75c7a35500,0,0,0,12076326139764726,12076326139928146,12076326140060785,12076326140064122
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,921341,921346,4194304,256,0,0,28,24,23680,0x7f76f7c91900,0x7f75c7a35540,0,0,0,12076326140114366,12076326140288625,12076326140550864,12076326140616379
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,921341,921346,4194304,256,0,0,28,24,24384,0x7f76f7c91800,0x7f75c7a35580,0,0,0,12076326140639492,12076326140822702,12076326141111821,12076326141182581
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,921341,921346,4194304,256,0,0,24,24,25088,0x7f76f7c91700,0x7f75c7a355c0,0,0,0,12076326141207337,12076326141389420,12076326141516460,12076326141519838
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,921341,921346,4194304,256,0,0,24,24,25792,0x7f76f7c91600,0x7f75c7a35600,0,0,0,12076326141568368,12076326141731179,12076326141871658,12076326141875108
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,921341,921346,4194304,256,0,0,24,24,26496,0x7f76f7c91500,0x7f75c7a35640,0,0,0,12076326141936562,12076326142112777,12076326142246537,12076326142250055
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,921341,921346,4194304,256,0,0,28,24,27712,0x7f76f7c91400,0x7f75c7a35680,0,0,0,12076326142299296,12076326142468296,12076326142724135,12076326142790660
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,921341,921346,4194304,256,0,0,28,24,28416,0x7f76f7c91300,0x7f75c7a356c0,0,0,0,12076326142816928,12076326142994854,12076326143250053,12076326143316437
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,921341,921346,4194304,256,0,0,24,24,29120,0x7f76f7c91a00,0x7f75c7a35700,0,0,0,12076326143342956,12076326143518212,12076326143645091,12076326143648664
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,921341,921346,4194304,256,0,0,24,24,30080,0x7f76f7c91900,0x7f75c7a35740,0,0,0,12076326143698056,12076326143859650,12076326143998050,12076326144004806
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,921341,921346,4194304,256,0,0,24,24,30784,0x7f76f7c91800,0x7f75c7a35780,0,0,0,12076326144061822,12076326144224289,12076326144352608,12076326144355939
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,921341,921346,4194304,256,0,0,28,24,32000,0x7f76f7c91700,0x7f75c7a357c0,0,0,0,12076326144405230,12076326144574687,12076326144832766,12076326144898166
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,921341,921346,4194304,256,0,0,28,24,32960,0x7f76f7c91600,0x7f75c7a35800,0,0,0,12076326144921770,12076326145106525,12076326145363004,12076326145430646
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,921341,921346,4194304,256,0,0,24,24,33920,0x7f76f7c91500,0x7f75c7a35840,0,0,0,12076326145457255,12076326145633403,12076326145769402,12076326145772661
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,921341,921346,4194304,256,0,0,24,24,34880,0x7f76f7c91400,0x7f75c7a35880,0,0,0,12076326145820711,12076326145989082,12076326146129241,12076326146132931
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,921341,921346,4194304,256,0,0,24,24,35840,0x7f76f7c91300,0x7f75c7a358c0,0,0,0,12076326146194425,12076326146359800,12076326146493239,12076326146496587
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,921341,921346,4194304,256,0,0,28,24,37312,0x7f76f7c91a00,0x7f75c7a35900,0,0,0,12076326146544316,12076326146711159,12076326146970678,12076326147037602
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,921341,921346,4194304,256,0,0,28,24,38272,0x7f76f7c91900,0x7f75c7a35940,0,0,0,12076326147064472,12076326147244756,12076326147498835,12076326147564652
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,921341,921346,4194304,256,0,0,24,24,39232,0x7f76f7c91800,0x7f75c7a35980,0,0,0,12076326147590159,12076326147767794,12076326147905394,12076326147908631
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,921341,921346,4194304,256,0,0,24,24,40192,0x7f76f7c91700,0x7f75c7a359c0,0,0,0,12076326147957392,12076326148124433,12076326148257552,12076326148261036
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,921341,921346,4194304,256,0,0,24,24,41152,0x7f76f7c91600,0x7f75c7a35a00,0,0,0,12076326148323743,12076326148487631,12076326148620911,12076326148624111
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,921341,921346,4194304,256,0,0,28,24,42624,0x7f76f7c91500,0x7f75c7a35a40,0,0,0,12076326148673733,12076326148851470,12076326149116749,12076326149187508
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,921341,921346,4194304,256,0,0,28,24,43584,0x7f76f7c91400,0x7f75c7a35a80,0,0,0,12076326149215590,12076326149390508,12076326149650027,12076326149716060
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,921341,921346,4194304,256,0,0,24,24,44544,0x7f76f7c91300,0x7f75c7a35ac0,0,0,0,12076326149737961,12076326149917386,12076326150051465,12076326150055281
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,921341,921346,4194304,256,0,0,24,24,45760,0x7f76f7c91a00,0x7f75c7a35b00,0,0,0,12076326150105654,12076326150268744,12076326150406664,12076326150410030
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,921341,921346,4194304,256,0,0,24,24,46720,0x7f76f7c91900,0x7f75c7a35b40,0,0,0,12076326150470733,12076326150631303,12076326150762182,12076326150765260
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,921341,921346,4194304,256,0,0,28,24,48448,0x7f76f7c91800,0x7f75c7a35b80,0,0,0,12076326150813239,12076326150972101,12076326151240580,12076326151309261
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,921341,921346,4194304,256,0,0,28,24,49408,0x7f76f7c91700,0x7f75c7a35bc0,0,0,0,12076326151331823,12076326151511779,12076326151769538,12076326151834457
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,921341,921346,4194304,256,0,0,24,24,50368,0x7f76f7c91600,0x7f75c7a35c00,0,0,0,12076326151859934,12076326152040897,12076326152174977,12076326152178847
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,921341,921346,4194304,256,0,0,24,24,51584,0x7f76f7c91500,0x7f75c7a35c40,0,0,0,12076326152227087,12076326152396736,12076326152539615,12076326152543194
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,921341,921346,4194304,256,0,0,24,24,52544,0x7f76f7c91400,0x7f75c7a35c80,0,0,0,12076326152602434,12076326152762654,12076326152898654,12076326152901921
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,921341,921346,4194304,256,0,0,28,24,54272,0x7f76f7c91300,0x7f75c7a35cc0,0,0,0,12076326152951092,12076326153130013,12076326153401212,12076326153469927
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,921341,921346,4194304,256,0,0,28,24,55488,0x7f76f7c91a00,0x7f75c7a35d00,0,0,0,12076326153493110,12076326153677050,12076326153933849,12076326154005251
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,921341,921346,4194304,256,0,0,24,24,56704,0x7f76f7c91900,0x7f75c7a35d40,0,0,0,12076326154030138,12076326154208248,12076326154341688,12076326154344853
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,921341,921346,4194304,256,0,0,24,24,58176,0x7f76f7c91800,0x7f75c7a35d80,0,0,0,12076326154395607,12076326154553687,12076326154694326,12076326154697708
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,921341,921346,4194304,256,0,0,24,24,59392,0x7f76f7c91700,0x7f75c7a35dc0,0,0,0,12076326154758101,12076326154917205,12076326155054645,12076326155058849
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,921341,921346,4194304,256,0,0,28,24,61376,0x7f76f7c91600,0x7f75c7a35e00,0,0,0,12076326155107029,12076326155275604,12076326155539763,12076326155580709
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,921341,921346,4194304,256,0,0,28,24,62592,0x7f76f7c91500,0x7f75c7a35e40,0,0,0,12076326155606617,12076326155780242,12076326156037841,12076326156104052
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,921341,921346,4194304,256,0,0,24,24,63808,0x7f76f7c91400,0x7f75c7a35e80,0,0,0,12076326156130281,12076326156309680,12076326156449039,12076326156452720
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,921341,921346,4194304,256,0,0,24,24,65280,0x7f76f7c91300,0x7f75c7a35ec0,0,0,0,12076326156502412,12076326156664078,12076326156808558,12076326156811677
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,921341,921346,4194304,256,0,0,24,24,66496,0x7f76f7c91a00,0x7f75c7a35f00,0,0,0,12076326156873191,12076326157039917,12076326157171436,12076326157175022
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,921341,921346,4194304,256,0,0,28,24,68480,0x7f76f7c91900,0x7f75c7a35f40,0,0,0,12076326157224584,12076326157385835,12076326157653674,12076326157694267
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,921341,921346,4194304,256,0,0,28,24,69696,0x7f76f7c91800,0x7f75c7a35f80,0,0,0,12076326157719434,12076326157892233,12076326158150312,12076326158217620
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,921341,921346,4194304,256,0,0,24,24,70912,0x7f76f7c91700,0x7f75c7a35fc0,0,0,0,12076326158242997,12076326158420391,12076326158554311,12076326158557742
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,921341,921346,4194304,256,0,0,24,24,72384,0x7f76f7c91600,0x7f75c7a36000,0,0,0,12076326158605280,12076326158770950,12076326158910309,12076326158913954
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,921341,921346,4194304,256,0,0,24,24,73600,0x7f76f7c91500,0x7f75c7a36040,0,0,0,12076326158974226,12076326159138948,12076326159272868,12076326159276448
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,921341,921346,4194304,256,0,0,28,24,75840,0x7f76f7c91400,0x7f75c7a36080,0,0,0,12076326159323255,12076326159495427,12076326159764866,12076326159811672
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,921341,921346,4194304,256,0,0,28,24,77056,0x7f76f7c91300,0x7f75c7a360c0,0,0,0,12076326159838242,12076326160012705,12076326160260704,12076326160310209
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,921341,921346,4194304,256,0,0,24,24,78272,0x7f76f7c91a00,0x7f75c7a36100,0,0,0,12076326160336428,12076326160511103,12076326160650142,12076326160653727
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,921341,921346,4194304,256,0,0,24,24,80000,0x7f76f7c91900,0x7f75c7a36140,0,0,0,12076326160704752,12076326160873181,12076326161017021,12076326161020739
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,921341,921346,4194304,256,0,0,24,24,81216,0x7f76f7c91800,0x7f75c7a36180,0,0,0,12076326161081973,12076326161244860,12076326161378299,12076326161381850
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,921341,921346,4194304,256,0,0,28,24,83456,0x7f76f7c91700,0x7f75c7a361c0,0,0,0,12076326161429559,12076326161597178,12076326161867737,12076326161889584
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,921341,921346,4194304,256,0,0,28,24,84928,0x7f76f7c91600,0x7f75c7a36200,0,0,0,12076326161931943,12076326162094776,12076326162349335,12076326162398099
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,921341,921346,4194304,256,0,0,24,24,86400,0x7f76f7c91500,0x7f75c7a36240,0,0,0,12076326162423236,12076326162599734,12076326162737334,12076326162740505
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,921341,921346,4194304,256,0,0,24,24,88128,0x7f76f7c91400,0x7f75c7a36280,0,0,0,12076326162790849,12076326162951253,12076326163102132,12076326163105955
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,921341,921346,4194304,256,0,0,24,24,89600,0x7f76f7c91300,0x7f75c7a362c0,0,0,0,12076326163188588,12076326163349171,12076326163480371,12076326163483917
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,921341,921346,4194304,256,0,0,28,24,92096,0x7f76f7c91a00,0x7f75c7a36300,0,0,0,12076326163533800,12076326163691890,12076326163957809,12076326164011979
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,921341,921346,4194304,256,0,0,28,24,93568,0x7f76f7c91900,0x7f75c7a36340,0,0,0,12076326164038738,12076326164214768,12076326164472527,12076326164519772
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,921341,921346,4194304,256,0,0,24,24,95040,0x7f76f7c91800,0x7f75c7a36380,0,0,0,12076326164543446,12076326164721806,12076326164860365,12076326164864002
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,921341,921346,4194304,256,0,0,24,24,96768,0x7f76f7c91700,0x7f75c7a363c0,0,0,0,12076326164914386,12076326165079884,12076326165237804,12076326165241544
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,921341,921346,4194304,256,0,0,24,24,98240,0x7f76f7c91600,0x7f75c7a36400,0,0,0,12076326165301735,12076326165462283,12076326165596362,12076326165599729
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,921341,921346,4194304,256,0,0,28,24,100736,0x7f76f7c91500,0x7f75c7a36440,0,0,0,12076326165647979,12076326165815561,12076326166082920,12076326166111721
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,921341,921346,4194304,256,0,0,28,24,102208,0x7f76f7c91400,0x7f75c7a36480,0,0,0,12076326166151415,12076326166309319,12076326166565638,12076326166590881
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,921341,921346,4194304,256,0,0,24,24,103680,0x7f76f7c91300,0x7f75c7a364c0,0,0,0,12076326166639852,12076326166800997,12076326166936197,12076326166939760
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,921341,921346,4194304,256,0,0,24,24,105664,0x7f76f7c91a00,0x7f75c7a36500,0,0,0,12076326166990905,12076326167156516,12076326167322595,12076326167326328
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,921341,921346,4194304,256,0,0,24,24,107136,0x7f76f7c91900,0x7f75c7a36540,0,0,0,12076326167387402,12076326167548194,12076326167683234,12076326167686868
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,921341,921346,4194304,256,0,0,28,24,109888,0x7f76f7c91800,0x7f75c7a36580,0,0,0,12076326167733485,12076326167898433,12076326168163232,12076326168188370
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,921341,921346,4194304,256,0,0,28,24,111360,0x7f76f7c91700,0x7f75c7a365c0,0,0,0,12076326168229276,12076326168390751,12076326168644990,12076326168664795
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,921341,921346,4194304,256,0,0,24,24,112832,0x7f76f7c91600,0x7f75c7a36600,0,0,0,12076326168708587,12076326168866749,12076326169008828,12076326169012582
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,921341,921346,4194304,256,0,0,24,24,114816,0x7f76f7c91500,0x7f75c7a36640,0,0,0,12076326169060611,12076326169230428,12076326169404027,12076326169407496
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,921341,921346,4194304,256,0,0,24,24,116288,0x7f76f7c91400,0x7f75c7a36680,0,0,0,12076326169468760,12076326169626426,12076326169767545,12076326169770981
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,921341,921346,4194304,256,0,0,28,24,119040,0x7f76f7c91300,0x7f75c7a366c0,0,0,0,12076326169819501,12076326169979225,12076326170240824,12076326170268686
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,921341,921346,4194304,256,0,0,28,24,120768,0x7f76f7c91a00,0x7f75c7a36700,0,0,0,12076326170308741,12076326170469943,12076326170723862,12076326170746825
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,921341,921346,4194304,256,0,0,24,24,122496,0x7f76f7c91900,0x7f75c7a36740,0,0,0,12076326170790476,12076326170946741,12076326171088340,12076326171092046
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,921341,921346,4194304,256,0,0,24,24,124736,0x7f76f7c91800,0x7f75c7a36780,0,0,0,12076326171140416,12076326171308499,12076326171491858,12076326171495336
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,921341,921346,4194304,256,0,0,24,24,126464,0x7f76f7c91700,0x7f75c7a367c0,0,0,0,12076326171554185,12076326171713458,12076326171854417,12076326171857940
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,921341,921346,4194304,256,0,0,20,24,127936,0x7f76f7c91600,0x7f75c7a36800,0,0,0,12076326171907041,12076326172073136,12076326172340175,12076326172364611
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,921341,921346,4194304,256,0,0,28,24,129664,0x7f76f7c91500,0x7f75c7a36840,0,0,0,12076326172409815,12076326172574734,12076326172834093,12076326172857427
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,921341,921346,4194304,256,0,0,24,24,131392,0x7f76f7c91400,0x7f75c7a36880,0,0,0,12076326172903733,12076326173060652,12076326173195532,12076326173199172
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,921341,921346,4194304,256,0,0,24,24,133632,0x7f76f7c91300,0x7f75c7a368c0,0,0,0,12076326173248955,12076326173412011,12076326173603690,12076326173626787
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,921341,921346,4194304,256,0,0,24,24,135360,0x7f76f7c91a00,0x7f75c7a36900,0,0,0,12076326173682180,12076326173843209,12076326173983848,12076326173987668
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,921341,921346,4194304,256,0,0,20,24,136832,0x7f76f7c91900,0x7f75c7a36940,0,0,0,12076326174035607,12076326174208007,12076326174491686,12076326174517883
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,921341,921346,4194304,256,0,0,28,24,138560,0x7f76f7c91800,0x7f75c7a36980,0,0,0,12076326174558418,12076326174713605,12076326174974084,12076326174996793
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,921341,921346,4194304,256,0,0,24,24,140288,0x7f76f7c91700,0x7f75c7a369c0,0,0,0,12076326175045013,12076326175202563,12076326175338083,12076326175341734
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,921341,921346,4194304,256,0,0,24,24,142784,0x7f76f7c91600,0x7f75c7a36a00,0,0,0,12076326175388361,12076326175553762,12076326175764641,12076326175784307
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,921341,921346,4194304,256,0,0,24,24,144768,0x7f76f7c91500,0x7f75c7a36a40,0,0,0,12076326175842906,12076326176006080,12076326176145120,12076326176149035
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,921341,921346,4194304,256,0,0,20,24,145728,0x7f76f7c91400,0x7f75c7a36a80,0,0,0,12076326176195491,12076326176371999,12076326176681437,12076326176704617
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,921341,921346,4194304,256,0,0,28,24,147712,0x7f76f7c91300,0x7f75c7a36ac0,0,0,0,12076326176749440,12076326176909437,12076326177175355,12076326177204276
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,921341,921346,4194304,256,0,0,24,24,149696,0x7f76f7c91a00,0x7f75c7a36b00,0,0,0,12076326177245282,12076326177402875,12076326177544954,12076326177548235
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,921341,921346,4194304,256,0,0,24,24,152192,0x7f76f7c91900,0x7f75c7a36b40,0,0,0,12076326177599340,12076326177756473,12076326177984952,12076326178013359
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,921341,921346,4194304,256,0,0,24,24,154176,0x7f76f7c91800,0x7f75c7a36b80,0,0,0,12076326178071167,12076326178232471,12076326178372951,12076326178376434
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,921341,921346,4194304,256,0,0,20,24,155648,0x7f76f7c91700,0x7f75c7a36bc0,0,0,0,12076326178424433,12076326178591350,12076326178920948,12076326178943718
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,921341,921346,4194304,256,0,0,28,24,157632,0x7f76f7c91600,0x7f75c7a36c00,0,0,0,12076326178986157,12076326179151028,12076326179416466,12076326179443577
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,921341,921346,4194304,256,0,0,24,24,159616,0x7f76f7c91500,0x7f75c7a36c40,0,0,0,12076326179482800,12076326179642546,12076326179779665,12076326179783329
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,921341,921346,4194304,256,0,0,24,24,162368,0x7f76f7c91400,0x7f75c7a36c80,0,0,0,12076326179831198,12076326179990704,12076326180235983,12076326180259293
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,921341,921346,4194304,256,0,0,24,24,164608,0x7f76f7c91300,0x7f75c7a36cc0,0,0,0,12076326180316890,12076326180482029,12076326180626509,12076326180633849
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,921341,921346,4194304,256,0,0,20,24,166336,0x7f76f7c91a00,0x7f75c7a36d00,0,0,0,12076326180677030,12076326180855947,12076326181257385,12076326181285881
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,921341,921346,4194304,256,0,0,28,24,168576,0x7f76f7c91900,0x7f75c7a36d40,0,0,0,12076326181326958,12076326181485545,12076326181750664,12076326181772816
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,921341,921346,4194304,256,0,0,24,24,170816,0x7f76f7c91800,0x7f75c7a36d80,0,0,0,12076326181815896,12076326181970983,12076326182110342,12076326182113700
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,921341,921346,4194304,256,0,0,24,24,174080,0x7f76f7c91700,0x7f75c7a36dc0,0,0,0,12076326182165897,12076326182331942,12076326182611461,12076326182634878
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,921341,921346,4194304,256,0,0,24,24,176576,0x7f76f7c91600,0x7f75c7a36e00,0,0,0,12076326182696092,12076326182857860,12076326182996259,12076326182999616
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,921341,921346,4194304,256,0,0,20,24,177792,0x7f76f7c91500,0x7f75c7a36e40,0,0,0,12076326183048026,12076326183220738,12076326183646337,12076326183672036
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,921341,921346,4194304,256,0,0,28,24,180288,0x7f76f7c91400,0x7f75c7a36e80,0,0,0,12076326183709986,12076326183869056,12076326184133855,12076326184157207
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,921341,921346,4194304,256,0,0,24,24,182784,0x7f76f7c91300,0x7f75c7a36ec0,0,0,0,12076326184200518,12076326184359135,12076326184498174,12076326184501497
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,921341,921346,4194304,256,0,0,24,24,186304,0x7f76f7c91a00,0x7f75c7a36f00,0,0,0,12076326184551580,12076326184711293,12076326185026652,12076326185051069
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,921341,921346,4194304,256,0,0,24,24,189312,0x7f76f7c91900,0x7f75c7a36f40,0,0,0,12076326185111311,12076326185274811,12076326185426491,12076326185429542
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,921341,921346,4194304,256,0,0,20,24,190784,0x7f76f7c91800,0x7f75c7a36f80,0,0,0,12076326185478333,12076326185639770,12076326186157208,12076326186181670
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,921341,921346,4194304,256,0,0,28,24,193792,0x7f76f7c91700,0x7f75c7a36fc0,0,0,0,12076326186223688,12076326186384727,12076326186684886,12076326186707146
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,921341,921346,4194304,256,0,0,24,24,196800,0x7f76f7c91600,0x7f75c7a37000,0,0,0,12076326186752681,12076326186915286,12076326187070645,12076326187074319
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,921341,921346,4194304,256,0,0,24,24,201088,0x7f76f7c91500,0x7f75c7a37040,0,0,0,12076326187124181,12076326187292884,12076326187704083,12076326187729196
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,921341,921346,4194304,256,0,0,24,24,204608,0x7f76f7c91400,0x7f75c7a37080,0,0,0,12076326187790570,12076326187952562,12076326188129841,12076326188133036
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,921341,921346,4194304,256,0,0,20,24,206080,0x7f76f7c91300,0x7f75c7a370c0,0,0,0,12076326188181166,12076326188350001,12076326188971758,12076326188995299
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,921341,921346,4194304,256,0,0,28,24,209600,0x7f76f7c91a00,0x7f75c7a37100,0,0,0,12076326189044100,12076326189201838,12076326189556876,12076326189580106
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,921341,921346,4194304,256,0,0,24,24,213120,0x7f76f7c91900,0x7f75c7a37140,0,0,0,12076326189627694,12076326189788556,12076326189967275,12076326189970311
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,921341,921346,4194304,256,0,0,24,24,218176,0x7f76f7c91800,0x7f75c7a37180,0,0,0,12076326190015445,12076326190203594,12076326190660713,12076326190686291
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,921341,921346,4194304,256,0,0,24,24,222208,0x7f76f7c91700,0x7f75c7a371c0,0,0,0,12076326190745031,12076326190905992,12076326191105991,12076326191133202
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,921341,921346,4194304,256,0,0,20,24,223936,0x7f76f7c91600,0x7f75c7a37200,0,0,0,12076326191175360,12076326191334950,12076326192037988,12076326192064543
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,921341,921346,4194304,256,0,0,28,24,227968,0x7f76f7c91500,0x7f75c7a37240,0,0,0,12076326192105990,12076326192265987,12076326192640066,12076326192664358
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,921341,921346,4194304,256,0,0,24,24,232000,0x7f76f7c91400,0x7f75c7a37280,0,0,0,12076326192713248,12076326192874305,12076326193077824,12076326193101670
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,921341,921346,4194304,256,0,0,24,24,237824,0x7f76f7c91300,0x7f75c7a372c0,0,0,0,12076326193152946,12076326193314463,12076326193857501,12076326193880999
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,921341,921346,4194304,256,0,0,24,24,242368,0x7f76f7c91a00,0x7f75c7a37300,0,0,0,12076326193942072,12076326194113021,12076326194370780,12076326194398350
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,921341,921346,4194304,256,0,0,20,24,243584,0x7f76f7c91900,0x7f75c7a37340,0,0,0,12076326194438775,12076326194600539,12076326195398936,12076326195446718
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,921341,921346,4194304,256,0,0,28,24,248128,0x7f76f7c91800,0x7f75c7a37380,0,0,0,12076326195476865,12076326195677015,12076326196096054,12076326196145738
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,921341,921346,4194304,256,0,0,24,24,252672,0x7f76f7c91700,0x7f75c7a373c0,0,0,0,12076326196178018,12076326196359893,12076326196586452,12076326196634085
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,921341,921346,4194304,256,0,0,24,24,259264,0x7f76f7c91600,0x7f75c7a37400,0,0,0,12076326196660624,12076326196833171,12076326197443569,12076326197495416
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,921341,921346,4194304,256,0,0,24,24,264832,0x7f76f7c91500,0x7f75c7a37440,0,0,0,12076326197534979,12076326197697808,12076326197967087,12076326198017276
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,921341,921346,4194304,256,0,0,20,24,266304,0x7f76f7c91400,0x7f75c7a37480,0,0,0,12076326198043214,12076326198220206,12076326199205803,12076326199272308
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,921341,921346,4194304,256,0,0,28,24,271872,0x7f76f7c91300,0x7f75c7a374c0,0,0,0,12076326199299058,12076326199479402,12076326200013480,12076326200080911
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,921341,921346,4194304,256,0,0,24,24,277440,0x7f76f7c91a00,0x7f75c7a37500,0,0,0,12076326200110796,12076326200290759,12076326200562598,12076326200628659
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,921341,921346,4194304,256,0,0,12,24,279936,0x7f76f7c91900,0x7f75c7a37540,0,0,0,12076326200654737,12076326200825477,12076326201564035,12076326201633917
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,921341,921346,4194304,256,0,0,24,24,286528,0x7f76f7c91800,0x7f75c7a37580,0,0,0,12076326201674473,12076326201836194,12076326202152673,12076326202220447
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,921341,921346,4194304,256,0,0,20,24,288000,0x7f76f7c91700,0x7f75c7a375c0,0,0,0,12076326202247007,12076326202420512,12076326203590908,12076326203659041
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,921341,921346,4194304,256,0,0,32,24,294592,0x7f76f7c91600,0x7f75c7a37600,0,0,0,12076326203688676,12076326203872027,12076326204480344,12076326204548744
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,921341,921346,4194304,256,0,0,24,24,301184,0x7f76f7c91500,0x7f75c7a37640,0,0,0,12076326204571687,12076326204756184,12076326205075862,12076326205142087
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,921341,921346,4194304,256,0,0,12,24,304960,0x7f76f7c91400,0x7f75c7a37680,0,0,0,12076326205169147,12076326205350901,12076326206228818,12076326206298105
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,921341,921346,4194304,256,0,0,24,24,313600,0x7f76f7c91300,0x7f75c7a376c0,0,0,0,12076326206340604,12076326206504657,12076326206915536,12076326206982287
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,921341,921346,4194304,256,0,0,20,24,314816,0x7f76f7c91a00,0x7f75c7a37700,0,0,0,12076326207017212,12076326207200495,12076326208746730,12076326208815464
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,921341,921346,4194304,256,0,0,20,24,317568,0x7f76f7c91900,0x7f75c7a37740,0,0,0,12076326208851220,12076326209013449,12076326209806726,12076326209875283
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,921341,921346,4194304,256,0,0,12,24,320320,0x7f76f7c91800,0x7f75c7a37780,0,0,0,12076326209911841,12076326210080965,12076326210495044,12076326210563202
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,921341,921346,4194304,256,0,0,12,24,324096,0x7f76f7c91700,0x7f75c7a377c0,0,0,0,12076326210593328,12076326210769603,12076326211929279,12076326211996726
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,921341,921346,4194304,256,0,0,12,24,328896,0x7f76f7c91600,0x7f75c7a37800,0,0,0,12076326212044795,12076326212212318,12076326212998075,12076326213066314
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,921341,921346,4194304,256,0,0,20,24,330112,0x7f76f7c91500,0x7f75c7a37840,0,0,0,12076326213095939,12076326213270074,12076326216318223,12076326216385793
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,921341,921346,4194304,256,0,0,20,24,332864,0x7f76f7c91400,0x7f75c7a37880,0,0,0,12076326216410419,12076326216603662,12076326218143177,12076326218211175
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,921341,921346,4194304,256,0,0,12,24,335616,0x7f76f7c91300,0x7f75c7a378c0,0,0,0,12076326218242043,12076326218420456,12076326219210053,12076326219276565
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,921341,921346,4194304,256,0,0,12,24,339392,0x7f76f7c91a00,0x7f75c7a37900,0,0,0,12076326219303325,12076326219484292,12076326221766204,12076326221833106
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,921341,921346,4194304,256,0,0,12,24,344192,0x7f76f7c91900,0x7f75c7a37940,0,0,0,12076326221877900,12076326222045243,12076326223580118,12076326223649212
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,921341,921346,4194304,256,0,0,20,24,345408,0x7f76f7c91800,0x7f75c7a37980,0,0,0,12076326223679478,12076326223858517,12076326229912096,12076326229982462
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,921341,921346,4194304,256,0,0,20,24,348160,0x7f76f7c91700,0x7f75c7a379c0,0,0,0,12076326230016785,12076326230196575,12076326233237044,12076326233306359
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,921341,921346,4194304,256,0,0,12,24,350912,0x7f76f7c91600,0x7f75c7a37a00,0,0,0,12076326233336234,12076326233514803,12076326235053998,12076326235121813
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,921341,921346,4194304,256,0,0,12,24,0,0x7f76f7c91500,0x7f75c7a37a40,0,0,0,12076326235150446,12076326235329197,12076326239856221,12076326239924749
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid grd Workgroup_Size LDS_Per_Workgroup scr vgpr SGPR fbar sig obj SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 __amd_rocclr_fillBuffer.kd 0 0 0 921341 921346 33554432 256 0 0 8 32 6464 0x0 0x7f75c7a04180 0 0 0 12076325872059438 12076326117604157 12076326117928636 12076326118038409
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 921341 921346 32768 256 0 0 24 24 12480 0x0 0x7f75c7a35100 0 0 0 12076326132896351 12076326133202573 12076326133209293 12076326133221776
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 4 921341 921346 4194304 256 0 0 24 24 12928 0x7f76f7c91900 0x7f75c7a35140 0 0 0 12076326133274564 12076326133491052 12076326133626091 12076326133629754
5 3 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 6 921341 921346 4194304 256 0 0 36 24 13632 0x7f76f7c91800 0x7f75c7a35180 0 0 0 12076326133699504 12076326133869611 12076326134124969 12076326134193793
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 8 921341 921346 4194304 256 0 0 28 24 14080 0x7f76f7c91700 0x7f75c7a351c0 0 0 0 12076326134229669 12076326134417768 12076326134668807 12076326134734778
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 10 921341 921346 4194304 256 0 0 24 24 14528 0x7f76f7c91600 0x7f75c7a35200 0 0 0 12076326134761488 12076326134943046 12076326135084326 12076326135088125
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 12 921341 921346 4194304 256 0 0 24 24 14976 0x7f76f7c91500 0x7f75c7a35240 0 0 0 12076326135137296 12076326135308805 12076326135447684 12076326135451039
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 14 921341 921346 4194304 256 0 0 24 24 15424 0x7f76f7c91400 0x7f75c7a35280 0 0 0 12076326135529615 12076326135693283 12076326135823523 12076326135826828
10 8 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 16 921341 921346 4194304 256 0 0 28 24 16128 0x7f76f7c91300 0x7f75c7a352c0 0 0 0 12076326135877061 12076326136052322 12076326136308321 12076326136350471
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 18 921341 921346 4194304 256 0 0 28 24 16832 0x7f76f7c91a00 0x7f75c7a35300 0 0 0 12076326136373504 12076326136557760 12076326136809439 12076326136850119
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 20 921341 921346 4194304 256 0 0 24 24 17536 0x7f76f7c91900 0x7f75c7a35340 0 0 0 12076326136873052 12076326137072958 12076326137201597 12076326137205129
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 22 921341 921346 4194304 256 0 0 24 24 18240 0x7f76f7c91800 0x7f75c7a35380 0 0 0 12076326137255543 12076326137421276 12076326137559996 12076326137563184
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 24 921341 921346 4194304 256 0 0 24 24 18944 0x7f76f7c91700 0x7f75c7a353c0 0 0 0 12076326137624148 12076326137790715 12076326137921754 12076326137925097
15 13 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 26 921341 921346 4194304 256 0 0 28 24 19904 0x7f76f7c91600 0x7f75c7a35400 0 0 0 12076326137973447 12076326138156953 12076326138407512 12076326138474969
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 28 921341 921346 4194304 256 0 0 28 24 20608 0x7f76f7c91500 0x7f75c7a35440 0 0 0 12076326138502099 12076326138682231 12076326138940150 12076326139012418
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 30 921341 921346 4194304 256 0 0 24 24 21312 0x7f76f7c91400 0x7f75c7a35480 0 0 0 12076326139040530 12076326139219029 12076326139348148 12076326139351418
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 32 921341 921346 4194304 256 0 0 24 24 22016 0x7f76f7c91300 0x7f75c7a354c0 0 0 0 12076326139399668 12076326139562388 12076326139700147 12076326139703232
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 34 921341 921346 4194304 256 0 0 24 24 22720 0x7f76f7c91a00 0x7f75c7a35500 0 0 0 12076326139764726 12076326139928146 12076326140060785 12076326140064122
20 18 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 36 921341 921346 4194304 256 0 0 28 24 23680 0x7f76f7c91900 0x7f75c7a35540 0 0 0 12076326140114366 12076326140288625 12076326140550864 12076326140616379
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 38 921341 921346 4194304 256 0 0 28 24 24384 0x7f76f7c91800 0x7f75c7a35580 0 0 0 12076326140639492 12076326140822702 12076326141111821 12076326141182581
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 40 921341 921346 4194304 256 0 0 24 24 25088 0x7f76f7c91700 0x7f75c7a355c0 0 0 0 12076326141207337 12076326141389420 12076326141516460 12076326141519838
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 42 921341 921346 4194304 256 0 0 24 24 25792 0x7f76f7c91600 0x7f75c7a35600 0 0 0 12076326141568368 12076326141731179 12076326141871658 12076326141875108
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 44 921341 921346 4194304 256 0 0 24 24 26496 0x7f76f7c91500 0x7f75c7a35640 0 0 0 12076326141936562 12076326142112777 12076326142246537 12076326142250055
25 23 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 46 921341 921346 4194304 256 0 0 28 24 27712 0x7f76f7c91400 0x7f75c7a35680 0 0 0 12076326142299296 12076326142468296 12076326142724135 12076326142790660
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 48 921341 921346 4194304 256 0 0 28 24 28416 0x7f76f7c91300 0x7f75c7a356c0 0 0 0 12076326142816928 12076326142994854 12076326143250053 12076326143316437
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 50 921341 921346 4194304 256 0 0 24 24 29120 0x7f76f7c91a00 0x7f75c7a35700 0 0 0 12076326143342956 12076326143518212 12076326143645091 12076326143648664
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 52 921341 921346 4194304 256 0 0 24 24 30080 0x7f76f7c91900 0x7f75c7a35740 0 0 0 12076326143698056 12076326143859650 12076326143998050 12076326144004806
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 54 921341 921346 4194304 256 0 0 24 24 30784 0x7f76f7c91800 0x7f75c7a35780 0 0 0 12076326144061822 12076326144224289 12076326144352608 12076326144355939
30 28 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 56 921341 921346 4194304 256 0 0 28 24 32000 0x7f76f7c91700 0x7f75c7a357c0 0 0 0 12076326144405230 12076326144574687 12076326144832766 12076326144898166
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 58 921341 921346 4194304 256 0 0 28 24 32960 0x7f76f7c91600 0x7f75c7a35800 0 0 0 12076326144921770 12076326145106525 12076326145363004 12076326145430646
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 60 921341 921346 4194304 256 0 0 24 24 33920 0x7f76f7c91500 0x7f75c7a35840 0 0 0 12076326145457255 12076326145633403 12076326145769402 12076326145772661
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 62 921341 921346 4194304 256 0 0 24 24 34880 0x7f76f7c91400 0x7f75c7a35880 0 0 0 12076326145820711 12076326145989082 12076326146129241 12076326146132931
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 64 921341 921346 4194304 256 0 0 24 24 35840 0x7f76f7c91300 0x7f75c7a358c0 0 0 0 12076326146194425 12076326146359800 12076326146493239 12076326146496587
35 33 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 66 921341 921346 4194304 256 0 0 28 24 37312 0x7f76f7c91a00 0x7f75c7a35900 0 0 0 12076326146544316 12076326146711159 12076326146970678 12076326147037602
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 68 921341 921346 4194304 256 0 0 28 24 38272 0x7f76f7c91900 0x7f75c7a35940 0 0 0 12076326147064472 12076326147244756 12076326147498835 12076326147564652
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 70 921341 921346 4194304 256 0 0 24 24 39232 0x7f76f7c91800 0x7f75c7a35980 0 0 0 12076326147590159 12076326147767794 12076326147905394 12076326147908631
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 72 921341 921346 4194304 256 0 0 24 24 40192 0x7f76f7c91700 0x7f75c7a359c0 0 0 0 12076326147957392 12076326148124433 12076326148257552 12076326148261036
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 74 921341 921346 4194304 256 0 0 24 24 41152 0x7f76f7c91600 0x7f75c7a35a00 0 0 0 12076326148323743 12076326148487631 12076326148620911 12076326148624111
40 38 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 76 921341 921346 4194304 256 0 0 28 24 42624 0x7f76f7c91500 0x7f75c7a35a40 0 0 0 12076326148673733 12076326148851470 12076326149116749 12076326149187508
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 78 921341 921346 4194304 256 0 0 28 24 43584 0x7f76f7c91400 0x7f75c7a35a80 0 0 0 12076326149215590 12076326149390508 12076326149650027 12076326149716060
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 80 921341 921346 4194304 256 0 0 24 24 44544 0x7f76f7c91300 0x7f75c7a35ac0 0 0 0 12076326149737961 12076326149917386 12076326150051465 12076326150055281
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 82 921341 921346 4194304 256 0 0 24 24 45760 0x7f76f7c91a00 0x7f75c7a35b00 0 0 0 12076326150105654 12076326150268744 12076326150406664 12076326150410030
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 84 921341 921346 4194304 256 0 0 24 24 46720 0x7f76f7c91900 0x7f75c7a35b40 0 0 0 12076326150470733 12076326150631303 12076326150762182 12076326150765260
45 43 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 86 921341 921346 4194304 256 0 0 28 24 48448 0x7f76f7c91800 0x7f75c7a35b80 0 0 0 12076326150813239 12076326150972101 12076326151240580 12076326151309261
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 88 921341 921346 4194304 256 0 0 28 24 49408 0x7f76f7c91700 0x7f75c7a35bc0 0 0 0 12076326151331823 12076326151511779 12076326151769538 12076326151834457
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 90 921341 921346 4194304 256 0 0 24 24 50368 0x7f76f7c91600 0x7f75c7a35c00 0 0 0 12076326151859934 12076326152040897 12076326152174977 12076326152178847
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 92 921341 921346 4194304 256 0 0 24 24 51584 0x7f76f7c91500 0x7f75c7a35c40 0 0 0 12076326152227087 12076326152396736 12076326152539615 12076326152543194
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 94 921341 921346 4194304 256 0 0 24 24 52544 0x7f76f7c91400 0x7f75c7a35c80 0 0 0 12076326152602434 12076326152762654 12076326152898654 12076326152901921
50 48 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 96 921341 921346 4194304 256 0 0 28 24 54272 0x7f76f7c91300 0x7f75c7a35cc0 0 0 0 12076326152951092 12076326153130013 12076326153401212 12076326153469927
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 98 921341 921346 4194304 256 0 0 28 24 55488 0x7f76f7c91a00 0x7f75c7a35d00 0 0 0 12076326153493110 12076326153677050 12076326153933849 12076326154005251
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 100 921341 921346 4194304 256 0 0 24 24 56704 0x7f76f7c91900 0x7f75c7a35d40 0 0 0 12076326154030138 12076326154208248 12076326154341688 12076326154344853
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 102 921341 921346 4194304 256 0 0 24 24 58176 0x7f76f7c91800 0x7f75c7a35d80 0 0 0 12076326154395607 12076326154553687 12076326154694326 12076326154697708
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 104 921341 921346 4194304 256 0 0 24 24 59392 0x7f76f7c91700 0x7f75c7a35dc0 0 0 0 12076326154758101 12076326154917205 12076326155054645 12076326155058849
55 53 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 106 921341 921346 4194304 256 0 0 28 24 61376 0x7f76f7c91600 0x7f75c7a35e00 0 0 0 12076326155107029 12076326155275604 12076326155539763 12076326155580709
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 108 921341 921346 4194304 256 0 0 28 24 62592 0x7f76f7c91500 0x7f75c7a35e40 0 0 0 12076326155606617 12076326155780242 12076326156037841 12076326156104052
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 110 921341 921346 4194304 256 0 0 24 24 63808 0x7f76f7c91400 0x7f75c7a35e80 0 0 0 12076326156130281 12076326156309680 12076326156449039 12076326156452720
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 112 921341 921346 4194304 256 0 0 24 24 65280 0x7f76f7c91300 0x7f75c7a35ec0 0 0 0 12076326156502412 12076326156664078 12076326156808558 12076326156811677
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 114 921341 921346 4194304 256 0 0 24 24 66496 0x7f76f7c91a00 0x7f75c7a35f00 0 0 0 12076326156873191 12076326157039917 12076326157171436 12076326157175022
60 58 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 116 921341 921346 4194304 256 0 0 28 24 68480 0x7f76f7c91900 0x7f75c7a35f40 0 0 0 12076326157224584 12076326157385835 12076326157653674 12076326157694267
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 118 921341 921346 4194304 256 0 0 28 24 69696 0x7f76f7c91800 0x7f75c7a35f80 0 0 0 12076326157719434 12076326157892233 12076326158150312 12076326158217620
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 120 921341 921346 4194304 256 0 0 24 24 70912 0x7f76f7c91700 0x7f75c7a35fc0 0 0 0 12076326158242997 12076326158420391 12076326158554311 12076326158557742
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 122 921341 921346 4194304 256 0 0 24 24 72384 0x7f76f7c91600 0x7f75c7a36000 0 0 0 12076326158605280 12076326158770950 12076326158910309 12076326158913954
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 124 921341 921346 4194304 256 0 0 24 24 73600 0x7f76f7c91500 0x7f75c7a36040 0 0 0 12076326158974226 12076326159138948 12076326159272868 12076326159276448
65 63 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 126 921341 921346 4194304 256 0 0 28 24 75840 0x7f76f7c91400 0x7f75c7a36080 0 0 0 12076326159323255 12076326159495427 12076326159764866 12076326159811672
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 128 921341 921346 4194304 256 0 0 28 24 77056 0x7f76f7c91300 0x7f75c7a360c0 0 0 0 12076326159838242 12076326160012705 12076326160260704 12076326160310209
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 130 921341 921346 4194304 256 0 0 24 24 78272 0x7f76f7c91a00 0x7f75c7a36100 0 0 0 12076326160336428 12076326160511103 12076326160650142 12076326160653727
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 132 921341 921346 4194304 256 0 0 24 24 80000 0x7f76f7c91900 0x7f75c7a36140 0 0 0 12076326160704752 12076326160873181 12076326161017021 12076326161020739
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 134 921341 921346 4194304 256 0 0 24 24 81216 0x7f76f7c91800 0x7f75c7a36180 0 0 0 12076326161081973 12076326161244860 12076326161378299 12076326161381850
70 68 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 136 921341 921346 4194304 256 0 0 28 24 83456 0x7f76f7c91700 0x7f75c7a361c0 0 0 0 12076326161429559 12076326161597178 12076326161867737 12076326161889584
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 138 921341 921346 4194304 256 0 0 28 24 84928 0x7f76f7c91600 0x7f75c7a36200 0 0 0 12076326161931943 12076326162094776 12076326162349335 12076326162398099
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 140 921341 921346 4194304 256 0 0 24 24 86400 0x7f76f7c91500 0x7f75c7a36240 0 0 0 12076326162423236 12076326162599734 12076326162737334 12076326162740505
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 142 921341 921346 4194304 256 0 0 24 24 88128 0x7f76f7c91400 0x7f75c7a36280 0 0 0 12076326162790849 12076326162951253 12076326163102132 12076326163105955
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 144 921341 921346 4194304 256 0 0 24 24 89600 0x7f76f7c91300 0x7f75c7a362c0 0 0 0 12076326163188588 12076326163349171 12076326163480371 12076326163483917
75 73 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 146 921341 921346 4194304 256 0 0 28 24 92096 0x7f76f7c91a00 0x7f75c7a36300 0 0 0 12076326163533800 12076326163691890 12076326163957809 12076326164011979
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 148 921341 921346 4194304 256 0 0 28 24 93568 0x7f76f7c91900 0x7f75c7a36340 0 0 0 12076326164038738 12076326164214768 12076326164472527 12076326164519772
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 150 921341 921346 4194304 256 0 0 24 24 95040 0x7f76f7c91800 0x7f75c7a36380 0 0 0 12076326164543446 12076326164721806 12076326164860365 12076326164864002
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 152 921341 921346 4194304 256 0 0 24 24 96768 0x7f76f7c91700 0x7f75c7a363c0 0 0 0 12076326164914386 12076326165079884 12076326165237804 12076326165241544
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 154 921341 921346 4194304 256 0 0 24 24 98240 0x7f76f7c91600 0x7f75c7a36400 0 0 0 12076326165301735 12076326165462283 12076326165596362 12076326165599729
80 78 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 156 921341 921346 4194304 256 0 0 28 24 100736 0x7f76f7c91500 0x7f75c7a36440 0 0 0 12076326165647979 12076326165815561 12076326166082920 12076326166111721
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 158 921341 921346 4194304 256 0 0 28 24 102208 0x7f76f7c91400 0x7f75c7a36480 0 0 0 12076326166151415 12076326166309319 12076326166565638 12076326166590881
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 160 921341 921346 4194304 256 0 0 24 24 103680 0x7f76f7c91300 0x7f75c7a364c0 0 0 0 12076326166639852 12076326166800997 12076326166936197 12076326166939760
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 162 921341 921346 4194304 256 0 0 24 24 105664 0x7f76f7c91a00 0x7f75c7a36500 0 0 0 12076326166990905 12076326167156516 12076326167322595 12076326167326328
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 164 921341 921346 4194304 256 0 0 24 24 107136 0x7f76f7c91900 0x7f75c7a36540 0 0 0 12076326167387402 12076326167548194 12076326167683234 12076326167686868
85 83 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 166 921341 921346 4194304 256 0 0 28 24 109888 0x7f76f7c91800 0x7f75c7a36580 0 0 0 12076326167733485 12076326167898433 12076326168163232 12076326168188370
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 168 921341 921346 4194304 256 0 0 28 24 111360 0x7f76f7c91700 0x7f75c7a365c0 0 0 0 12076326168229276 12076326168390751 12076326168644990 12076326168664795
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 170 921341 921346 4194304 256 0 0 24 24 112832 0x7f76f7c91600 0x7f75c7a36600 0 0 0 12076326168708587 12076326168866749 12076326169008828 12076326169012582
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 172 921341 921346 4194304 256 0 0 24 24 114816 0x7f76f7c91500 0x7f75c7a36640 0 0 0 12076326169060611 12076326169230428 12076326169404027 12076326169407496
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 174 921341 921346 4194304 256 0 0 24 24 116288 0x7f76f7c91400 0x7f75c7a36680 0 0 0 12076326169468760 12076326169626426 12076326169767545 12076326169770981
90 88 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 176 921341 921346 4194304 256 0 0 28 24 119040 0x7f76f7c91300 0x7f75c7a366c0 0 0 0 12076326169819501 12076326169979225 12076326170240824 12076326170268686
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 178 921341 921346 4194304 256 0 0 28 24 120768 0x7f76f7c91a00 0x7f75c7a36700 0 0 0 12076326170308741 12076326170469943 12076326170723862 12076326170746825
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 180 921341 921346 4194304 256 0 0 24 24 122496 0x7f76f7c91900 0x7f75c7a36740 0 0 0 12076326170790476 12076326170946741 12076326171088340 12076326171092046
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 182 921341 921346 4194304 256 0 0 24 24 124736 0x7f76f7c91800 0x7f75c7a36780 0 0 0 12076326171140416 12076326171308499 12076326171491858 12076326171495336
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 184 921341 921346 4194304 256 0 0 24 24 126464 0x7f76f7c91700 0x7f75c7a367c0 0 0 0 12076326171554185 12076326171713458 12076326171854417 12076326171857940
95 93 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 186 921341 921346 4194304 256 0 0 20 24 127936 0x7f76f7c91600 0x7f75c7a36800 0 0 0 12076326171907041 12076326172073136 12076326172340175 12076326172364611
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 188 921341 921346 4194304 256 0 0 28 24 129664 0x7f76f7c91500 0x7f75c7a36840 0 0 0 12076326172409815 12076326172574734 12076326172834093 12076326172857427
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 190 921341 921346 4194304 256 0 0 24 24 131392 0x7f76f7c91400 0x7f75c7a36880 0 0 0 12076326172903733 12076326173060652 12076326173195532 12076326173199172
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 192 921341 921346 4194304 256 0 0 24 24 133632 0x7f76f7c91300 0x7f75c7a368c0 0 0 0 12076326173248955 12076326173412011 12076326173603690 12076326173626787
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 194 921341 921346 4194304 256 0 0 24 24 135360 0x7f76f7c91a00 0x7f75c7a36900 0 0 0 12076326173682180 12076326173843209 12076326173983848 12076326173987668
100 98 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 196 921341 921346 4194304 256 0 0 20 24 136832 0x7f76f7c91900 0x7f75c7a36940 0 0 0 12076326174035607 12076326174208007 12076326174491686 12076326174517883
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 198 921341 921346 4194304 256 0 0 28 24 138560 0x7f76f7c91800 0x7f75c7a36980 0 0 0 12076326174558418 12076326174713605 12076326174974084 12076326174996793
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 200 921341 921346 4194304 256 0 0 24 24 140288 0x7f76f7c91700 0x7f75c7a369c0 0 0 0 12076326175045013 12076326175202563 12076326175338083 12076326175341734
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 202 921341 921346 4194304 256 0 0 24 24 142784 0x7f76f7c91600 0x7f75c7a36a00 0 0 0 12076326175388361 12076326175553762 12076326175764641 12076326175784307
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 204 921341 921346 4194304 256 0 0 24 24 144768 0x7f76f7c91500 0x7f75c7a36a40 0 0 0 12076326175842906 12076326176006080 12076326176145120 12076326176149035
105 103 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 206 921341 921346 4194304 256 0 0 20 24 145728 0x7f76f7c91400 0x7f75c7a36a80 0 0 0 12076326176195491 12076326176371999 12076326176681437 12076326176704617
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 208 921341 921346 4194304 256 0 0 28 24 147712 0x7f76f7c91300 0x7f75c7a36ac0 0 0 0 12076326176749440 12076326176909437 12076326177175355 12076326177204276
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 210 921341 921346 4194304 256 0 0 24 24 149696 0x7f76f7c91a00 0x7f75c7a36b00 0 0 0 12076326177245282 12076326177402875 12076326177544954 12076326177548235
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 212 921341 921346 4194304 256 0 0 24 24 152192 0x7f76f7c91900 0x7f75c7a36b40 0 0 0 12076326177599340 12076326177756473 12076326177984952 12076326178013359
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 214 921341 921346 4194304 256 0 0 24 24 154176 0x7f76f7c91800 0x7f75c7a36b80 0 0 0 12076326178071167 12076326178232471 12076326178372951 12076326178376434
110 108 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 216 921341 921346 4194304 256 0 0 20 24 155648 0x7f76f7c91700 0x7f75c7a36bc0 0 0 0 12076326178424433 12076326178591350 12076326178920948 12076326178943718
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 218 921341 921346 4194304 256 0 0 28 24 157632 0x7f76f7c91600 0x7f75c7a36c00 0 0 0 12076326178986157 12076326179151028 12076326179416466 12076326179443577
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 220 921341 921346 4194304 256 0 0 24 24 159616 0x7f76f7c91500 0x7f75c7a36c40 0 0 0 12076326179482800 12076326179642546 12076326179779665 12076326179783329
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 222 921341 921346 4194304 256 0 0 24 24 162368 0x7f76f7c91400 0x7f75c7a36c80 0 0 0 12076326179831198 12076326179990704 12076326180235983 12076326180259293
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 224 921341 921346 4194304 256 0 0 24 24 164608 0x7f76f7c91300 0x7f75c7a36cc0 0 0 0 12076326180316890 12076326180482029 12076326180626509 12076326180633849
115 113 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 226 921341 921346 4194304 256 0 0 20 24 166336 0x7f76f7c91a00 0x7f75c7a36d00 0 0 0 12076326180677030 12076326180855947 12076326181257385 12076326181285881
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 228 921341 921346 4194304 256 0 0 28 24 168576 0x7f76f7c91900 0x7f75c7a36d40 0 0 0 12076326181326958 12076326181485545 12076326181750664 12076326181772816
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 230 921341 921346 4194304 256 0 0 24 24 170816 0x7f76f7c91800 0x7f75c7a36d80 0 0 0 12076326181815896 12076326181970983 12076326182110342 12076326182113700
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 232 921341 921346 4194304 256 0 0 24 24 174080 0x7f76f7c91700 0x7f75c7a36dc0 0 0 0 12076326182165897 12076326182331942 12076326182611461 12076326182634878
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 234 921341 921346 4194304 256 0 0 24 24 176576 0x7f76f7c91600 0x7f75c7a36e00 0 0 0 12076326182696092 12076326182857860 12076326182996259 12076326182999616
120 118 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 236 921341 921346 4194304 256 0 0 20 24 177792 0x7f76f7c91500 0x7f75c7a36e40 0 0 0 12076326183048026 12076326183220738 12076326183646337 12076326183672036
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 238 921341 921346 4194304 256 0 0 28 24 180288 0x7f76f7c91400 0x7f75c7a36e80 0 0 0 12076326183709986 12076326183869056 12076326184133855 12076326184157207
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 240 921341 921346 4194304 256 0 0 24 24 182784 0x7f76f7c91300 0x7f75c7a36ec0 0 0 0 12076326184200518 12076326184359135 12076326184498174 12076326184501497
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 242 921341 921346 4194304 256 0 0 24 24 186304 0x7f76f7c91a00 0x7f75c7a36f00 0 0 0 12076326184551580 12076326184711293 12076326185026652 12076326185051069
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 244 921341 921346 4194304 256 0 0 24 24 189312 0x7f76f7c91900 0x7f75c7a36f40 0 0 0 12076326185111311 12076326185274811 12076326185426491 12076326185429542
125 123 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 246 921341 921346 4194304 256 0 0 20 24 190784 0x7f76f7c91800 0x7f75c7a36f80 0 0 0 12076326185478333 12076326185639770 12076326186157208 12076326186181670
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 248 921341 921346 4194304 256 0 0 28 24 193792 0x7f76f7c91700 0x7f75c7a36fc0 0 0 0 12076326186223688 12076326186384727 12076326186684886 12076326186707146
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 250 921341 921346 4194304 256 0 0 24 24 196800 0x7f76f7c91600 0x7f75c7a37000 0 0 0 12076326186752681 12076326186915286 12076326187070645 12076326187074319
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 252 921341 921346 4194304 256 0 0 24 24 201088 0x7f76f7c91500 0x7f75c7a37040 0 0 0 12076326187124181 12076326187292884 12076326187704083 12076326187729196
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 254 921341 921346 4194304 256 0 0 24 24 204608 0x7f76f7c91400 0x7f75c7a37080 0 0 0 12076326187790570 12076326187952562 12076326188129841 12076326188133036
130 128 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 256 921341 921346 4194304 256 0 0 20 24 206080 0x7f76f7c91300 0x7f75c7a370c0 0 0 0 12076326188181166 12076326188350001 12076326188971758 12076326188995299
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 258 921341 921346 4194304 256 0 0 28 24 209600 0x7f76f7c91a00 0x7f75c7a37100 0 0 0 12076326189044100 12076326189201838 12076326189556876 12076326189580106
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 260 921341 921346 4194304 256 0 0 24 24 213120 0x7f76f7c91900 0x7f75c7a37140 0 0 0 12076326189627694 12076326189788556 12076326189967275 12076326189970311
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 262 921341 921346 4194304 256 0 0 24 24 218176 0x7f76f7c91800 0x7f75c7a37180 0 0 0 12076326190015445 12076326190203594 12076326190660713 12076326190686291
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 264 921341 921346 4194304 256 0 0 24 24 222208 0x7f76f7c91700 0x7f75c7a371c0 0 0 0 12076326190745031 12076326190905992 12076326191105991 12076326191133202
135 133 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 266 921341 921346 4194304 256 0 0 20 24 223936 0x7f76f7c91600 0x7f75c7a37200 0 0 0 12076326191175360 12076326191334950 12076326192037988 12076326192064543
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 268 921341 921346 4194304 256 0 0 28 24 227968 0x7f76f7c91500 0x7f75c7a37240 0 0 0 12076326192105990 12076326192265987 12076326192640066 12076326192664358
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 270 921341 921346 4194304 256 0 0 24 24 232000 0x7f76f7c91400 0x7f75c7a37280 0 0 0 12076326192713248 12076326192874305 12076326193077824 12076326193101670
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 272 921341 921346 4194304 256 0 0 24 24 237824 0x7f76f7c91300 0x7f75c7a372c0 0 0 0 12076326193152946 12076326193314463 12076326193857501 12076326193880999
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 274 921341 921346 4194304 256 0 0 24 24 242368 0x7f76f7c91a00 0x7f75c7a37300 0 0 0 12076326193942072 12076326194113021 12076326194370780 12076326194398350
140 138 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 276 921341 921346 4194304 256 0 0 20 24 243584 0x7f76f7c91900 0x7f75c7a37340 0 0 0 12076326194438775 12076326194600539 12076326195398936 12076326195446718
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 278 921341 921346 4194304 256 0 0 28 24 248128 0x7f76f7c91800 0x7f75c7a37380 0 0 0 12076326195476865 12076326195677015 12076326196096054 12076326196145738
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 280 921341 921346 4194304 256 0 0 24 24 252672 0x7f76f7c91700 0x7f75c7a373c0 0 0 0 12076326196178018 12076326196359893 12076326196586452 12076326196634085
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 282 921341 921346 4194304 256 0 0 24 24 259264 0x7f76f7c91600 0x7f75c7a37400 0 0 0 12076326196660624 12076326196833171 12076326197443569 12076326197495416
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 284 921341 921346 4194304 256 0 0 24 24 264832 0x7f76f7c91500 0x7f75c7a37440 0 0 0 12076326197534979 12076326197697808 12076326197967087 12076326198017276
145 143 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 286 921341 921346 4194304 256 0 0 20 24 266304 0x7f76f7c91400 0x7f75c7a37480 0 0 0 12076326198043214 12076326198220206 12076326199205803 12076326199272308
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 288 921341 921346 4194304 256 0 0 28 24 271872 0x7f76f7c91300 0x7f75c7a374c0 0 0 0 12076326199299058 12076326199479402 12076326200013480 12076326200080911
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 290 921341 921346 4194304 256 0 0 24 24 277440 0x7f76f7c91a00 0x7f75c7a37500 0 0 0 12076326200110796 12076326200290759 12076326200562598 12076326200628659
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 292 921341 921346 4194304 256 0 0 12 24 279936 0x7f76f7c91900 0x7f75c7a37540 0 0 0 12076326200654737 12076326200825477 12076326201564035 12076326201633917
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 294 921341 921346 4194304 256 0 0 24 24 286528 0x7f76f7c91800 0x7f75c7a37580 0 0 0 12076326201674473 12076326201836194 12076326202152673 12076326202220447
150 148 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 296 921341 921346 4194304 256 0 0 20 24 288000 0x7f76f7c91700 0x7f75c7a375c0 0 0 0 12076326202247007 12076326202420512 12076326203590908 12076326203659041
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 298 921341 921346 4194304 256 0 0 32 24 294592 0x7f76f7c91600 0x7f75c7a37600 0 0 0 12076326203688676 12076326203872027 12076326204480344 12076326204548744
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 300 921341 921346 4194304 256 0 0 24 24 301184 0x7f76f7c91500 0x7f75c7a37640 0 0 0 12076326204571687 12076326204756184 12076326205075862 12076326205142087
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 302 921341 921346 4194304 256 0 0 12 24 304960 0x7f76f7c91400 0x7f75c7a37680 0 0 0 12076326205169147 12076326205350901 12076326206228818 12076326206298105
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 304 921341 921346 4194304 256 0 0 24 24 313600 0x7f76f7c91300 0x7f75c7a376c0 0 0 0 12076326206340604 12076326206504657 12076326206915536 12076326206982287
155 153 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 306 921341 921346 4194304 256 0 0 20 24 314816 0x7f76f7c91a00 0x7f75c7a37700 0 0 0 12076326207017212 12076326207200495 12076326208746730 12076326208815464
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 308 921341 921346 4194304 256 0 0 20 24 317568 0x7f76f7c91900 0x7f75c7a37740 0 0 0 12076326208851220 12076326209013449 12076326209806726 12076326209875283
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 310 921341 921346 4194304 256 0 0 12 24 320320 0x7f76f7c91800 0x7f75c7a37780 0 0 0 12076326209911841 12076326210080965 12076326210495044 12076326210563202
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 312 921341 921346 4194304 256 0 0 12 24 324096 0x7f76f7c91700 0x7f75c7a377c0 0 0 0 12076326210593328 12076326210769603 12076326211929279 12076326211996726
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 314 921341 921346 4194304 256 0 0 12 24 328896 0x7f76f7c91600 0x7f75c7a37800 0 0 0 12076326212044795 12076326212212318 12076326212998075 12076326213066314
160 158 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 316 921341 921346 4194304 256 0 0 20 24 330112 0x7f76f7c91500 0x7f75c7a37840 0 0 0 12076326213095939 12076326213270074 12076326216318223 12076326216385793
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 318 921341 921346 4194304 256 0 0 20 24 332864 0x7f76f7c91400 0x7f75c7a37880 0 0 0 12076326216410419 12076326216603662 12076326218143177 12076326218211175
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 320 921341 921346 4194304 256 0 0 12 24 335616 0x7f76f7c91300 0x7f75c7a378c0 0 0 0 12076326218242043 12076326218420456 12076326219210053 12076326219276565
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 322 921341 921346 4194304 256 0 0 12 24 339392 0x7f76f7c91a00 0x7f75c7a37900 0 0 0 12076326219303325 12076326219484292 12076326221766204 12076326221833106
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 324 921341 921346 4194304 256 0 0 12 24 344192 0x7f76f7c91900 0x7f75c7a37940 0 0 0 12076326221877900 12076326222045243 12076326223580118 12076326223649212
165 163 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 326 921341 921346 4194304 256 0 0 20 24 345408 0x7f76f7c91800 0x7f75c7a37980 0 0 0 12076326223679478 12076326223858517 12076326229912096 12076326229982462
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 328 921341 921346 4194304 256 0 0 20 24 348160 0x7f76f7c91700 0x7f75c7a379c0 0 0 0 12076326230016785 12076326230196575 12076326233237044 12076326233306359
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 330 921341 921346 4194304 256 0 0 12 24 350912 0x7f76f7c91600 0x7f75c7a37a00 0 0 0 12076326233336234 12076326233514803 12076326235053998 12076326235121813
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 332 921341 921346 4194304 256 0 0 12 24 0 0x7f76f7c91500 0x7f75c7a37a40 0 0 0 12076326235150446 12076326235329197 12076326239856221 12076326239924749
@@ -0,0 +1,168 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,grd,Workgroup_Size,LDS_Per_Workgroup,scr,vgpr,SGPR,fbar,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"__amd_rocclr_fillBuffer.kd",0,0,0,920962,920967,33554432,256,0,0,8,32,6464,0x0,0x7f7263004180,4194304,3135444,401545944,12076323351077524,12076323592299708,12076323592623867,12076323592733000
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,920962,920967,32768,256,0,0,24,24,12480,0x0,0x7f7263035100,512,24896,3171600,12076323607390380,12076323607684997,12076323607691557,12076323607697111
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,920962,920967,4194304,256,0,0,24,24,12928,0x7f7393007900,0x7f7263035140,65536,199274,25512368,12076323607762212,12076323607972035,12076323608104675,12076323608108936
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,920962,920967,4194304,256,0,0,36,24,13632,0x7f7393007800,0x7f7263035180,65536,160944,20540400,12076323608178325,12076323608357474,12076323608605152,12076323608672253
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,920962,920967,4194304,256,0,0,28,24,14080,0x7f7393007700,0x7f72630351c0,65536,200012,25576368,12076323608705605,12076323608885311,12076323609132670,12076323609203490
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,920962,920967,4194304,256,0,0,24,24,14528,0x7f7393007600,0x7f7263035200,65536,192548,24657112,12076323609233927,12076323609419549,12076323609557308,12076323609560974
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,920962,920967,4194304,256,0,0,24,24,14976,0x7f7393007500,0x7f7263035240,65536,201756,25789000,12076323609615696,12076323609779547,12076323609916666,12076323609920593
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,920962,920967,4194304,256,0,0,24,24,15424,0x7f7393007400,0x7f7263035280,131072,245308,31232888,12076323609990523,12076323610162105,12076323610293785,12076323610297623
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,920962,920967,4194304,256,0,0,28,24,16128,0x7f7393007300,0x7f72630352c0,131072,200518,25634984,12076323610344220,12076323610519704,12076323610769622,12076323610810206
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,920962,920967,4194304,256,0,0,28,24,16832,0x7f7393007a00,0x7f7263035300,65536,179708,22941752,12076323610835333,12076323611013941,12076323611266580,12076323611305296
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,920962,920967,4194304,256,0,0,24,24,17536,0x7f7393007900,0x7f7263035340,131072,247130,31623792,12076323611329822,12076323611521459,12076323611652498,12076323611656288
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,920962,920967,4194304,256,0,0,24,24,18240,0x7f7393007800,0x7f7263035380,131072,264724,34008888,12076323611701232,12076323611879217,12076323612015697,12076323612019664
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,920962,920967,4194304,256,0,0,24,24,18944,0x7f7393007700,0x7f72630353c0,131072,244246,31482840,12076323612083482,12076323612256496,12076323612386415,12076323612390363
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,920962,920967,4194304,256,0,0,28,24,19904,0x7f7393007600,0x7f7263035400,131072,213208,27239808,12076323612443391,12076323612605454,12076323612861773,12076323612927150
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,920962,920967,4194304,256,0,0,28,24,20608,0x7f7393007500,0x7f7263035440,65536,196076,25275816,12076323612953149,12076323613135532,12076323613383050,12076323613448068
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,920962,920967,4194304,256,0,0,24,24,21312,0x7f7393007400,0x7f7263035480,131072,242030,30925496,12076323613474588,12076323613650249,12076323613778889,12076323613782841
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,920962,920967,4194304,256,0,0,24,24,22016,0x7f7393007300,0x7f72630354c0,131072,244734,31308384,12076323613837853,12076323613996648,12076323614128007,12076323614132150
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,920962,920967,4194304,256,0,0,24,24,22720,0x7f7393007a00,0x7f7263035500,131072,254372,32612704,12076323614193303,12076323614355846,12076323614488165,12076323614491988
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,920962,920967,4194304,256,0,0,28,24,23680,0x7f7393007900,0x7f7263035540,131072,231684,29588352,12076323614543384,12076323614709604,12076323614969443,12076323615035949
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,920962,920967,4194304,256,0,0,28,24,24384,0x7f7393007800,0x7f7263035580,65536,176878,22653784,12076323615061597,12076323615254082,12076323615510721,12076323615575652
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,920962,920967,4194304,256,0,0,24,24,25088,0x7f7393007700,0x7f72630355c0,131072,239276,30622448,12076323615601120,12076323615781439,12076323615918239,12076323615921966
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,920962,920967,4194304,256,0,0,24,24,25792,0x7f7393007600,0x7f7263035600,131072,240084,30830432,12076323615974083,12076323616147998,12076323616278877,12076323616282867
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,920962,920967,4194304,256,0,0,24,24,26496,0x7f7393007500,0x7f7263035640,131072,273802,35277120,12076323616345493,12076323616510556,12076323616637595,12076323616641573
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,920962,920967,4194304,256,0,0,28,24,27712,0x7f7393007400,0x7f7263035680,131072,225544,28745000,12076323616689422,12076323616857754,12076323617111513,12076323617177008
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,920962,920967,4194304,256,0,0,28,24,28416,0x7f7393007300,0x7f72630356c0,65536,201166,25813712,12076323617202917,12076323617381432,12076323617627191,12076323617691765
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,920962,920967,4194304,256,0,0,24,24,29120,0x7f7393007a00,0x7f7263035700,131072,243484,31154056,12076323617718425,12076323617889590,12076323618019189,12076323618023131
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,920962,920967,4194304,256,0,0,24,24,30080,0x7f7393007900,0x7f7263035740,131072,268342,34452464,12076323618066572,12076323618248948,12076323618379827,12076323618383821
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,920962,920967,4194304,256,0,0,24,24,30784,0x7f7393007800,0x7f7263035780,131072,245610,31610232,12076323618445366,12076323618606866,12076323618735826,12076323618739542
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,920962,920967,4194304,256,0,0,28,24,32000,0x7f7393007700,0x7f72630357c0,131072,229882,29441200,12076323618789986,12076323618964305,12076323619220144,12076323619285327
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,920962,920967,4194304,256,0,0,28,24,32960,0x7f7393007600,0x7f7263035800,65536,185232,23694696,12076323619309532,12076323619489742,12076323619738861,12076323619803981
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,920962,920967,4194304,256,0,0,24,24,33920,0x7f7393007500,0x7f7263035840,131072,256836,32780368,12076323619829568,12076323620003020,12076323620131819,12076323620135827
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,920962,920967,4194304,256,0,0,24,24,34880,0x7f7393007400,0x7f7263035880,131072,261330,33319384,12076323620179368,12076323620356778,12076323620488618,12076323620492420
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,920962,920967,4194304,256,0,0,24,24,35840,0x7f7393007300,0x7f72630358c0,131072,280200,35738192,12076323620553834,12076323620714377,12076323620846536,12076323620850315
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,920962,920967,4194304,256,0,0,28,24,37312,0x7f7393007a00,0x7f7263035900,131072,225070,28804256,12076323620901330,12076323621078375,12076323621335814,12076323621401139
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,920962,920967,4194304,256,0,0,28,24,38272,0x7f7393007900,0x7f7263035940,65536,167896,21475136,12076323621424532,12076323621602693,12076323621853731,12076323621892512
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,920962,920967,4194304,256,0,0,24,24,39232,0x7f7393007800,0x7f7263035980,131072,247034,31388232,12076323621917148,12076323622100130,12076323622230850,12076323622234698
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,920962,920967,4194304,256,0,0,24,24,40192,0x7f7393007700,0x7f72630359c0,131072,245000,31370136,12076323622285943,12076323622447649,12076323622580928,12076323622584658
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,920962,920967,4194304,256,0,0,24,24,41152,0x7f7393007600,0x7f7263035a00,131072,228836,29280720,12076323622647315,12076323622810367,12076323622941886,12076323622945860
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,920962,920967,4194304,256,0,0,28,24,42624,0x7f7393007500,0x7f7263035a40,131072,199872,25664664,12076323622995662,12076323623168765,12076323623424924,12076323623490412
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,920962,920967,4194304,256,0,0,28,24,43584,0x7f7393007400,0x7f7263035a80,65536,180488,23097792,12076323623514015,12076323623690843,12076323623940122,12076323624010608
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,920962,920967,4194304,256,0,0,24,24,44544,0x7f7393007300,0x7f7263035ac0,131072,229426,29189648,12076323624038510,12076323624215481,12076323624346040,12076323624350069
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,920962,920967,4194304,256,0,0,24,24,45760,0x7f7393007a00,0x7f7263035b00,131072,247200,31674880,12076323624399341,12076323624560759,12076323624691638,12076323624695481
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,920962,920967,4194304,256,0,0,24,24,46720,0x7f7393007900,0x7f7263035b40,131072,230340,29218688,12076323624756074,12076323624917717,12076323625044757,12076323625048748
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,920962,920967,4194304,256,0,0,28,24,48448,0x7f7393007800,0x7f7263035b80,131072,224878,28730232,12076323625101255,12076323625263636,12076323625528114,12076323625571169
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,920962,920967,4194304,256,0,0,28,24,49408,0x7f7393007700,0x7f7263035bc0,65536,202786,25939176,12076323625596766,12076323625771313,12076323626062192,12076323626127663
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,920962,920967,4194304,256,0,0,24,24,50368,0x7f7393007600,0x7f7263035c00,131072,276026,35451600,12076323626159702,12076323626335951,12076323626465870,12076323626469678
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,920962,920967,4194304,256,0,0,24,24,51584,0x7f7393007500,0x7f7263035c40,131072,270312,34520392,12076323626520994,12076323626699789,12076323626835148,12076323626838845
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,920962,920967,4194304,256,0,0,24,24,52544,0x7f7393007400,0x7f7263035c80,131072,242800,31121504,12076323626901020,12076323627065707,12076323627196107,12076323627200306
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,920962,920967,4194304,256,0,0,28,24,54272,0x7f7393007300,0x7f7263035cc0,131072,226928,29085304,12076323627248476,12076323627417706,12076323627676425,12076323627742083
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,920962,920967,4194304,256,0,0,28,24,55488,0x7f7393007a00,0x7f7263035d00,65536,202828,25941824,12076323627767250,12076323627940423,12076323628194822,12076323628262440
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,920962,920967,4194304,256,0,0,24,24,56704,0x7f7393007900,0x7f7263035d40,131072,259198,32951472,12076323628286976,12076323628463621,12076323628601060,12076323628604786
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,920962,920967,4194304,256,0,0,24,24,58176,0x7f7393007800,0x7f7263035d80,131072,258282,33021128,12076323628659398,12076323628817859,12076323628958979,12076323628962852
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,920962,920967,4194304,256,0,0,24,24,59392,0x7f7393007700,0x7f7263035dc0,131072,246652,31546856,12076323629030508,12076323629193058,12076323629326977,12076323629330896
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,920962,920967,4194304,256,0,0,28,24,61376,0x7f7393007600,0x7f7263035e00,131072,245768,31560440,12076323629386489,12076323629542816,12076323629802175,12076323629843308
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,920962,920967,4194304,256,0,0,28,24,62592,0x7f7393007500,0x7f7263035e40,65536,173704,22245464,12076323629867744,12076323630053854,12076323630304572,12076323630369406
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,920962,920967,4194304,256,0,0,24,24,63808,0x7f7393007400,0x7f7263035e80,131072,275760,35575200,12076323630396136,12076323630575771,12076323630705851,12076323630709839
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,920962,920967,4194304,256,0,0,24,24,65280,0x7f7393007300,0x7f7263035ec0,131072,244024,31108304,12076323630758709,12076323630925690,12076323631065529,12076323631069196
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,920962,920967,4194304,256,0,0,24,24,66496,0x7f7393007a00,0x7f7263035f00,131072,279584,35794400,12076323631131202,12076323631293528,12076323631422807,12076323631426681
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,920962,920967,4194304,256,0,0,28,24,68480,0x7f7393007900,0x7f7263035f40,131072,228846,29230256,12076323631480451,12076323631638646,12076323631904725,12076323631949863
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,920962,920967,4194304,256,0,0,28,24,69696,0x7f7393007800,0x7f7263035f80,65536,199242,25601280,12076323631974689,12076323632154964,12076323632410643,12076323632457957
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,920962,920967,4194304,256,0,0,24,24,70912,0x7f7393007700,0x7f7263035fc0,131072,275868,35385664,12076323632483795,12076323632658802,12076323632792881,12076323632796607
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,920962,920967,4194304,256,0,0,24,24,72384,0x7f7393007600,0x7f7263036000,131072,271282,35165760,12076323632845918,12076323633015120,12076323633153199,12076323633157317
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,920962,920967,4194304,256,0,0,24,24,73600,0x7f7393007500,0x7f7263036040,131072,249424,31654416,12076323633219923,12076323633379598,12076323633507598,12076323633511495
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,920962,920967,4194304,256,0,0,28,24,75840,0x7f7393007400,0x7f7263036080,131072,231548,29587792,12076323633560647,12076323633723597,12076323633993835,12076323634041110
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,920962,920967,4194304,256,0,0,28,24,77056,0x7f7393007300,0x7f72630360c0,65536,171078,21878256,12076323634064573,12076323634247754,12076323634497513,12076323634544395
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,920962,920967,4194304,256,0,0,24,24,78272,0x7f7393007a00,0x7f7263036100,131072,279070,35673072,12076323634566676,12076323634744392,12076323634881991,12076323634885539
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,920962,920967,4194304,256,0,0,24,24,80000,0x7f7393007900,0x7f7263036140,131072,219862,28157320,12076323634935893,12076323635109030,12076323635251590,12076323635255527
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,920962,920967,4194304,256,0,0,24,24,81216,0x7f7393007800,0x7f7263036180,131072,280770,35921656,12076323635319345,12076323635479429,12076323635616548,12076323635620505
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,920962,920967,4194304,256,0,0,28,24,83456,0x7f7393007700,0x7f72630361c0,131072,225682,28885744,12076323635670889,12076323635830627,12076323636091906,12076323636139600
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,920962,920967,4194304,256,0,0,28,24,84928,0x7f7393007600,0x7f7263036200,65536,201798,25883064,12076323636164396,12076323636340705,12076323636596864,12076323636643787
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,920962,920967,4194304,256,0,0,24,24,86400,0x7f7393007500,0x7f7263036240,131072,252542,32432200,12076323636670386,12076323636858942,12076323636997182,12076323637004858
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,920962,920967,4194304,256,0,0,24,24,88128,0x7f7393007400,0x7f7263036280,131072,231120,29646360,12076323637050883,12076323637215581,12076323637365500,12076323637369425
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,920962,920967,4194304,256,0,0,24,24,89600,0x7f7393007300,0x7f72630362c0,131072,247918,31659608,12076323637448462,12076323637609019,12076323637738138,12076323637741947
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,920962,920967,4194304,256,0,0,28,24,92096,0x7f7393007a00,0x7f7263036300,131072,229196,29396248,12076323637791129,12076323637955257,12076323638219416,12076323638265911
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,920962,920967,4194304,256,0,0,28,24,93568,0x7f7393007900,0x7f7263036340,65536,171128,21860632,12076323638292190,12076323638465335,12076323638713494,12076323638759559
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,920962,920967,4194304,256,0,0,24,24,95040,0x7f7393007800,0x7f7263036380,131072,269838,34491744,12076323638783784,12076323638956053,12076323639092532,12076323639096996
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,920962,920967,4194304,256,0,0,24,24,96768,0x7f7393007700,0x7f72630363c0,131072,250148,31950712,12076323639146939,12076323639306611,12076323639463410,12076323639467314
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,920962,920967,4194304,256,0,0,24,24,98240,0x7f7393007600,0x7f7263036400,131072,278424,35527744,12076323639529730,12076323639688369,12076323639816529,12076323639820390
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,920962,920967,4194304,256,0,0,28,24,100736,0x7f7393007500,0x7f7263036440,131072,229564,29332528,12076323639870634,12076323640039248,12076323640302286,12076323640328254
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,920962,920967,4194304,256,0,0,28,24,102208,0x7f7393007400,0x7f7263036480,65536,197912,25313256,12076323640369481,12076323640524365,12076323640777804,12076323640798889
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,920962,920967,4194304,256,0,0,24,24,103680,0x7f7393007300,0x7f72630364c0,131072,241314,30851752,12076323640843542,12076323640998763,12076323641131883,12076323641136055
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,920962,920967,4194304,256,0,0,24,24,105664,0x7f7393007a00,0x7f7263036500,131072,245368,31363504,12076323641187371,12076323641361162,12076323641526441,12076323641530699
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,920962,920967,4194304,256,0,0,24,24,107136,0x7f7393007900,0x7f7263036540,131072,249022,31724096,12076323641592574,12076323641748200,12076323641886919,12076323641891058
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,920962,920967,4194304,256,0,0,28,24,109888,0x7f7393007800,0x7f7263036580,131072,201048,25737440,12076323641941292,12076323642098758,12076323642357637,12076323642381981
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,920962,920967,4194304,256,0,0,28,24,111360,0x7f7393007700,0x7f72630365c0,65536,184142,23592320,12076323642424540,12076323642581796,12076323642833315,12076323642855160
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,920962,920967,4194304,256,0,0,24,24,112832,0x7f7393007600,0x7f7263036600,131072,246264,31616104,12076323642900564,12076323643068674,12076323643204193,12076323643208517
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,920962,920967,4194304,256,0,0,24,24,114816,0x7f7393007500,0x7f7263036640,131072,273018,34992472,12076323643260002,12076323643419712,12076323643593311,12076323643597510
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,920962,920967,4194304,256,0,0,24,24,116288,0x7f7393007400,0x7f7263036680,131072,280378,35882680,12076323643659204,12076323643815870,12076323643953950,12076323643958020
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,920962,920967,4194304,256,0,0,28,24,119040,0x7f7393007300,0x7f72630366c0,131072,205034,26250952,12076323644013503,12076323644174589,12076323644432507,12076323644458490
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,920962,920967,4194304,256,0,0,28,24,120768,0x7f7393007a00,0x7f7263036700,65536,198622,25316456,12076323644499306,12076323644652186,12076323644904505,12076323644926209
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,920962,920967,4194304,256,0,0,24,24,122496,0x7f7393007900,0x7f7263036740,131072,261612,33500992,12076323644970712,12076323645130904,12076323645305783,12076323645309822
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,920962,920967,4194304,256,0,0,24,24,124736,0x7f7393007800,0x7f7263036780,131072,267348,34363840,12076323645359484,12076323645526742,12076323645709782,12076323645713653
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,920962,920967,4194304,256,0,0,24,24,126464,0x7f7393007700,0x7f72630367c0,131072,247098,31735760,12076323645779445,12076323645934741,12076323646068660,12076323646073081
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,920962,920967,4194304,256,0,0,20,24,127936,0x7f7393007600,0x7f7263036800,131072,270960,34546432,12076323646122943,12076323646289619,12076323646556818,12076323646579101
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,920962,920967,4194304,256,0,0,28,24,129664,0x7f7393007500,0x7f7263036840,65536,174178,22248688,12076323646622692,12076323646779857,12076323647036015,12076323647061838
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,920962,920967,4194304,256,0,0,24,24,131392,0x7f7393007400,0x7f7263036880,131072,222078,28508408,12076323647105479,12076323647273294,12076323647411054,12076323647414984
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,920962,920967,4194304,256,0,0,24,24,133632,0x7f7393007300,0x7f72630368c0,131072,254992,32479592,12076323647464476,12076323647644013,12076323647835692,12076323647856705
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,920962,920967,4194304,256,0,0,24,24,135360,0x7f7393007a00,0x7f7263036900,131072,241268,30908928,12076323647916827,12076323648093771,12076323648229770,12076323648234087
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,920962,920967,4194304,256,0,0,20,24,136832,0x7f7393007900,0x7f7263036940,131072,254598,32667048,12076323648276766,12076323648458729,12076323648773287,12076323648791362
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,920962,920967,4194304,256,0,0,28,24,138560,0x7f7393007800,0x7f7263036980,65536,206060,26411944,12076323648838079,12076323649005126,12076323649256005,12076323649277977
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,920962,920967,4194304,256,0,0,24,24,140288,0x7f7393007700,0x7f72630369c0,131072,240384,30637304,12076323649326036,12076323649491044,12076323649621124,12076323649625092
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,920962,920967,4194304,256,0,0,24,24,142784,0x7f7393007600,0x7f7263036a00,131072,240522,30740944,12076323649680595,12076323649842883,12076323650052162,12076323650076410
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,920962,920967,4194304,256,0,0,24,24,144768,0x7f7393007500,0x7f7263036a40,131072,265848,33910808,12076323650135931,12076323650304160,12076323650439680,12076323650443833
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,920962,920967,4194304,256,0,0,20,24,145728,0x7f7393007400,0x7f7263036a80,131072,251302,32293864,12076323650496311,12076323650666879,12076323650974077,12076323650994046
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,920962,920967,4194304,256,0,0,28,24,147712,0x7f7393007300,0x7f7263036ac0,65536,185108,23763296,12076323651055961,12076323651225276,12076323651481595,12076323651501198
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,920962,920967,4194304,256,0,0,24,24,149696,0x7f7393007a00,0x7f7263036b00,131072,260708,33431120,12076323651553466,12076323651720794,12076323651861753,12076323651865916
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,920962,920967,4194304,256,0,0,24,24,152192,0x7f7393007900,0x7f7263036b40,131072,243794,30960016,12076323651916691,12076323652097912,12076323652325591,12076323652350136
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,920962,920967,4194304,256,0,0,24,24,154176,0x7f7393007800,0x7f7263036b80,131072,246144,31516136,12076323652403676,12076323652569750,12076323652710069,12076323652714123
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,920962,920967,4194304,256,0,0,20,24,155648,0x7f7393007700,0x7f7263036bc0,131072,238694,30613232,12076323652763665,12076323652943508,12076323653301427,12076323653323185
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,920962,920967,4194304,256,0,0,28,24,157632,0x7f7393007600,0x7f7263036c00,65536,194502,24878424,12076323653368719,12076323653534386,12076323653794064,12076323653815029
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,920962,920967,4194304,256,0,0,24,24,159616,0x7f7393007500,0x7f7263036c40,131072,243150,31094624,12076323653859551,12076323654027503,12076323654207822,12076323654212217
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,920962,920967,4194304,256,0,0,24,24,162368,0x7f7393007400,0x7f7263036c80,131072,280728,35873288,12076323654261919,12076323654437901,12076323654682860,12076323654704502
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,920962,920967,4194304,256,0,0,24,24,164608,0x7f7393007300,0x7f7263036cc0,131072,268110,34345528,12076323654766988,12076323654933579,12076323655073098,12076323655077264
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,920962,920967,4194304,256,0,0,20,24,166336,0x7f7393007a00,0x7f7263036d00,131072,264734,34046968,12076323655131836,12076323655300233,12076323655676232,12076323655700312
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,920962,920967,4194304,256,0,0,28,24,168576,0x7f7393007900,0x7f7263036d40,65536,171002,21915616,12076323655742691,12076323655909670,12076323656170149,12076323656195052
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,920962,920967,4194304,256,0,0,24,24,170816,0x7f7393007800,0x7f7263036d80,131072,273494,35074952,12076323656241849,12076323656407588,12076323656551108,12076323656553819
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,920962,920967,4194304,256,0,0,24,24,174080,0x7f7393007700,0x7f7263036dc0,131072,244350,31350440,12076323656603721,12076323656771747,12076323657081346,12076323657101136
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,920962,920967,4194304,256,0,0,24,24,176576,0x7f7393007600,0x7f7263036e00,131072,272266,34966264,12076323657165044,12076323657337025,12076323657479905,12076323657482895
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,920962,920967,4194304,256,0,0,20,24,177792,0x7f7393007500,0x7f7263036e40,131072,250608,32167248,12076323657532858,12076323657712384,12076323658135263,12076323658155425
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,920962,920967,4194304,256,0,0,28,24,180288,0x7f7393007400,0x7f7263036e80,65536,187080,23892424,12076323658200890,12076323658366782,12076323658626941,12076323658646518
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,920962,920967,4194304,256,0,0,24,24,182784,0x7f7393007300,0x7f7263036ec0,131072,273216,34911920,12076323658691571,12076323658863581,12076323659002780,12076323659011135
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,920962,920967,4194304,256,0,0,24,24,186304,0x7f7393007a00,0x7f7263036f00,131072,267540,34379304,12076323659056800,12076323659238300,12076323659553819,12076323659577328
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,920962,920967,4194304,256,0,0,24,24,189312,0x7f7393007900,0x7f7263036f40,131072,235356,30315176,12076323659636908,12076323659806618,12076323659958297,12076323659961081
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,920962,920967,4194304,256,0,0,20,24,190784,0x7f7393007800,0x7f7263036f80,131072,267360,34113064,12076323660017666,12076323660195097,12076323660711415,12076323660735460
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,920962,920967,4194304,256,0,0,28,24,193792,0x7f7393007700,0x7f7263036fc0,65536,190478,24411512,12076323660777127,12076323660943734,12076323661245973,12076323661266196
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,920962,920967,4194304,256,0,0,24,24,196800,0x7f7393007600,0x7f7263037000,131072,270202,34510000,12076323661315488,12076323661485813,12076323661640532,12076323661643397
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,920962,920967,4194304,256,0,0,24,24,201088,0x7f7393007500,0x7f7263037040,131072,241254,31062272,12076323661695865,12076323661881811,12076323662292210,12076323662315797
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,920962,920967,4194304,256,0,0,24,24,204608,0x7f7393007400,0x7f7263037080,131072,247580,31499496,12076323662372633,12076323662543249,12076323662719249,12076323662722222
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,920962,920967,4194304,256,0,0,20,24,206080,0x7f7393007300,0x7f72630370c0,131072,276044,35254912,12076323662771854,12076323662946928,12076323663556046,12076323663576370
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,920962,920967,4194304,256,0,0,28,24,209600,0x7f7393007a00,0x7f7263037100,65536,183066,23358592,12076323663620852,12076323663787086,12076323664114765,12076323664138274
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,920962,920967,4194304,256,0,0,24,24,213120,0x7f7393007900,0x7f7263037140,131072,268336,34289904,12076323664180352,12076323664344684,12076323664524363,12076323664527257
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,920962,920967,4194304,256,0,0,24,24,218176,0x7f7393007800,0x7f7263037180,131072,245282,31478568,12076323664577129,12076323664755883,12076323665211721,12076323665232327
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,920962,920967,4194304,256,0,0,24,24,222208,0x7f7393007700,0x7f72630371c0,131072,262508,33623432,12076323665292599,12076323665461320,12076323665661640,12076323665677815
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,920962,920967,4194304,256,0,0,20,24,223936,0x7f7393007600,0x7f7263037200,131072,272266,35134032,12076323665727437,12076323665892519,12076323666594117,12076323666617932
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,920962,920967,4194304,256,0,0,28,24,227968,0x7f7393007500,0x7f7263037240,65536,183994,23642032,12076323666658768,12076323666829796,12076323667204195,12076323667223918
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,920962,920967,4194304,256,0,0,24,24,232000,0x7f7393007400,0x7f7263037280,131072,243438,31099776,12076323667270735,12076323667437154,12076323667639074,12076323667659808
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,920962,920967,4194304,256,0,0,24,24,237824,0x7f7393007300,0x7f72630372c0,131072,248044,31575664,12076323667703059,12076323667867233,12076323668392991,12076323668420122
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,920962,920967,4194304,256,0,0,24,24,242368,0x7f7393007a00,0x7f7263037300,131072,251398,31976816,12076323668481055,12076323668652351,12076323668876830,12076323668897068
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,920962,920967,4194304,256,0,0,20,24,243584,0x7f7393007900,0x7f7263037340,131072,235974,30452504,12076323668940909,12076323669110589,12076323669908507,12076323669931871
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,920962,920967,4194304,256,0,0,28,24,248128,0x7f7393007800,0x7f7263037380,65536,187722,23922960,12076323669974450,12076323670149146,12076323670570585,12076323670594963
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,920962,920967,4194304,256,0,0,24,24,252672,0x7f7393007700,0x7f72630373c0,131072,257792,33088104,12076323670635920,12076323670808184,12076323671035863,12076323671057253
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,920962,920967,4194304,256,0,0,24,24,259264,0x7f7393007600,0x7f7263037400,131072,275128,35343024,12076323671101405,12076323671258583,12076323671855061,12076323671876725
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,920962,920967,4194304,256,0,0,24,24,264832,0x7f7393007500,0x7f7263037440,131072,241150,31176032,12076323671927931,12076323672091860,12076323672360339,12076323672384890
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,920962,920967,4194304,256,0,0,20,24,266304,0x7f7393007400,0x7f7263037480,131072,245240,31135608,12076323672428952,12076323672588339,12076323673572336,12076323673639532
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,920962,920967,4194304,256,0,0,28,24,271872,0x7f7393007300,0x7f72630374c0,65536,185494,23810848,12076323673667443,12076323673849455,12076323674363053,12076323674429710
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,920962,920967,4194304,256,0,0,24,24,277440,0x7f7393007a00,0x7f7263037500,131072,270626,34681168,12076323674461469,12076323674637132,12076323674908011,12076323674970535
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,920962,920967,4194304,256,0,0,12,24,279936,0x7f7393007900,0x7f7263037540,131072,260462,33475128,12076323675006943,12076323675186411,12076323675924008,12076323675991472
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,920962,920967,4194304,256,0,0,24,24,286528,0x7f7393007800,0x7f7263037580,131072,244092,31314424,12076323676037167,12076323676197447,12076323676512647,12076323676578483
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,920962,920967,4194304,256,0,0,20,24,288000,0x7f7393007700,0x7f72630375c0,131072,252970,32336632,12076323676603239,12076323676779046,12076323677948322,12076323678020764
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,920962,920967,4194304,256,0,0,32,24,294592,0x7f7393007600,0x7f7263037600,65536,189272,24113696,12076323678050098,12076323678234721,12076323678844159,12076323678909375
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,920962,920967,4194304,256,0,0,24,24,301184,0x7f7393007500,0x7f7263037640,131072,244778,31233472,12076323678933039,12076323679122398,12076323679440798,12076323679505072
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,920962,920967,4194304,256,0,0,12,24,304960,0x7f7393007400,0x7f7263037680,131072,241846,31135968,12076323679531732,12076323679705277,12076323680583034,12076323680649179
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,920962,920967,4194304,256,0,0,24,24,313600,0x7f7393007300,0x7f72630376c0,131072,250416,31980512,12076323680686989,12076323680856473,12076323681267192,12076323681336947
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,920962,920967,4194304,256,0,0,20,24,314816,0x7f7393007a00,0x7f7263037700,131072,277318,35157984,12076323681365360,12076323681546391,12076323683093586,12076323683159244
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,920962,920967,4194304,256,0,0,20,24,317568,0x7f7393007900,0x7f7263037740,65536,174154,22345656,12076323683188548,12076323683365585,12076323684158383,12076323684223451
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,920962,920967,4194304,256,0,0,12,24,320320,0x7f7393007800,0x7f7263037780,131072,279118,35872752,12076323684246374,12076323684431982,12076323684846381,12076323684910077
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,920962,920967,4194304,256,0,0,12,24,324096,0x7f7393007700,0x7f72630377c0,131072,247552,31617312,12076323684935525,12076323685122220,12076323686280456,12076323686347078
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,920962,920967,4194304,256,0,0,12,24,328896,0x7f7393007600,0x7f7263037800,131072,277944,35691800,12076323686387293,12076323686546216,12076323687332453,12076323687401077
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,920962,920967,4194304,256,0,0,20,24,330112,0x7f7393007500,0x7f7263037840,131072,246180,31661440,12076323687432706,12076323687605252,12076323690654203,12076323690720816
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,920962,920967,4194304,256,0,0,20,24,332864,0x7f7393007400,0x7f7263037880,65536,191938,24518880,12076323690752285,12076323690931962,12076323692473717,12076323692541400
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,920962,920967,4194304,256,0,0,12,24,335616,0x7f7393007300,0x7f72630378c0,131072,239628,30708424,12076323692574762,12076323692744437,12076323693534834,12076323693601841
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,920962,920967,4194304,256,0,0,12,24,339392,0x7f7393007a00,0x7f7263037900,131072,274278,35149648,12076323693628941,12076323693813553,12076323696095786,12076323696163692
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,920962,920967,4194304,256,0,0,12,24,344192,0x7f7393007900,0x7f7263037940,131072,248204,31666344,12076323696207553,12076323696367785,12076323697903461,12076323697970319
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,920962,920967,4194304,256,0,0,20,24,345408,0x7f7393007800,0x7f7263037980,131072,279784,35644216,12076323697998331,12076323698187300,12076323704239601,12076323704292348
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,920962,920967,4194304,256,0,0,20,24,348160,0x7f7393007700,0x7f72630379c0,65536,171254,22059944,12076323704321372,12076323704501520,12076323707542631,12076323707610255
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,920962,920967,4194304,256,0,0,12,24,350912,0x7f7393007600,0x7f7263037a00,131072,272624,34769824,12076323707638567,12076323707815270,12076323709354626,12076323709422493
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,920962,920967,4194304,256,0,0,12,24,0,0x7f7393007500,0x7f7263037a40,131072,267182,34191504,12076323709451777,12076323709631745,12076323714158451,12076323714224717
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid grd Workgroup_Size LDS_Per_Workgroup scr vgpr SGPR fbar sig obj SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 __amd_rocclr_fillBuffer.kd 0 0 0 920962 920967 33554432 256 0 0 8 32 6464 0x0 0x7f7263004180 4194304 3135444 401545944 12076323351077524 12076323592299708 12076323592623867 12076323592733000
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 920962 920967 32768 256 0 0 24 24 12480 0x0 0x7f7263035100 512 24896 3171600 12076323607390380 12076323607684997 12076323607691557 12076323607697111
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 4 920962 920967 4194304 256 0 0 24 24 12928 0x7f7393007900 0x7f7263035140 65536 199274 25512368 12076323607762212 12076323607972035 12076323608104675 12076323608108936
5 3 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 6 920962 920967 4194304 256 0 0 36 24 13632 0x7f7393007800 0x7f7263035180 65536 160944 20540400 12076323608178325 12076323608357474 12076323608605152 12076323608672253
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 8 920962 920967 4194304 256 0 0 28 24 14080 0x7f7393007700 0x7f72630351c0 65536 200012 25576368 12076323608705605 12076323608885311 12076323609132670 12076323609203490
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 10 920962 920967 4194304 256 0 0 24 24 14528 0x7f7393007600 0x7f7263035200 65536 192548 24657112 12076323609233927 12076323609419549 12076323609557308 12076323609560974
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 12 920962 920967 4194304 256 0 0 24 24 14976 0x7f7393007500 0x7f7263035240 65536 201756 25789000 12076323609615696 12076323609779547 12076323609916666 12076323609920593
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 14 920962 920967 4194304 256 0 0 24 24 15424 0x7f7393007400 0x7f7263035280 131072 245308 31232888 12076323609990523 12076323610162105 12076323610293785 12076323610297623
10 8 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 16 920962 920967 4194304 256 0 0 28 24 16128 0x7f7393007300 0x7f72630352c0 131072 200518 25634984 12076323610344220 12076323610519704 12076323610769622 12076323610810206
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 18 920962 920967 4194304 256 0 0 28 24 16832 0x7f7393007a00 0x7f7263035300 65536 179708 22941752 12076323610835333 12076323611013941 12076323611266580 12076323611305296
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 20 920962 920967 4194304 256 0 0 24 24 17536 0x7f7393007900 0x7f7263035340 131072 247130 31623792 12076323611329822 12076323611521459 12076323611652498 12076323611656288
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 22 920962 920967 4194304 256 0 0 24 24 18240 0x7f7393007800 0x7f7263035380 131072 264724 34008888 12076323611701232 12076323611879217 12076323612015697 12076323612019664
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 24 920962 920967 4194304 256 0 0 24 24 18944 0x7f7393007700 0x7f72630353c0 131072 244246 31482840 12076323612083482 12076323612256496 12076323612386415 12076323612390363
15 13 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 26 920962 920967 4194304 256 0 0 28 24 19904 0x7f7393007600 0x7f7263035400 131072 213208 27239808 12076323612443391 12076323612605454 12076323612861773 12076323612927150
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 28 920962 920967 4194304 256 0 0 28 24 20608 0x7f7393007500 0x7f7263035440 65536 196076 25275816 12076323612953149 12076323613135532 12076323613383050 12076323613448068
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 30 920962 920967 4194304 256 0 0 24 24 21312 0x7f7393007400 0x7f7263035480 131072 242030 30925496 12076323613474588 12076323613650249 12076323613778889 12076323613782841
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 32 920962 920967 4194304 256 0 0 24 24 22016 0x7f7393007300 0x7f72630354c0 131072 244734 31308384 12076323613837853 12076323613996648 12076323614128007 12076323614132150
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 34 920962 920967 4194304 256 0 0 24 24 22720 0x7f7393007a00 0x7f7263035500 131072 254372 32612704 12076323614193303 12076323614355846 12076323614488165 12076323614491988
20 18 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 36 920962 920967 4194304 256 0 0 28 24 23680 0x7f7393007900 0x7f7263035540 131072 231684 29588352 12076323614543384 12076323614709604 12076323614969443 12076323615035949
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 38 920962 920967 4194304 256 0 0 28 24 24384 0x7f7393007800 0x7f7263035580 65536 176878 22653784 12076323615061597 12076323615254082 12076323615510721 12076323615575652
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 40 920962 920967 4194304 256 0 0 24 24 25088 0x7f7393007700 0x7f72630355c0 131072 239276 30622448 12076323615601120 12076323615781439 12076323615918239 12076323615921966
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 42 920962 920967 4194304 256 0 0 24 24 25792 0x7f7393007600 0x7f7263035600 131072 240084 30830432 12076323615974083 12076323616147998 12076323616278877 12076323616282867
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 44 920962 920967 4194304 256 0 0 24 24 26496 0x7f7393007500 0x7f7263035640 131072 273802 35277120 12076323616345493 12076323616510556 12076323616637595 12076323616641573
25 23 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 46 920962 920967 4194304 256 0 0 28 24 27712 0x7f7393007400 0x7f7263035680 131072 225544 28745000 12076323616689422 12076323616857754 12076323617111513 12076323617177008
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 48 920962 920967 4194304 256 0 0 28 24 28416 0x7f7393007300 0x7f72630356c0 65536 201166 25813712 12076323617202917 12076323617381432 12076323617627191 12076323617691765
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 50 920962 920967 4194304 256 0 0 24 24 29120 0x7f7393007a00 0x7f7263035700 131072 243484 31154056 12076323617718425 12076323617889590 12076323618019189 12076323618023131
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 52 920962 920967 4194304 256 0 0 24 24 30080 0x7f7393007900 0x7f7263035740 131072 268342 34452464 12076323618066572 12076323618248948 12076323618379827 12076323618383821
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 54 920962 920967 4194304 256 0 0 24 24 30784 0x7f7393007800 0x7f7263035780 131072 245610 31610232 12076323618445366 12076323618606866 12076323618735826 12076323618739542
30 28 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 56 920962 920967 4194304 256 0 0 28 24 32000 0x7f7393007700 0x7f72630357c0 131072 229882 29441200 12076323618789986 12076323618964305 12076323619220144 12076323619285327
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 58 920962 920967 4194304 256 0 0 28 24 32960 0x7f7393007600 0x7f7263035800 65536 185232 23694696 12076323619309532 12076323619489742 12076323619738861 12076323619803981
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 60 920962 920967 4194304 256 0 0 24 24 33920 0x7f7393007500 0x7f7263035840 131072 256836 32780368 12076323619829568 12076323620003020 12076323620131819 12076323620135827
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 62 920962 920967 4194304 256 0 0 24 24 34880 0x7f7393007400 0x7f7263035880 131072 261330 33319384 12076323620179368 12076323620356778 12076323620488618 12076323620492420
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 64 920962 920967 4194304 256 0 0 24 24 35840 0x7f7393007300 0x7f72630358c0 131072 280200 35738192 12076323620553834 12076323620714377 12076323620846536 12076323620850315
35 33 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 66 920962 920967 4194304 256 0 0 28 24 37312 0x7f7393007a00 0x7f7263035900 131072 225070 28804256 12076323620901330 12076323621078375 12076323621335814 12076323621401139
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 68 920962 920967 4194304 256 0 0 28 24 38272 0x7f7393007900 0x7f7263035940 65536 167896 21475136 12076323621424532 12076323621602693 12076323621853731 12076323621892512
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 70 920962 920967 4194304 256 0 0 24 24 39232 0x7f7393007800 0x7f7263035980 131072 247034 31388232 12076323621917148 12076323622100130 12076323622230850 12076323622234698
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 72 920962 920967 4194304 256 0 0 24 24 40192 0x7f7393007700 0x7f72630359c0 131072 245000 31370136 12076323622285943 12076323622447649 12076323622580928 12076323622584658
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 74 920962 920967 4194304 256 0 0 24 24 41152 0x7f7393007600 0x7f7263035a00 131072 228836 29280720 12076323622647315 12076323622810367 12076323622941886 12076323622945860
40 38 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 76 920962 920967 4194304 256 0 0 28 24 42624 0x7f7393007500 0x7f7263035a40 131072 199872 25664664 12076323622995662 12076323623168765 12076323623424924 12076323623490412
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 78 920962 920967 4194304 256 0 0 28 24 43584 0x7f7393007400 0x7f7263035a80 65536 180488 23097792 12076323623514015 12076323623690843 12076323623940122 12076323624010608
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 80 920962 920967 4194304 256 0 0 24 24 44544 0x7f7393007300 0x7f7263035ac0 131072 229426 29189648 12076323624038510 12076323624215481 12076323624346040 12076323624350069
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 82 920962 920967 4194304 256 0 0 24 24 45760 0x7f7393007a00 0x7f7263035b00 131072 247200 31674880 12076323624399341 12076323624560759 12076323624691638 12076323624695481
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 84 920962 920967 4194304 256 0 0 24 24 46720 0x7f7393007900 0x7f7263035b40 131072 230340 29218688 12076323624756074 12076323624917717 12076323625044757 12076323625048748
45 43 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 86 920962 920967 4194304 256 0 0 28 24 48448 0x7f7393007800 0x7f7263035b80 131072 224878 28730232 12076323625101255 12076323625263636 12076323625528114 12076323625571169
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 88 920962 920967 4194304 256 0 0 28 24 49408 0x7f7393007700 0x7f7263035bc0 65536 202786 25939176 12076323625596766 12076323625771313 12076323626062192 12076323626127663
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 90 920962 920967 4194304 256 0 0 24 24 50368 0x7f7393007600 0x7f7263035c00 131072 276026 35451600 12076323626159702 12076323626335951 12076323626465870 12076323626469678
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 92 920962 920967 4194304 256 0 0 24 24 51584 0x7f7393007500 0x7f7263035c40 131072 270312 34520392 12076323626520994 12076323626699789 12076323626835148 12076323626838845
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 94 920962 920967 4194304 256 0 0 24 24 52544 0x7f7393007400 0x7f7263035c80 131072 242800 31121504 12076323626901020 12076323627065707 12076323627196107 12076323627200306
50 48 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 96 920962 920967 4194304 256 0 0 28 24 54272 0x7f7393007300 0x7f7263035cc0 131072 226928 29085304 12076323627248476 12076323627417706 12076323627676425 12076323627742083
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 98 920962 920967 4194304 256 0 0 28 24 55488 0x7f7393007a00 0x7f7263035d00 65536 202828 25941824 12076323627767250 12076323627940423 12076323628194822 12076323628262440
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 100 920962 920967 4194304 256 0 0 24 24 56704 0x7f7393007900 0x7f7263035d40 131072 259198 32951472 12076323628286976 12076323628463621 12076323628601060 12076323628604786
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 102 920962 920967 4194304 256 0 0 24 24 58176 0x7f7393007800 0x7f7263035d80 131072 258282 33021128 12076323628659398 12076323628817859 12076323628958979 12076323628962852
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 104 920962 920967 4194304 256 0 0 24 24 59392 0x7f7393007700 0x7f7263035dc0 131072 246652 31546856 12076323629030508 12076323629193058 12076323629326977 12076323629330896
55 53 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 106 920962 920967 4194304 256 0 0 28 24 61376 0x7f7393007600 0x7f7263035e00 131072 245768 31560440 12076323629386489 12076323629542816 12076323629802175 12076323629843308
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 108 920962 920967 4194304 256 0 0 28 24 62592 0x7f7393007500 0x7f7263035e40 65536 173704 22245464 12076323629867744 12076323630053854 12076323630304572 12076323630369406
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 110 920962 920967 4194304 256 0 0 24 24 63808 0x7f7393007400 0x7f7263035e80 131072 275760 35575200 12076323630396136 12076323630575771 12076323630705851 12076323630709839
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 112 920962 920967 4194304 256 0 0 24 24 65280 0x7f7393007300 0x7f7263035ec0 131072 244024 31108304 12076323630758709 12076323630925690 12076323631065529 12076323631069196
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 114 920962 920967 4194304 256 0 0 24 24 66496 0x7f7393007a00 0x7f7263035f00 131072 279584 35794400 12076323631131202 12076323631293528 12076323631422807 12076323631426681
60 58 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 116 920962 920967 4194304 256 0 0 28 24 68480 0x7f7393007900 0x7f7263035f40 131072 228846 29230256 12076323631480451 12076323631638646 12076323631904725 12076323631949863
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 118 920962 920967 4194304 256 0 0 28 24 69696 0x7f7393007800 0x7f7263035f80 65536 199242 25601280 12076323631974689 12076323632154964 12076323632410643 12076323632457957
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 120 920962 920967 4194304 256 0 0 24 24 70912 0x7f7393007700 0x7f7263035fc0 131072 275868 35385664 12076323632483795 12076323632658802 12076323632792881 12076323632796607
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 122 920962 920967 4194304 256 0 0 24 24 72384 0x7f7393007600 0x7f7263036000 131072 271282 35165760 12076323632845918 12076323633015120 12076323633153199 12076323633157317
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 124 920962 920967 4194304 256 0 0 24 24 73600 0x7f7393007500 0x7f7263036040 131072 249424 31654416 12076323633219923 12076323633379598 12076323633507598 12076323633511495
65 63 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 126 920962 920967 4194304 256 0 0 28 24 75840 0x7f7393007400 0x7f7263036080 131072 231548 29587792 12076323633560647 12076323633723597 12076323633993835 12076323634041110
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 128 920962 920967 4194304 256 0 0 28 24 77056 0x7f7393007300 0x7f72630360c0 65536 171078 21878256 12076323634064573 12076323634247754 12076323634497513 12076323634544395
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 130 920962 920967 4194304 256 0 0 24 24 78272 0x7f7393007a00 0x7f7263036100 131072 279070 35673072 12076323634566676 12076323634744392 12076323634881991 12076323634885539
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 132 920962 920967 4194304 256 0 0 24 24 80000 0x7f7393007900 0x7f7263036140 131072 219862 28157320 12076323634935893 12076323635109030 12076323635251590 12076323635255527
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 134 920962 920967 4194304 256 0 0 24 24 81216 0x7f7393007800 0x7f7263036180 131072 280770 35921656 12076323635319345 12076323635479429 12076323635616548 12076323635620505
70 68 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 136 920962 920967 4194304 256 0 0 28 24 83456 0x7f7393007700 0x7f72630361c0 131072 225682 28885744 12076323635670889 12076323635830627 12076323636091906 12076323636139600
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 138 920962 920967 4194304 256 0 0 28 24 84928 0x7f7393007600 0x7f7263036200 65536 201798 25883064 12076323636164396 12076323636340705 12076323636596864 12076323636643787
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 140 920962 920967 4194304 256 0 0 24 24 86400 0x7f7393007500 0x7f7263036240 131072 252542 32432200 12076323636670386 12076323636858942 12076323636997182 12076323637004858
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 142 920962 920967 4194304 256 0 0 24 24 88128 0x7f7393007400 0x7f7263036280 131072 231120 29646360 12076323637050883 12076323637215581 12076323637365500 12076323637369425
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 144 920962 920967 4194304 256 0 0 24 24 89600 0x7f7393007300 0x7f72630362c0 131072 247918 31659608 12076323637448462 12076323637609019 12076323637738138 12076323637741947
75 73 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 146 920962 920967 4194304 256 0 0 28 24 92096 0x7f7393007a00 0x7f7263036300 131072 229196 29396248 12076323637791129 12076323637955257 12076323638219416 12076323638265911
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 148 920962 920967 4194304 256 0 0 28 24 93568 0x7f7393007900 0x7f7263036340 65536 171128 21860632 12076323638292190 12076323638465335 12076323638713494 12076323638759559
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 150 920962 920967 4194304 256 0 0 24 24 95040 0x7f7393007800 0x7f7263036380 131072 269838 34491744 12076323638783784 12076323638956053 12076323639092532 12076323639096996
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 152 920962 920967 4194304 256 0 0 24 24 96768 0x7f7393007700 0x7f72630363c0 131072 250148 31950712 12076323639146939 12076323639306611 12076323639463410 12076323639467314
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 154 920962 920967 4194304 256 0 0 24 24 98240 0x7f7393007600 0x7f7263036400 131072 278424 35527744 12076323639529730 12076323639688369 12076323639816529 12076323639820390
80 78 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 156 920962 920967 4194304 256 0 0 28 24 100736 0x7f7393007500 0x7f7263036440 131072 229564 29332528 12076323639870634 12076323640039248 12076323640302286 12076323640328254
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 158 920962 920967 4194304 256 0 0 28 24 102208 0x7f7393007400 0x7f7263036480 65536 197912 25313256 12076323640369481 12076323640524365 12076323640777804 12076323640798889
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 160 920962 920967 4194304 256 0 0 24 24 103680 0x7f7393007300 0x7f72630364c0 131072 241314 30851752 12076323640843542 12076323640998763 12076323641131883 12076323641136055
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 162 920962 920967 4194304 256 0 0 24 24 105664 0x7f7393007a00 0x7f7263036500 131072 245368 31363504 12076323641187371 12076323641361162 12076323641526441 12076323641530699
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 164 920962 920967 4194304 256 0 0 24 24 107136 0x7f7393007900 0x7f7263036540 131072 249022 31724096 12076323641592574 12076323641748200 12076323641886919 12076323641891058
85 83 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 166 920962 920967 4194304 256 0 0 28 24 109888 0x7f7393007800 0x7f7263036580 131072 201048 25737440 12076323641941292 12076323642098758 12076323642357637 12076323642381981
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 168 920962 920967 4194304 256 0 0 28 24 111360 0x7f7393007700 0x7f72630365c0 65536 184142 23592320 12076323642424540 12076323642581796 12076323642833315 12076323642855160
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 170 920962 920967 4194304 256 0 0 24 24 112832 0x7f7393007600 0x7f7263036600 131072 246264 31616104 12076323642900564 12076323643068674 12076323643204193 12076323643208517
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 172 920962 920967 4194304 256 0 0 24 24 114816 0x7f7393007500 0x7f7263036640 131072 273018 34992472 12076323643260002 12076323643419712 12076323643593311 12076323643597510
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 174 920962 920967 4194304 256 0 0 24 24 116288 0x7f7393007400 0x7f7263036680 131072 280378 35882680 12076323643659204 12076323643815870 12076323643953950 12076323643958020
90 88 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 176 920962 920967 4194304 256 0 0 28 24 119040 0x7f7393007300 0x7f72630366c0 131072 205034 26250952 12076323644013503 12076323644174589 12076323644432507 12076323644458490
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 178 920962 920967 4194304 256 0 0 28 24 120768 0x7f7393007a00 0x7f7263036700 65536 198622 25316456 12076323644499306 12076323644652186 12076323644904505 12076323644926209
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 180 920962 920967 4194304 256 0 0 24 24 122496 0x7f7393007900 0x7f7263036740 131072 261612 33500992 12076323644970712 12076323645130904 12076323645305783 12076323645309822
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 182 920962 920967 4194304 256 0 0 24 24 124736 0x7f7393007800 0x7f7263036780 131072 267348 34363840 12076323645359484 12076323645526742 12076323645709782 12076323645713653
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 184 920962 920967 4194304 256 0 0 24 24 126464 0x7f7393007700 0x7f72630367c0 131072 247098 31735760 12076323645779445 12076323645934741 12076323646068660 12076323646073081
95 93 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 186 920962 920967 4194304 256 0 0 20 24 127936 0x7f7393007600 0x7f7263036800 131072 270960 34546432 12076323646122943 12076323646289619 12076323646556818 12076323646579101
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 188 920962 920967 4194304 256 0 0 28 24 129664 0x7f7393007500 0x7f7263036840 65536 174178 22248688 12076323646622692 12076323646779857 12076323647036015 12076323647061838
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 190 920962 920967 4194304 256 0 0 24 24 131392 0x7f7393007400 0x7f7263036880 131072 222078 28508408 12076323647105479 12076323647273294 12076323647411054 12076323647414984
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 192 920962 920967 4194304 256 0 0 24 24 133632 0x7f7393007300 0x7f72630368c0 131072 254992 32479592 12076323647464476 12076323647644013 12076323647835692 12076323647856705
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 194 920962 920967 4194304 256 0 0 24 24 135360 0x7f7393007a00 0x7f7263036900 131072 241268 30908928 12076323647916827 12076323648093771 12076323648229770 12076323648234087
100 98 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 196 920962 920967 4194304 256 0 0 20 24 136832 0x7f7393007900 0x7f7263036940 131072 254598 32667048 12076323648276766 12076323648458729 12076323648773287 12076323648791362
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 198 920962 920967 4194304 256 0 0 28 24 138560 0x7f7393007800 0x7f7263036980 65536 206060 26411944 12076323648838079 12076323649005126 12076323649256005 12076323649277977
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 200 920962 920967 4194304 256 0 0 24 24 140288 0x7f7393007700 0x7f72630369c0 131072 240384 30637304 12076323649326036 12076323649491044 12076323649621124 12076323649625092
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 202 920962 920967 4194304 256 0 0 24 24 142784 0x7f7393007600 0x7f7263036a00 131072 240522 30740944 12076323649680595 12076323649842883 12076323650052162 12076323650076410
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 204 920962 920967 4194304 256 0 0 24 24 144768 0x7f7393007500 0x7f7263036a40 131072 265848 33910808 12076323650135931 12076323650304160 12076323650439680 12076323650443833
105 103 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 206 920962 920967 4194304 256 0 0 20 24 145728 0x7f7393007400 0x7f7263036a80 131072 251302 32293864 12076323650496311 12076323650666879 12076323650974077 12076323650994046
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 208 920962 920967 4194304 256 0 0 28 24 147712 0x7f7393007300 0x7f7263036ac0 65536 185108 23763296 12076323651055961 12076323651225276 12076323651481595 12076323651501198
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 210 920962 920967 4194304 256 0 0 24 24 149696 0x7f7393007a00 0x7f7263036b00 131072 260708 33431120 12076323651553466 12076323651720794 12076323651861753 12076323651865916
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 212 920962 920967 4194304 256 0 0 24 24 152192 0x7f7393007900 0x7f7263036b40 131072 243794 30960016 12076323651916691 12076323652097912 12076323652325591 12076323652350136
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 214 920962 920967 4194304 256 0 0 24 24 154176 0x7f7393007800 0x7f7263036b80 131072 246144 31516136 12076323652403676 12076323652569750 12076323652710069 12076323652714123
110 108 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 216 920962 920967 4194304 256 0 0 20 24 155648 0x7f7393007700 0x7f7263036bc0 131072 238694 30613232 12076323652763665 12076323652943508 12076323653301427 12076323653323185
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 218 920962 920967 4194304 256 0 0 28 24 157632 0x7f7393007600 0x7f7263036c00 65536 194502 24878424 12076323653368719 12076323653534386 12076323653794064 12076323653815029
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 220 920962 920967 4194304 256 0 0 24 24 159616 0x7f7393007500 0x7f7263036c40 131072 243150 31094624 12076323653859551 12076323654027503 12076323654207822 12076323654212217
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 222 920962 920967 4194304 256 0 0 24 24 162368 0x7f7393007400 0x7f7263036c80 131072 280728 35873288 12076323654261919 12076323654437901 12076323654682860 12076323654704502
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 224 920962 920967 4194304 256 0 0 24 24 164608 0x7f7393007300 0x7f7263036cc0 131072 268110 34345528 12076323654766988 12076323654933579 12076323655073098 12076323655077264
115 113 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 226 920962 920967 4194304 256 0 0 20 24 166336 0x7f7393007a00 0x7f7263036d00 131072 264734 34046968 12076323655131836 12076323655300233 12076323655676232 12076323655700312
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 228 920962 920967 4194304 256 0 0 28 24 168576 0x7f7393007900 0x7f7263036d40 65536 171002 21915616 12076323655742691 12076323655909670 12076323656170149 12076323656195052
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 230 920962 920967 4194304 256 0 0 24 24 170816 0x7f7393007800 0x7f7263036d80 131072 273494 35074952 12076323656241849 12076323656407588 12076323656551108 12076323656553819
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 232 920962 920967 4194304 256 0 0 24 24 174080 0x7f7393007700 0x7f7263036dc0 131072 244350 31350440 12076323656603721 12076323656771747 12076323657081346 12076323657101136
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 234 920962 920967 4194304 256 0 0 24 24 176576 0x7f7393007600 0x7f7263036e00 131072 272266 34966264 12076323657165044 12076323657337025 12076323657479905 12076323657482895
120 118 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 236 920962 920967 4194304 256 0 0 20 24 177792 0x7f7393007500 0x7f7263036e40 131072 250608 32167248 12076323657532858 12076323657712384 12076323658135263 12076323658155425
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 238 920962 920967 4194304 256 0 0 28 24 180288 0x7f7393007400 0x7f7263036e80 65536 187080 23892424 12076323658200890 12076323658366782 12076323658626941 12076323658646518
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 240 920962 920967 4194304 256 0 0 24 24 182784 0x7f7393007300 0x7f7263036ec0 131072 273216 34911920 12076323658691571 12076323658863581 12076323659002780 12076323659011135
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 242 920962 920967 4194304 256 0 0 24 24 186304 0x7f7393007a00 0x7f7263036f00 131072 267540 34379304 12076323659056800 12076323659238300 12076323659553819 12076323659577328
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 244 920962 920967 4194304 256 0 0 24 24 189312 0x7f7393007900 0x7f7263036f40 131072 235356 30315176 12076323659636908 12076323659806618 12076323659958297 12076323659961081
125 123 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 246 920962 920967 4194304 256 0 0 20 24 190784 0x7f7393007800 0x7f7263036f80 131072 267360 34113064 12076323660017666 12076323660195097 12076323660711415 12076323660735460
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 248 920962 920967 4194304 256 0 0 28 24 193792 0x7f7393007700 0x7f7263036fc0 65536 190478 24411512 12076323660777127 12076323660943734 12076323661245973 12076323661266196
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 250 920962 920967 4194304 256 0 0 24 24 196800 0x7f7393007600 0x7f7263037000 131072 270202 34510000 12076323661315488 12076323661485813 12076323661640532 12076323661643397
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 252 920962 920967 4194304 256 0 0 24 24 201088 0x7f7393007500 0x7f7263037040 131072 241254 31062272 12076323661695865 12076323661881811 12076323662292210 12076323662315797
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 254 920962 920967 4194304 256 0 0 24 24 204608 0x7f7393007400 0x7f7263037080 131072 247580 31499496 12076323662372633 12076323662543249 12076323662719249 12076323662722222
130 128 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 256 920962 920967 4194304 256 0 0 20 24 206080 0x7f7393007300 0x7f72630370c0 131072 276044 35254912 12076323662771854 12076323662946928 12076323663556046 12076323663576370
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 258 920962 920967 4194304 256 0 0 28 24 209600 0x7f7393007a00 0x7f7263037100 65536 183066 23358592 12076323663620852 12076323663787086 12076323664114765 12076323664138274
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 260 920962 920967 4194304 256 0 0 24 24 213120 0x7f7393007900 0x7f7263037140 131072 268336 34289904 12076323664180352 12076323664344684 12076323664524363 12076323664527257
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 262 920962 920967 4194304 256 0 0 24 24 218176 0x7f7393007800 0x7f7263037180 131072 245282 31478568 12076323664577129 12076323664755883 12076323665211721 12076323665232327
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 264 920962 920967 4194304 256 0 0 24 24 222208 0x7f7393007700 0x7f72630371c0 131072 262508 33623432 12076323665292599 12076323665461320 12076323665661640 12076323665677815
135 133 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 266 920962 920967 4194304 256 0 0 20 24 223936 0x7f7393007600 0x7f7263037200 131072 272266 35134032 12076323665727437 12076323665892519 12076323666594117 12076323666617932
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 268 920962 920967 4194304 256 0 0 28 24 227968 0x7f7393007500 0x7f7263037240 65536 183994 23642032 12076323666658768 12076323666829796 12076323667204195 12076323667223918
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 270 920962 920967 4194304 256 0 0 24 24 232000 0x7f7393007400 0x7f7263037280 131072 243438 31099776 12076323667270735 12076323667437154 12076323667639074 12076323667659808
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 272 920962 920967 4194304 256 0 0 24 24 237824 0x7f7393007300 0x7f72630372c0 131072 248044 31575664 12076323667703059 12076323667867233 12076323668392991 12076323668420122
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 274 920962 920967 4194304 256 0 0 24 24 242368 0x7f7393007a00 0x7f7263037300 131072 251398 31976816 12076323668481055 12076323668652351 12076323668876830 12076323668897068
140 138 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 276 920962 920967 4194304 256 0 0 20 24 243584 0x7f7393007900 0x7f7263037340 131072 235974 30452504 12076323668940909 12076323669110589 12076323669908507 12076323669931871
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 278 920962 920967 4194304 256 0 0 28 24 248128 0x7f7393007800 0x7f7263037380 65536 187722 23922960 12076323669974450 12076323670149146 12076323670570585 12076323670594963
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 280 920962 920967 4194304 256 0 0 24 24 252672 0x7f7393007700 0x7f72630373c0 131072 257792 33088104 12076323670635920 12076323670808184 12076323671035863 12076323671057253
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 282 920962 920967 4194304 256 0 0 24 24 259264 0x7f7393007600 0x7f7263037400 131072 275128 35343024 12076323671101405 12076323671258583 12076323671855061 12076323671876725
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 284 920962 920967 4194304 256 0 0 24 24 264832 0x7f7393007500 0x7f7263037440 131072 241150 31176032 12076323671927931 12076323672091860 12076323672360339 12076323672384890
145 143 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 286 920962 920967 4194304 256 0 0 20 24 266304 0x7f7393007400 0x7f7263037480 131072 245240 31135608 12076323672428952 12076323672588339 12076323673572336 12076323673639532
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 288 920962 920967 4194304 256 0 0 28 24 271872 0x7f7393007300 0x7f72630374c0 65536 185494 23810848 12076323673667443 12076323673849455 12076323674363053 12076323674429710
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 290 920962 920967 4194304 256 0 0 24 24 277440 0x7f7393007a00 0x7f7263037500 131072 270626 34681168 12076323674461469 12076323674637132 12076323674908011 12076323674970535
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 292 920962 920967 4194304 256 0 0 12 24 279936 0x7f7393007900 0x7f7263037540 131072 260462 33475128 12076323675006943 12076323675186411 12076323675924008 12076323675991472
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 294 920962 920967 4194304 256 0 0 24 24 286528 0x7f7393007800 0x7f7263037580 131072 244092 31314424 12076323676037167 12076323676197447 12076323676512647 12076323676578483
150 148 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 296 920962 920967 4194304 256 0 0 20 24 288000 0x7f7393007700 0x7f72630375c0 131072 252970 32336632 12076323676603239 12076323676779046 12076323677948322 12076323678020764
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 298 920962 920967 4194304 256 0 0 32 24 294592 0x7f7393007600 0x7f7263037600 65536 189272 24113696 12076323678050098 12076323678234721 12076323678844159 12076323678909375
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 300 920962 920967 4194304 256 0 0 24 24 301184 0x7f7393007500 0x7f7263037640 131072 244778 31233472 12076323678933039 12076323679122398 12076323679440798 12076323679505072
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 302 920962 920967 4194304 256 0 0 12 24 304960 0x7f7393007400 0x7f7263037680 131072 241846 31135968 12076323679531732 12076323679705277 12076323680583034 12076323680649179
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 304 920962 920967 4194304 256 0 0 24 24 313600 0x7f7393007300 0x7f72630376c0 131072 250416 31980512 12076323680686989 12076323680856473 12076323681267192 12076323681336947
155 153 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 306 920962 920967 4194304 256 0 0 20 24 314816 0x7f7393007a00 0x7f7263037700 131072 277318 35157984 12076323681365360 12076323681546391 12076323683093586 12076323683159244
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 308 920962 920967 4194304 256 0 0 20 24 317568 0x7f7393007900 0x7f7263037740 65536 174154 22345656 12076323683188548 12076323683365585 12076323684158383 12076323684223451
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 310 920962 920967 4194304 256 0 0 12 24 320320 0x7f7393007800 0x7f7263037780 131072 279118 35872752 12076323684246374 12076323684431982 12076323684846381 12076323684910077
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 312 920962 920967 4194304 256 0 0 12 24 324096 0x7f7393007700 0x7f72630377c0 131072 247552 31617312 12076323684935525 12076323685122220 12076323686280456 12076323686347078
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 314 920962 920967 4194304 256 0 0 12 24 328896 0x7f7393007600 0x7f7263037800 131072 277944 35691800 12076323686387293 12076323686546216 12076323687332453 12076323687401077
160 158 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 316 920962 920967 4194304 256 0 0 20 24 330112 0x7f7393007500 0x7f7263037840 131072 246180 31661440 12076323687432706 12076323687605252 12076323690654203 12076323690720816
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 318 920962 920967 4194304 256 0 0 20 24 332864 0x7f7393007400 0x7f7263037880 65536 191938 24518880 12076323690752285 12076323690931962 12076323692473717 12076323692541400
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 320 920962 920967 4194304 256 0 0 12 24 335616 0x7f7393007300 0x7f72630378c0 131072 239628 30708424 12076323692574762 12076323692744437 12076323693534834 12076323693601841
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 322 920962 920967 4194304 256 0 0 12 24 339392 0x7f7393007a00 0x7f7263037900 131072 274278 35149648 12076323693628941 12076323693813553 12076323696095786 12076323696163692
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 324 920962 920967 4194304 256 0 0 12 24 344192 0x7f7393007900 0x7f7263037940 131072 248204 31666344 12076323696207553 12076323696367785 12076323697903461 12076323697970319
165 163 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 326 920962 920967 4194304 256 0 0 20 24 345408 0x7f7393007800 0x7f7263037980 131072 279784 35644216 12076323697998331 12076323698187300 12076323704239601 12076323704292348
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 328 920962 920967 4194304 256 0 0 20 24 348160 0x7f7393007700 0x7f72630379c0 65536 171254 22059944 12076323704321372 12076323704501520 12076323707542631 12076323707610255
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 330 920962 920967 4194304 256 0 0 12 24 350912 0x7f7393007600 0x7f7263037a00 131072 272624 34769824 12076323707638567 12076323707815270 12076323709354626 12076323709422493
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 332 920962 920967 4194304 256 0 0 12 24 0 0x7f7393007500 0x7f7263037a40 131072 267182 34191504 12076323709451777 12076323709631745 12076323714158451 12076323714224717
@@ -0,0 +1,168 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,grd,Workgroup_Size,LDS_Per_Workgroup,scr,vgpr,SGPR,fbar,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"__amd_rocclr_fillBuffer.kd",0,0,0,921153,921158,33554432,256,0,0,8,32,6464,0x0,0x7fbf7ac04180,1048576,11001658,1408052856,12076324607361092,12076324851578856,12076324851903654,12076324852039846
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,921153,921158,32768,256,0,0,24,24,12480,0x0,0x7fbf7ac35100,4096,113289,14479660,12076324866554932,12076324866851777,12076324866858017,12076324866863235
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,921153,921158,4194304,256,0,0,24,24,12928,0x7fc0aab91900,0x7fbf7ac35140,524288,12401318,1587311276,12076324866927514,12076324867148415,12076324867279615,12076324867283767
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,921153,921158,4194304,256,0,0,36,24,13632,0x7fc0aab91800,0x7fbf7ac35180,524288,13924068,1782351476,12076324867354438,12076324867525693,12076324867773532,12076324867842695
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,921153,921158,4194304,256,0,0,28,24,14080,0x7fc0aab91700,0x7fbf7ac351c0,524288,14366779,1838880984,12076324867872430,12076324868062971,12076324868314809,12076324868383570
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,921153,921158,4194304,256,0,0,24,24,14528,0x7fc0aab91600,0x7fbf7ac35200,524288,11167660,1429516928,12076324868408617,12076324868594968,12076324868731607,12076324868735214
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,921153,921158,4194304,256,0,0,24,24,14976,0x7fc0aab91500,0x7fbf7ac35240,524288,12212582,1563143728,12076324868785387,12076324868956246,12076324869088885,12076324869092698
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,921153,921158,4194304,256,0,0,24,24,15424,0x7fc0aab91400,0x7fbf7ac35280,524288,12734855,1630074280,12076324869171385,12076324869342644,12076324869472563,12076324869476321
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,921153,921158,4194304,256,0,0,28,24,16128,0x7fc0aab91300,0x7fbf7ac352c0,524288,13905355,1779832888,12076324869526575,12076324869705202,12076324869958961,12076324870005104
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,921153,921158,4194304,256,0,0,28,24,16832,0x7fc0aab91a00,0x7fbf7ac35300,524288,13638895,1745720368,12076324870031794,12076324870211280,12076324870466638,12076324870507167
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,921153,921158,4194304,256,0,0,24,24,17536,0x7fc0aab91900,0x7fbf7ac35340,524288,11953865,1530028984,12076324870530250,12076324870718637,12076324870851916,12076324870855575
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,921153,921158,4194304,256,0,0,24,24,18240,0x7fc0aab91800,0x7fbf7ac35380,524288,11019037,1410452988,12076324870903554,12076324871079435,12076324871216235,12076324871220112
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,921153,921158,4194304,256,0,0,24,24,18944,0x7fc0aab91700,0x7fbf7ac353c0,524288,12347166,1580393688,12076324871281817,12076324871445993,12076324871577833,12076324871581554
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,921153,921158,4194304,256,0,0,28,24,19904,0x7fc0aab91600,0x7fbf7ac35400,524288,14251323,1824182664,12076324871624504,12076324871801512,12076324872056070,12076324872124513
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,921153,921158,4194304,256,0,0,28,24,20608,0x7fc0aab91500,0x7fbf7ac35440,524288,14134381,1809184948,12076324872148016,12076324872336869,12076324872590788,12076324872657093
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,921153,921158,4194304,256,0,0,24,24,21312,0x7fc0aab91400,0x7fbf7ac35480,524288,12003708,1536401320,12076324872680987,12076324872859106,12076324872992066,12076324872995692
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,921153,921158,4194304,256,0,0,24,24,22016,0x7fc0aab91300,0x7fbf7ac354c0,524288,12761839,1633550800,12076324873044783,12076324873215584,12076324873345824,12076324873349419
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,921153,921158,4194304,256,0,0,24,24,22720,0x7fc0aab91a00,0x7fbf7ac35500,524288,12355665,1581510772,12076324873408950,12076324873572063,12076324873703742,12076324873707294
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,921153,921158,4194304,256,0,0,28,24,23680,0x7fc0aab91900,0x7fbf7ac35540,524288,13960437,1786860424,12076324873758660,12076324873919901,12076324874172059,12076324874214918
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,921153,921158,4194304,256,0,0,28,24,24384,0x7fc0aab91800,0x7fbf7ac35580,524288,14296440,1829925976,12076324874237069,12076324874424378,12076324874672537,12076324874713925
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,921153,921158,4194304,256,0,0,24,24,25088,0x7fc0aab91700,0x7fbf7ac355c0,524288,11419318,1461579156,12076324874735505,12076324874917976,12076324875052855,12076324875056792
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,921153,921158,4194304,256,0,0,24,24,25792,0x7fc0aab91600,0x7fbf7ac35600,524288,12716538,1627629044,12076324875107927,12076324875278934,12076324875409173,12076324875413004
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,921153,921158,4194304,256,0,0,24,24,26496,0x7fc0aab91500,0x7fbf7ac35640,524288,12786121,1636755892,12076324875472425,12076324875634612,12076324875764851,12076324875768585
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,921153,921158,4194304,256,0,0,28,24,27712,0x7fc0aab91400,0x7fbf7ac35680,524288,13985714,1790158532,12076324875816554,12076324875982770,12076324876235249,12076324876303439
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,921153,921158,4194304,256,0,0,28,24,28416,0x7fc0aab91300,0x7fbf7ac356c0,524288,13560902,1735756300,12076324876330079,12076324876507248,12076324876758446,12076324876825439
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,921153,921158,4194304,256,0,0,24,24,29120,0x7fc0aab91a00,0x7fbf7ac35700,524288,11718659,1499951512,12076324876850366,12076324877034445,12076324877168204,12076324877171973
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,921153,921158,4194304,256,0,0,24,24,30080,0x7fc0aab91900,0x7fbf7ac35740,524288,12932359,1655304508,12076324877219902,12076324877389163,12076324877519402,12076324877523086
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,921153,921158,4194304,256,0,0,24,24,30784,0x7fc0aab91800,0x7fbf7ac35780,524288,12610659,1614160584,12076324877581434,12076324877741481,12076324877871401,12076324877875140
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,921153,921158,4194304,256,0,0,28,24,32000,0x7fc0aab91700,0x7fbf7ac357c0,524288,14065498,1800337208,12076324877923720,12076324878115879,12076324878372038,12076324878439409
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,921153,921158,4194304,256,0,0,28,24,32960,0x7fc0aab91600,0x7fbf7ac35800,524288,14390289,1841900872,12076324878466319,12076324878642597,12076324878896835,12076324878963042
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,921153,921158,4194304,256,0,0,24,24,33920,0x7fc0aab91500,0x7fbf7ac35840,524288,11632795,1488875344,12076324878988389,12076324879172194,12076324879307713,12076324879311890
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,921153,921158,4194304,256,0,0,24,24,34880,0x7fc0aab91400,0x7fbf7ac35880,524288,13041589,1669311224,12076324879360360,12076324879526272,12076324879656991,12076324879660839
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,921153,921158,4194304,256,0,0,24,24,35840,0x7fc0aab91300,0x7fbf7ac358c0,524288,13141993,1682249604,12076324879722754,12076324879885790,12076324880014110,12076324880017852
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,921153,921158,4194304,256,0,0,28,24,37312,0x7fc0aab91a00,0x7fbf7ac35900,524288,13903488,1779637896,12076324880067464,12076324880239229,12076324880495707,12076324880563456
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,921153,921158,4194304,256,0,0,28,24,38272,0x7fc0aab91900,0x7fbf7ac35940,524288,13863049,1774444876,12076324880586780,12076324880772026,12076324881022745,12076324881091307
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,921153,921158,4194304,256,0,0,24,24,39232,0x7fc0aab91800,0x7fbf7ac35980,524288,12585259,1610915156,12076324881119910,12076324881299543,12076324881430582,12076324881434365
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,921153,921158,4194304,256,0,0,24,24,40192,0x7fc0aab91700,0x7fbf7ac359c0,524288,12147124,1554843264,12076324881482705,12076324881653941,12076324881787221,12076324881791128
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,921153,921158,4194304,256,0,0,24,24,41152,0x7fc0aab91600,0x7fbf7ac35a00,524288,12065079,1544321884,12076324881850709,12076324882012339,12076324882144979,12076324882148993
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,921153,921158,4194304,256,0,0,28,24,42624,0x7fc0aab91500,0x7fbf7ac35a40,524288,13593200,1739929944,12076324882196461,12076324882368338,12076324882625456,12076324882691912
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,921153,921158,4194304,256,0,0,28,24,43584,0x7fc0aab91400,0x7fbf7ac35a80,524288,14200515,1817602084,12076324882713462,12076324882892175,12076324883145294,12076324883216226
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,921153,921158,4194304,256,0,0,24,24,44544,0x7fc0aab91300,0x7fbf7ac35ac0,524288,12974942,1660889500,12076324883238357,12076324883418092,12076324883547532,12076324883551209
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,921153,921158,4194304,256,0,0,24,24,45760,0x7fc0aab91a00,0x7fbf7ac35b00,524288,12389424,1585815896,12076324883599499,12076324883764651,12076324883896810,12076324883900618
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,921153,921158,4194304,256,0,0,24,24,46720,0x7fc0aab91900,0x7fbf7ac35b40,524288,12579260,1610101880,12076324883959738,12076324884128009,12076324884258248,12076324884262240
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,921153,921158,4194304,256,0,0,28,24,48448,0x7fc0aab91800,0x7fbf7ac35b80,524288,13798283,1766179384,12076324884310390,12076324884477287,12076324884741606,12076324884808636
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,921153,921158,4194304,256,0,0,28,24,49408,0x7fc0aab91700,0x7fbf7ac35bc0,524288,13967280,1787765120,12076324884832991,12076324885007524,12076324885301443,12076324885368246
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,921153,921158,4194304,256,0,0,24,24,50368,0x7fc0aab91600,0x7fbf7ac35c00,524288,12768928,1634420072,12076324885393152,12076324885575521,12076324885705281,12076324885709039
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,921153,921158,4194304,256,0,0,24,24,51584,0x7fc0aab91500,0x7fbf7ac35c40,524288,11048220,1414101748,12076324885756788,12076324885922719,12076324886059999,12076324886063758
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,921153,921158,4194304,256,0,0,24,24,52544,0x7fc0aab91400,0x7fbf7ac35c80,524288,11869975,1519411292,12076324886124431,12076324886288158,12076324886420317,12076324886424038
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,921153,921158,4194304,256,0,0,28,24,54272,0x7fc0aab91300,0x7fbf7ac35cc0,524288,12994597,1663228396,12076324886468681,12076324886637116,12076324886906874,12076324886949354
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,921153,921158,4194304,256,0,0,28,24,55488,0x7fc0aab91a00,0x7fbf7ac35d00,524288,14232764,1821788460,12076324886975783,12076324887154713,12076324887406712,12076324887475632
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,921153,921158,4194304,256,0,0,24,24,56704,0x7fc0aab91900,0x7fbf7ac35d40,524288,13097771,1676571164,12076324887499006,12076324887675351,12076324887804150,12076324887808080
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,921153,921158,4194304,256,0,0,24,24,58176,0x7fc0aab91800,0x7fbf7ac35d80,524288,9712685,1243268284,12076324887858624,12076324888030709,12076324888172788,12076324888176825
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,921153,921158,4194304,256,0,0,24,24,59392,0x7fc0aab91700,0x7fbf7ac35dc0,524288,11709071,1498779836,12076324888236827,12076324888397907,12076324888531026,12076324888534821
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,921153,921158,4194304,256,0,0,28,24,61376,0x7fc0aab91600,0x7fbf7ac35e00,524288,14539178,1861072408,12076324888582319,12076324888746865,12076324889014544,12076324889081958
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,921153,921158,4194304,256,0,0,28,24,62592,0x7fc0aab91500,0x7fbf7ac35e40,524288,14171868,1814021376,12076324889105682,12076324889292942,12076324889544781,12076324889611411
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,921153,921158,4194304,256,0,0,24,24,63808,0x7fc0aab91400,0x7fbf7ac35e80,524288,11767035,1506177424,12076324889635867,12076324889818380,12076324889993419,12076324889997218
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,921153,921158,4194304,256,0,0,24,24,65280,0x7fc0aab91300,0x7fbf7ac35ec0,524288,9202080,1177852572,12076324890047051,12076324890215818,12076324890356777,12076324890360614
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,921153,921158,4194304,256,0,0,24,24,66496,0x7fc0aab91a00,0x7fbf7ac35f00,524288,12333047,1578665472,12076324890422609,12076324890583496,12076324890714055,12076324890718158
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,921153,921158,4194304,256,0,0,28,24,68480,0x7fc0aab91900,0x7fbf7ac35f40,524288,13147150,1682780388,12076324890763743,12076324890932934,12076324891196933,12076324891267369
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,921153,921158,4194304,256,0,0,28,24,69696,0x7fc0aab91800,0x7fbf7ac35f80,524288,14153714,1811632852,12076324891292906,12076324891468931,12076324891717890,12076324891784791
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,921153,921158,4194304,256,0,0,24,24,70912,0x7fc0aab91700,0x7fbf7ac35fc0,524288,11152062,1427486812,12076324891810709,12076324891983809,12076324892118048,12076324892122168
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,921153,921158,4194304,256,0,0,24,24,72384,0x7fc0aab91600,0x7fbf7ac36000,524288,7595469,972160732,12076324892171249,12076324892335487,12076324892475806,12076324892479612
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,921153,921158,4194304,256,0,0,24,24,73600,0x7fc0aab91500,0x7fbf7ac36040,524288,12148182,1554948808,12076324892538181,12076324892695805,12076324892828924,12076324892832708
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,921153,921158,4194304,256,0,0,28,24,75840,0x7fc0aab91400,0x7fbf7ac36080,524288,13124035,1679848188,12076324892880517,12076324893070203,12076324893331802,12076324893381418
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,921153,921158,4194304,256,0,0,28,24,77056,0x7fc0aab91300,0x7fbf7ac360c0,524288,14233274,1821792808,12076324893405332,12076324893586040,12076324893839159,12076324893888650
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,921153,921158,4194304,256,0,0,24,24,78272,0x7fc0aab91a00,0x7fbf7ac36100,524288,12840930,1643719556,12076324893913857,12076324894095478,12076324894224117,12076324894228342
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,921153,921158,4194304,256,0,0,24,24,80000,0x7fc0aab91900,0x7fbf7ac36140,524288,7040782,901187228,12076324894275089,12076324894446196,12076324894590355,12076324894594292
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,921153,921158,4194304,256,0,0,24,24,81216,0x7fc0aab91800,0x7fbf7ac36180,524288,12809973,1639613120,12076324894654794,12076324894813234,12076324894943473,12076324894947218
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,921153,921158,4194304,256,0,0,28,24,83456,0x7fc0aab91700,0x7fbf7ac361c0,524288,14132386,1808914756,12076324894994185,12076324895168432,12076324895433711,12076324895484486
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,921153,921158,4194304,256,0,0,28,24,84928,0x7fc0aab91600,0x7fbf7ac36200,524288,13678968,1750855192,12076324895509914,12076324895688270,12076324895938348,12076324895987581
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,921153,921158,4194304,256,0,0,24,24,86400,0x7fc0aab91500,0x7fbf7ac36240,524288,11779596,1507833372,12076324896020793,12076324896204907,12076324896338986,12076324896342932
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,921153,921158,4194304,256,0,0,24,24,88128,0x7fc0aab91400,0x7fbf7ac36280,524288,5370329,687500044,12076324896392764,12076324896558985,12076324896710184,12076324896714011
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,921153,921158,4194304,256,0,0,24,24,89600,0x7fc0aab91300,0x7fbf7ac362c0,524288,12296817,1573999032,12076324896791876,12076324896949543,12076324897081543,12076324897085722
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,921153,921158,4194304,256,0,0,28,24,92096,0x7fc0aab91a00,0x7fbf7ac36300,524288,11501488,1472202096,12076324897134282,12076324897305541,12076324897573540,12076324897596201
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,921153,921158,4194304,256,0,0,28,24,93568,0x7fc0aab91900,0x7fbf7ac36340,524288,13320122,1704983752,12076324897638279,12076324897797219,12076324898055458,12076324898107120
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,921153,921158,4194304,256,0,0,24,24,95040,0x7fc0aab91800,0x7fbf7ac36380,524288,12016359,1538034476,12076324898134050,12076324898310816,12076324898443616,12076324898447503
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,921153,921158,4194304,256,0,0,24,24,96768,0x7fc0aab91700,0x7fbf7ac363c0,524288,4326131,553723324,12076324898495282,12076324898661854,12076324898819294,12076324898823261
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,921153,921158,4194304,256,0,0,24,24,98240,0x7fc0aab91600,0x7fbf7ac36400,524288,12239178,1566613400,12076324898883263,12076324899049212,12076324899182172,12076324899186055
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,921153,921158,4194304,256,0,0,28,24,100736,0x7fc0aab91500,0x7fbf7ac36440,524288,12133403,1553101152,12076324899233854,12076324899407131,12076324899674489,12076324899722693
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,921153,921158,4194304,256,0,0,28,24,102208,0x7fc0aab91400,0x7fbf7ac36480,524288,13469460,1724089464,12076324899748821,12076324899922648,12076324900183607,12076324900237450
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,921153,921158,4194304,256,0,0,24,24,103680,0x7fc0aab91300,0x7fbf7ac364c0,524288,10572687,1353220160,12076324900264750,12076324900443285,12076324900583285,12076324900586959
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,921153,921158,4194304,256,0,0,24,24,105664,0x7fc0aab91a00,0x7fbf7ac36500,524288,4142103,530260360,12076324900636742,12076324900810483,12076324900976403,12076324900980340
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,921153,921158,4194304,256,0,0,24,24,107136,0x7fc0aab91900,0x7fbf7ac36540,524288,12008178,1537017356,12076324901042836,12076324901205361,12076324901338641,12076324901342203
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,921153,921158,4194304,256,0,0,28,24,109888,0x7fc0aab91800,0x7fbf7ac36580,524288,9834726,1258810876,12076324901393728,12076324901555280,12076324901821678,12076324901867108
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,921153,921158,4194304,256,0,0,28,24,111360,0x7fc0aab91700,0x7fbf7ac365c0,524288,14102675,1805176040,12076324901893748,12076324902072877,12076324902326636,12076324902374351
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,921153,921158,4194304,256,0,0,24,24,112832,0x7fc0aab91600,0x7fbf7ac36600,524288,10607477,1357736056,12076324902401040,12076324902577194,12076324902715754,12076324902719783
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,921153,921158,4194304,256,0,0,24,24,114816,0x7fc0aab91500,0x7fbf7ac36640,524288,3527276,451413128,12076324902766670,12076324902933033,12076324903106952,12076324903111360
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,921153,921158,4194304,256,0,0,24,24,116288,0x7fc0aab91400,0x7fbf7ac36680,524288,12880722,1648750984,12076324903171562,12076324903335751,12076324903465030,12076324903468805
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,921153,921158,4194304,256,0,0,28,24,119040,0x7fc0aab91300,0x7fbf7ac366c0,524288,9146419,1170760916,12076324903512506,12076324903682309,12076324903939907,12076324903986697
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,921153,921158,4194304,256,0,0,28,24,120768,0x7fc0aab91a00,0x7fbf7ac36700,524288,14038124,1796871968,12076324904016483,12076324904198306,12076324904453505,12076324904502616
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,921153,921158,4194304,256,0,0,24,24,122496,0x7fc0aab91900,0x7fbf7ac36740,524288,10574105,1353496756,12076324904529416,12076324904710464,12076324904849663,12076324904853478
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,921153,921158,4194304,256,0,0,24,24,124736,0x7fc0aab91800,0x7fbf7ac36780,524288,3457399,442518116,12076324904902720,12076324905072382,12076324905255741,12076324905259603
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,921153,921158,4194304,256,0,0,24,24,126464,0x7fc0aab91700,0x7fbf7ac367c0,524288,10207108,1306525100,12076324905320226,12076324905479740,12076324905664379,12076324905668333
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,921153,921158,4194304,256,0,0,20,24,127936,0x7fc0aab91600,0x7fbf7ac36800,524288,4125913,528139660,12076324905718255,12076324905879578,12076324906178616,12076324906225939
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,921153,921158,4194304,256,0,0,28,24,129664,0x7fc0aab91500,0x7fbf7ac36840,524288,13900881,1779277944,12076324906251737,12076324906430775,12076324906685333,12076324906733031
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,921153,921158,4194304,256,0,0,24,24,131392,0x7fc0aab91400,0x7fbf7ac36880,524288,11632847,1488971872,12076324906758919,12076324906931732,12076324907066132,12076324907069937
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,921153,921158,4194304,256,0,0,24,24,133632,0x7fc0aab91300,0x7fbf7ac368c0,524288,3437352,439997196,12076324907120692,12076324907290770,12076324907482769,12076324907530934
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,921153,921158,4194304,256,0,0,24,24,135360,0x7fc0aab91a00,0x7fbf7ac36900,524288,11389714,1457913640,12076324907569756,12076324907729168,12076324907864207,12076324907868001
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,921153,921158,4194304,256,0,0,20,24,136832,0x7fc0aab91900,0x7fbf7ac36940,524288,2914743,373162536,12076324907916030,12076324908096526,12076324908381805,12076324908430977
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,921153,921158,4194304,256,0,0,28,24,138560,0x7fc0aab91800,0x7fbf7ac36980,524288,13932315,1783280116,12076324908456384,12076324908633324,12076324908892522,12076324908913363
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,921153,921158,4194304,256,0,0,24,24,140288,0x7fc0aab91700,0x7fbf7ac369c0,524288,10430768,1335016856,12076324908955692,12076324909121001,12076324909261160,12076324909265337
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,921153,921158,4194304,256,0,0,24,24,142784,0x7fc0aab91600,0x7fbf7ac36a00,524288,3351105,429074216,12076324909313978,12076324909480199,12076324909690118,12076324909737725
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,921153,921158,4194304,256,0,0,24,24,144768,0x7fc0aab91500,0x7fbf7ac36a40,524288,10451016,1337718216,12076324909776077,12076324909934917,12076324910073476,12076324910077457
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,921153,921158,4194304,256,0,0,20,24,145728,0x7fc0aab91400,0x7fbf7ac36a80,524288,2564820,328282864,12076324910127720,12076324910298755,12076324910608673,12076324910655411
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,921153,921158,4194304,256,0,0,28,24,147712,0x7fc0aab91300,0x7fbf7ac36ac0,524288,14030770,1795889424,12076324910681670,12076324910854752,12076324911109951,12076324911160049
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,921153,921158,4194304,256,0,0,24,24,149696,0x7fc0aab91a00,0x7fbf7ac36b00,524288,10435639,1335811920,12076324911186838,12076324911362910,12076324911502109,12076324911506032
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,921153,921158,4194304,256,0,0,24,24,152192,0x7fc0aab91900,0x7fbf7ac36b40,524288,3233595,413830248,12076324911554852,12076324911720828,12076324911982426,12076324912029735
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,921153,921158,4194304,256,0,0,24,24,154176,0x7fc0aab91800,0x7fbf7ac36b80,524288,10017803,1282209860,12076324912064670,12076324912235865,12076324912375864,12076324912379866
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,921153,921158,4194304,256,0,0,20,24,155648,0x7fc0aab91700,0x7fbf7ac36bc0,524288,2492896,319050360,12076324912427394,12076324912594263,12076324912925782,12076324912947611
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,921153,921158,4194304,256,0,0,28,24,157632,0x7fc0aab91600,0x7fbf7ac36c00,524288,12895056,1650572240,12076324912984680,12076324913146900,12076324913407379,12076324913456707
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,921153,921158,4194304,256,0,0,24,24,159616,0x7fc0aab91500,0x7fbf7ac36c40,524288,10583640,1354717808,12076324913478728,12076324913656658,12076324913796497,12076324913800476
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,921153,921158,4194304,256,0,0,24,24,162368,0x7fc0aab91400,0x7fbf7ac36c80,524288,3376223,432037936,12076324913848214,12076324914015216,12076324914261135,12076324914308670
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,921153,921158,4194304,256,0,0,24,24,164608,0x7fc0aab91300,0x7fbf7ac36cc0,524288,9625041,1232048032,12076324914345469,12076324914511300,12076324914651460,12076324914658581
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,921153,921158,4194304,256,0,0,20,24,166336,0x7fc0aab91a00,0x7fbf7ac36d00,524288,2385143,305245444,12076324914705838,12076324914865378,12076324915242656,12076324915293090
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,921153,921158,4194304,256,0,0,28,24,168576,0x7fc0aab91900,0x7fbf7ac36d40,524288,13874201,1775809428,12076324915318427,12076324915494335,12076324915749054,12076324915769124
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,921153,921158,4194304,256,0,0,24,24,170816,0x7fc0aab91800,0x7fbf7ac36d80,524288,9307681,1191433172,12076324915812435,12076324915970173,12076324916114332,12076324916118083
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,921153,921158,4194304,256,0,0,24,24,174080,0x7fc0aab91700,0x7fbf7ac36dc0,524288,3367622,430932036,12076324916167244,12076324916342651,12076324916653210,12076324916701397
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,921153,921158,4194304,256,0,0,24,24,176576,0x7fc0aab91600,0x7fbf7ac36e00,524288,8639586,1105829828,12076324916739287,12076324916897209,12076324917032249,12076324917035628
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,921153,921158,4194304,256,0,0,20,24,177792,0x7fc0aab91500,0x7fbf7ac36e40,524288,2339059,299339440,12076324917083978,12076324917253048,12076324917677686,12076324917724418
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,921153,921158,4194304,256,0,0,28,24,180288,0x7fc0aab91400,0x7fbf7ac36e80,524288,10103691,1293250032,12076324917750777,12076324917927285,12076324918192244,12076324918240618
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,921153,921158,4194304,256,0,0,24,24,182784,0x7fc0aab91300,0x7fbf7ac36ec0,524288,7301788,934484428,12076324918267037,12076324918444883,12076324918586162,12076324918589426
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,921153,921158,4194304,256,0,0,24,24,186304,0x7fc0aab91a00,0x7fbf7ac36f00,524288,3448522,441367708,12076324918637465,12076324918803921,12076324919119600,12076324919170886
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,921153,921158,4194304,256,0,0,24,24,189312,0x7fc0aab91900,0x7fbf7ac36f40,524288,3610119,462206688,12076324919207244,12076324919369519,12076324919523918,12076324919527128
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,921153,921158,4194304,256,0,0,20,24,190784,0x7fc0aab91800,0x7fbf7ac36f80,524288,2302329,294751312,12076324919574777,12076324919743917,12076324920260715,12076324920307849
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,921153,921158,4194304,256,0,0,28,24,193792,0x7fc0aab91700,0x7fbf7ac36fc0,524288,8378304,1072369756,12076324920330802,12076324920519754,12076324920817833,12076324920838546
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,921153,921158,4194304,256,0,0,24,24,196800,0x7fc0aab91600,0x7fbf7ac37000,524288,3326783,425884268,12076324920890202,12076324921054472,12076324921209031,12076324921212571
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,921153,921158,4194304,256,0,0,24,24,201088,0x7fc0aab91500,0x7fbf7ac37040,524288,3268023,418386768,12076324921259578,12076324921438470,12076324921824388,12076324921871065
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,921153,921158,4194304,256,0,0,24,24,204608,0x7fc0aab91400,0x7fbf7ac37080,524288,3406692,435950804,12076324921914355,12076324922081347,12076324922258467,12076324922261971
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,921153,921158,4194304,256,0,0,20,24,206080,0x7fc0aab91300,0x7fbf7ac370c0,524288,2321360,297201432,12076324922310371,12076324922480066,12076324923090623,12076324923138600
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,921153,921158,4194304,256,0,0,28,24,209600,0x7fc0aab91a00,0x7fbf7ac37100,524288,3726423,476982952,12076324923164739,12076324923348382,12076324923675741,12076324923721464
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,921153,921158,4194304,256,0,0,24,24,213120,0x7fc0aab91900,0x7fbf7ac37140,524288,3106039,397473404,12076324923748774,12076324923927260,12076324924105979,12076324924109525
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,921153,921158,4194304,256,0,0,24,24,218176,0x7fc0aab91800,0x7fbf7ac37180,524288,3312643,423978688,12076324924156622,12076324924328058,12076324924784376,12076324924832679
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,921153,921158,4194304,256,0,0,24,24,222208,0x7fc0aab91700,0x7fbf7ac371c0,524288,2983092,381885796,12076324924872042,12076324925039575,12076324925240214,12076324925289097
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,921153,921158,4194304,256,0,0,20,24,223936,0x7fc0aab91600,0x7fbf7ac37200,524288,2291301,293339744,12076324925311018,12076324925497013,12076324926207570,12076324926256495
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,921153,921158,4194304,256,0,0,28,24,227968,0x7fc0aab91500,0x7fbf7ac37240,524288,3602250,461175832,12076324926280810,12076324926461009,12076324926835087,12076324926881707
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,921153,921158,4194304,256,0,0,24,24,232000,0x7fc0aab91400,0x7fbf7ac37280,524288,3089036,395326984,12076324926908056,12076324927093806,12076324927297645,12076324927346741
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,921153,921158,4194304,256,0,0,24,24,237824,0x7fc0aab91300,0x7fbf7ac372c0,524288,4037597,516856392,12076324927371627,12076324927546764,12076324928073482,12076324928121651
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,921153,921158,4194304,256,0,0,24,24,242368,0x7fc0aab91a00,0x7fbf7ac37300,524288,3050385,390352172,12076324928160734,12076324928321641,12076324928545160,12076324928591574
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,921153,921158,4194304,256,0,0,20,24,243584,0x7fc0aab91900,0x7fbf7ac37340,524288,2324407,297411124,12076324928613475,12076324928796199,12076324929596196,12076324929646785
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,921153,921158,4194304,256,0,0,28,24,248128,0x7fc0aab91800,0x7fbf7ac37380,524288,3451819,441894164,12076324929672984,12076324929850595,12076324930272033,12076324930325016
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,921153,921158,4194304,256,0,0,24,24,252672,0x7fc0aab91700,0x7fbf7ac373c0,524288,3136706,401476888,12076324930351976,12076324930531072,12076324930757951,12076324930806060
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,921153,921158,4194304,256,0,0,24,24,259264,0x7fc0aab91600,0x7fbf7ac37400,524288,4642750,594336476,12076324930829994,12076324931004510,12076324931601467,12076324931650459
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,921153,921158,4194304,256,0,0,24,24,264832,0x7fc0aab91500,0x7fbf7ac37440,524288,3205878,410331404,12076324931687067,12076324931855866,12076324932126585,12076324932177739
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,921153,921158,4194304,256,0,0,20,24,266304,0x7fc0aab91400,0x7fbf7ac37480,524288,2309146,295428132,12076324932200201,12076324932379224,12076324933364020,12076324933431459
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,921153,921158,4194304,256,0,0,28,24,271872,0x7fc0aab91300,0x7fbf7ac374c0,524288,3535941,452505508,12076324933462126,12076324933637779,12076324934152977,12076324934219604
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,921153,921158,4194304,256,0,0,24,24,277440,0x7fc0aab91a00,0x7fbf7ac37500,524288,3205779,410295868,12076324934248407,12076324934424976,12076324934699054,12076324934765919
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,921153,921158,4194304,256,0,0,12,24,279936,0x7fc0aab91900,0x7fbf7ac37540,524288,2194670,280910352,12076324934793480,12076324934964493,12076324935704650,12076324935773872
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,921153,921158,4194304,256,0,0,24,24,286528,0x7fc0aab91800,0x7fbf7ac37580,524288,3287385,420792036,12076324935815820,12076324935979209,12076324936297128,12076324936364590
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,921153,921158,4194304,256,0,0,20,24,288000,0x7fc0aab91700,0x7fbf7ac375c0,524288,2280821,291909728,12076324936393123,12076324936571687,12076324937743362,12076324937809225
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,921153,921158,4194304,256,0,0,32,24,294592,0x7fc0aab91600,0x7fbf7ac37600,524288,3407856,436190608,12076324937839431,12076324938009281,12076324938618078,12076324938686485
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,921153,921158,4194304,256,0,0,24,24,301184,0x7fc0aab91500,0x7fbf7ac37640,524288,3310205,423678296,12076324938717172,12076324938892157,12076324939211196,12076324939280329
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,921153,921158,4194304,256,0,0,12,24,304960,0x7fc0aab91400,0x7fbf7ac37680,524288,2196223,280992068,12076324939309994,12076324939492634,12076324940371831,12076324940438000
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,921153,921158,4194304,256,0,0,24,24,313600,0x7fc0aab91300,0x7fbf7ac376c0,524288,3278376,419575164,12076324940480008,12076324940641750,12076324941053428,12076324941120028
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,921153,921158,4194304,256,0,0,20,24,314816,0x7fc0aab91a00,0x7fbf7ac37700,524288,2331810,298531300,12076324941151126,12076324941323667,12076324942873420,12076324942940451
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,921153,921158,4194304,256,0,0,20,24,317568,0x7fc0aab91900,0x7fbf7ac37740,524288,2263036,289789640,12076324942963183,12076324943154379,12076324943949736,12076324944019366
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,921153,921158,4194304,256,0,0,12,24,320320,0x7fc0aab91800,0x7fbf7ac37780,524288,2173619,278217040,12076324944048741,12076324944228614,12076324944643973,12076324944709699
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,921153,921158,4194304,256,0,0,12,24,324096,0x7fc0aab91700,0x7fbf7ac377c0,524288,2242042,286971484,12076324944733664,12076324944908772,12076324946068287,12076324946136180
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,921153,921158,4194304,256,0,0,12,24,328896,0x7fc0aab91600,0x7fbf7ac37800,524288,2242646,287191700,12076324946175754,12076324946337406,12076324947123642,12076324947191211
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,921153,921158,4194304,256,0,0,20,24,330112,0x7fc0aab91500,0x7fbf7ac37840,524288,2662363,340770928,12076324947220205,12076324947398521,12076324950447468,12076324950514557
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,921153,921158,4194304,256,0,0,20,24,332864,0x7fc0aab91400,0x7fbf7ac37880,524288,2298931,294319360,12076324950544573,12076324950722507,12076324952264421,12076324952331274
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,921153,921158,4194304,256,0,0,12,24,335616,0x7fc0aab91300,0x7fbf7ac378c0,524288,2197160,281088936,12076324952360167,12076324952544740,12076324953334016,12076324953402354
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,921153,921158,4194304,256,0,0,12,24,339392,0x7fc0aab91a00,0x7fbf7ac37900,524288,2535602,324582428,12076324953432911,12076324953610655,12076324955893526,12076324955961731
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,921153,921158,4194304,256,0,0,12,24,344192,0x7fc0aab91900,0x7fbf7ac37940,524288,2385934,305369720,12076324956007636,12076324956173524,12076324957708878,12076324957778467
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,921153,921158,4194304,256,0,0,20,24,345408,0x7fc0aab91800,0x7fbf7ac37980,524288,2884153,369236128,12076324957808362,12076324957987437,12076324964042291,12076324964112859
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,921153,921158,4194304,256,0,0,20,24,348160,0x7fc0aab91700,0x7fbf7ac379c0,524288,3377375,432171988,12076324964139058,12076324964317330,12076324967362437,12076324967593037
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,921153,921158,4194304,256,0,0,12,24,350912,0x7fc0aab91600,0x7fbf7ac37a00,524288,2262042,289551444,12076324967625167,12076324967808676,12076324969347709,12076324969417327
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,921153,921158,4194304,256,0,0,12,24,0,0x7fc0aab91500,0x7fbf7ac37a40,524288,2567679,328586028,12076324969444798,12076324969626428,12076324974153289,12076324974220834
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid grd Workgroup_Size LDS_Per_Workgroup scr vgpr SGPR fbar sig obj SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 __amd_rocclr_fillBuffer.kd 0 0 0 921153 921158 33554432 256 0 0 8 32 6464 0x0 0x7fbf7ac04180 1048576 11001658 1408052856 12076324607361092 12076324851578856 12076324851903654 12076324852039846
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 921153 921158 32768 256 0 0 24 24 12480 0x0 0x7fbf7ac35100 4096 113289 14479660 12076324866554932 12076324866851777 12076324866858017 12076324866863235
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 4 921153 921158 4194304 256 0 0 24 24 12928 0x7fc0aab91900 0x7fbf7ac35140 524288 12401318 1587311276 12076324866927514 12076324867148415 12076324867279615 12076324867283767
5 3 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 6 921153 921158 4194304 256 0 0 36 24 13632 0x7fc0aab91800 0x7fbf7ac35180 524288 13924068 1782351476 12076324867354438 12076324867525693 12076324867773532 12076324867842695
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 8 921153 921158 4194304 256 0 0 28 24 14080 0x7fc0aab91700 0x7fbf7ac351c0 524288 14366779 1838880984 12076324867872430 12076324868062971 12076324868314809 12076324868383570
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 10 921153 921158 4194304 256 0 0 24 24 14528 0x7fc0aab91600 0x7fbf7ac35200 524288 11167660 1429516928 12076324868408617 12076324868594968 12076324868731607 12076324868735214
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 12 921153 921158 4194304 256 0 0 24 24 14976 0x7fc0aab91500 0x7fbf7ac35240 524288 12212582 1563143728 12076324868785387 12076324868956246 12076324869088885 12076324869092698
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 14 921153 921158 4194304 256 0 0 24 24 15424 0x7fc0aab91400 0x7fbf7ac35280 524288 12734855 1630074280 12076324869171385 12076324869342644 12076324869472563 12076324869476321
10 8 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 16 921153 921158 4194304 256 0 0 28 24 16128 0x7fc0aab91300 0x7fbf7ac352c0 524288 13905355 1779832888 12076324869526575 12076324869705202 12076324869958961 12076324870005104
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 18 921153 921158 4194304 256 0 0 28 24 16832 0x7fc0aab91a00 0x7fbf7ac35300 524288 13638895 1745720368 12076324870031794 12076324870211280 12076324870466638 12076324870507167
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 20 921153 921158 4194304 256 0 0 24 24 17536 0x7fc0aab91900 0x7fbf7ac35340 524288 11953865 1530028984 12076324870530250 12076324870718637 12076324870851916 12076324870855575
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 22 921153 921158 4194304 256 0 0 24 24 18240 0x7fc0aab91800 0x7fbf7ac35380 524288 11019037 1410452988 12076324870903554 12076324871079435 12076324871216235 12076324871220112
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 24 921153 921158 4194304 256 0 0 24 24 18944 0x7fc0aab91700 0x7fbf7ac353c0 524288 12347166 1580393688 12076324871281817 12076324871445993 12076324871577833 12076324871581554
15 13 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 26 921153 921158 4194304 256 0 0 28 24 19904 0x7fc0aab91600 0x7fbf7ac35400 524288 14251323 1824182664 12076324871624504 12076324871801512 12076324872056070 12076324872124513
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 28 921153 921158 4194304 256 0 0 28 24 20608 0x7fc0aab91500 0x7fbf7ac35440 524288 14134381 1809184948 12076324872148016 12076324872336869 12076324872590788 12076324872657093
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 30 921153 921158 4194304 256 0 0 24 24 21312 0x7fc0aab91400 0x7fbf7ac35480 524288 12003708 1536401320 12076324872680987 12076324872859106 12076324872992066 12076324872995692
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 32 921153 921158 4194304 256 0 0 24 24 22016 0x7fc0aab91300 0x7fbf7ac354c0 524288 12761839 1633550800 12076324873044783 12076324873215584 12076324873345824 12076324873349419
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 34 921153 921158 4194304 256 0 0 24 24 22720 0x7fc0aab91a00 0x7fbf7ac35500 524288 12355665 1581510772 12076324873408950 12076324873572063 12076324873703742 12076324873707294
20 18 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 36 921153 921158 4194304 256 0 0 28 24 23680 0x7fc0aab91900 0x7fbf7ac35540 524288 13960437 1786860424 12076324873758660 12076324873919901 12076324874172059 12076324874214918
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 38 921153 921158 4194304 256 0 0 28 24 24384 0x7fc0aab91800 0x7fbf7ac35580 524288 14296440 1829925976 12076324874237069 12076324874424378 12076324874672537 12076324874713925
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 40 921153 921158 4194304 256 0 0 24 24 25088 0x7fc0aab91700 0x7fbf7ac355c0 524288 11419318 1461579156 12076324874735505 12076324874917976 12076324875052855 12076324875056792
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 42 921153 921158 4194304 256 0 0 24 24 25792 0x7fc0aab91600 0x7fbf7ac35600 524288 12716538 1627629044 12076324875107927 12076324875278934 12076324875409173 12076324875413004
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 44 921153 921158 4194304 256 0 0 24 24 26496 0x7fc0aab91500 0x7fbf7ac35640 524288 12786121 1636755892 12076324875472425 12076324875634612 12076324875764851 12076324875768585
25 23 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 46 921153 921158 4194304 256 0 0 28 24 27712 0x7fc0aab91400 0x7fbf7ac35680 524288 13985714 1790158532 12076324875816554 12076324875982770 12076324876235249 12076324876303439
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 48 921153 921158 4194304 256 0 0 28 24 28416 0x7fc0aab91300 0x7fbf7ac356c0 524288 13560902 1735756300 12076324876330079 12076324876507248 12076324876758446 12076324876825439
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 50 921153 921158 4194304 256 0 0 24 24 29120 0x7fc0aab91a00 0x7fbf7ac35700 524288 11718659 1499951512 12076324876850366 12076324877034445 12076324877168204 12076324877171973
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 52 921153 921158 4194304 256 0 0 24 24 30080 0x7fc0aab91900 0x7fbf7ac35740 524288 12932359 1655304508 12076324877219902 12076324877389163 12076324877519402 12076324877523086
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 54 921153 921158 4194304 256 0 0 24 24 30784 0x7fc0aab91800 0x7fbf7ac35780 524288 12610659 1614160584 12076324877581434 12076324877741481 12076324877871401 12076324877875140
30 28 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 56 921153 921158 4194304 256 0 0 28 24 32000 0x7fc0aab91700 0x7fbf7ac357c0 524288 14065498 1800337208 12076324877923720 12076324878115879 12076324878372038 12076324878439409
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 58 921153 921158 4194304 256 0 0 28 24 32960 0x7fc0aab91600 0x7fbf7ac35800 524288 14390289 1841900872 12076324878466319 12076324878642597 12076324878896835 12076324878963042
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 60 921153 921158 4194304 256 0 0 24 24 33920 0x7fc0aab91500 0x7fbf7ac35840 524288 11632795 1488875344 12076324878988389 12076324879172194 12076324879307713 12076324879311890
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 62 921153 921158 4194304 256 0 0 24 24 34880 0x7fc0aab91400 0x7fbf7ac35880 524288 13041589 1669311224 12076324879360360 12076324879526272 12076324879656991 12076324879660839
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 64 921153 921158 4194304 256 0 0 24 24 35840 0x7fc0aab91300 0x7fbf7ac358c0 524288 13141993 1682249604 12076324879722754 12076324879885790 12076324880014110 12076324880017852
35 33 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 66 921153 921158 4194304 256 0 0 28 24 37312 0x7fc0aab91a00 0x7fbf7ac35900 524288 13903488 1779637896 12076324880067464 12076324880239229 12076324880495707 12076324880563456
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 68 921153 921158 4194304 256 0 0 28 24 38272 0x7fc0aab91900 0x7fbf7ac35940 524288 13863049 1774444876 12076324880586780 12076324880772026 12076324881022745 12076324881091307
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 70 921153 921158 4194304 256 0 0 24 24 39232 0x7fc0aab91800 0x7fbf7ac35980 524288 12585259 1610915156 12076324881119910 12076324881299543 12076324881430582 12076324881434365
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 72 921153 921158 4194304 256 0 0 24 24 40192 0x7fc0aab91700 0x7fbf7ac359c0 524288 12147124 1554843264 12076324881482705 12076324881653941 12076324881787221 12076324881791128
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 74 921153 921158 4194304 256 0 0 24 24 41152 0x7fc0aab91600 0x7fbf7ac35a00 524288 12065079 1544321884 12076324881850709 12076324882012339 12076324882144979 12076324882148993
40 38 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 76 921153 921158 4194304 256 0 0 28 24 42624 0x7fc0aab91500 0x7fbf7ac35a40 524288 13593200 1739929944 12076324882196461 12076324882368338 12076324882625456 12076324882691912
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 78 921153 921158 4194304 256 0 0 28 24 43584 0x7fc0aab91400 0x7fbf7ac35a80 524288 14200515 1817602084 12076324882713462 12076324882892175 12076324883145294 12076324883216226
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 80 921153 921158 4194304 256 0 0 24 24 44544 0x7fc0aab91300 0x7fbf7ac35ac0 524288 12974942 1660889500 12076324883238357 12076324883418092 12076324883547532 12076324883551209
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 82 921153 921158 4194304 256 0 0 24 24 45760 0x7fc0aab91a00 0x7fbf7ac35b00 524288 12389424 1585815896 12076324883599499 12076324883764651 12076324883896810 12076324883900618
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 84 921153 921158 4194304 256 0 0 24 24 46720 0x7fc0aab91900 0x7fbf7ac35b40 524288 12579260 1610101880 12076324883959738 12076324884128009 12076324884258248 12076324884262240
45 43 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 86 921153 921158 4194304 256 0 0 28 24 48448 0x7fc0aab91800 0x7fbf7ac35b80 524288 13798283 1766179384 12076324884310390 12076324884477287 12076324884741606 12076324884808636
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 88 921153 921158 4194304 256 0 0 28 24 49408 0x7fc0aab91700 0x7fbf7ac35bc0 524288 13967280 1787765120 12076324884832991 12076324885007524 12076324885301443 12076324885368246
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 90 921153 921158 4194304 256 0 0 24 24 50368 0x7fc0aab91600 0x7fbf7ac35c00 524288 12768928 1634420072 12076324885393152 12076324885575521 12076324885705281 12076324885709039
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 92 921153 921158 4194304 256 0 0 24 24 51584 0x7fc0aab91500 0x7fbf7ac35c40 524288 11048220 1414101748 12076324885756788 12076324885922719 12076324886059999 12076324886063758
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 94 921153 921158 4194304 256 0 0 24 24 52544 0x7fc0aab91400 0x7fbf7ac35c80 524288 11869975 1519411292 12076324886124431 12076324886288158 12076324886420317 12076324886424038
50 48 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 96 921153 921158 4194304 256 0 0 28 24 54272 0x7fc0aab91300 0x7fbf7ac35cc0 524288 12994597 1663228396 12076324886468681 12076324886637116 12076324886906874 12076324886949354
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 98 921153 921158 4194304 256 0 0 28 24 55488 0x7fc0aab91a00 0x7fbf7ac35d00 524288 14232764 1821788460 12076324886975783 12076324887154713 12076324887406712 12076324887475632
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 100 921153 921158 4194304 256 0 0 24 24 56704 0x7fc0aab91900 0x7fbf7ac35d40 524288 13097771 1676571164 12076324887499006 12076324887675351 12076324887804150 12076324887808080
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 102 921153 921158 4194304 256 0 0 24 24 58176 0x7fc0aab91800 0x7fbf7ac35d80 524288 9712685 1243268284 12076324887858624 12076324888030709 12076324888172788 12076324888176825
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 104 921153 921158 4194304 256 0 0 24 24 59392 0x7fc0aab91700 0x7fbf7ac35dc0 524288 11709071 1498779836 12076324888236827 12076324888397907 12076324888531026 12076324888534821
55 53 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 106 921153 921158 4194304 256 0 0 28 24 61376 0x7fc0aab91600 0x7fbf7ac35e00 524288 14539178 1861072408 12076324888582319 12076324888746865 12076324889014544 12076324889081958
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 108 921153 921158 4194304 256 0 0 28 24 62592 0x7fc0aab91500 0x7fbf7ac35e40 524288 14171868 1814021376 12076324889105682 12076324889292942 12076324889544781 12076324889611411
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 110 921153 921158 4194304 256 0 0 24 24 63808 0x7fc0aab91400 0x7fbf7ac35e80 524288 11767035 1506177424 12076324889635867 12076324889818380 12076324889993419 12076324889997218
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 112 921153 921158 4194304 256 0 0 24 24 65280 0x7fc0aab91300 0x7fbf7ac35ec0 524288 9202080 1177852572 12076324890047051 12076324890215818 12076324890356777 12076324890360614
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 114 921153 921158 4194304 256 0 0 24 24 66496 0x7fc0aab91a00 0x7fbf7ac35f00 524288 12333047 1578665472 12076324890422609 12076324890583496 12076324890714055 12076324890718158
60 58 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 116 921153 921158 4194304 256 0 0 28 24 68480 0x7fc0aab91900 0x7fbf7ac35f40 524288 13147150 1682780388 12076324890763743 12076324890932934 12076324891196933 12076324891267369
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 118 921153 921158 4194304 256 0 0 28 24 69696 0x7fc0aab91800 0x7fbf7ac35f80 524288 14153714 1811632852 12076324891292906 12076324891468931 12076324891717890 12076324891784791
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 120 921153 921158 4194304 256 0 0 24 24 70912 0x7fc0aab91700 0x7fbf7ac35fc0 524288 11152062 1427486812 12076324891810709 12076324891983809 12076324892118048 12076324892122168
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 122 921153 921158 4194304 256 0 0 24 24 72384 0x7fc0aab91600 0x7fbf7ac36000 524288 7595469 972160732 12076324892171249 12076324892335487 12076324892475806 12076324892479612
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 124 921153 921158 4194304 256 0 0 24 24 73600 0x7fc0aab91500 0x7fbf7ac36040 524288 12148182 1554948808 12076324892538181 12076324892695805 12076324892828924 12076324892832708
65 63 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 126 921153 921158 4194304 256 0 0 28 24 75840 0x7fc0aab91400 0x7fbf7ac36080 524288 13124035 1679848188 12076324892880517 12076324893070203 12076324893331802 12076324893381418
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 128 921153 921158 4194304 256 0 0 28 24 77056 0x7fc0aab91300 0x7fbf7ac360c0 524288 14233274 1821792808 12076324893405332 12076324893586040 12076324893839159 12076324893888650
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 130 921153 921158 4194304 256 0 0 24 24 78272 0x7fc0aab91a00 0x7fbf7ac36100 524288 12840930 1643719556 12076324893913857 12076324894095478 12076324894224117 12076324894228342
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 132 921153 921158 4194304 256 0 0 24 24 80000 0x7fc0aab91900 0x7fbf7ac36140 524288 7040782 901187228 12076324894275089 12076324894446196 12076324894590355 12076324894594292
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 134 921153 921158 4194304 256 0 0 24 24 81216 0x7fc0aab91800 0x7fbf7ac36180 524288 12809973 1639613120 12076324894654794 12076324894813234 12076324894943473 12076324894947218
70 68 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 136 921153 921158 4194304 256 0 0 28 24 83456 0x7fc0aab91700 0x7fbf7ac361c0 524288 14132386 1808914756 12076324894994185 12076324895168432 12076324895433711 12076324895484486
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 138 921153 921158 4194304 256 0 0 28 24 84928 0x7fc0aab91600 0x7fbf7ac36200 524288 13678968 1750855192 12076324895509914 12076324895688270 12076324895938348 12076324895987581
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 140 921153 921158 4194304 256 0 0 24 24 86400 0x7fc0aab91500 0x7fbf7ac36240 524288 11779596 1507833372 12076324896020793 12076324896204907 12076324896338986 12076324896342932
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 142 921153 921158 4194304 256 0 0 24 24 88128 0x7fc0aab91400 0x7fbf7ac36280 524288 5370329 687500044 12076324896392764 12076324896558985 12076324896710184 12076324896714011
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 144 921153 921158 4194304 256 0 0 24 24 89600 0x7fc0aab91300 0x7fbf7ac362c0 524288 12296817 1573999032 12076324896791876 12076324896949543 12076324897081543 12076324897085722
75 73 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 146 921153 921158 4194304 256 0 0 28 24 92096 0x7fc0aab91a00 0x7fbf7ac36300 524288 11501488 1472202096 12076324897134282 12076324897305541 12076324897573540 12076324897596201
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 148 921153 921158 4194304 256 0 0 28 24 93568 0x7fc0aab91900 0x7fbf7ac36340 524288 13320122 1704983752 12076324897638279 12076324897797219 12076324898055458 12076324898107120
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 150 921153 921158 4194304 256 0 0 24 24 95040 0x7fc0aab91800 0x7fbf7ac36380 524288 12016359 1538034476 12076324898134050 12076324898310816 12076324898443616 12076324898447503
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 152 921153 921158 4194304 256 0 0 24 24 96768 0x7fc0aab91700 0x7fbf7ac363c0 524288 4326131 553723324 12076324898495282 12076324898661854 12076324898819294 12076324898823261
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 154 921153 921158 4194304 256 0 0 24 24 98240 0x7fc0aab91600 0x7fbf7ac36400 524288 12239178 1566613400 12076324898883263 12076324899049212 12076324899182172 12076324899186055
80 78 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 156 921153 921158 4194304 256 0 0 28 24 100736 0x7fc0aab91500 0x7fbf7ac36440 524288 12133403 1553101152 12076324899233854 12076324899407131 12076324899674489 12076324899722693
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 158 921153 921158 4194304 256 0 0 28 24 102208 0x7fc0aab91400 0x7fbf7ac36480 524288 13469460 1724089464 12076324899748821 12076324899922648 12076324900183607 12076324900237450
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 160 921153 921158 4194304 256 0 0 24 24 103680 0x7fc0aab91300 0x7fbf7ac364c0 524288 10572687 1353220160 12076324900264750 12076324900443285 12076324900583285 12076324900586959
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 162 921153 921158 4194304 256 0 0 24 24 105664 0x7fc0aab91a00 0x7fbf7ac36500 524288 4142103 530260360 12076324900636742 12076324900810483 12076324900976403 12076324900980340
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 164 921153 921158 4194304 256 0 0 24 24 107136 0x7fc0aab91900 0x7fbf7ac36540 524288 12008178 1537017356 12076324901042836 12076324901205361 12076324901338641 12076324901342203
85 83 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 166 921153 921158 4194304 256 0 0 28 24 109888 0x7fc0aab91800 0x7fbf7ac36580 524288 9834726 1258810876 12076324901393728 12076324901555280 12076324901821678 12076324901867108
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 168 921153 921158 4194304 256 0 0 28 24 111360 0x7fc0aab91700 0x7fbf7ac365c0 524288 14102675 1805176040 12076324901893748 12076324902072877 12076324902326636 12076324902374351
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 170 921153 921158 4194304 256 0 0 24 24 112832 0x7fc0aab91600 0x7fbf7ac36600 524288 10607477 1357736056 12076324902401040 12076324902577194 12076324902715754 12076324902719783
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 172 921153 921158 4194304 256 0 0 24 24 114816 0x7fc0aab91500 0x7fbf7ac36640 524288 3527276 451413128 12076324902766670 12076324902933033 12076324903106952 12076324903111360
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 174 921153 921158 4194304 256 0 0 24 24 116288 0x7fc0aab91400 0x7fbf7ac36680 524288 12880722 1648750984 12076324903171562 12076324903335751 12076324903465030 12076324903468805
90 88 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 176 921153 921158 4194304 256 0 0 28 24 119040 0x7fc0aab91300 0x7fbf7ac366c0 524288 9146419 1170760916 12076324903512506 12076324903682309 12076324903939907 12076324903986697
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 178 921153 921158 4194304 256 0 0 28 24 120768 0x7fc0aab91a00 0x7fbf7ac36700 524288 14038124 1796871968 12076324904016483 12076324904198306 12076324904453505 12076324904502616
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 180 921153 921158 4194304 256 0 0 24 24 122496 0x7fc0aab91900 0x7fbf7ac36740 524288 10574105 1353496756 12076324904529416 12076324904710464 12076324904849663 12076324904853478
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 182 921153 921158 4194304 256 0 0 24 24 124736 0x7fc0aab91800 0x7fbf7ac36780 524288 3457399 442518116 12076324904902720 12076324905072382 12076324905255741 12076324905259603
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 184 921153 921158 4194304 256 0 0 24 24 126464 0x7fc0aab91700 0x7fbf7ac367c0 524288 10207108 1306525100 12076324905320226 12076324905479740 12076324905664379 12076324905668333
95 93 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 186 921153 921158 4194304 256 0 0 20 24 127936 0x7fc0aab91600 0x7fbf7ac36800 524288 4125913 528139660 12076324905718255 12076324905879578 12076324906178616 12076324906225939
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 188 921153 921158 4194304 256 0 0 28 24 129664 0x7fc0aab91500 0x7fbf7ac36840 524288 13900881 1779277944 12076324906251737 12076324906430775 12076324906685333 12076324906733031
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 190 921153 921158 4194304 256 0 0 24 24 131392 0x7fc0aab91400 0x7fbf7ac36880 524288 11632847 1488971872 12076324906758919 12076324906931732 12076324907066132 12076324907069937
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 192 921153 921158 4194304 256 0 0 24 24 133632 0x7fc0aab91300 0x7fbf7ac368c0 524288 3437352 439997196 12076324907120692 12076324907290770 12076324907482769 12076324907530934
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 194 921153 921158 4194304 256 0 0 24 24 135360 0x7fc0aab91a00 0x7fbf7ac36900 524288 11389714 1457913640 12076324907569756 12076324907729168 12076324907864207 12076324907868001
100 98 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 196 921153 921158 4194304 256 0 0 20 24 136832 0x7fc0aab91900 0x7fbf7ac36940 524288 2914743 373162536 12076324907916030 12076324908096526 12076324908381805 12076324908430977
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 198 921153 921158 4194304 256 0 0 28 24 138560 0x7fc0aab91800 0x7fbf7ac36980 524288 13932315 1783280116 12076324908456384 12076324908633324 12076324908892522 12076324908913363
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 200 921153 921158 4194304 256 0 0 24 24 140288 0x7fc0aab91700 0x7fbf7ac369c0 524288 10430768 1335016856 12076324908955692 12076324909121001 12076324909261160 12076324909265337
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 202 921153 921158 4194304 256 0 0 24 24 142784 0x7fc0aab91600 0x7fbf7ac36a00 524288 3351105 429074216 12076324909313978 12076324909480199 12076324909690118 12076324909737725
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 204 921153 921158 4194304 256 0 0 24 24 144768 0x7fc0aab91500 0x7fbf7ac36a40 524288 10451016 1337718216 12076324909776077 12076324909934917 12076324910073476 12076324910077457
105 103 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 206 921153 921158 4194304 256 0 0 20 24 145728 0x7fc0aab91400 0x7fbf7ac36a80 524288 2564820 328282864 12076324910127720 12076324910298755 12076324910608673 12076324910655411
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 208 921153 921158 4194304 256 0 0 28 24 147712 0x7fc0aab91300 0x7fbf7ac36ac0 524288 14030770 1795889424 12076324910681670 12076324910854752 12076324911109951 12076324911160049
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 210 921153 921158 4194304 256 0 0 24 24 149696 0x7fc0aab91a00 0x7fbf7ac36b00 524288 10435639 1335811920 12076324911186838 12076324911362910 12076324911502109 12076324911506032
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 212 921153 921158 4194304 256 0 0 24 24 152192 0x7fc0aab91900 0x7fbf7ac36b40 524288 3233595 413830248 12076324911554852 12076324911720828 12076324911982426 12076324912029735
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 214 921153 921158 4194304 256 0 0 24 24 154176 0x7fc0aab91800 0x7fbf7ac36b80 524288 10017803 1282209860 12076324912064670 12076324912235865 12076324912375864 12076324912379866
110 108 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 216 921153 921158 4194304 256 0 0 20 24 155648 0x7fc0aab91700 0x7fbf7ac36bc0 524288 2492896 319050360 12076324912427394 12076324912594263 12076324912925782 12076324912947611
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 218 921153 921158 4194304 256 0 0 28 24 157632 0x7fc0aab91600 0x7fbf7ac36c00 524288 12895056 1650572240 12076324912984680 12076324913146900 12076324913407379 12076324913456707
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 220 921153 921158 4194304 256 0 0 24 24 159616 0x7fc0aab91500 0x7fbf7ac36c40 524288 10583640 1354717808 12076324913478728 12076324913656658 12076324913796497 12076324913800476
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 222 921153 921158 4194304 256 0 0 24 24 162368 0x7fc0aab91400 0x7fbf7ac36c80 524288 3376223 432037936 12076324913848214 12076324914015216 12076324914261135 12076324914308670
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 224 921153 921158 4194304 256 0 0 24 24 164608 0x7fc0aab91300 0x7fbf7ac36cc0 524288 9625041 1232048032 12076324914345469 12076324914511300 12076324914651460 12076324914658581
115 113 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 226 921153 921158 4194304 256 0 0 20 24 166336 0x7fc0aab91a00 0x7fbf7ac36d00 524288 2385143 305245444 12076324914705838 12076324914865378 12076324915242656 12076324915293090
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 228 921153 921158 4194304 256 0 0 28 24 168576 0x7fc0aab91900 0x7fbf7ac36d40 524288 13874201 1775809428 12076324915318427 12076324915494335 12076324915749054 12076324915769124
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 230 921153 921158 4194304 256 0 0 24 24 170816 0x7fc0aab91800 0x7fbf7ac36d80 524288 9307681 1191433172 12076324915812435 12076324915970173 12076324916114332 12076324916118083
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 232 921153 921158 4194304 256 0 0 24 24 174080 0x7fc0aab91700 0x7fbf7ac36dc0 524288 3367622 430932036 12076324916167244 12076324916342651 12076324916653210 12076324916701397
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 234 921153 921158 4194304 256 0 0 24 24 176576 0x7fc0aab91600 0x7fbf7ac36e00 524288 8639586 1105829828 12076324916739287 12076324916897209 12076324917032249 12076324917035628
120 118 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 236 921153 921158 4194304 256 0 0 20 24 177792 0x7fc0aab91500 0x7fbf7ac36e40 524288 2339059 299339440 12076324917083978 12076324917253048 12076324917677686 12076324917724418
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 238 921153 921158 4194304 256 0 0 28 24 180288 0x7fc0aab91400 0x7fbf7ac36e80 524288 10103691 1293250032 12076324917750777 12076324917927285 12076324918192244 12076324918240618
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 240 921153 921158 4194304 256 0 0 24 24 182784 0x7fc0aab91300 0x7fbf7ac36ec0 524288 7301788 934484428 12076324918267037 12076324918444883 12076324918586162 12076324918589426
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 242 921153 921158 4194304 256 0 0 24 24 186304 0x7fc0aab91a00 0x7fbf7ac36f00 524288 3448522 441367708 12076324918637465 12076324918803921 12076324919119600 12076324919170886
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 244 921153 921158 4194304 256 0 0 24 24 189312 0x7fc0aab91900 0x7fbf7ac36f40 524288 3610119 462206688 12076324919207244 12076324919369519 12076324919523918 12076324919527128
125 123 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 246 921153 921158 4194304 256 0 0 20 24 190784 0x7fc0aab91800 0x7fbf7ac36f80 524288 2302329 294751312 12076324919574777 12076324919743917 12076324920260715 12076324920307849
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 248 921153 921158 4194304 256 0 0 28 24 193792 0x7fc0aab91700 0x7fbf7ac36fc0 524288 8378304 1072369756 12076324920330802 12076324920519754 12076324920817833 12076324920838546
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 250 921153 921158 4194304 256 0 0 24 24 196800 0x7fc0aab91600 0x7fbf7ac37000 524288 3326783 425884268 12076324920890202 12076324921054472 12076324921209031 12076324921212571
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 252 921153 921158 4194304 256 0 0 24 24 201088 0x7fc0aab91500 0x7fbf7ac37040 524288 3268023 418386768 12076324921259578 12076324921438470 12076324921824388 12076324921871065
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 254 921153 921158 4194304 256 0 0 24 24 204608 0x7fc0aab91400 0x7fbf7ac37080 524288 3406692 435950804 12076324921914355 12076324922081347 12076324922258467 12076324922261971
130 128 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 256 921153 921158 4194304 256 0 0 20 24 206080 0x7fc0aab91300 0x7fbf7ac370c0 524288 2321360 297201432 12076324922310371 12076324922480066 12076324923090623 12076324923138600
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 258 921153 921158 4194304 256 0 0 28 24 209600 0x7fc0aab91a00 0x7fbf7ac37100 524288 3726423 476982952 12076324923164739 12076324923348382 12076324923675741 12076324923721464
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 260 921153 921158 4194304 256 0 0 24 24 213120 0x7fc0aab91900 0x7fbf7ac37140 524288 3106039 397473404 12076324923748774 12076324923927260 12076324924105979 12076324924109525
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 262 921153 921158 4194304 256 0 0 24 24 218176 0x7fc0aab91800 0x7fbf7ac37180 524288 3312643 423978688 12076324924156622 12076324924328058 12076324924784376 12076324924832679
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 264 921153 921158 4194304 256 0 0 24 24 222208 0x7fc0aab91700 0x7fbf7ac371c0 524288 2983092 381885796 12076324924872042 12076324925039575 12076324925240214 12076324925289097
135 133 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 266 921153 921158 4194304 256 0 0 20 24 223936 0x7fc0aab91600 0x7fbf7ac37200 524288 2291301 293339744 12076324925311018 12076324925497013 12076324926207570 12076324926256495
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 268 921153 921158 4194304 256 0 0 28 24 227968 0x7fc0aab91500 0x7fbf7ac37240 524288 3602250 461175832 12076324926280810 12076324926461009 12076324926835087 12076324926881707
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 270 921153 921158 4194304 256 0 0 24 24 232000 0x7fc0aab91400 0x7fbf7ac37280 524288 3089036 395326984 12076324926908056 12076324927093806 12076324927297645 12076324927346741
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 272 921153 921158 4194304 256 0 0 24 24 237824 0x7fc0aab91300 0x7fbf7ac372c0 524288 4037597 516856392 12076324927371627 12076324927546764 12076324928073482 12076324928121651
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 274 921153 921158 4194304 256 0 0 24 24 242368 0x7fc0aab91a00 0x7fbf7ac37300 524288 3050385 390352172 12076324928160734 12076324928321641 12076324928545160 12076324928591574
140 138 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 276 921153 921158 4194304 256 0 0 20 24 243584 0x7fc0aab91900 0x7fbf7ac37340 524288 2324407 297411124 12076324928613475 12076324928796199 12076324929596196 12076324929646785
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 278 921153 921158 4194304 256 0 0 28 24 248128 0x7fc0aab91800 0x7fbf7ac37380 524288 3451819 441894164 12076324929672984 12076324929850595 12076324930272033 12076324930325016
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 280 921153 921158 4194304 256 0 0 24 24 252672 0x7fc0aab91700 0x7fbf7ac373c0 524288 3136706 401476888 12076324930351976 12076324930531072 12076324930757951 12076324930806060
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 282 921153 921158 4194304 256 0 0 24 24 259264 0x7fc0aab91600 0x7fbf7ac37400 524288 4642750 594336476 12076324930829994 12076324931004510 12076324931601467 12076324931650459
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 284 921153 921158 4194304 256 0 0 24 24 264832 0x7fc0aab91500 0x7fbf7ac37440 524288 3205878 410331404 12076324931687067 12076324931855866 12076324932126585 12076324932177739
145 143 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 286 921153 921158 4194304 256 0 0 20 24 266304 0x7fc0aab91400 0x7fbf7ac37480 524288 2309146 295428132 12076324932200201 12076324932379224 12076324933364020 12076324933431459
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 288 921153 921158 4194304 256 0 0 28 24 271872 0x7fc0aab91300 0x7fbf7ac374c0 524288 3535941 452505508 12076324933462126 12076324933637779 12076324934152977 12076324934219604
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 290 921153 921158 4194304 256 0 0 24 24 277440 0x7fc0aab91a00 0x7fbf7ac37500 524288 3205779 410295868 12076324934248407 12076324934424976 12076324934699054 12076324934765919
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 292 921153 921158 4194304 256 0 0 12 24 279936 0x7fc0aab91900 0x7fbf7ac37540 524288 2194670 280910352 12076324934793480 12076324934964493 12076324935704650 12076324935773872
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 294 921153 921158 4194304 256 0 0 24 24 286528 0x7fc0aab91800 0x7fbf7ac37580 524288 3287385 420792036 12076324935815820 12076324935979209 12076324936297128 12076324936364590
150 148 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 296 921153 921158 4194304 256 0 0 20 24 288000 0x7fc0aab91700 0x7fbf7ac375c0 524288 2280821 291909728 12076324936393123 12076324936571687 12076324937743362 12076324937809225
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 298 921153 921158 4194304 256 0 0 32 24 294592 0x7fc0aab91600 0x7fbf7ac37600 524288 3407856 436190608 12076324937839431 12076324938009281 12076324938618078 12076324938686485
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 300 921153 921158 4194304 256 0 0 24 24 301184 0x7fc0aab91500 0x7fbf7ac37640 524288 3310205 423678296 12076324938717172 12076324938892157 12076324939211196 12076324939280329
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 302 921153 921158 4194304 256 0 0 12 24 304960 0x7fc0aab91400 0x7fbf7ac37680 524288 2196223 280992068 12076324939309994 12076324939492634 12076324940371831 12076324940438000
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 304 921153 921158 4194304 256 0 0 24 24 313600 0x7fc0aab91300 0x7fbf7ac376c0 524288 3278376 419575164 12076324940480008 12076324940641750 12076324941053428 12076324941120028
155 153 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 306 921153 921158 4194304 256 0 0 20 24 314816 0x7fc0aab91a00 0x7fbf7ac37700 524288 2331810 298531300 12076324941151126 12076324941323667 12076324942873420 12076324942940451
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 308 921153 921158 4194304 256 0 0 20 24 317568 0x7fc0aab91900 0x7fbf7ac37740 524288 2263036 289789640 12076324942963183 12076324943154379 12076324943949736 12076324944019366
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 310 921153 921158 4194304 256 0 0 12 24 320320 0x7fc0aab91800 0x7fbf7ac37780 524288 2173619 278217040 12076324944048741 12076324944228614 12076324944643973 12076324944709699
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 312 921153 921158 4194304 256 0 0 12 24 324096 0x7fc0aab91700 0x7fbf7ac377c0 524288 2242042 286971484 12076324944733664 12076324944908772 12076324946068287 12076324946136180
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 314 921153 921158 4194304 256 0 0 12 24 328896 0x7fc0aab91600 0x7fbf7ac37800 524288 2242646 287191700 12076324946175754 12076324946337406 12076324947123642 12076324947191211
160 158 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 316 921153 921158 4194304 256 0 0 20 24 330112 0x7fc0aab91500 0x7fbf7ac37840 524288 2662363 340770928 12076324947220205 12076324947398521 12076324950447468 12076324950514557
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 318 921153 921158 4194304 256 0 0 20 24 332864 0x7fc0aab91400 0x7fbf7ac37880 524288 2298931 294319360 12076324950544573 12076324950722507 12076324952264421 12076324952331274
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 320 921153 921158 4194304 256 0 0 12 24 335616 0x7fc0aab91300 0x7fbf7ac378c0 524288 2197160 281088936 12076324952360167 12076324952544740 12076324953334016 12076324953402354
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 322 921153 921158 4194304 256 0 0 12 24 339392 0x7fc0aab91a00 0x7fbf7ac37900 524288 2535602 324582428 12076324953432911 12076324953610655 12076324955893526 12076324955961731
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 324 921153 921158 4194304 256 0 0 12 24 344192 0x7fc0aab91900 0x7fbf7ac37940 524288 2385934 305369720 12076324956007636 12076324956173524 12076324957708878 12076324957778467
165 163 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 326 921153 921158 4194304 256 0 0 20 24 345408 0x7fc0aab91800 0x7fbf7ac37980 524288 2884153 369236128 12076324957808362 12076324957987437 12076324964042291 12076324964112859
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 328 921153 921158 4194304 256 0 0 20 24 348160 0x7fc0aab91700 0x7fbf7ac379c0 524288 3377375 432171988 12076324964139058 12076324964317330 12076324967362437 12076324967593037
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 330 921153 921158 4194304 256 0 0 12 24 350912 0x7fc0aab91600 0x7fbf7ac37a00 524288 2262042 289551444 12076324967625167 12076324967808676 12076324969347709 12076324969417327
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 332 921153 921158 4194304 256 0 0 12 24 0 0x7fc0aab91500 0x7fbf7ac37a40 524288 2567679 328586028 12076324969444798 12076324969626428 12076324974153289 12076324974220834
@@ -0,0 +1,168 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,grd,Workgroup_Size,LDS_Per_Workgroup,scr,vgpr,SGPR,fbar,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"__amd_rocclr_fillBuffer.kd",0,0,0,921529,921534,33554432,256,0,0,8,32,6464,0x0,0x7f6f26204180,502695,502695,17046,4021568,524288,372600279,3816924,0,1505167052,12076327135265660,12076327381325743,12076327381649102,12076327381757735
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,921529,921534,32768,256,0,0,24,24,12480,0x0,0x7f6f26235100,27819,27819,20311,222560,512,1122712,74488,0,4504968,12076327396356075,12076327396679513,12076327396685593,12076327396695125
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,921529,921534,4194304,256,0,0,24,24,12928,0x7f7031f1d900,0x7f6f26235140,219204,219204,20615,1753640,65536,131444628,1582707,0,527592892,12076327396760457,12076327397000951,12076327397134071,12076327397138189
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,921529,921534,4194304,256,0,0,36,24,13632,0x7f7031f1d800,0x7f6f26235180,393764,393764,29108,3150120,65536,273156985,2982062,0,1094444912,12076327397217927,12076327397422229,12076327397672148,12076327397741230
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,921529,921534,4194304,256,0,0,28,24,14080,0x7f7031f1d700,0x7f6f262351c0,395572,395572,29591,3164584,65536,329910429,2975811,0,1321457988,12076327397777507,12076327397981747,12076327398231986,12076327398301691
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,921529,921534,4194304,256,0,0,24,24,14528,0x7f7031f1d600,0x7f6f26235200,218644,218644,19473,1749160,65536,142658733,1577012,0,572449732,12076327398326708,12076327398535344,12076327398668944,12076327398672611
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,921529,921534,4194304,256,0,0,24,24,14976,0x7f7031f1d500,0x7f6f26235240,223812,223812,21749,1790504,65536,129076135,1616347,0,518113844,12076327398733073,12076327398925743,12076327399061742,12076327399065290
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,921529,921534,4194304,256,0,0,24,24,15424,0x7f7031f1d400,0x7f6f26235280,214716,214716,21675,1717736,65536,156951182,1550654,0,629619912,12076327399159065,12076327399352781,12076327399483820,12076327399487345
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,921529,921534,4194304,256,0,0,28,24,16128,0x7f7031f1d300,0x7f6f262352c0,410276,410276,35397,3282216,65536,251123097,3107336,0,1006308440,12076327399545924,12076327399746699,12076327400007178,12076327400048898
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,921529,921534,4194304,256,0,0,28,24,16832,0x7f7031f1da00,0x7f6f26235300,402596,402596,32151,3220776,65536,344690180,3048123,0,1380576460,12076327400084054,12076327400278697,12076327400534855,12076327400600644
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,921529,921534,4194304,256,0,0,24,24,17536,0x7f7031f1d900,0x7f6f26235340,212812,212812,20992,1702504,65536,158222018,1522110,0,634707908,12076327400625730,12076327400831974,12076327400960773,12076327400964410
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,921529,921534,4194304,256,0,0,24,24,18240,0x7f7031f1d800,0x7f6f26235380,220165,220165,19547,1761328,65536,130366679,1592966,0,523283296,12076327401031384,12076327401226212,12076327401360932,12076327401364714
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,921529,921534,4194304,256,0,0,24,24,18944,0x7f7031f1d700,0x7f6f262353c0,211117,211117,23784,1688944,65536,161737692,1514441,0,648770336,12076327401438120,12076327401618050,12076327401745730,12076327401749449
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,921529,921534,4194304,256,0,0,28,24,19904,0x7f7031f1d600,0x7f6f26235400,390460,390460,32628,3123688,65536,354858086,2954174,0,1421250132,12076327401809110,12076327402004129,12076327402252448,12076327402320219
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,921529,921534,4194304,256,0,0,28,24,20608,0x7f7031f1d500,0x7f6f26235440,394516,394516,24590,3156136,65536,283285198,2973684,0,1134958092,12076327402348241,12076327402558526,12076327402808765,12076327402875511
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,921529,921534,4194304,256,0,0,24,24,21312,0x7f7031f1d400,0x7f6f26235480,217573,217573,21130,1740592,65536,153580056,1576273,0,616131828,12076327402899105,12076327403106044,12076327403239163,12076327403242664
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,921529,921534,4194304,256,0,0,24,24,22016,0x7f7031f1d300,0x7f6f262354c0,225605,225605,22467,1804848,65536,131000276,1631073,0,525813924,12076327403301754,12076327403496282,12076327403633881,12076327403637518
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,921529,921534,4194304,256,0,0,24,24,22720,0x7f7031f1da00,0x7f6f26235500,217076,217076,22910,1736616,65536,149158415,1571313,0,598450084,12076327403711806,12076327403894680,12076327404027480,12076327404031019
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,921529,921534,4194304,256,0,0,28,24,23680,0x7f7031f1d900,0x7f6f26235540,404245,404245,28723,3233968,65536,304219837,3050101,0,1218693512,12076327404091441,12076327404286678,12076327404543957,12076327404609955
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,921529,921534,4194304,256,0,0,28,24,24384,0x7f7031f1d800,0x7f6f26235580,403804,403804,32386,3230440,65536,310926216,3042740,0,1245520580,12076327404635522,12076327404835956,12076327405091795,12076327405160448
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,921529,921534,4194304,256,0,0,24,24,25088,0x7f7031f1d700,0x7f6f262355c0,216180,216180,22874,1729448,65536,158862653,1556802,0,637268020,12076327405185514,12076327405387953,12076327405519473,12076327405522942
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,921529,921534,4194304,256,0,0,24,24,25792,0x7f7031f1d600,0x7f6f26235600,217501,217501,21934,1740016,65536,147479529,1568848,0,591739008,12076327405580599,12076327405776112,12076327405909071,12076327405912806
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,921529,921534,4194304,256,0,0,24,24,26496,0x7f7031f1d500,0x7f6f26235640,210060,210060,23028,1680488,65536,164043640,1511714,0,657992736,12076327405985571,12076327406168270,12076327406295949,12076327406299665
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,921529,921534,4194304,256,0,0,28,24,27712,0x7f7031f1d400,0x7f6f26235680,393477,393477,32926,3147824,65536,357396499,2976003,0,1431403828,12076327406360127,12076327406545388,12076327406796107,12076327406862571
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,921529,921534,4194304,256,0,0,28,24,28416,0x7f7031f1d300,0x7f6f262356c0,398429,398429,33952,3187440,65536,332660786,3007281,0,1332456112,12076327406887347,12076327407098186,12076327407351304,12076327407418034
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,921529,921534,4194304,256,0,0,24,24,29120,0x7f7031f1da00,0x7f6f26235700,216244,216244,22358,1729960,65536,157383696,1557729,0,631354700,12076327407442800,12076327407643783,12076327407776103,12076327407779575
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,921529,921534,4194304,256,0,0,24,24,30080,0x7f7031f1d900,0x7f6f26235740,217580,217580,24233,1740648,65536,150988090,1559666,0,605769248,12076327407840849,12076327408034501,12076327408167141,12076327408170622
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,921529,921534,4194304,256,0,0,24,24,30784,0x7f7031f1d800,0x7f6f26235780,210893,210893,22265,1687152,65536,149125876,1519036,0,598327684,12076327408242526,12076327408421700,12076327408550659,12076327408554225
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,921529,921534,4194304,256,0,0,28,24,32000,0x7f7031f1d700,0x7f6f262357c0,409284,409284,25773,3274280,65536,292572722,3093447,0,1172118292,12076327408611902,12076327408807618,12076327409069217,12076327409137980
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,921529,921534,4194304,256,0,0,28,24,32960,0x7f7031f1d600,0x7f6f26235800,408380,408380,28494,3267048,65536,299768216,3087224,0,1200888340,12076327409163868,12076327409364255,12076327409624734,12076327409691719
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,921529,921534,4194304,256,0,0,24,24,33920,0x7f7031f1d500,0x7f6f26235840,213756,213756,20522,1710056,65536,152821004,1532412,0,613119968,12076327409714421,12076327409916093,12076327410046012,12076327410049744
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,921529,921534,4194304,256,0,0,24,24,34880,0x7f7031f1d400,0x7f6f26235880,218309,218309,24528,1746480,65536,149435080,1579429,0,599589488,12076327410109516,12076327410298011,12076327410432091,12076327410435742
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,921529,921534,4194304,256,0,0,24,24,35840,0x7f7031f1d300,0x7f6f262358c0,215316,215316,23307,1722536,65536,163066672,1547928,0,654085080,12076327410507655,12076327410681529,12076327410812729,12076327410816469
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,921529,921534,4194304,256,0,0,28,24,37312,0x7f7031f1da00,0x7f6f26235900,397596,397596,34004,3180776,65536,339692340,3011197,0,1360585612,12076327410876621,12076327411063448,12076327411318167,12076327411367904
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,921529,921534,4194304,256,0,0,28,24,38272,0x7f7031f1d900,0x7f6f26235940,405661,405661,25737,3245296,65536,299813626,3067280,0,1201063276,12076327411394413,12076327411595605,12076327411854164,12076327411874325
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,921529,921534,4194304,256,0,0,24,24,39232,0x7f7031f1d800,0x7f6f26235980,226668,226668,23868,1813352,65536,132811821,1636779,0,533068744,12076327411933886,12076327412106323,12076327412245522,12076327412249032
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,921529,921534,4194304,256,0,0,24,24,40192,0x7f7031f1d700,0x7f6f262359c0,230268,230268,25125,1842152,65536,143495999,1669554,0,575821568,12076327412308292,12076327412496241,12076327412637841,12076327412641491
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,921529,921534,4194304,256,0,0,24,24,41152,0x7f7031f1d600,0x7f6f26235a00,218252,218252,22378,1746024,65536,155191739,1582506,0,622584292,12076327412713294,12076327412889039,12076327413022959,12076327413026697
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,921529,921534,4194304,256,0,0,28,24,42624,0x7f7031f1d500,0x7f6f26235a40,413413,413413,32653,3307312,65536,316670030,3129785,0,1268499144,12076327413087500,12076327413278478,12076327413543276,12076327413610221
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,921529,921534,4194304,256,0,0,28,24,43584,0x7f7031f1d400,0x7f6f26235a80,399837,399837,32660,3198704,65536,338705455,3027094,0,1356637164,12076327413634026,12076327413830955,12076327414086474,12076327414155715
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,921529,921534,4194304,256,0,0,24,24,44544,0x7f7031f1d300,0x7f6f26235ac0,218965,218965,22655,1751728,65536,153280811,1578906,0,614938856,12076327414180111,12076327414379593,12076327414513032,12076327414516636
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,921529,921534,4194304,256,0,0,24,24,45760,0x7f7031f1da00,0x7f6f26235b00,223740,223740,25739,1789928,65536,154857430,1610991,0,621254560,12076327414576868,12076327414766151,12076327414904070,12076327414907853
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,921529,921534,4194304,256,0,0,24,24,46720,0x7f7031f1d900,0x7f6f26235b40,213637,213637,23276,1709104,65536,154593955,1534868,0,620206840,12076327414979075,12076327415161349,12076327415291589,12076327415295213
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,921529,921534,4194304,256,0,0,28,24,48448,0x7f7031f1d800,0x7f6f26235b80,422453,422453,31736,3379632,65536,347170319,3198706,0,1390498552,12076327415352569,12076327415540387,12076327415811106,12076327415877134
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,921529,921534,4194304,256,0,0,28,24,49408,0x7f7031f1d700,0x7f6f26235bc0,402364,402364,27621,3218920,65536,295437547,3043653,0,1183568840,12076327415901850,12076327416100545,12076327416357664,12076327416424562
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,921529,921534,4194304,256,0,0,24,24,50368,0x7f7031f1d600,0x7f6f26235c00,212053,212053,21868,1696432,65536,167095985,1525051,0,670203184,12076327416448827,12076327416651742,12076327416781662,12076327416785302
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,921529,921534,4194304,256,0,0,24,24,51584,0x7f7031f1d500,0x7f6f26235c40,222060,222060,27474,1776488,65536,153260821,1586295,0,614878272,12076327416843450,12076327417037821,12076327417173980,12076327417177762
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,921529,921534,4194304,256,0,0,24,24,52544,0x7f7031f1d400,0x7f6f26235c80,220788,220788,25033,1766312,65536,154861311,1578134,0,621263124,12076327417249405,12076327417427739,12076327417561658,12076327417565572
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,921529,921534,4194304,256,0,0,28,24,54272,0x7f7031f1d300,0x7f6f26235cc0,424573,424573,33241,3396592,65536,315580726,3210664,0,1264140496,12076327417628589,12076327417817497,12076327418089176,12076327418157532
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,921529,921534,4194304,256,0,0,28,24,55488,0x7f7031f1da00,0x7f6f26235d00,407037,407037,25976,3256304,65536,270289769,3083323,0,1082974556,12076327418183921,12076327418383894,12076327418644373,12076327418685403
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,921529,921534,4194304,256,0,0,24,24,56704,0x7f7031f1d900,0x7f6f26235d40,217708,217708,23341,1741672,65536,156839408,1568149,0,629187568,12076327418717453,12076327418904532,12076327419037492,12076327419041255
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,921529,921534,4194304,256,0,0,24,24,58176,0x7f7031f1d800,0x7f6f26235d80,228813,228813,28100,1830512,65536,154939878,1639042,0,621630896,12076327419100204,12076327419287090,12076327419428530,12076327419432662
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,921529,921534,4194304,256,0,0,24,24,59392,0x7f7031f1d700,0x7f6f26235dc0,215820,215820,23377,1726568,65536,153362587,1548163,0,615282076,12076327419503885,12076327419677009,12076327419809008,12076327419812538
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,921529,921534,4194304,256,0,0,28,24,61376,0x7f7031f1d600,0x7f6f26235e00,409525,409525,32150,3276208,65536,301364347,3089841,0,1207276568,12076327419871979,12076327420063407,12076327420326606,12076327420392746
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,921529,921534,4194304,256,0,0,28,24,62592,0x7f7031f1d500,0x7f6f26235e40,406124,406124,31722,3249000,65536,310573904,3068570,0,1244112300,12076327420417472,12076327420615884,12076327420875243,12076327420941486
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,921529,921534,4194304,256,0,0,24,24,63808,0x7f7031f1d400,0x7f6f26235e80,217965,217965,22411,1743728,65536,150401905,1576953,0,603452992,12076327420965751,12076327421174122,12076327421308201,12076327421312155
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,921529,921534,4194304,256,0,0,24,24,65280,0x7f7031f1d300,0x7f6f26235ec0,223125,223125,29767,1785008,65536,165065178,1589301,0,662106268,12076327421372577,12076327421560520,12076327421697959,12076327421701499
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,921529,921534,4194304,256,0,0,24,24,66496,0x7f7031f1da00,0x7f6f26235f00,218885,218885,22790,1751088,65536,148990112,1583444,0,597783068,12076327421773042,12076327421946598,12076327422081158,12076327422085011
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,921529,921534,4194304,256,0,0,28,24,68480,0x7f7031f1d900,0x7f6f26235f40,411148,411148,33901,3289192,65536,338400769,3104057,0,1355437308,12076327422144492,12076327422334757,12076327422598115,12076327422665029
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,921529,921534,4194304,256,0,0,28,24,69696,0x7f7031f1d800,0x7f6f26235f80,408093,408093,27376,3264752,65536,283857796,3074190,0,1137242732,12076327422690376,12076327422885634,12076327423146753,12076327423213539
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,921529,921534,4194304,256,0,0,24,24,70912,0x7f7031f1d700,0x7f6f26235fc0,212516,212516,25414,1700136,65536,163318892,1522937,0,655110428,12076327423239517,12076327423436832,12076327423566431,12076327423570091
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,921529,921534,4194304,256,0,0,24,24,72384,0x7f7031f1d600,0x7f6f26236000,222780,222780,27440,1782248,65536,184868604,1601401,0,741343652,12076327423627638,12076327423818110,12076327423956189,12076327423959836
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,921529,921534,4194304,256,0,0,24,24,73600,0x7f7031f1d500,0x7f6f26236040,220364,220364,24433,1762920,65536,149119121,1581565,0,598323544,12076327424037430,12076327424214268,12076327424348667,12076327424352355
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,921529,921534,4194304,256,0,0,28,24,75840,0x7f7031f1d400,0x7f6f26236080,408988,408988,32263,3271912,65536,320979092,3083789,0,1285733124,12076327424410684,12076327424598266,12076327424861305,12076327424901776
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,921529,921534,4194304,256,0,0,28,24,77056,0x7f7031f1d300,0x7f6f262360c0,391132,391132,32409,3129064,65536,353412992,2963613,0,1415469032,12076327424942843,12076327425126584,12076327425377463,12076327425418577
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,921529,921534,4194304,256,0,0,24,24,78272,0x7f7031f1da00,0x7f6f26236100,217293,217293,22948,1738352,65536,155239009,1565948,0,622791596,12076327425451177,12076327425639862,12076327425773461,12076327425777273
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,921529,921534,4194304,256,0,0,24,24,80000,0x7f7031f1d900,0x7f6f26236140,232428,232428,27876,1859432,65536,195594787,1679946,0,784230672,12076327425836784,12076327426028660,12076327426171859,12076327426175674
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,921529,921534,4194304,256,0,0,24,24,81216,0x7f7031f1d800,0x7f6f26236180,223645,223645,23883,1789168,65536,145183396,1617226,0,582602460,12076327426247878,12076327426426418,12076327426564337,12076327426568073
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,921529,921534,4194304,256,0,0,28,24,83456,0x7f7031f1d700,0x7f6f262361c0,414460,414460,32555,3315688,65536,305746233,3117629,0,1224808600,12076327426624498,12076327426818096,12076327427085135,12076327427152028
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,921529,921534,4194304,256,0,0,28,24,84928,0x7f7031f1d600,0x7f6f26236200,401477,401477,34196,3211824,65536,335221921,3041646,0,1342703124,12076327427176985,12076327427376494,12076327427634413,12076327427700878
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,921529,921534,4194304,256,0,0,24,24,86400,0x7f7031f1d500,0x7f6f26236240,227021,227021,26580,1816176,65536,138787551,1632726,0,556996696,12076327427725213,12076327427923371,12076327428062571,12076327428066197
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,921529,921534,4194304,256,0,0,24,24,88128,0x7f7031f1d400,0x7f6f26236280,242348,242348,27594,1938792,65536,209708783,1767698,0,840693360,12076327428126770,12076327428313129,12076327428463689,12076327428467433
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,921529,921534,4194304,256,0,0,24,24,89600,0x7f7031f1d300,0x7f6f262362c0,225845,225845,25029,1806768,65536,137865768,1635760,0,553284708,12076327428561548,12076327428734728,12076327428873287,12076327428876904
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,921529,921534,4194304,256,0,0,28,24,92096,0x7f7031f1da00,0x7f6f26236300,419101,419101,32113,3352816,65536,296978305,3151701,0,1189729116,12076327428934922,12076327429126886,12076327429397605,12076327429455048
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,921529,921534,4194304,256,0,0,28,24,93568,0x7f7031f1d900,0x7f6f26236340,402333,402333,31713,3218672,65536,334236171,3045584,0,1338758204,12076327429479895,12076327429675363,12076327429933922,12076327429979904
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,921529,921534,4194304,256,0,0,24,24,95040,0x7f7031f1d800,0x7f6f26236380,227940,227940,25948,1823528,65536,141446042,1624412,0,567649260,12076327430012294,12076327430211521,12076327430350560,12076327430354440
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,921529,921534,4194304,256,0,0,24,24,96768,0x7f7031f1d700,0x7f6f262363c0,252172,252172,28691,2017384,65536,219587427,1851182,0,880202016,12076327430415323,12076327430600959,12076327430758078,12076327430761807
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,921529,921534,4194304,256,0,0,24,24,98240,0x7f7031f1d600,0x7f6f26236400,225357,225357,24327,1802864,65536,149769581,1633947,0,600952260,12076327430832588,12076327431005117,12076327431144157,12076327431148135
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,921529,921534,4194304,256,0,0,28,24,100736,0x7f7031f1d500,0x7f6f26236440,409412,409412,33883,3275304,65536,315787504,3088788,0,1264966996,12076327431206664,12076327431396156,12076327431660634,12076327431708196
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,921529,921534,4194304,256,0,0,28,24,102208,0x7f7031f1d400,0x7f6f26236480,400348,400348,29983,3202792,65536,324847309,3032320,0,1301216560,12076327431734034,12076327431926393,12076327432184632,12076327432233041
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,921529,921534,4194304,256,0,0,24,24,103680,0x7f7031f1d300,0x7f6f262364c0,221956,221956,25582,1775656,65536,147481606,1594631,0,591802116,12076327432257046,12076327432457751,12076327432593910,12076327432597729
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,921529,921534,4194304,256,0,0,24,24,105664,0x7f7031f1da00,0x7f6f26236500,263724,263724,28572,2109800,65536,235041528,1943765,0,942025504,12076327432654835,12076327432848469,12076327433014068,12076327433017749
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,921529,921534,4194304,256,0,0,24,24,107136,0x7f7031f1d900,0x7f6f26236540,219060,219060,23687,1752488,65536,152404572,1576119,0,611446008,12076327433090545,12076327433271027,12076327433405266,12076327433408886
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,921529,921534,4194304,256,0,0,28,24,109888,0x7f7031f1d800,0x7f6f26236580,419340,419340,36699,3354728,65536,324040229,3156233,0,1297980316,12076327433465331,12076327433656145,12076327433927184,12076327433949251
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,921529,921534,4194304,256,0,0,28,24,111360,0x7f7031f1d700,0x7f6f262365c0,409181,409181,31598,3273456,65536,292613348,3085096,0,1172280348,12076327434009422,12076327434189103,12076327434451662,12076327434503731
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,921529,921534,4194304,256,0,0,24,24,112832,0x7f7031f1d600,0x7f6f26236600,222981,222981,24024,1783856,65536,149896144,1612689,0,601442240,12076327434528377,12076327434728940,12076327434866060,12076327434869801
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,921529,921534,4194304,256,0,0,24,24,114816,0x7f7031f1d500,0x7f6f26236640,277020,277020,31065,2216168,65536,248052652,2044666,0,994052548,12076327434931306,12076327435124939,12076327435298058,12076327435301924
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,921529,921534,4194304,256,0,0,24,24,116288,0x7f7031f1d400,0x7f6f26236680,220573,220573,22459,1764592,65536,165346140,1588658,0,663226476,12076327435374459,12076327435549737,12076327435685416,12076327435689505
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,921529,921534,4194304,256,0,0,28,24,119040,0x7f7031f1d300,0x7f6f262366c0,404628,404628,37892,3237032,65536,315795617,3035555,0,1265015904,12076327435745910,12076327435939015,12076327436199654,12076327436249676
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,921529,921534,4194304,256,0,0,28,24,120768,0x7f7031f1da00,0x7f6f26236700,457901,457901,15291,3663216,65536,296982808,3065379,0,1189746456,12076327436273169,12076327436474212,12076327436770371,12076327436818583
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,921529,921534,4194304,256,0,0,24,24,122496,0x7f7031f1d900,0x7f6f26236740,223005,223005,25216,1784048,65536,150815369,1604902,0,605136716,12076327436842538,12076327437043330,12076327437179809,12076327437183842
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,921529,921534,4194304,256,0,0,24,24,124736,0x7f7031f1d800,0x7f6f26236780,290572,290572,30899,2324584,65536,260280880,2154890,0,1042972684,12076327437242010,12076327437432928,12076327437616287,12076327437622207
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,921529,921534,4194304,256,0,0,24,24,126464,0x7f7031f1d700,0x7f6f262367c0,223317,223317,25702,1786544,65536,143093189,1615056,0,574262752,12076327437704730,12076327437881726,12076327438019805,12076327438023893
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,921529,921534,4194304,256,0,0,20,24,127936,0x7f7031f1d600,0x7f6f26236800,413908,413908,36504,3311272,65536,380760177,3142546,0,1524861416,12076327438080578,12076327438271484,12076327438539643,12076327438589374
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,921529,921534,4194304,256,0,0,28,24,129664,0x7f7031f1d500,0x7f6f26236840,395004,395004,34433,3160040,65536,334017531,2985646,0,1337889236,12076327438615022,12076327438814362,12076327439068281,12076327439117596
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,921529,921534,4194304,256,0,0,24,24,131392,0x7f7031f1d400,0x7f6f26236880,220508,220508,25162,1764072,65536,160293233,1584140,0,643006552,12076327439141300,12076327439340600,12076327439476599,12076327439480370
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,921529,921534,4194304,256,0,0,24,24,133632,0x7f7031f1d300,0x7f6f262368c0,303348,303348,32459,2426792,65536,272397563,2253283,0,1091431836,12076327439539269,12076327439725078,12076327439916757,12076327439968387
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,921529,921534,4194304,256,0,0,24,24,135360,0x7f7031f1da00,0x7f6f26236900,218932,218932,26009,1751464,65536,154615993,1567950,0,620325540,12076327440012309,12076327440194516,12076327440329715,12076327440333576
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,921529,921534,4194304,256,0,0,20,24,136832,0x7f7031f1d900,0x7f6f26236940,438060,438060,40923,3504488,65536,406700091,3333517,0,1628620276,12076327440391784,12076327440580914,12076327440865233,12076327440914295
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,921529,921534,4194304,256,0,0,28,24,138560,0x7f7031f1d800,0x7f6f26236980,404189,404189,32075,3233520,65536,320696391,3056109,0,1284604624,12076327440937508,12076327441141391,12076327441402190,12076327441452836
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,921529,921534,4194304,256,0,0,24,24,140288,0x7f7031f1d700,0x7f6f262369c0,222933,222933,26446,1783472,65536,151298942,1601376,0,607076608,12076327441476319,12076327441672109,12076327441809068,12076327441812935
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,921529,921534,4194304,256,0,0,24,24,142784,0x7f7031f1d600,0x7f6f26236a00,331445,331445,33780,2651568,65536,299751261,2483426,0,1200858452,12076327441874970,12076327442068587,12076327442279146,12076327442330086
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,921529,921534,4194304,256,0,0,24,24,144768,0x7f7031f1d500,0x7f6f26236a40,223189,223189,26144,1785520,65536,146378075,1608324,0,587388236,12076327442365472,12076327442551945,12076327442689544,12076327442693351
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,921529,921534,4194304,256,0,0,20,24,145728,0x7f7031f1d400,0x7f6f26236a80,472444,472444,43233,3779560,65536,439173511,3590778,0,1758514404,12076327442750828,12076327442936263,12076327443242982,12076327443290020
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,921529,921534,4194304,256,0,0,28,24,147712,0x7f7031f1d300,0x7f6f26236ac0,407284,407284,31468,3258280,65536,261914357,3056209,0,1049494120,12076327443327690,12076327443513701,12076327443775779,12076327443821929
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,921529,921534,4194304,256,0,0,24,24,149696,0x7f7031f1da00,0x7f6f26236b00,222084,222084,24880,1776680,65536,153353024,1592647,0,615268220,12076327443854429,12076327444048418,12076327444185858,12076327444189762
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,921529,921534,4194304,256,0,0,24,24,152192,0x7f7031f1d900,0x7f6f26236b40,358669,358669,36823,2869360,65536,327245960,2696314,0,1310831392,12076327444249323,12076327444436377,12076327444664696,12076327444714257
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,921529,921534,4194304,256,0,0,24,24,154176,0x7f7031f1d800,0x7f6f26236b80,222588,222588,27050,1780712,65536,161613304,1600887,0,648323568,12076327444756666,12076327444933974,12076327445071733,12076327445075488
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,921529,921534,4194304,256,0,0,20,24,155648,0x7f7031f1d700,0x7f6f26236bc0,504180,504180,44136,4033448,65536,471469664,3865220,0,1887698484,12076327445132975,12076327445328852,12076327445657650,12076327445705068
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,921529,921534,4194304,256,0,0,28,24,157632,0x7f7031f1d600,0x7f6f26236c00,401748,401748,30490,3213992,65536,300767866,2999630,0,1204893592,12076327445734894,12076327445926449,12076327446186288,12076327446237468
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,921529,921534,4194304,256,0,0,24,24,159616,0x7f7031f1d500,0x7f6f26236c40,225429,225429,27825,1803440,65536,157817115,1620370,0,633136516,12076327446262274,12076327446461167,12076327446600046,12076327446603889
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,921529,921534,4194304,256,0,0,24,24,162368,0x7f7031f1d400,0x7f6f26236c80,383100,383100,36758,3064808,65536,352102369,2898986,0,1410263924,12076327446662367,12076327446846125,12076327447091244,12076327447140817
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,921529,921534,4194304,256,0,0,24,24,164608,0x7f7031f1d300,0x7f6f26236cc0,219500,219500,27388,1756008,65536,162354413,1569011,0,651287132,12076327447177034,12076327447364523,12076327447499882,12076327447503651
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,921529,921534,4194304,256,0,0,20,24,166336,0x7f7031f1da00,0x7f6f26236d00,575309,575309,48139,4602480,65536,541767186,4429341,0,2168889116,12076327447560727,12076327447745641,12076327448122280,12076327448173185
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,921529,921534,4194304,256,0,0,28,24,168576,0x7f7031f1d900,0x7f6f26236d40,409644,409644,33505,3277160,65536,300693997,3067599,0,1204605360,12076327448197100,12076327448412038,12076327448676677,12076327448695205
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,921529,921534,4194304,256,0,0,24,24,170816,0x7f7031f1d800,0x7f6f26236d80,225909,225909,27312,1807280,65536,166754503,1630258,0,668896656,12076327448754706,12076327448931876,12076327449072515,12076327449076334
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,921529,921534,4194304,256,0,0,24,24,174080,0x7f7031f1d700,0x7f6f26236dc0,434821,434821,40942,3478576,65536,400645665,3305378,0,1604433640,12076327449136656,12076327449334914,12076327449613953,12076327449663064
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,921529,921534,4194304,256,0,0,24,24,176576,0x7f7031f1d600,0x7f6f26236e00,227580,227580,26972,1820648,65536,182547740,1649162,0,732089040,12076327449698790,12076327449881472,12076327450023071,12076327450027361
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,921529,921534,4194304,256,0,0,20,24,177792,0x7f7031f1d500,0x7f6f26236e40,644196,644196,51967,5153576,65536,611537704,4986023,0,2447971452,12076327450085429,12076327450275550,12076327450698588,12076327450744474
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,921529,921534,4194304,256,0,0,28,24,180288,0x7f7031f1d400,0x7f6f26236e80,414684,414684,33984,3317480,65536,325679697,3126541,0,1304555352,12076327450772917,12076327450963227,12076327451232346,12076327451280169
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,921529,921534,4194304,256,0,0,24,24,182784,0x7f7031f1d300,0x7f6f26236ec0,225124,225124,27994,1801000,65536,183537361,1620656,0,736035852,12076327451305567,12076327451502745,12076327451642584,12076327451646250
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,921529,921534,4194304,256,0,0,24,24,186304,0x7f7031f1da00,0x7f6f26236f00,489029,489029,42650,3912240,65536,456665273,3746571,0,1828511312,12076327451704007,12076327451896983,12076327452212982,12076327452257826
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,921529,921534,4194304,256,0,0,24,24,189312,0x7f7031f1d900,0x7f6f26236f40,242156,242156,28169,1937256,65536,214219388,1772586,0,858759044,12076327452307599,12076327452487220,12076327452638900,12076327452642591
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,921529,921534,4194304,256,0,0,20,24,190784,0x7f7031f1d800,0x7f6f26236f80,784476,784476,59291,6275816,65536,751137040,6109488,0,3006369528,12076327452700128,12076327452887699,12076327453404016,12076327453428251
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,921529,921534,4194304,256,0,0,28,24,193792,0x7f7031f1d700,0x7f6f26236fc0,457189,457189,40278,3657520,65536,377118755,3475801,0,1510304444,12076327453482212,12076327453663215,12076327453960654,12076327453980718
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,921529,921534,4194304,256,0,0,24,24,196800,0x7f7031f1d600,0x7f6f26237000,245468,245468,27285,1963752,65536,217867234,1800044,0,873357636,12076327454042623,12076327454221453,12076327454375372,12076327454379098
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,921529,921534,4194304,256,0,0,24,24,201088,0x7f7031f1d500,0x7f6f26237040,632789,632789,16512,5062320,65536,561747940,4589196,0,2248845944,12076327454439972,12076327454626411,12076327455036969,12076327455080602
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,921529,921534,4194304,256,0,0,24,24,204608,0x7f7031f1d400,0x7f6f26237080,279837,279837,30251,2238704,65536,249828270,2068744,0,1001199200,12076327455130315,12076327455310728,12076327455487207,12076327455490915
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,921529,921534,4194304,256,0,0,20,24,206080,0x7f7031f1d300,0x7f6f262370c0,924461,924461,67066,7395696,65536,889569140,7231932,0,3560097332,12076327455548562,12076327455743206,12076327456352163,12076327456399433
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,921529,921534,4194304,256,0,0,28,24,209600,0x7f7031f1da00,0x7f6f26237100,500637,500637,44537,4005104,65536,464298889,3830255,0,1859052364,12076327456432445,12076327456631202,12076327456958561,12076327457010679
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,921529,921534,4194304,256,0,0,24,24,213120,0x7f7031f1d900,0x7f6f26237140,282037,282037,29556,2256304,65536,254101760,2092270,0,1018291448,12076327457043851,12076327457242400,12076327457421599,12076327457425330
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,921529,921534,4194304,256,0,0,24,24,218176,0x7f7031f1d800,0x7f6f26237180,700772,700772,57754,5606184,65536,664650009,5415350,0,2660446968,12076327457486584,12076327457672958,12076327458127996,12076327458177217
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,921529,921534,4194304,256,0,0,24,24,222208,0x7f7031f1d700,0x7f6f262371c0,313669,313669,31681,2509360,65536,285350498,2346446,0,1143297024,12076327458223734,12076327458403675,12076327458603994,12076327458649986
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,921529,921534,4194304,256,0,0,20,24,223936,0x7f7031f1d600,0x7f6f26237200,1066581,1066581,77332,8532656,65536,1028208571,8356608,0,4114654956,12076327458681735,12076327458873752,12076327459576149,12076327459627533
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,921529,921534,4194304,256,0,0,28,24,227968,0x7f7031f1d500,0x7f6f26237240,566956,566956,47385,4535656,65536,532587577,4365736,0,2132192884,12076327459652649,12076327459855508,12076327460227667,12076327460277090
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,921529,921534,4194304,256,0,0,24,24,232000,0x7f7031f1d400,0x7f6f26237280,319468,319468,32704,2555752,65536,289506099,2387498,0,1159913240,12076327460300694,12076327460500785,12076327460704304,12076327460752473
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,921529,921534,4194304,256,0,0,24,24,237824,0x7f7031f1d300,0x7f6f262372c0,803221,803221,60806,6425776,65536,767733220,6255591,0,3072775544,12076327460775676,12076327460970223,12076327461496141,12076327461546389
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,921529,921534,4194304,256,0,0,24,24,242368,0x7f7031f1da00,0x7f6f26237300,351500,351500,36540,2812008,65536,320014175,2630801,0,1281961004,12076327461582325,12076327461768140,12076327461992299,12076327462044635
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,921529,921534,4194304,256,0,0,20,24,243584,0x7f7031f1d900,0x7f6f26237340,1207757,1207757,85294,9662064,65536,1169193706,9490895,0,4678594368,12076327462068589,12076327462268778,12076327463067974,12076327463135792
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,921529,921534,4194304,256,0,0,28,24,248128,0x7f7031f1d800,0x7f6f26237380,673884,673884,16747,5391080,65536,602526433,4945484,0,2411943540,12076327463162242,12076327463366213,12076327463810051,12076327463877281
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,921529,921534,4194304,256,0,0,24,24,252672,0x7f7031f1d700,0x7f6f262373c0,355796,355796,35489,2846376,65536,325671565,2669737,0,1304577388,12076327463900183,12076327464119489,12076327464346688,12076327464415721
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,921529,921534,4194304,256,0,0,24,24,259264,0x7f7031f1d600,0x7f6f26237400,911021,911021,67086,7288176,65536,875199644,7120624,0,3502644540,12076327464440567,12076327464642047,12076327465239805,12076327465308110
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,921529,921534,4194304,256,0,0,24,24,264832,0x7f7031f1d500,0x7f6f26237440,419516,419516,40855,3356136,65536,386941796,3175295,0,1549661548,12076327465343636,12076327465540123,12076327465809082,12076327465875684
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,921529,921534,4194304,256,0,0,20,24,266304,0x7f7031f1d400,0x7f6f26237480,1487725,1487725,100754,11901808,65536,1447187792,11735182,0,5790571912,12076327465900080,12076327466105401,12076327467090836,12076327467160192
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,921529,921534,4194304,256,0,0,28,24,271872,0x7f7031f1d300,0x7f6f262374c0,804020,804020,16254,6432168,65536,737761527,6055813,0,2952886016,12076327467185128,12076327467397075,12076327467928273,12076327467996005
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,921529,921534,4194304,256,0,0,24,24,277440,0x7f7031f1da00,0x7f6f26237500,422949,422949,40497,3383600,65536,390751573,3206117,0,1564894460,12076327468027784,12076327468232751,12076327468504750,12076327468574039
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,921529,921534,4194304,256,0,0,12,24,279936,0x7f7031f1d900,0x7f6f26237540,1126132,1126132,79445,9009064,65536,1089845165,8842241,0,4361203736,12076327468600158,12076327468792269,12076327469530026,12076327469598864
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,921529,921534,4194304,256,0,0,24,24,286528,0x7f7031f1d800,0x7f6f26237580,493468,493468,45315,3947752,65536,459603534,3772007,0,1840310892,12076327469635692,12076327469821864,12076327470140103,12076327470208767
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,921529,921534,4194304,256,0,0,20,24,288000,0x7f7031f1d700,0x7f6f262375c0,1768844,1768844,118324,14150760,65536,1723639655,13982118,0,6896378308,12076327470234154,12076327470433222,12076327471602497,12076327471670614
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,921529,921534,4194304,256,0,0,32,24,294592,0x7f7031f1d600,0x7f6f26237600,922484,922484,66355,7379880,65536,808434371,7201184,0,3235580684,12076327471698857,12076327471899615,12076327472510493,12076327472581256
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,921529,921534,4194304,256,0,0,24,24,301184,0x7f7031f1d500,0x7f6f26237640,491701,491701,43190,3933616,65536,459379596,3766902,0,1839417628,12076327472604209,12076327472814171,12076327473133050,12076327473199926
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,921529,921534,4194304,256,0,0,12,24,304960,0x7f7031f1d400,0x7f6f26237680,1338989,1338989,94366,10711920,65536,1297305485,10531704,0,5191044600,12076327473226145,12076327473430009,12076327474308405,12076327474377084
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,921529,921534,4194304,256,0,0,24,24,313600,0x7f7031f1d300,0x7f6f262376c0,631181,631181,53286,5049456,65536,596092182,4874212,0,2386266096,12076327474422088,12076327474602804,12076327475013522,12076327475081834
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,921529,921534,4194304,256,0,0,20,24,314816,0x7f7031f1da00,0x7f6f26237700,2333732,2333732,151312,18669864,65536,2284938455,18503363,0,9141574476,12076327475110126,12076327475310960,12076327476858474,12076327476931651
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,921529,921534,4194304,256,0,0,20,24,317568,0x7f7031f1d900,0x7f6f26237740,1202364,1202364,15250,9618920,65536,1162048908,9433323,0,4650017668,12076327476964272,12076327477174632,12076327477969029,12076327478288343
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,921529,921534,4194304,256,0,0,12,24,320320,0x7f7031f1d800,0x7f6f26237780,644389,644389,54450,5155120,65536,608696803,4969808,0,2436613984,12076327478312357,12076327478521906,12076327478937105,12076327479012028
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,921529,921534,4194304,256,0,0,12,24,324096,0x7f7031f1d700,0x7f6f262377c0,1757796,1757796,46114,14062376,65536,1715011761,13896501,0,6861870600,12076327479042625,12076327479239503,12076327480398058,12076327480466140
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,921529,921534,4194304,256,0,0,12,24,328896,0x7f7031f1d600,0x7f6f26237800,1200124,1200124,85398,9601000,65536,1160737821,9420660,0,4644781084,12076327480509340,12076327480689737,12076327481475013,12076327481543342
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,921529,921534,4194304,256,0,0,20,24,330112,0x7f7031f1d500,0x7f6f26237840,4586309,4586309,282847,36690480,65536,4514982965,36501638,0,18061753356,12076327481570933,12076327481773892,12076327484823959,12076327484892897
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,921529,921534,4194304,256,0,0,20,24,332864,0x7f7031f1d400,0x7f6f26237880,2325189,2325189,150804,18601520,65536,2276865554,18430717,0,9109285784,12076327484921430,12076327485134197,12076327486677231,12076327486746191
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,921529,921534,4194304,256,0,0,12,24,335616,0x7f7031f1d300,0x7f6f262378c0,1203813,1203813,84257,9630512,65536,1165562290,9458642,0,4664073264,12076327486771038,12076327486980109,12076327487769706,12076327487838231
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,921529,921534,4194304,256,0,0,12,24,339392,0x7f7031f1da00,0x7f6f26237900,3443652,3443652,145637,27549224,65536,3383207326,27379437,0,13534654516,12076327487863708,12076327488074664,12076327490355454,12076327490423525
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,921529,921534,4194304,256,0,0,12,24,344192,0x7f7031f1d900,0x7f6f26237940,2325508,2325508,152068,18604072,65536,2274678312,18420484,0,9100535904,12076327490468168,12076327490646973,12076327492182326,12076327492249860
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,921529,921534,4194304,256,0,0,20,24,345408,0x7f7031f1d800,0x7f6f26237980,9087333,9087333,544171,72698672,65536,8977280861,72531278,0,35910944660,12076327492280386,12076327492477365,12076327498530299,12076327498598388
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,921529,921534,4194304,256,0,0,20,24,348160,0x7f7031f1d700,0x7f6f262379c0,4574436,4574436,284141,36595496,65536,4502597830,36411997,0,18012214892,12076327498627422,12076327498826777,12076327501868524,12076327501942032
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,921529,921534,4194304,256,0,0,12,24,350912,0x7f7031f1d600,0x7f6f26237a00,2329572,2329572,150766,18636584,65536,2280499819,18463002,0,9123823536,12076327501966948,12076327502177803,12076327503717156,12076327503790938
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,921529,921534,4194304,256,0,0,12,24,0,0x7f7031f1d500,0x7f6f26237a40,6814428,6814428,414267,54515432,65536,6722407797,54333595,0,26891453672,12076327503817648,12076327504026421,12076327508552803,12076327508625613
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid grd Workgroup_Size LDS_Per_Workgroup scr vgpr SGPR fbar sig obj GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 __amd_rocclr_fillBuffer.kd 0 0 0 921529 921534 33554432 256 0 0 8 32 6464 0x0 0x7f6f26204180 502695 502695 17046 4021568 524288 372600279 3816924 0 1505167052 12076327135265660 12076327381325743 12076327381649102 12076327381757735
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 921529 921534 32768 256 0 0 24 24 12480 0x0 0x7f6f26235100 27819 27819 20311 222560 512 1122712 74488 0 4504968 12076327396356075 12076327396679513 12076327396685593 12076327396695125
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 4 921529 921534 4194304 256 0 0 24 24 12928 0x7f7031f1d900 0x7f6f26235140 219204 219204 20615 1753640 65536 131444628 1582707 0 527592892 12076327396760457 12076327397000951 12076327397134071 12076327397138189
5 3 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 6 921529 921534 4194304 256 0 0 36 24 13632 0x7f7031f1d800 0x7f6f26235180 393764 393764 29108 3150120 65536 273156985 2982062 0 1094444912 12076327397217927 12076327397422229 12076327397672148 12076327397741230
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 8 921529 921534 4194304 256 0 0 28 24 14080 0x7f7031f1d700 0x7f6f262351c0 395572 395572 29591 3164584 65536 329910429 2975811 0 1321457988 12076327397777507 12076327397981747 12076327398231986 12076327398301691
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 10 921529 921534 4194304 256 0 0 24 24 14528 0x7f7031f1d600 0x7f6f26235200 218644 218644 19473 1749160 65536 142658733 1577012 0 572449732 12076327398326708 12076327398535344 12076327398668944 12076327398672611
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 12 921529 921534 4194304 256 0 0 24 24 14976 0x7f7031f1d500 0x7f6f26235240 223812 223812 21749 1790504 65536 129076135 1616347 0 518113844 12076327398733073 12076327398925743 12076327399061742 12076327399065290
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 14 921529 921534 4194304 256 0 0 24 24 15424 0x7f7031f1d400 0x7f6f26235280 214716 214716 21675 1717736 65536 156951182 1550654 0 629619912 12076327399159065 12076327399352781 12076327399483820 12076327399487345
10 8 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 16 921529 921534 4194304 256 0 0 28 24 16128 0x7f7031f1d300 0x7f6f262352c0 410276 410276 35397 3282216 65536 251123097 3107336 0 1006308440 12076327399545924 12076327399746699 12076327400007178 12076327400048898
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 18 921529 921534 4194304 256 0 0 28 24 16832 0x7f7031f1da00 0x7f6f26235300 402596 402596 32151 3220776 65536 344690180 3048123 0 1380576460 12076327400084054 12076327400278697 12076327400534855 12076327400600644
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 20 921529 921534 4194304 256 0 0 24 24 17536 0x7f7031f1d900 0x7f6f26235340 212812 212812 20992 1702504 65536 158222018 1522110 0 634707908 12076327400625730 12076327400831974 12076327400960773 12076327400964410
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 22 921529 921534 4194304 256 0 0 24 24 18240 0x7f7031f1d800 0x7f6f26235380 220165 220165 19547 1761328 65536 130366679 1592966 0 523283296 12076327401031384 12076327401226212 12076327401360932 12076327401364714
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 24 921529 921534 4194304 256 0 0 24 24 18944 0x7f7031f1d700 0x7f6f262353c0 211117 211117 23784 1688944 65536 161737692 1514441 0 648770336 12076327401438120 12076327401618050 12076327401745730 12076327401749449
15 13 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 26 921529 921534 4194304 256 0 0 28 24 19904 0x7f7031f1d600 0x7f6f26235400 390460 390460 32628 3123688 65536 354858086 2954174 0 1421250132 12076327401809110 12076327402004129 12076327402252448 12076327402320219
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 28 921529 921534 4194304 256 0 0 28 24 20608 0x7f7031f1d500 0x7f6f26235440 394516 394516 24590 3156136 65536 283285198 2973684 0 1134958092 12076327402348241 12076327402558526 12076327402808765 12076327402875511
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 30 921529 921534 4194304 256 0 0 24 24 21312 0x7f7031f1d400 0x7f6f26235480 217573 217573 21130 1740592 65536 153580056 1576273 0 616131828 12076327402899105 12076327403106044 12076327403239163 12076327403242664
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 32 921529 921534 4194304 256 0 0 24 24 22016 0x7f7031f1d300 0x7f6f262354c0 225605 225605 22467 1804848 65536 131000276 1631073 0 525813924 12076327403301754 12076327403496282 12076327403633881 12076327403637518
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 34 921529 921534 4194304 256 0 0 24 24 22720 0x7f7031f1da00 0x7f6f26235500 217076 217076 22910 1736616 65536 149158415 1571313 0 598450084 12076327403711806 12076327403894680 12076327404027480 12076327404031019
20 18 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 36 921529 921534 4194304 256 0 0 28 24 23680 0x7f7031f1d900 0x7f6f26235540 404245 404245 28723 3233968 65536 304219837 3050101 0 1218693512 12076327404091441 12076327404286678 12076327404543957 12076327404609955
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 38 921529 921534 4194304 256 0 0 28 24 24384 0x7f7031f1d800 0x7f6f26235580 403804 403804 32386 3230440 65536 310926216 3042740 0 1245520580 12076327404635522 12076327404835956 12076327405091795 12076327405160448
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 40 921529 921534 4194304 256 0 0 24 24 25088 0x7f7031f1d700 0x7f6f262355c0 216180 216180 22874 1729448 65536 158862653 1556802 0 637268020 12076327405185514 12076327405387953 12076327405519473 12076327405522942
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 42 921529 921534 4194304 256 0 0 24 24 25792 0x7f7031f1d600 0x7f6f26235600 217501 217501 21934 1740016 65536 147479529 1568848 0 591739008 12076327405580599 12076327405776112 12076327405909071 12076327405912806
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 44 921529 921534 4194304 256 0 0 24 24 26496 0x7f7031f1d500 0x7f6f26235640 210060 210060 23028 1680488 65536 164043640 1511714 0 657992736 12076327405985571 12076327406168270 12076327406295949 12076327406299665
25 23 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 46 921529 921534 4194304 256 0 0 28 24 27712 0x7f7031f1d400 0x7f6f26235680 393477 393477 32926 3147824 65536 357396499 2976003 0 1431403828 12076327406360127 12076327406545388 12076327406796107 12076327406862571
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 48 921529 921534 4194304 256 0 0 28 24 28416 0x7f7031f1d300 0x7f6f262356c0 398429 398429 33952 3187440 65536 332660786 3007281 0 1332456112 12076327406887347 12076327407098186 12076327407351304 12076327407418034
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 50 921529 921534 4194304 256 0 0 24 24 29120 0x7f7031f1da00 0x7f6f26235700 216244 216244 22358 1729960 65536 157383696 1557729 0 631354700 12076327407442800 12076327407643783 12076327407776103 12076327407779575
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 52 921529 921534 4194304 256 0 0 24 24 30080 0x7f7031f1d900 0x7f6f26235740 217580 217580 24233 1740648 65536 150988090 1559666 0 605769248 12076327407840849 12076327408034501 12076327408167141 12076327408170622
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 54 921529 921534 4194304 256 0 0 24 24 30784 0x7f7031f1d800 0x7f6f26235780 210893 210893 22265 1687152 65536 149125876 1519036 0 598327684 12076327408242526 12076327408421700 12076327408550659 12076327408554225
30 28 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 56 921529 921534 4194304 256 0 0 28 24 32000 0x7f7031f1d700 0x7f6f262357c0 409284 409284 25773 3274280 65536 292572722 3093447 0 1172118292 12076327408611902 12076327408807618 12076327409069217 12076327409137980
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 58 921529 921534 4194304 256 0 0 28 24 32960 0x7f7031f1d600 0x7f6f26235800 408380 408380 28494 3267048 65536 299768216 3087224 0 1200888340 12076327409163868 12076327409364255 12076327409624734 12076327409691719
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 60 921529 921534 4194304 256 0 0 24 24 33920 0x7f7031f1d500 0x7f6f26235840 213756 213756 20522 1710056 65536 152821004 1532412 0 613119968 12076327409714421 12076327409916093 12076327410046012 12076327410049744
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 62 921529 921534 4194304 256 0 0 24 24 34880 0x7f7031f1d400 0x7f6f26235880 218309 218309 24528 1746480 65536 149435080 1579429 0 599589488 12076327410109516 12076327410298011 12076327410432091 12076327410435742
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 64 921529 921534 4194304 256 0 0 24 24 35840 0x7f7031f1d300 0x7f6f262358c0 215316 215316 23307 1722536 65536 163066672 1547928 0 654085080 12076327410507655 12076327410681529 12076327410812729 12076327410816469
35 33 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 66 921529 921534 4194304 256 0 0 28 24 37312 0x7f7031f1da00 0x7f6f26235900 397596 397596 34004 3180776 65536 339692340 3011197 0 1360585612 12076327410876621 12076327411063448 12076327411318167 12076327411367904
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 68 921529 921534 4194304 256 0 0 28 24 38272 0x7f7031f1d900 0x7f6f26235940 405661 405661 25737 3245296 65536 299813626 3067280 0 1201063276 12076327411394413 12076327411595605 12076327411854164 12076327411874325
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 70 921529 921534 4194304 256 0 0 24 24 39232 0x7f7031f1d800 0x7f6f26235980 226668 226668 23868 1813352 65536 132811821 1636779 0 533068744 12076327411933886 12076327412106323 12076327412245522 12076327412249032
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 72 921529 921534 4194304 256 0 0 24 24 40192 0x7f7031f1d700 0x7f6f262359c0 230268 230268 25125 1842152 65536 143495999 1669554 0 575821568 12076327412308292 12076327412496241 12076327412637841 12076327412641491
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 74 921529 921534 4194304 256 0 0 24 24 41152 0x7f7031f1d600 0x7f6f26235a00 218252 218252 22378 1746024 65536 155191739 1582506 0 622584292 12076327412713294 12076327412889039 12076327413022959 12076327413026697
40 38 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 76 921529 921534 4194304 256 0 0 28 24 42624 0x7f7031f1d500 0x7f6f26235a40 413413 413413 32653 3307312 65536 316670030 3129785 0 1268499144 12076327413087500 12076327413278478 12076327413543276 12076327413610221
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 78 921529 921534 4194304 256 0 0 28 24 43584 0x7f7031f1d400 0x7f6f26235a80 399837 399837 32660 3198704 65536 338705455 3027094 0 1356637164 12076327413634026 12076327413830955 12076327414086474 12076327414155715
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 80 921529 921534 4194304 256 0 0 24 24 44544 0x7f7031f1d300 0x7f6f26235ac0 218965 218965 22655 1751728 65536 153280811 1578906 0 614938856 12076327414180111 12076327414379593 12076327414513032 12076327414516636
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 82 921529 921534 4194304 256 0 0 24 24 45760 0x7f7031f1da00 0x7f6f26235b00 223740 223740 25739 1789928 65536 154857430 1610991 0 621254560 12076327414576868 12076327414766151 12076327414904070 12076327414907853
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 84 921529 921534 4194304 256 0 0 24 24 46720 0x7f7031f1d900 0x7f6f26235b40 213637 213637 23276 1709104 65536 154593955 1534868 0 620206840 12076327414979075 12076327415161349 12076327415291589 12076327415295213
45 43 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 86 921529 921534 4194304 256 0 0 28 24 48448 0x7f7031f1d800 0x7f6f26235b80 422453 422453 31736 3379632 65536 347170319 3198706 0 1390498552 12076327415352569 12076327415540387 12076327415811106 12076327415877134
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 88 921529 921534 4194304 256 0 0 28 24 49408 0x7f7031f1d700 0x7f6f26235bc0 402364 402364 27621 3218920 65536 295437547 3043653 0 1183568840 12076327415901850 12076327416100545 12076327416357664 12076327416424562
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 90 921529 921534 4194304 256 0 0 24 24 50368 0x7f7031f1d600 0x7f6f26235c00 212053 212053 21868 1696432 65536 167095985 1525051 0 670203184 12076327416448827 12076327416651742 12076327416781662 12076327416785302
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 92 921529 921534 4194304 256 0 0 24 24 51584 0x7f7031f1d500 0x7f6f26235c40 222060 222060 27474 1776488 65536 153260821 1586295 0 614878272 12076327416843450 12076327417037821 12076327417173980 12076327417177762
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 94 921529 921534 4194304 256 0 0 24 24 52544 0x7f7031f1d400 0x7f6f26235c80 220788 220788 25033 1766312 65536 154861311 1578134 0 621263124 12076327417249405 12076327417427739 12076327417561658 12076327417565572
50 48 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 96 921529 921534 4194304 256 0 0 28 24 54272 0x7f7031f1d300 0x7f6f26235cc0 424573 424573 33241 3396592 65536 315580726 3210664 0 1264140496 12076327417628589 12076327417817497 12076327418089176 12076327418157532
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 98 921529 921534 4194304 256 0 0 28 24 55488 0x7f7031f1da00 0x7f6f26235d00 407037 407037 25976 3256304 65536 270289769 3083323 0 1082974556 12076327418183921 12076327418383894 12076327418644373 12076327418685403
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 100 921529 921534 4194304 256 0 0 24 24 56704 0x7f7031f1d900 0x7f6f26235d40 217708 217708 23341 1741672 65536 156839408 1568149 0 629187568 12076327418717453 12076327418904532 12076327419037492 12076327419041255
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 102 921529 921534 4194304 256 0 0 24 24 58176 0x7f7031f1d800 0x7f6f26235d80 228813 228813 28100 1830512 65536 154939878 1639042 0 621630896 12076327419100204 12076327419287090 12076327419428530 12076327419432662
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 104 921529 921534 4194304 256 0 0 24 24 59392 0x7f7031f1d700 0x7f6f26235dc0 215820 215820 23377 1726568 65536 153362587 1548163 0 615282076 12076327419503885 12076327419677009 12076327419809008 12076327419812538
55 53 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 106 921529 921534 4194304 256 0 0 28 24 61376 0x7f7031f1d600 0x7f6f26235e00 409525 409525 32150 3276208 65536 301364347 3089841 0 1207276568 12076327419871979 12076327420063407 12076327420326606 12076327420392746
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 108 921529 921534 4194304 256 0 0 28 24 62592 0x7f7031f1d500 0x7f6f26235e40 406124 406124 31722 3249000 65536 310573904 3068570 0 1244112300 12076327420417472 12076327420615884 12076327420875243 12076327420941486
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 110 921529 921534 4194304 256 0 0 24 24 63808 0x7f7031f1d400 0x7f6f26235e80 217965 217965 22411 1743728 65536 150401905 1576953 0 603452992 12076327420965751 12076327421174122 12076327421308201 12076327421312155
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 112 921529 921534 4194304 256 0 0 24 24 65280 0x7f7031f1d300 0x7f6f26235ec0 223125 223125 29767 1785008 65536 165065178 1589301 0 662106268 12076327421372577 12076327421560520 12076327421697959 12076327421701499
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 114 921529 921534 4194304 256 0 0 24 24 66496 0x7f7031f1da00 0x7f6f26235f00 218885 218885 22790 1751088 65536 148990112 1583444 0 597783068 12076327421773042 12076327421946598 12076327422081158 12076327422085011
60 58 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 116 921529 921534 4194304 256 0 0 28 24 68480 0x7f7031f1d900 0x7f6f26235f40 411148 411148 33901 3289192 65536 338400769 3104057 0 1355437308 12076327422144492 12076327422334757 12076327422598115 12076327422665029
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 118 921529 921534 4194304 256 0 0 28 24 69696 0x7f7031f1d800 0x7f6f26235f80 408093 408093 27376 3264752 65536 283857796 3074190 0 1137242732 12076327422690376 12076327422885634 12076327423146753 12076327423213539
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 120 921529 921534 4194304 256 0 0 24 24 70912 0x7f7031f1d700 0x7f6f26235fc0 212516 212516 25414 1700136 65536 163318892 1522937 0 655110428 12076327423239517 12076327423436832 12076327423566431 12076327423570091
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 122 921529 921534 4194304 256 0 0 24 24 72384 0x7f7031f1d600 0x7f6f26236000 222780 222780 27440 1782248 65536 184868604 1601401 0 741343652 12076327423627638 12076327423818110 12076327423956189 12076327423959836
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 124 921529 921534 4194304 256 0 0 24 24 73600 0x7f7031f1d500 0x7f6f26236040 220364 220364 24433 1762920 65536 149119121 1581565 0 598323544 12076327424037430 12076327424214268 12076327424348667 12076327424352355
65 63 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 126 921529 921534 4194304 256 0 0 28 24 75840 0x7f7031f1d400 0x7f6f26236080 408988 408988 32263 3271912 65536 320979092 3083789 0 1285733124 12076327424410684 12076327424598266 12076327424861305 12076327424901776
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 128 921529 921534 4194304 256 0 0 28 24 77056 0x7f7031f1d300 0x7f6f262360c0 391132 391132 32409 3129064 65536 353412992 2963613 0 1415469032 12076327424942843 12076327425126584 12076327425377463 12076327425418577
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 130 921529 921534 4194304 256 0 0 24 24 78272 0x7f7031f1da00 0x7f6f26236100 217293 217293 22948 1738352 65536 155239009 1565948 0 622791596 12076327425451177 12076327425639862 12076327425773461 12076327425777273
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 132 921529 921534 4194304 256 0 0 24 24 80000 0x7f7031f1d900 0x7f6f26236140 232428 232428 27876 1859432 65536 195594787 1679946 0 784230672 12076327425836784 12076327426028660 12076327426171859 12076327426175674
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 134 921529 921534 4194304 256 0 0 24 24 81216 0x7f7031f1d800 0x7f6f26236180 223645 223645 23883 1789168 65536 145183396 1617226 0 582602460 12076327426247878 12076327426426418 12076327426564337 12076327426568073
70 68 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 136 921529 921534 4194304 256 0 0 28 24 83456 0x7f7031f1d700 0x7f6f262361c0 414460 414460 32555 3315688 65536 305746233 3117629 0 1224808600 12076327426624498 12076327426818096 12076327427085135 12076327427152028
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 138 921529 921534 4194304 256 0 0 28 24 84928 0x7f7031f1d600 0x7f6f26236200 401477 401477 34196 3211824 65536 335221921 3041646 0 1342703124 12076327427176985 12076327427376494 12076327427634413 12076327427700878
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 140 921529 921534 4194304 256 0 0 24 24 86400 0x7f7031f1d500 0x7f6f26236240 227021 227021 26580 1816176 65536 138787551 1632726 0 556996696 12076327427725213 12076327427923371 12076327428062571 12076327428066197
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 142 921529 921534 4194304 256 0 0 24 24 88128 0x7f7031f1d400 0x7f6f26236280 242348 242348 27594 1938792 65536 209708783 1767698 0 840693360 12076327428126770 12076327428313129 12076327428463689 12076327428467433
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 144 921529 921534 4194304 256 0 0 24 24 89600 0x7f7031f1d300 0x7f6f262362c0 225845 225845 25029 1806768 65536 137865768 1635760 0 553284708 12076327428561548 12076327428734728 12076327428873287 12076327428876904
75 73 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 146 921529 921534 4194304 256 0 0 28 24 92096 0x7f7031f1da00 0x7f6f26236300 419101 419101 32113 3352816 65536 296978305 3151701 0 1189729116 12076327428934922 12076327429126886 12076327429397605 12076327429455048
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 148 921529 921534 4194304 256 0 0 28 24 93568 0x7f7031f1d900 0x7f6f26236340 402333 402333 31713 3218672 65536 334236171 3045584 0 1338758204 12076327429479895 12076327429675363 12076327429933922 12076327429979904
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 150 921529 921534 4194304 256 0 0 24 24 95040 0x7f7031f1d800 0x7f6f26236380 227940 227940 25948 1823528 65536 141446042 1624412 0 567649260 12076327430012294 12076327430211521 12076327430350560 12076327430354440
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 152 921529 921534 4194304 256 0 0 24 24 96768 0x7f7031f1d700 0x7f6f262363c0 252172 252172 28691 2017384 65536 219587427 1851182 0 880202016 12076327430415323 12076327430600959 12076327430758078 12076327430761807
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 154 921529 921534 4194304 256 0 0 24 24 98240 0x7f7031f1d600 0x7f6f26236400 225357 225357 24327 1802864 65536 149769581 1633947 0 600952260 12076327430832588 12076327431005117 12076327431144157 12076327431148135
80 78 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 156 921529 921534 4194304 256 0 0 28 24 100736 0x7f7031f1d500 0x7f6f26236440 409412 409412 33883 3275304 65536 315787504 3088788 0 1264966996 12076327431206664 12076327431396156 12076327431660634 12076327431708196
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 158 921529 921534 4194304 256 0 0 28 24 102208 0x7f7031f1d400 0x7f6f26236480 400348 400348 29983 3202792 65536 324847309 3032320 0 1301216560 12076327431734034 12076327431926393 12076327432184632 12076327432233041
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 160 921529 921534 4194304 256 0 0 24 24 103680 0x7f7031f1d300 0x7f6f262364c0 221956 221956 25582 1775656 65536 147481606 1594631 0 591802116 12076327432257046 12076327432457751 12076327432593910 12076327432597729
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 162 921529 921534 4194304 256 0 0 24 24 105664 0x7f7031f1da00 0x7f6f26236500 263724 263724 28572 2109800 65536 235041528 1943765 0 942025504 12076327432654835 12076327432848469 12076327433014068 12076327433017749
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 164 921529 921534 4194304 256 0 0 24 24 107136 0x7f7031f1d900 0x7f6f26236540 219060 219060 23687 1752488 65536 152404572 1576119 0 611446008 12076327433090545 12076327433271027 12076327433405266 12076327433408886
85 83 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 166 921529 921534 4194304 256 0 0 28 24 109888 0x7f7031f1d800 0x7f6f26236580 419340 419340 36699 3354728 65536 324040229 3156233 0 1297980316 12076327433465331 12076327433656145 12076327433927184 12076327433949251
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 168 921529 921534 4194304 256 0 0 28 24 111360 0x7f7031f1d700 0x7f6f262365c0 409181 409181 31598 3273456 65536 292613348 3085096 0 1172280348 12076327434009422 12076327434189103 12076327434451662 12076327434503731
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 170 921529 921534 4194304 256 0 0 24 24 112832 0x7f7031f1d600 0x7f6f26236600 222981 222981 24024 1783856 65536 149896144 1612689 0 601442240 12076327434528377 12076327434728940 12076327434866060 12076327434869801
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 172 921529 921534 4194304 256 0 0 24 24 114816 0x7f7031f1d500 0x7f6f26236640 277020 277020 31065 2216168 65536 248052652 2044666 0 994052548 12076327434931306 12076327435124939 12076327435298058 12076327435301924
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 174 921529 921534 4194304 256 0 0 24 24 116288 0x7f7031f1d400 0x7f6f26236680 220573 220573 22459 1764592 65536 165346140 1588658 0 663226476 12076327435374459 12076327435549737 12076327435685416 12076327435689505
90 88 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 176 921529 921534 4194304 256 0 0 28 24 119040 0x7f7031f1d300 0x7f6f262366c0 404628 404628 37892 3237032 65536 315795617 3035555 0 1265015904 12076327435745910 12076327435939015 12076327436199654 12076327436249676
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 178 921529 921534 4194304 256 0 0 28 24 120768 0x7f7031f1da00 0x7f6f26236700 457901 457901 15291 3663216 65536 296982808 3065379 0 1189746456 12076327436273169 12076327436474212 12076327436770371 12076327436818583
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 180 921529 921534 4194304 256 0 0 24 24 122496 0x7f7031f1d900 0x7f6f26236740 223005 223005 25216 1784048 65536 150815369 1604902 0 605136716 12076327436842538 12076327437043330 12076327437179809 12076327437183842
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 182 921529 921534 4194304 256 0 0 24 24 124736 0x7f7031f1d800 0x7f6f26236780 290572 290572 30899 2324584 65536 260280880 2154890 0 1042972684 12076327437242010 12076327437432928 12076327437616287 12076327437622207
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 184 921529 921534 4194304 256 0 0 24 24 126464 0x7f7031f1d700 0x7f6f262367c0 223317 223317 25702 1786544 65536 143093189 1615056 0 574262752 12076327437704730 12076327437881726 12076327438019805 12076327438023893
95 93 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 186 921529 921534 4194304 256 0 0 20 24 127936 0x7f7031f1d600 0x7f6f26236800 413908 413908 36504 3311272 65536 380760177 3142546 0 1524861416 12076327438080578 12076327438271484 12076327438539643 12076327438589374
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 188 921529 921534 4194304 256 0 0 28 24 129664 0x7f7031f1d500 0x7f6f26236840 395004 395004 34433 3160040 65536 334017531 2985646 0 1337889236 12076327438615022 12076327438814362 12076327439068281 12076327439117596
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 190 921529 921534 4194304 256 0 0 24 24 131392 0x7f7031f1d400 0x7f6f26236880 220508 220508 25162 1764072 65536 160293233 1584140 0 643006552 12076327439141300 12076327439340600 12076327439476599 12076327439480370
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 192 921529 921534 4194304 256 0 0 24 24 133632 0x7f7031f1d300 0x7f6f262368c0 303348 303348 32459 2426792 65536 272397563 2253283 0 1091431836 12076327439539269 12076327439725078 12076327439916757 12076327439968387
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 194 921529 921534 4194304 256 0 0 24 24 135360 0x7f7031f1da00 0x7f6f26236900 218932 218932 26009 1751464 65536 154615993 1567950 0 620325540 12076327440012309 12076327440194516 12076327440329715 12076327440333576
100 98 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 196 921529 921534 4194304 256 0 0 20 24 136832 0x7f7031f1d900 0x7f6f26236940 438060 438060 40923 3504488 65536 406700091 3333517 0 1628620276 12076327440391784 12076327440580914 12076327440865233 12076327440914295
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 198 921529 921534 4194304 256 0 0 28 24 138560 0x7f7031f1d800 0x7f6f26236980 404189 404189 32075 3233520 65536 320696391 3056109 0 1284604624 12076327440937508 12076327441141391 12076327441402190 12076327441452836
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 200 921529 921534 4194304 256 0 0 24 24 140288 0x7f7031f1d700 0x7f6f262369c0 222933 222933 26446 1783472 65536 151298942 1601376 0 607076608 12076327441476319 12076327441672109 12076327441809068 12076327441812935
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 202 921529 921534 4194304 256 0 0 24 24 142784 0x7f7031f1d600 0x7f6f26236a00 331445 331445 33780 2651568 65536 299751261 2483426 0 1200858452 12076327441874970 12076327442068587 12076327442279146 12076327442330086
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 204 921529 921534 4194304 256 0 0 24 24 144768 0x7f7031f1d500 0x7f6f26236a40 223189 223189 26144 1785520 65536 146378075 1608324 0 587388236 12076327442365472 12076327442551945 12076327442689544 12076327442693351
105 103 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 206 921529 921534 4194304 256 0 0 20 24 145728 0x7f7031f1d400 0x7f6f26236a80 472444 472444 43233 3779560 65536 439173511 3590778 0 1758514404 12076327442750828 12076327442936263 12076327443242982 12076327443290020
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 208 921529 921534 4194304 256 0 0 28 24 147712 0x7f7031f1d300 0x7f6f26236ac0 407284 407284 31468 3258280 65536 261914357 3056209 0 1049494120 12076327443327690 12076327443513701 12076327443775779 12076327443821929
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 210 921529 921534 4194304 256 0 0 24 24 149696 0x7f7031f1da00 0x7f6f26236b00 222084 222084 24880 1776680 65536 153353024 1592647 0 615268220 12076327443854429 12076327444048418 12076327444185858 12076327444189762
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 212 921529 921534 4194304 256 0 0 24 24 152192 0x7f7031f1d900 0x7f6f26236b40 358669 358669 36823 2869360 65536 327245960 2696314 0 1310831392 12076327444249323 12076327444436377 12076327444664696 12076327444714257
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 214 921529 921534 4194304 256 0 0 24 24 154176 0x7f7031f1d800 0x7f6f26236b80 222588 222588 27050 1780712 65536 161613304 1600887 0 648323568 12076327444756666 12076327444933974 12076327445071733 12076327445075488
110 108 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 216 921529 921534 4194304 256 0 0 20 24 155648 0x7f7031f1d700 0x7f6f26236bc0 504180 504180 44136 4033448 65536 471469664 3865220 0 1887698484 12076327445132975 12076327445328852 12076327445657650 12076327445705068
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 218 921529 921534 4194304 256 0 0 28 24 157632 0x7f7031f1d600 0x7f6f26236c00 401748 401748 30490 3213992 65536 300767866 2999630 0 1204893592 12076327445734894 12076327445926449 12076327446186288 12076327446237468
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 220 921529 921534 4194304 256 0 0 24 24 159616 0x7f7031f1d500 0x7f6f26236c40 225429 225429 27825 1803440 65536 157817115 1620370 0 633136516 12076327446262274 12076327446461167 12076327446600046 12076327446603889
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 222 921529 921534 4194304 256 0 0 24 24 162368 0x7f7031f1d400 0x7f6f26236c80 383100 383100 36758 3064808 65536 352102369 2898986 0 1410263924 12076327446662367 12076327446846125 12076327447091244 12076327447140817
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 224 921529 921534 4194304 256 0 0 24 24 164608 0x7f7031f1d300 0x7f6f26236cc0 219500 219500 27388 1756008 65536 162354413 1569011 0 651287132 12076327447177034 12076327447364523 12076327447499882 12076327447503651
115 113 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 226 921529 921534 4194304 256 0 0 20 24 166336 0x7f7031f1da00 0x7f6f26236d00 575309 575309 48139 4602480 65536 541767186 4429341 0 2168889116 12076327447560727 12076327447745641 12076327448122280 12076327448173185
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 228 921529 921534 4194304 256 0 0 28 24 168576 0x7f7031f1d900 0x7f6f26236d40 409644 409644 33505 3277160 65536 300693997 3067599 0 1204605360 12076327448197100 12076327448412038 12076327448676677 12076327448695205
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 230 921529 921534 4194304 256 0 0 24 24 170816 0x7f7031f1d800 0x7f6f26236d80 225909 225909 27312 1807280 65536 166754503 1630258 0 668896656 12076327448754706 12076327448931876 12076327449072515 12076327449076334
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 232 921529 921534 4194304 256 0 0 24 24 174080 0x7f7031f1d700 0x7f6f26236dc0 434821 434821 40942 3478576 65536 400645665 3305378 0 1604433640 12076327449136656 12076327449334914 12076327449613953 12076327449663064
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 234 921529 921534 4194304 256 0 0 24 24 176576 0x7f7031f1d600 0x7f6f26236e00 227580 227580 26972 1820648 65536 182547740 1649162 0 732089040 12076327449698790 12076327449881472 12076327450023071 12076327450027361
120 118 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 236 921529 921534 4194304 256 0 0 20 24 177792 0x7f7031f1d500 0x7f6f26236e40 644196 644196 51967 5153576 65536 611537704 4986023 0 2447971452 12076327450085429 12076327450275550 12076327450698588 12076327450744474
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 238 921529 921534 4194304 256 0 0 28 24 180288 0x7f7031f1d400 0x7f6f26236e80 414684 414684 33984 3317480 65536 325679697 3126541 0 1304555352 12076327450772917 12076327450963227 12076327451232346 12076327451280169
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 240 921529 921534 4194304 256 0 0 24 24 182784 0x7f7031f1d300 0x7f6f26236ec0 225124 225124 27994 1801000 65536 183537361 1620656 0 736035852 12076327451305567 12076327451502745 12076327451642584 12076327451646250
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 242 921529 921534 4194304 256 0 0 24 24 186304 0x7f7031f1da00 0x7f6f26236f00 489029 489029 42650 3912240 65536 456665273 3746571 0 1828511312 12076327451704007 12076327451896983 12076327452212982 12076327452257826
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 244 921529 921534 4194304 256 0 0 24 24 189312 0x7f7031f1d900 0x7f6f26236f40 242156 242156 28169 1937256 65536 214219388 1772586 0 858759044 12076327452307599 12076327452487220 12076327452638900 12076327452642591
125 123 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 246 921529 921534 4194304 256 0 0 20 24 190784 0x7f7031f1d800 0x7f6f26236f80 784476 784476 59291 6275816 65536 751137040 6109488 0 3006369528 12076327452700128 12076327452887699 12076327453404016 12076327453428251
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 248 921529 921534 4194304 256 0 0 28 24 193792 0x7f7031f1d700 0x7f6f26236fc0 457189 457189 40278 3657520 65536 377118755 3475801 0 1510304444 12076327453482212 12076327453663215 12076327453960654 12076327453980718
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 250 921529 921534 4194304 256 0 0 24 24 196800 0x7f7031f1d600 0x7f6f26237000 245468 245468 27285 1963752 65536 217867234 1800044 0 873357636 12076327454042623 12076327454221453 12076327454375372 12076327454379098
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 252 921529 921534 4194304 256 0 0 24 24 201088 0x7f7031f1d500 0x7f6f26237040 632789 632789 16512 5062320 65536 561747940 4589196 0 2248845944 12076327454439972 12076327454626411 12076327455036969 12076327455080602
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 254 921529 921534 4194304 256 0 0 24 24 204608 0x7f7031f1d400 0x7f6f26237080 279837 279837 30251 2238704 65536 249828270 2068744 0 1001199200 12076327455130315 12076327455310728 12076327455487207 12076327455490915
130 128 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 256 921529 921534 4194304 256 0 0 20 24 206080 0x7f7031f1d300 0x7f6f262370c0 924461 924461 67066 7395696 65536 889569140 7231932 0 3560097332 12076327455548562 12076327455743206 12076327456352163 12076327456399433
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 258 921529 921534 4194304 256 0 0 28 24 209600 0x7f7031f1da00 0x7f6f26237100 500637 500637 44537 4005104 65536 464298889 3830255 0 1859052364 12076327456432445 12076327456631202 12076327456958561 12076327457010679
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 260 921529 921534 4194304 256 0 0 24 24 213120 0x7f7031f1d900 0x7f6f26237140 282037 282037 29556 2256304 65536 254101760 2092270 0 1018291448 12076327457043851 12076327457242400 12076327457421599 12076327457425330
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 262 921529 921534 4194304 256 0 0 24 24 218176 0x7f7031f1d800 0x7f6f26237180 700772 700772 57754 5606184 65536 664650009 5415350 0 2660446968 12076327457486584 12076327457672958 12076327458127996 12076327458177217
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 264 921529 921534 4194304 256 0 0 24 24 222208 0x7f7031f1d700 0x7f6f262371c0 313669 313669 31681 2509360 65536 285350498 2346446 0 1143297024 12076327458223734 12076327458403675 12076327458603994 12076327458649986
135 133 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 266 921529 921534 4194304 256 0 0 20 24 223936 0x7f7031f1d600 0x7f6f26237200 1066581 1066581 77332 8532656 65536 1028208571 8356608 0 4114654956 12076327458681735 12076327458873752 12076327459576149 12076327459627533
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 268 921529 921534 4194304 256 0 0 28 24 227968 0x7f7031f1d500 0x7f6f26237240 566956 566956 47385 4535656 65536 532587577 4365736 0 2132192884 12076327459652649 12076327459855508 12076327460227667 12076327460277090
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 270 921529 921534 4194304 256 0 0 24 24 232000 0x7f7031f1d400 0x7f6f26237280 319468 319468 32704 2555752 65536 289506099 2387498 0 1159913240 12076327460300694 12076327460500785 12076327460704304 12076327460752473
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 272 921529 921534 4194304 256 0 0 24 24 237824 0x7f7031f1d300 0x7f6f262372c0 803221 803221 60806 6425776 65536 767733220 6255591 0 3072775544 12076327460775676 12076327460970223 12076327461496141 12076327461546389
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 274 921529 921534 4194304 256 0 0 24 24 242368 0x7f7031f1da00 0x7f6f26237300 351500 351500 36540 2812008 65536 320014175 2630801 0 1281961004 12076327461582325 12076327461768140 12076327461992299 12076327462044635
140 138 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 276 921529 921534 4194304 256 0 0 20 24 243584 0x7f7031f1d900 0x7f6f26237340 1207757 1207757 85294 9662064 65536 1169193706 9490895 0 4678594368 12076327462068589 12076327462268778 12076327463067974 12076327463135792
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 278 921529 921534 4194304 256 0 0 28 24 248128 0x7f7031f1d800 0x7f6f26237380 673884 673884 16747 5391080 65536 602526433 4945484 0 2411943540 12076327463162242 12076327463366213 12076327463810051 12076327463877281
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 280 921529 921534 4194304 256 0 0 24 24 252672 0x7f7031f1d700 0x7f6f262373c0 355796 355796 35489 2846376 65536 325671565 2669737 0 1304577388 12076327463900183 12076327464119489 12076327464346688 12076327464415721
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 282 921529 921534 4194304 256 0 0 24 24 259264 0x7f7031f1d600 0x7f6f26237400 911021 911021 67086 7288176 65536 875199644 7120624 0 3502644540 12076327464440567 12076327464642047 12076327465239805 12076327465308110
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 284 921529 921534 4194304 256 0 0 24 24 264832 0x7f7031f1d500 0x7f6f26237440 419516 419516 40855 3356136 65536 386941796 3175295 0 1549661548 12076327465343636 12076327465540123 12076327465809082 12076327465875684
145 143 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 286 921529 921534 4194304 256 0 0 20 24 266304 0x7f7031f1d400 0x7f6f26237480 1487725 1487725 100754 11901808 65536 1447187792 11735182 0 5790571912 12076327465900080 12076327466105401 12076327467090836 12076327467160192
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 288 921529 921534 4194304 256 0 0 28 24 271872 0x7f7031f1d300 0x7f6f262374c0 804020 804020 16254 6432168 65536 737761527 6055813 0 2952886016 12076327467185128 12076327467397075 12076327467928273 12076327467996005
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 290 921529 921534 4194304 256 0 0 24 24 277440 0x7f7031f1da00 0x7f6f26237500 422949 422949 40497 3383600 65536 390751573 3206117 0 1564894460 12076327468027784 12076327468232751 12076327468504750 12076327468574039
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 292 921529 921534 4194304 256 0 0 12 24 279936 0x7f7031f1d900 0x7f6f26237540 1126132 1126132 79445 9009064 65536 1089845165 8842241 0 4361203736 12076327468600158 12076327468792269 12076327469530026 12076327469598864
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 294 921529 921534 4194304 256 0 0 24 24 286528 0x7f7031f1d800 0x7f6f26237580 493468 493468 45315 3947752 65536 459603534 3772007 0 1840310892 12076327469635692 12076327469821864 12076327470140103 12076327470208767
150 148 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 296 921529 921534 4194304 256 0 0 20 24 288000 0x7f7031f1d700 0x7f6f262375c0 1768844 1768844 118324 14150760 65536 1723639655 13982118 0 6896378308 12076327470234154 12076327470433222 12076327471602497 12076327471670614
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 298 921529 921534 4194304 256 0 0 32 24 294592 0x7f7031f1d600 0x7f6f26237600 922484 922484 66355 7379880 65536 808434371 7201184 0 3235580684 12076327471698857 12076327471899615 12076327472510493 12076327472581256
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 300 921529 921534 4194304 256 0 0 24 24 301184 0x7f7031f1d500 0x7f6f26237640 491701 491701 43190 3933616 65536 459379596 3766902 0 1839417628 12076327472604209 12076327472814171 12076327473133050 12076327473199926
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 302 921529 921534 4194304 256 0 0 12 24 304960 0x7f7031f1d400 0x7f6f26237680 1338989 1338989 94366 10711920 65536 1297305485 10531704 0 5191044600 12076327473226145 12076327473430009 12076327474308405 12076327474377084
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 304 921529 921534 4194304 256 0 0 24 24 313600 0x7f7031f1d300 0x7f6f262376c0 631181 631181 53286 5049456 65536 596092182 4874212 0 2386266096 12076327474422088 12076327474602804 12076327475013522 12076327475081834
155 153 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 306 921529 921534 4194304 256 0 0 20 24 314816 0x7f7031f1da00 0x7f6f26237700 2333732 2333732 151312 18669864 65536 2284938455 18503363 0 9141574476 12076327475110126 12076327475310960 12076327476858474 12076327476931651
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 308 921529 921534 4194304 256 0 0 20 24 317568 0x7f7031f1d900 0x7f6f26237740 1202364 1202364 15250 9618920 65536 1162048908 9433323 0 4650017668 12076327476964272 12076327477174632 12076327477969029 12076327478288343
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 310 921529 921534 4194304 256 0 0 12 24 320320 0x7f7031f1d800 0x7f6f26237780 644389 644389 54450 5155120 65536 608696803 4969808 0 2436613984 12076327478312357 12076327478521906 12076327478937105 12076327479012028
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 312 921529 921534 4194304 256 0 0 12 24 324096 0x7f7031f1d700 0x7f6f262377c0 1757796 1757796 46114 14062376 65536 1715011761 13896501 0 6861870600 12076327479042625 12076327479239503 12076327480398058 12076327480466140
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 314 921529 921534 4194304 256 0 0 12 24 328896 0x7f7031f1d600 0x7f6f26237800 1200124 1200124 85398 9601000 65536 1160737821 9420660 0 4644781084 12076327480509340 12076327480689737 12076327481475013 12076327481543342
160 158 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 316 921529 921534 4194304 256 0 0 20 24 330112 0x7f7031f1d500 0x7f6f26237840 4586309 4586309 282847 36690480 65536 4514982965 36501638 0 18061753356 12076327481570933 12076327481773892 12076327484823959 12076327484892897
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 318 921529 921534 4194304 256 0 0 20 24 332864 0x7f7031f1d400 0x7f6f26237880 2325189 2325189 150804 18601520 65536 2276865554 18430717 0 9109285784 12076327484921430 12076327485134197 12076327486677231 12076327486746191
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 320 921529 921534 4194304 256 0 0 12 24 335616 0x7f7031f1d300 0x7f6f262378c0 1203813 1203813 84257 9630512 65536 1165562290 9458642 0 4664073264 12076327486771038 12076327486980109 12076327487769706 12076327487838231
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 322 921529 921534 4194304 256 0 0 12 24 339392 0x7f7031f1da00 0x7f6f26237900 3443652 3443652 145637 27549224 65536 3383207326 27379437 0 13534654516 12076327487863708 12076327488074664 12076327490355454 12076327490423525
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 324 921529 921534 4194304 256 0 0 12 24 344192 0x7f7031f1d900 0x7f6f26237940 2325508 2325508 152068 18604072 65536 2274678312 18420484 0 9100535904 12076327490468168 12076327490646973 12076327492182326 12076327492249860
165 163 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 326 921529 921534 4194304 256 0 0 20 24 345408 0x7f7031f1d800 0x7f6f26237980 9087333 9087333 544171 72698672 65536 8977280861 72531278 0 35910944660 12076327492280386 12076327492477365 12076327498530299 12076327498598388
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 328 921529 921534 4194304 256 0 0 20 24 348160 0x7f7031f1d700 0x7f6f262379c0 4574436 4574436 284141 36595496 65536 4502597830 36411997 0 18012214892 12076327498627422 12076327498826777 12076327501868524 12076327501942032
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 330 921529 921534 4194304 256 0 0 12 24 350912 0x7f7031f1d600 0x7f6f26237a00 2329572 2329572 150766 18636584 65536 2280499819 18463002 0 9123823536 12076327501966948 12076327502177803 12076327503717156 12076327503790938
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 332 921529 921534 4194304 256 0 0 12 24 0 0x7f7031f1d500 0x7f6f26237a40 6814428 6814428 414267 54515432 65536 6722407797 54333595 0 26891453672 12076327503817648 12076327504026421 12076327508552803 12076327508625613
@@ -0,0 +1,5 @@
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,21 @@
pmc: SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU SQ_INSTS_VSKIPPED SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_SH_FIFO_BUSY_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum
pmc: SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG SQ_INSTS SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_SH_FIFO_CMD_BUSY_sum TA_SH_FIFO_ADDR_BUSY_sum TD_COALESCABLE_WAVEFRONT_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum
pmc: SQ_ACTIVE_INST_ANY SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_INSTS_VALU SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_SH_FIFO_DATA_BUSY_sum TA_SH_FIFO_DATA_SFIFO_BUSY_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum
pmc: SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_SH_FIFO_DATA_TFIFO_BUSY_sum TA_SQ_TA_CMD_CYCLES_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum
pmc: SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES SQ_WAVES_EQ_64 SQ_WAVES_LT_64 TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_SP_TA_ADDR_CYCLES_sum TA_SP_TA_DATA_CYCLES_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_STALL_sum
pmc: SQ_WAVES_LT_48 SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_SH_FIFO_ADDR_STARVED_WHILE_BUSY_CYCLES_sum TA_SH_FIFO_CMD_STARVED_WHILE_BUSY_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_IO_CREDIT_STALL_sum TCC_EA_WRREQ_GMI_CREDIT_STALL_sum TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum
pmc: SQ_WAVES_SAVED SQ_INSTS_SMEM_NORM SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ SQC_TC_DATA_WRITE_REQ SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_SH_FIFO_DATA_STARVED_WHILE_BUSY_CYCLES_sum TA_TA_SH_FIFO_STARVED_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_ATOMIC_sum TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum
pmc: SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES SQC_ICACHE_MISSES_DUPLICATE SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_BUFFER_WAVEFRONTS_sum TA_BUFFER_READ_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_EA_RDREQ_IO_CREDIT_STALL_sum TCC_EA_RDREQ_GMI_CREDIT_STALL_sum TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum TCC_TAG_STALL_sum
pmc: SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum
pmc: TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum TA_BUFFER_TOTAL_CYCLES_sum TA_BUFFER_COALESCABLE_WAVEFRONTS_sum TCC_EA_RDREQ_DRAM_sum TCC_EA_WRREQ_DRAM_sum TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum
pmc: TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TCC_EA_ATOMIC_LEVEL_sum
pmc: TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31]
pmc: TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31]
pmc: TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31]
pmc: TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31]
pmc: TA_FLAT_COALESCEABLE_WAVEFRONTS_sum TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31]
pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31]
gpu:
range:
kernel:
@@ -0,0 +1,168 @@
Dispatch_ID,Kernel_Name,GPU_ID
0,__amd_rocclr_fillBuffer.kd,0
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0
1 Dispatch_ID Kernel_Name GPU_ID
2 0 __amd_rocclr_fillBuffer.kd 0
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0
5 3 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0
10 8 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0
15 13 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0
20 18 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0
25 23 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0
30 28 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0
35 33 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0
40 38 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0
45 43 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0
50 48 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0
55 53 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0
60 58 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0
65 63 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0
70 68 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0
75 73 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0
80 78 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0
85 83 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0
90 88 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0
95 93 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0
100 98 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0
105 103 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0
110 108 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0
115 113 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0
120 118 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0
125 123 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0
130 128 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0
135 133 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0
140 138 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0
145 143 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0
150 148 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0
155 153 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0
160 158 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0
165 163 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0
File diff suppressed because one or more lines are too long
@@ -0,0 +1,11 @@
Kernel_Name,Count,Sum(ns),Mean(ns),Median(ns),Pct
"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",1,6055312.0,6055312.0,6055312.0,9.17581889130573
"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",1,4527004.0,4527004.0,4527004.0,6.859922135179261
"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",1,3055336.0,3055336.0,3055336.0,4.629853884999894
"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",1,3043336.0,3043336.0,3043336.0,4.611669879502627
"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",1,2281742.0,2281742.0,2281742.0,3.4576007559454767
"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",1,1549745.0,1549745.0,1549745.0,2.3483809666135445
"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",1,1542068.0,1542068.0,1542068.0,2.336747749096668
"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",1,1539027.0,1539027.0,1539027.0,2.332139619036902
"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",1,1534708.0,1534708.0,1534708.0,2.325594892391677
"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",1,1170709.0,1170709.0,1170709.0,1.7740149076416936
1 Kernel_Name Count Sum(ns) Mean(ns) Median(ns) Pct
2 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 1 6055312.0 6055312.0 6055312.0 9.17581889130573
3 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 1 4527004.0 4527004.0 4527004.0 6.859922135179261
4 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 1 3055336.0 3055336.0 3055336.0 4.629853884999894
5 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 1 3043336.0 3043336.0 3043336.0 4.611669879502627
6 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 1 2281742.0 2281742.0 2281742.0 3.4576007559454767
7 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 1 1549745.0 1549745.0 1549745.0 2.3483809666135445
8 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 1 1542068.0 1542068.0 1542068.0 2.336747749096668
9 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 1 1539027.0 1539027.0 1539027.0 2.332139619036902
10 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 1 1534708.0 1534708.0 1534708.0 2.325594892391677
11 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 1 1170709.0 1170709.0 1170709.0 1.7740149076416936
@@ -0,0 +1,9 @@
Metric,Count,Unit
VALU - Vector,,Instr per wave
VMEM,,Instr per wave
LDS_Per_Workgroup,0.0,Instr per wave
VALU - MFMA,,Instr per wave
SALU,46.862275449101794,Instr per wave
SMEM,1.8083832335329342,Instr per wave
Branch,21.97005988023952,Instr per wave
GDS,0.0,Instr per wave
1 Metric Count Unit
2 VALU - Vector Instr per wave
3 VMEM Instr per wave
4 LDS_Per_Workgroup 0.0 Instr per wave
5 VALU - MFMA Instr per wave
6 SALU 46.862275449101794 Instr per wave
7 SMEM 1.8083832335329342 Instr per wave
8 Branch 21.97005988023952 Instr per wave
9 GDS 0.0 Instr per wave
@@ -0,0 +1,16 @@
Metric,Count,Unit
INT-32,,Instr per wave
INT-64,,Instr per wave
F16-ADD,,Instr per wave
F16-Mult,,Instr per wave
F16-FMA,,Instr per wave
F16-Trans,,Instr per wave
F32-ADD,,Instr per wave
F32-Mult,,Instr per wave
F32-FMA,,Instr per wave
F32-Trans,,Instr per wave
F64-ADD,,Instr per wave
F64-Mult,,Instr per wave
F64-FMA,,Instr per wave
F64-Trans,,Instr per wave
Conversion,,Instr per wave
1 Metric Count Unit
2 INT-32 Instr per wave
3 INT-64 Instr per wave
4 F16-ADD Instr per wave
5 F16-Mult Instr per wave
6 F16-FMA Instr per wave
7 F16-Trans Instr per wave
8 F32-ADD Instr per wave
9 F32-Mult Instr per wave
10 F32-FMA Instr per wave
11 F32-Trans Instr per wave
12 F64-ADD Instr per wave
13 F64-Mult Instr per wave
14 F64-FMA Instr per wave
15 F64-Trans Instr per wave
16 Conversion Instr per wave
@@ -0,0 +1,9 @@
Type,Count
Buffer Instr,0.0
Buffer Read,0.0
Buffer Write,0.0
Buffer Atomic,0.0
Flat Instr,7.9640718562874255
Flat Read,7.952095808383233
Flat Write,0.011976047904191617
Flat Atomic,0.0
1 Type Count
2 Buffer Instr 0.0
3 Buffer Read 0.0
4 Buffer Write 0.0
5 Buffer Atomic 0.0
6 Flat Instr 7.9640718562874255
7 Flat Read 7.952095808383233
8 Flat Write 0.011976047904191617
9 Flat Atomic 0.0
@@ -0,0 +1,6 @@
Type,Count
MFMA-I8,
MFMA-F16,
MFMA-BF16,
MFMA-F32,
MFMA-F64,
1 Type Count
2 MFMA-I8
3 MFMA-F16
4 MFMA-BF16
5 MFMA-F32
6 MFMA-F64
@@ -0,0 +1,26 @@
Info
dev0
vesuvius
AMD EPYC 7542 32-Core Processor
""
4.18.0-240.15.1.el8_3.x86_64
4.2.0-21
Thu Sep 22 11:31:14 2022 (CDT)
gfx908
8
120
4
64
40
1024
16
""
1502
1200
300
1200
32
mi100
48
1228.8
SQ|LDS_Per_Workgroup|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF
1 Info
2 dev0
3 vesuvius
4 AMD EPYC 7542 32-Core Processor
5
6 4.18.0-240.15.1.el8_3.x86_64
7 4.2.0-21
8 Thu Sep 22 11:31:14 2022 (CDT)
9 gfx908
10 8
11 120
12 4
13 64
14 40
15 1024
16 16
17
18 1502
19 1200
20 300
21 1200
22 32
23 mi100
24 48
25 1228.8
26 SQ|LDS_Per_Workgroup|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF
@@ -0,0 +1,7 @@
Metric,Value
valu_flops_pop,
mfma_flops_bf16_pop,
mfma_flops_f16_pop,
mfma_flops_f32_pop,
mfma_flops_f64_pop,
mfma_flops_i8_pop,
1 Metric Value
2 valu_flops_pop
3 mfma_flops_bf16_pop
4 mfma_flops_f16_pop
5 mfma_flops_f32_pop
6 mfma_flops_f64_pop
7 mfma_flops_i8_pop
@@ -0,0 +1,8 @@
Metric,Avg,Min,Max,Unit
IPC (Avg),0.6029909891401224,0.03271929093384457,1.4281498664831591,Instr/cycle
IPC (Issue),0.8437242643821745,0.5168951684473764,0.9995913989478523,Instr/cycle
SALU Util,2.098901705245223,0.02913096416663822,22.534990722482537,Pct
VALU Util,59.49293302260621,0.8593634429158274,99.12275297739212,Pct
VALU Active Threads,63.96757475781579,63.720123967221156,64.0,Threads
MFMA Util,,,,Pct
MFMA Instr Cycles,,,,Cycles/instr
1 Metric Avg Min Max Unit
2 IPC (Avg) 0.6029909891401224 0.03271929093384457 1.4281498664831591 Instr/cycle
3 IPC (Issue) 0.8437242643821745 0.5168951684473764 0.9995913989478523 Instr/cycle
4 SALU Util 2.098901705245223 0.02913096416663822 22.534990722482537 Pct
5 VALU Util 59.49293302260621 0.8593634429158274 99.12275297739212 Pct
6 VALU Active Threads 63.96757475781579 63.720123967221156 64.0 Threads
7 MFMA Util Pct
8 MFMA Instr Cycles Cycles/instr
@@ -0,0 +1,7 @@
Metric,Avg,Min,Max,Unit
FLOPs (Total),,,,Ops per wave
INT8 OPs,,,,Ops per wave
F16 OPs,,,,Ops per wave
BF16 OPs,,,,Ops per wave
F32 OPs,,,,Ops per wave
F64 OPs,,,,Ops per wave
1 Metric Avg Min Max Unit
2 FLOPs (Total) Ops per wave
3 INT8 OPs Ops per wave
4 F16 OPs Ops per wave
5 BF16 OPs Ops per wave
6 F32 OPs Ops per wave
7 F64 OPs Ops per wave
@@ -0,0 +1,5 @@
Metric,Value
Utilization,0.0
Access Rate,0.0
Bandwith (Pct-of-Peak),0.0
Bank Conflict Rate,
1 Metric Value
2 Utilization 0.0
3 Access Rate 0.0
4 Bandwith (Pct-of-Peak) 0.0
5 Bank Conflict Rate
@@ -0,0 +1,12 @@
Metric,Avg,Min,Max,Unit
Wave Cycles,33761.37244470105,2805.687400817871,547941.7736816406,Cycles/wave
LDS_Per_Workgroup Instrs,0.0,0.0,0.0,Instr per wave
Bandwidth,0.0,0.0,0.0,Bytes per wave
Bank Conficts/Access,,,,Conflicts/access
Dispatch_ID Accesses,0.0,0.0,0.0,Cycles per wave
Atomic Cycles,0.0,0.0,0.0,Cycles per wave
Bank Conflict,0.0,0.0,0.0,Cycles per wave
Addr Conflict,0.0,0.0,0.0,Cycles per wave
Unaligned Stall,0.0,0.0,0.0,Cycles per wave
Mem Violations,0.0,0.0,0.0, per wave
LDS_Per_Workgroup Latency,,,,Cycles
1 Metric Avg Min Max Unit
2 Wave Cycles 33761.37244470105 2805.687400817871 547941.7736816406 Cycles/wave
3 LDS_Per_Workgroup Instrs 0.0 0.0 0.0 Instr per wave
4 Bandwidth 0.0 0.0 0.0 Bytes per wave
5 Bank Conficts/Access Conflicts/access
6 Dispatch_ID Accesses 0.0 0.0 0.0 Cycles per wave
7 Atomic Cycles 0.0 0.0 0.0 Cycles per wave
8 Bank Conflict 0.0 0.0 0.0 Cycles per wave
9 Addr Conflict 0.0 0.0 0.0 Cycles per wave
10 Unaligned Stall 0.0 0.0 0.0 Cycles per wave
11 Mem Violations 0.0 0.0 0.0 per wave
12 LDS_Per_Workgroup Latency Cycles
@@ -0,0 +1,3 @@
Metric,Value
Bandwidth,30.541380839910357
Cache Hit,99.51595260335603
1 Metric Value
2 Bandwidth 30.541380839910357
3 Cache Hit 99.51595260335603
@@ -0,0 +1,6 @@
L1I Metric,Mean,Min,Max,Unit
Req,162.66467065868264,12.0,3215.0,Req per wave
Hits,162.47656599490227,11.996280670166016,3214.9824829101562,Hits per wave
Misses - Non Duplicated,0.0020694390028536676,0.00018310546875,0.09375,Misses per wave
Misses - Duplicated,0.29937503152264805,0.0039310455322265625,3.05078125,Misses per wave
Cache Hit,99.51595260335603,80.3466796875,99.99928381109659,Pct
1 L1I Metric Mean Min Max Unit
2 Req 162.66467065868264 12.0 3215.0 Req per wave
3 Hits 162.47656599490227 11.996280670166016 3214.9824829101562 Hits per wave
4 Misses - Non Duplicated 0.0020694390028536676 0.00018310546875 0.09375 Misses per wave
5 Misses - Duplicated 0.29937503152264805 0.0039310455322265625 3.05078125 Misses per wave
6 Cache Hit 99.51595260335603 80.3466796875 99.99928381109659 Pct
@@ -0,0 +1,3 @@
Metric,Value
Bandwidth,0.932716752528059
Cache Hit,98.02738263935386
1 Metric Value
2 Bandwidth 0.932716752528059
3 Cache Hit 98.02738263935386
@@ -0,0 +1,13 @@
Metric,Mean,Min,Max,Unit
Req,1.8083832335329342,1.0,8.0,Req per wave
Hits,1.779911361054746,0.0,7.991535186767578,Req per wave
Misses - Non Duplicated,0.0012866722609468563,0.000274658203125,0.09375,Req per wave
Misses- Duplicated,0.027185200217241298,0.008190155029296875,0.90625,Req per wave
Cache Hit,98.02738263935386,0.0,99.89418983459473,Pct
Read Req (Total),1.8083832335329342,1.0,8.0,Req per wave
Atomic Req,0.0,0.0,0.0,Req per wave
Read Req (1 DWord),0.5988023952095808,0.0,4.0,Req per wave
Read Req (2 DWord),1.0,0.0,2.0,Req per wave
Read Req (4 DWord),0.20958083832335328,0.0,3.0,Req per wave
Read Req (8 DWord),0.0,0.0,0.0,Req per wave
Read Req (16 DWord),0.0,0.0,0.0,Req per wave
1 Metric Mean Min Max Unit
2 Req 1.8083832335329342 1.0 8.0 Req per wave
3 Hits 1.779911361054746 0.0 7.991535186767578 Req per wave
4 Misses - Non Duplicated 0.0012866722609468563 0.000274658203125 0.09375 Req per wave
5 Misses- Duplicated 0.027185200217241298 0.008190155029296875 0.90625 Req per wave
6 Cache Hit 98.02738263935386 0.0 99.89418983459473 Pct
7 Read Req (Total) 1.8083832335329342 1.0 8.0 Req per wave
8 Atomic Req 0.0 0.0 0.0 Req per wave
9 Read Req (1 DWord) 0.5988023952095808 0.0 4.0 Req per wave
10 Read Req (2 DWord) 1.0 0.0 2.0 Req per wave
11 Read Req (4 DWord) 0.20958083832335328 0.0 3.0 Req per wave
12 Read Req (8 DWord) 0.0 0.0 0.0 Req per wave
13 Read Req (16 DWord) 0.0 0.0 0.0 Req per wave
@@ -0,0 +1,5 @@
Metric,Mean,Min,Max,Unit
Read Req,0.0012866722609468563,0.000274658203125,0.09375,Req per wave
Write Req,0.0,0.0,0.0,Req per wave
Atomic Req,0.0,0.0,0.0,Req per wave
Stall,0.0,0.0,0.0,Cycles per wave
1 Metric Mean Min Max Unit
2 Read Req 0.0012866722609468563 0.000274658203125 0.09375 Req per wave
3 Write Req 0.0 0.0 0.0 Req per wave
4 Atomic Req 0.0 0.0 0.0 Req per wave
5 Stall 0.0 0.0 0.0 Cycles per wave
@@ -0,0 +1,17 @@
Metric,Avg,Min,Max,Unit
TA Busy,58.81991196237737,2.2226216956269593,92.81644483413112,Pct
TC2TA Addr Stall,45.14015376424508,0.09798501454743884,82.04610020047697,Pct
TC2TA Data Stall,0.3703927017395877,0.0,61.855581190511145,Pct
TD2TA Addr Stall,0.0,0.0,0.0,Pct
Total Instructions,7.9640718562874255,2.0,8.0,Instr per wave
Flat Instr,7.9640718562874255,2.0,8.0,Instr per wave
Flat Read Instr,7.952095808383233,0.0,8.0,Instr per wave
Flat Write Instr,0.011976047904191617,0.0,2.0,Instr per wave
Flat Atomic Instr,0.0,0.0,0.0,Instr per wave
Buffer Instr,0.0,0.0,0.0,Instr per wave
Buffer Read Instr,0.0,0.0,0.0,Instr per wave
Buffer Write Instr,0.0,0.0,0.0,Instr per wave
Buffer Atomic Instr,0.0,0.0,0.0,Instr per wave
Buffer Total Cylces,0.0,0.0,0.0,Cycles per wave
Buffer Coalesced Read,0.0,0.0,0.0,Cycles per wave
Buffer Coalesced Write,0.0,0.0,0.0,Cycles per wave
1 Metric Avg Min Max Unit
2 TA Busy 58.81991196237737 2.2226216956269593 92.81644483413112 Pct
3 TC2TA Addr Stall 45.14015376424508 0.09798501454743884 82.04610020047697 Pct
4 TC2TA Data Stall 0.3703927017395877 0.0 61.855581190511145 Pct
5 TD2TA Addr Stall 0.0 0.0 0.0 Pct
6 Total Instructions 7.9640718562874255 2.0 8.0 Instr per wave
7 Flat Instr 7.9640718562874255 2.0 8.0 Instr per wave
8 Flat Read Instr 7.952095808383233 0.0 8.0 Instr per wave
9 Flat Write Instr 0.011976047904191617 0.0 2.0 Instr per wave
10 Flat Atomic Instr 0.0 0.0 0.0 Instr per wave
11 Buffer Instr 0.0 0.0 0.0 Instr per wave
12 Buffer Read Instr 0.0 0.0 0.0 Instr per wave
13 Buffer Write Instr 0.0 0.0 0.0 Instr per wave
14 Buffer Atomic Instr 0.0 0.0 0.0 Instr per wave
15 Buffer Total Cylces 0.0 0.0 0.0 Cycles per wave
16 Buffer Coalesced Read 0.0 0.0 0.0 Cycles per wave
17 Buffer Coalesced Write 0.0 0.0 0.0 Cycles per wave
@@ -0,0 +1,8 @@
Metric,Avg,Min,Max,Unit
TD Busy,74.57524258510159,16.500257891686957,93.34669784490931,Pct
TC2TD Stall,64.59357832904712,14.255763760232846,89.80822386127235,Pct
SPI2TD Stall,,,,Pct
Coalescable Instr,4.802395209580839,0.0,8.0,Instr per wave
Load Instr,7.952095808383233,0.0,8.0,Instr per wave
Store Instr,0.011976047904191617,0.0,2.0,Instr per wave
Atomic Instr,0.0,0.0,0.0,Instr per wave
1 Metric Avg Min Max Unit
2 TD Busy 74.57524258510159 16.500257891686957 93.34669784490931 Pct
3 TC2TD Stall 64.59357832904712 14.255763760232846 89.80822386127235 Pct
4 SPI2TD Stall Pct
5 Coalescable Instr 4.802395209580839 0.0 8.0 Instr per wave
6 Load Instr 7.952095808383233 0.0 8.0 Instr per wave
7 Store Instr 0.011976047904191617 0.0 2.0 Instr per wave
8 Atomic Instr 0.0 0.0 0.0 Instr per wave
@@ -0,0 +1,5 @@
Metric,Value
Buffer Coalescing,69.91017964071857
Cache Util,80.57693674800218
Cache BW,2.4338444285238587
Cache Hit,20.508982035928145
1 Metric Value
2 Buffer Coalescing 69.91017964071857
3 Cache Util 80.57693674800218
4 Cache BW 2.4338444285238587
5 Cache Hit 20.508982035928145
@@ -0,0 +1,6 @@
Metric,Mean,Min,Max,Unit
Stalled on L2 Data,61.281736847034324,13.856365328179427,85.69598377660014,Pct
Stalled on L2 Req,30.145402628072453,0.007227374234591863,69.6455646056741,Pct
Tag RAM Stall (Read),0.0,0.0,0.0,Pct
Tag RAM Stall (Write),0.0,0.0,0.0,Pct
Tag RAM Stall (Atomic),0.0,0.0,0.0,Pct
1 Metric Mean Min Max Unit
2 Stalled on L2 Data 61.281736847034324 13.856365328179427 85.69598377660014 Pct
3 Stalled on L2 Req 30.145402628072453 0.007227374234591863 69.6455646056741 Pct
4 Tag RAM Stall (Read) 0.0 0.0 0.0 Pct
5 Tag RAM Stall (Write) 0.0 0.0 0.0 Pct
6 Tag RAM Stall (Atomic) 0.0 0.0 0.0 Pct
@@ -0,0 +1,15 @@
Metric,Avg,Min,Max,Unit
Total Req,279.76047904191614,128.0,512.0,Req per wave
Read Req,278.9940119760479,0.0,512.0,Req per wave
Write Req,0.7664670658682635,0.0,128.0,Req per wave
Atomic Req,0.0,0.0,0.0,Req per wave
Cache Accesses,70.13173652694611,32.0,128.0,Req per wave
Cache Hits,25.676646706586826,0.0,64.0,Req per wave
Cache Hit Rate,20.508982035928145,0.0,75.0,Pct
Invalidate,0.009641818657606662,0.0006866455078125,0.703125, per wave
L1-TCR Read,44.35928143712575,0.0,64.0,Req per wave
L1-L2 Write,0.09580838323353294,0.0,16.0,Req per wave
L1-L2 Atomic,0.0,0.0,0.0,Req per wave
L1 Access Latency,1501.1507881130287,405.978723526001,2918.2216796875,Cycles
L1-L2 Read Latency,732.4865848917559,350.19577717781067,2094.9354248046875,Cycles
L1-L2 Write Latency,332.24009692668915,332.24009692668915,332.24009692668915,Cycles
1 Metric Avg Min Max Unit
2 Total Req 279.76047904191614 128.0 512.0 Req per wave
3 Read Req 278.9940119760479 0.0 512.0 Req per wave
4 Write Req 0.7664670658682635 0.0 128.0 Req per wave
5 Atomic Req 0.0 0.0 0.0 Req per wave
6 Cache Accesses 70.13173652694611 32.0 128.0 Req per wave
7 Cache Hits 25.676646706586826 0.0 64.0 Req per wave
8 Cache Hit Rate 20.508982035928145 0.0 75.0 Pct
9 Invalidate 0.009641818657606662 0.0006866455078125 0.703125 per wave
10 L1-TCR Read 44.35928143712575 0.0 64.0 Req per wave
11 L1-L2 Write 0.09580838323353294 0.0 16.0 Req per wave
12 L1-L2 Atomic 0.0 0.0 0.0 Req per wave
13 L1 Access Latency 1501.1507881130287 405.978723526001 2918.2216796875 Cycles
14 L1-L2 Read Latency 732.4865848917559 350.19577717781067 2094.9354248046875 Cycles
15 L1-L2 Write Latency 332.24009692668915 332.24009692668915 332.24009692668915 Cycles
@@ -0,0 +1,13 @@
Xfer,Mean,Min,Max,Unit
NC - Read,0.0,0.0,0.0,Req per wave
UC - Read,0.0,0.0,0.0,Req per wave
CC - Read,0.0,0.0,0.0,Req per wave
RW - Read,44.35928143712575,0.0,64.0,Req per wave
RW - Write,0.09580838323353294,0.0,16.0,Req per wave
NC - Write,0.0,0.0,0.0,Req per wave
UC - Write,0.0,0.0,0.0,Req per wave
CC - Write,0.0,0.0,0.0,Req per wave
NC - Atomic,0.0,0.0,0.0,Req per wave
UC - Atomic,0.0,0.0,0.0,Req per wave
CC - Atomic,0.0,0.0,0.0,Req per wave
RW - Atomic,0.0,0.0,0.0,Req per wave
1 Xfer Mean Min Max Unit
2 NC - Read 0.0 0.0 0.0 Req per wave
3 UC - Read 0.0 0.0 0.0 Req per wave
4 CC - Read 0.0 0.0 0.0 Req per wave
5 RW - Read 44.35928143712575 0.0 64.0 Req per wave
6 RW - Write 0.09580838323353294 0.0 16.0 Req per wave
7 NC - Write 0.0 0.0 0.0 Req per wave
8 UC - Write 0.0 0.0 0.0 Req per wave
9 CC - Write 0.0 0.0 0.0 Req per wave
10 NC - Atomic 0.0 0.0 0.0 Req per wave
11 UC - Atomic 0.0 0.0 0.0 Req per wave
12 CC - Atomic 0.0 0.0 0.0 Req per wave
13 RW - Atomic 0.0 0.0 0.0 Req per wave
@@ -0,0 +1,6 @@
Metric,Mean,Min,Max,Units
Req,69.94011976047904,32.0,128.0, per wave
Hit Ratio,97.72816971390547,91.943359375,98.99584650993347,Pct
Hits,68.50638670550136,29.421875,125.928466796875, per wave
Misses (Translation),0.159064892523303,0.029230117797851562,0.234375, per wave
Misses (Permission),0.0,0.0,0.0, per wave
1 Metric Mean Min Max Units
2 Req 69.94011976047904 32.0 128.0 per wave
3 Hit Ratio 97.72816971390547 91.943359375 98.99584650993347 Pct
4 Hits 68.50638670550136 29.421875 125.928466796875 per wave
5 Misses (Translation) 0.159064892523303 0.029230117797851562 0.234375 per wave
6 Misses (Permission) 0.0 0.0 0.0 per wave
@@ -0,0 +1,5 @@
Metric,Value,Unit
L2 Util,87.66189628706876,Pct
Cache Hit,0.39296569201373344,Pct
L2-EA Rd BW,837.087019227418,Gb/s
L2-EA Wr BW,4.9809517205699905,Gb/s
1 Metric Value Unit
2 L2 Util 87.66189628706876 Pct
3 Cache Hit 0.39296569201373344 Pct
4 L2-EA Rd BW 837.087019227418 Gb/s
5 L2-EA Wr BW 4.9809517205699905 Gb/s
@@ -0,0 +1,16 @@
Metric,Avg,Min,Max,Unit
Read BW,2840.754344095013,1.3084716796875,4099.3017578125,Bytes per wave
Write BW,3.0659442833083834,0.0,512.0126953125,Bytes per wave
Read (32B),0.0,0.0,0.0,Req per wave
Read (Uncached 32B),0.053744881452914485,0.0125732421875,0.85546875,Req per wave
Read (64B),44.38678662648458,0.020444869995117188,64.05158996582031,Req per wave
HBM Read,44.38823577743804,0.019823074340820312,64.06573486328125,Req per wave
Write (32B),0.0,0.0,0.0,Req per wave
Write (Uncached 32B),0.0,0.0,0.0,Req per wave
Write (64B),0.04790537942669349,0.0,8.000198364257812,Req per wave
HBM Write,0.04790520810795401,0.0,8.00016975402832,Req per wave
Read Latency,443.50771438331117,239.75638239245325,1160.805485586342,Cycles
Write Latency,145.00192732800434,145.00192732800434,145.00192732800434,Cycles
Atomic Latency,,,,Cycles
Read Stall,5.375855050041276,0.0,16.215760989060865,Pct
Write Stall,0.008312090415207715,0.0,1.3881190993396884,Pct
1 Metric Avg Min Max Unit
2 Read BW 2840.754344095013 1.3084716796875 4099.3017578125 Bytes per wave
3 Write BW 3.0659442833083834 0.0 512.0126953125 Bytes per wave
4 Read (32B) 0.0 0.0 0.0 Req per wave
5 Read (Uncached 32B) 0.053744881452914485 0.0125732421875 0.85546875 Req per wave
6 Read (64B) 44.38678662648458 0.020444869995117188 64.05158996582031 Req per wave
7 HBM Read 44.38823577743804 0.019823074340820312 64.06573486328125 Req per wave
8 Write (32B) 0.0 0.0 0.0 Req per wave
9 Write (Uncached 32B) 0.0 0.0 0.0 Req per wave
10 Write (64B) 0.04790537942669349 0.0 8.000198364257812 Req per wave
11 HBM Write 0.04790520810795401 0.0 8.00016975402832 Req per wave
12 Read Latency 443.50771438331117 239.75638239245325 1160.805485586342 Cycles
13 Write Latency 145.00192732800434 145.00192732800434 145.00192732800434 Cycles
14 Atomic Latency Cycles
15 Read Stall 5.375855050041276 0.0 16.215760989060865 Pct
16 Write Stall 0.008312090415207715 0.0 1.3881190993396884 Pct
@@ -0,0 +1,19 @@
Metric,Avg,Min,Max,Unit
Req,44.5101472888878,16.021303176879883,64.09040832519531,Req per wave
Streaming Req,0.0,0.0,0.0,Req per wave
Read Req,44.419850286609396,0.02136993408203125,64.08892822265625,Req per wave
Write Req,0.09580838323353294,0.0,16.0,Req per wave
Atomic Req,0.0,0.0,0.0,Req per wave
Probe Req,0.0,0.0,0.0,Req per wave
Hits,0.0776433773383409,0.0064544677734375,8.00080680847168,Hits per wave
Misses,44.43250391154946,8.020496368408203,64.06112670898438,Misses per wave
Cache Hit,0.39296569201373344,0.010079830830413637,49.93855194012889,Pct
Writeback,0.048734950448224644,0.0004730224609375,8.000141143798828, per wave
NC Req,0.0012861240409805389,0.00018310546875,0.09375,Req per wave
UC Req,0.028315424205300338,0.0058135986328125,0.4296875,Req per wave
CC Req,0.0,0.0,0.0,Req per wave
RW Req,44.48417563067225,16.000640869140625,64.076904296875,Req per wave
Writeback (Normal),0.04715657948019976,0.0,7.875148773193359, per wave
Writeback (TC Req),0.0007484801515133795,0.0,0.12499618530273438, per wave
Evict (Normal),42.33439600824596,0.0,62.00164794921875, per wave
Evict (TC Req),0.0,0.0,0.0, per wave
1 Metric Avg Min Max Unit
2 Req 44.5101472888878 16.021303176879883 64.09040832519531 Req per wave
3 Streaming Req 0.0 0.0 0.0 Req per wave
4 Read Req 44.419850286609396 0.02136993408203125 64.08892822265625 Req per wave
5 Write Req 0.09580838323353294 0.0 16.0 Req per wave
6 Atomic Req 0.0 0.0 0.0 Req per wave
7 Probe Req 0.0 0.0 0.0 Req per wave
8 Hits 0.0776433773383409 0.0064544677734375 8.00080680847168 Hits per wave
9 Misses 44.43250391154946 8.020496368408203 64.06112670898438 Misses per wave
10 Cache Hit 0.39296569201373344 0.010079830830413637 49.93855194012889 Pct
11 Writeback 0.048734950448224644 0.0004730224609375 8.000141143798828 per wave
12 NC Req 0.0012861240409805389 0.00018310546875 0.09375 Req per wave
13 UC Req 0.028315424205300338 0.0058135986328125 0.4296875 Req per wave
14 CC Req 0.0 0.0 0.0 Req per wave
15 RW Req 44.48417563067225 16.000640869140625 64.076904296875 Req per wave
16 Writeback (Normal) 0.04715657948019976 0.0 7.875148773193359 per wave
17 Writeback (TC Req) 0.0007484801515133795 0.0 0.12499618530273438 per wave
18 Evict (Normal) 42.33439600824596 0.0 62.00164794921875 per wave
19 Evict (TC Req) 0.0 0.0 0.0 per wave
@@ -0,0 +1,8 @@
Metric,Avg,Min,Max,Unit
Read - Remote Socket Stall,0.0,0.0,0.0,Req per wave
Read - Peer GCD Stall,0.0,0.0,0.0,Req per wave
Read - HBM Stall,6.995750016081119,0.0,26.757217407226562,Req per wave
Write - Remote Socket Stall,0.0,0.0,0.0,Req per wave
Write - Peer GCD Stall,0.0,0.0,0.0,Req per wave
Write - HBM Stall,0.0024245256435371444,0.0,0.4048957824707031,Req per wave
Write - Credit Starvation,0.0,0.0,0.0,Req per wave
1 Metric Avg Min Max Unit
2 Read - Remote Socket Stall 0.0 0.0 0.0 Req per wave
3 Read - Peer GCD Stall 0.0 0.0 0.0 Req per wave
4 Read - HBM Stall 6.995750016081119 0.0 26.757217407226562 Req per wave
5 Write - Remote Socket Stall 0.0 0.0 0.0 Req per wave
6 Write - Peer GCD Stall 0.0 0.0 0.0 Req per wave
7 Write - HBM Stall 0.0024245256435371444 0.0 0.4048957824707031 Req per wave
8 Write - Credit Starvation 0.0 0.0 0.0 Req per wave
@@ -0,0 +1,17 @@
Channel,Hit Rate,Req,Read Req,Write Req,AtomicReq,EA Read Req,EA Write Req,EA AtomicReq,EA Read Lat - cycles,EA Write Lat - cycles,EA Atomic Lat - cycles,EA Read Stall - IO,EA Read Stall - GMI,EA Read Stall - DRAM,EA Write Stall - IO,EA Write Stall - GMI,EA Write Stall - DRAM,EA Write Stall - Starve
0,0.3597037180413185,1.3912614833808945,1.3882674714048466,0.0029940119760479044,0.0,1.3875288363702283,0.0014970059880239522,0.0,433.1151544686359,130.97077178955078,,0.0,0.0,0.1431858268326628,0.0,0.0,8.497409477919161e-06,0.0
1,0.3655668003446464,1.389973714680015,1.386979702703967,0.0029940119760479044,0.0,1.3862432491279648,0.0014970059880239522,0.0,430.18821295592284,132.2540512084961,,0.0,0.0,0.13643687356731848,0.0,0.0,9.057050693534805e-06,0.0
2,0.3567994395856584,1.3899671588829177,1.3869731469068698,0.0029940119760479044,0.0,1.3862430778092254,0.0014970059880239522,0.0,430.35838280864215,134.1629867553711,,0.0,0.0,0.13642581779799776,0.0,0.0,1.0027856883888473e-05,0.0
3,0.3603322926988777,1.3928740267268198,1.389880014750772,0.0029940119760479044,0.0,1.387237480300629,0.0014970059880239522,0.0,434.46995833702056,130.60980987548828,,0.0,0.0,0.22032211212340944,0.0,0.0,8.485988228620883e-06,0.0
4,0.3565355609725706,1.3899764557798466,1.3869824438037988,0.0029940119760479044,0.0,1.386243260549214,0.0014970059880239522,0.0,427.24068435459554,132.79178619384766,,0.0,0.0,0.1759821726176553,0.0,0.0,9.38826692318488e-06,0.0
5,0.36279067181399044,1.3899759075598803,1.3869818955838322,0.0029940119760479044,0.0,1.386243260549214,0.0014970059880239522,0.0,448.23836396226574,131.89773559570312,,0.0,0.0,0.1682660679617328,0.0,0.0,1.2997381701440869e-05,0.0
6,0.3589398273883731,1.3899715218001496,1.3869775098241017,0.0029940119760479044,0.0,1.3862431691792196,0.0014970516730211452,0.0,439.02631883446935,140.33766669718332,,0.0,0.0,0.1516769317809693,0.0,0.0,9.216948183710704e-06,0.0
7,0.35672636620615517,1.401587046548992,1.398593034572944,0.0029940119760479044,0.0,1.386243260549214,0.0014970059880239522,0.0,452.9829005526777,240.68163299560547,,0.0,0.0,0.17272400998783682,0.0,0.0,0.0005770471995462201,0.0
8,0.3568021945790094,1.3899759075598803,1.3869818955838322,0.0029940119760479044,0.0,1.3891702069493825,0.0014970059880239522,0.0,410.0509537505996,131.6666717529297,,0.0,0.0,0.1799614272431699,0.0,0.0,8.64588571879678e-06,0.0
9,0.3604368304672359,1.3899715218001496,1.3869775098241017,0.0029940119760479044,0.0,1.3862431691792196,0.0014970059880239522,0.0,423.39921167626255,132.22219848632812,,0.0,0.0,0.16428114839656624,0.0,0.0,1.854810886040419e-05,0.0
10,0.35658626900038287,1.389971990071371,1.386977978095323,0.0029940119760479044,0.0,1.3862426209592533,0.0014970059880239522,0.0,455.4110329104956,131.52307891845703,,0.0,0.0,0.14508732778583458,0.0,0.0,8.851468206165794e-06,0.0
11,0.35763606018982164,1.3910740606799097,1.3880800487038618,0.0029940119760479044,0.0,1.3862430778092254,0.0014970516730211452,0.0,445.53680510761313,226.10250541670482,,0.0,0.0,0.16984238310488398,0.0,0.0,0.0005420639129455932,0.0
12,0.3595841527203406,1.3900158476686764,1.3870218356926285,0.0029940119760479044,0.0,1.3862435346591973,0.0014971087792676366,0.0,441.98445960159205,132.83021185373929,,0.0,0.0,0.12440125242678705,0.0,0.0,8.760098211779566e-06,0.0
13,0.3640730353860431,1.3899715218001496,1.3869775098241017,0.0029940119760479044,0.0,1.3875287450002338,0.0014970516730211452,0.0,440.3003910703902,132.3393298544356,,0.0,0.0,0.11938175041518526,0.0,0.0,1.753161767285741e-05,0.0
14,0.6082974782277631,1.3922082592627245,1.3892142472866766,0.0029940119760479044,0.0,1.3862897678763566,0.0014970973580183383,0.0,431.4932858516832,140.78315532499238,,0.0,0.0,0.1776395329458271,0.0,0.0,1.4116664132672156e-05,0.0
15,0.36000958471288586,1.389967136040419,1.3869731240643712,0.0029940119760479044,0.0,1.3974210659186996,0.0014970059880239522,0.0,437.0384182903367,141.9864730834961,,0.0,0.0,0.8352936156495603,0.0,0.0,1.6423756490924402e-05,0.0
1 Channel Hit Rate Req Read Req Write Req AtomicReq EA Read Req EA Write Req EA AtomicReq EA Read Lat - cycles EA Write Lat - cycles EA Atomic Lat - cycles EA Read Stall - IO EA Read Stall - GMI EA Read Stall - DRAM EA Write Stall - IO EA Write Stall - GMI EA Write Stall - DRAM EA Write Stall - Starve
2 0 0.3597037180413185 1.3912614833808945 1.3882674714048466 0.0029940119760479044 0.0 1.3875288363702283 0.0014970059880239522 0.0 433.1151544686359 130.97077178955078 0.0 0.0 0.1431858268326628 0.0 0.0 8.497409477919161e-06 0.0
3 1 0.3655668003446464 1.389973714680015 1.386979702703967 0.0029940119760479044 0.0 1.3862432491279648 0.0014970059880239522 0.0 430.18821295592284 132.2540512084961 0.0 0.0 0.13643687356731848 0.0 0.0 9.057050693534805e-06 0.0
4 2 0.3567994395856584 1.3899671588829177 1.3869731469068698 0.0029940119760479044 0.0 1.3862430778092254 0.0014970059880239522 0.0 430.35838280864215 134.1629867553711 0.0 0.0 0.13642581779799776 0.0 0.0 1.0027856883888473e-05 0.0
5 3 0.3603322926988777 1.3928740267268198 1.389880014750772 0.0029940119760479044 0.0 1.387237480300629 0.0014970059880239522 0.0 434.46995833702056 130.60980987548828 0.0 0.0 0.22032211212340944 0.0 0.0 8.485988228620883e-06 0.0
6 4 0.3565355609725706 1.3899764557798466 1.3869824438037988 0.0029940119760479044 0.0 1.386243260549214 0.0014970059880239522 0.0 427.24068435459554 132.79178619384766 0.0 0.0 0.1759821726176553 0.0 0.0 9.38826692318488e-06 0.0
7 5 0.36279067181399044 1.3899759075598803 1.3869818955838322 0.0029940119760479044 0.0 1.386243260549214 0.0014970059880239522 0.0 448.23836396226574 131.89773559570312 0.0 0.0 0.1682660679617328 0.0 0.0 1.2997381701440869e-05 0.0
8 6 0.3589398273883731 1.3899715218001496 1.3869775098241017 0.0029940119760479044 0.0 1.3862431691792196 0.0014970516730211452 0.0 439.02631883446935 140.33766669718332 0.0 0.0 0.1516769317809693 0.0 0.0 9.216948183710704e-06 0.0
9 7 0.35672636620615517 1.401587046548992 1.398593034572944 0.0029940119760479044 0.0 1.386243260549214 0.0014970059880239522 0.0 452.9829005526777 240.68163299560547 0.0 0.0 0.17272400998783682 0.0 0.0 0.0005770471995462201 0.0
10 8 0.3568021945790094 1.3899759075598803 1.3869818955838322 0.0029940119760479044 0.0 1.3891702069493825 0.0014970059880239522 0.0 410.0509537505996 131.6666717529297 0.0 0.0 0.1799614272431699 0.0 0.0 8.64588571879678e-06 0.0
11 9 0.3604368304672359 1.3899715218001496 1.3869775098241017 0.0029940119760479044 0.0 1.3862431691792196 0.0014970059880239522 0.0 423.39921167626255 132.22219848632812 0.0 0.0 0.16428114839656624 0.0 0.0 1.854810886040419e-05 0.0
12 10 0.35658626900038287 1.389971990071371 1.386977978095323 0.0029940119760479044 0.0 1.3862426209592533 0.0014970059880239522 0.0 455.4110329104956 131.52307891845703 0.0 0.0 0.14508732778583458 0.0 0.0 8.851468206165794e-06 0.0
13 11 0.35763606018982164 1.3910740606799097 1.3880800487038618 0.0029940119760479044 0.0 1.3862430778092254 0.0014970516730211452 0.0 445.53680510761313 226.10250541670482 0.0 0.0 0.16984238310488398 0.0 0.0 0.0005420639129455932 0.0
14 12 0.3595841527203406 1.3900158476686764 1.3870218356926285 0.0029940119760479044 0.0 1.3862435346591973 0.0014971087792676366 0.0 441.98445960159205 132.83021185373929 0.0 0.0 0.12440125242678705 0.0 0.0 8.760098211779566e-06 0.0
15 13 0.3640730353860431 1.3899715218001496 1.3869775098241017 0.0029940119760479044 0.0 1.3875287450002338 0.0014970516730211452 0.0 440.3003910703902 132.3393298544356 0.0 0.0 0.11938175041518526 0.0 0.0 1.753161767285741e-05 0.0
16 14 0.6082974782277631 1.3922082592627245 1.3892142472866766 0.0029940119760479044 0.0 1.3862897678763566 0.0014970973580183383 0.0 431.4932858516832 140.78315532499238 0.0 0.0 0.1776395329458271 0.0 0.0 1.4116664132672156e-05 0.0
17 15 0.36000958471288586 1.389967136040419 1.3869731240643712 0.0029940119760479044 0.0 1.3974210659186996 0.0014970059880239522 0.0 437.0384182903367 141.9864730834961 0.0 0.0 0.8352936156495603 0.0 0.0 1.6423756490924402e-05 0.0
@@ -0,0 +1,17 @@
Channel,Hit Rate,Req,Read Req,Write Req,AtomicReq,EA Read Req,EA Write Req,EA AtomicReq,EA Read Lat - cycles,EA Write Lat - cycles,EA Atomic Lat - cycles,EA Read Stall - IO,EA Read Stall - GMI,EA Read Stall - DRAM,EA Write Stall - IO,EA Write Stall - GMI,EA Write Stall - DRAM,EA Write Stall - Starve
16,0.36129577393177476,1.390037776467329,1.3870437644912812,0.0029940119760479044,0.0,1.3862707743387737,0.0014970059880239522,0.0,19295.208471607406,129.39098358154297,,0.0,0.0,0.13155908641700972,0.0,0.0,9.696640654238398e-06,0.0
17,0.3670100813688908,1.3899731664600488,1.3869791544840007,0.0029940119760479044,0.0,1.3862432034429675,0.0014970059880239522,0.0,436.8734374571566,127.18833923339844,,0.0,0.0,0.13534052500467814,0.0,0.0,1.1341300553190493e-05,0.0
18,0.608297478227763,1.3922082592627245,1.3892142472866766,0.0029940119760479044,0.0,1.3863165507059612,0.0014970973580183383,0.0,426.6642619888519,132.23951022276472,,0.0,0.0,0.15872164971814184,0.0,0.0,1.3088751695827095e-05,0.0
19,0.35958077370786723,1.3899583645209581,1.3869643525449102,0.0029940119760479044,0.0,1.3981898530514654,0.0014970059880239522,0.0,434.205416441725,129.4867706298828,,0.0,0.0,0.6129189679722586,0.0,0.0,1.694913395864521e-05,0.0
20,0.3570187143809455,1.3899802933196108,1.386986281343563,0.0029940119760479044,0.0,1.3862433519192086,0.0014970516730211452,0.0,436.3546912065439,132.9824910738808,,0.0,0.0,0.15584175886508234,0.0,0.0,1.239205548863211e-05,0.0
21,0.36364641610907317,1.3899890648390718,1.386995052863024,0.0029940119760479044,0.0,1.3862435346591973,0.0014970059880239522,0.0,435.0955386447166,132.51148223876953,,0.0,0.0,0.15291472109491955,0.0,0.0,1.4562092855305016e-05,0.0
22,0.5089989205486418,1.391265869140625,1.3882718571645771,0.0029940119760479044,0.0,1.3862433519192086,0.0014970516730211452,0.0,546.5651355463219,139.98441362263114,,0.0,0.0,0.15386113149677208,0.0,0.0,1.5098891572324102e-05,0.0
23,0.36006211284147027,1.3899764557798466,1.3869824438037988,0.0029940119760479044,0.0,1.3862432719704634,0.0014970516730211452,0.0,473.7518057339894,141.2401202355885,,0.0,0.0,0.1502354787495322,0.0,0.0,1.613822525846744e-05,0.0
24,0.35637714141192556,1.389967136040419,1.3869731240643712,0.0029940119760479044,0.0,1.3862430778092254,0.0014970973580183383,0.0,432.46204587828595,127.7646551724138,,0.0,0.0,0.127010139876497,0.0,0.0,9.034208194938249e-06,0.0
25,0.36076514135868903,1.3912663374118461,1.3882723254357983,0.0029940119760479044,0.0,1.3862428036992422,0.0014970059880239522,0.0,441.5601837265902,128.66181182861328,,0.0,0.0,0.13789650922763846,0.0,0.0,1.1752465527928518e-05,0.0
26,0.35616109237090826,1.3899539787612276,1.3869599667851797,0.0029940119760479044,0.0,1.3862428036992422,0.0014970516730211452,0.0,434.1555537390461,132.328748207147,,0.0,0.0,0.13790409293717254,0.0,0.0,1.429940412144461e-05,0.0
27,0.35549774414245916,1.3914206270686167,1.3884266150925688,0.0029940119760479044,0.0,1.3862697692688353,0.0014970059880239522,0.0,436.5550572295896,230.33299255371094,,0.0,0.0,0.1439780960539858,0.0,0.0,0.0005386603806547063,0.0
28,0.36065695238662526,1.390006607877994,1.3870125959019461,0.0029940119760479044,0.0,1.3862439001391749,0.0014970059880239522,0.0,449.0258396422935,132.6700668334961,,0.0,0.0,0.1758580921652788,0.0,0.0,1.2083681757578593e-05,0.0
29,0.3640717800237613,1.3899802933196108,1.386986281343563,0.0029940119760479044,0.0,1.3862433519192086,0.0014970516730211452,0.0,448.2916171462928,132.42044310171198,,0.0,0.0,0.16029047252175338,0.0,0.0,9.46821566827283e-06,0.0
30,0.4495938970351085,1.390519741766467,1.387525729790419,0.0029940119760479044,0.0,1.3862813732581225,0.0014970059880239522,0.0,430.260458105258,141.56510162353516,,0.0,0.0,0.16309032325973055,0.0,0.0,1.5247367813201722e-05,0.0
31,0.3569733773132006,1.4027545609160097,1.3997605489399618,0.0029940119760479044,0.0,1.3872548291783133,0.0014970059880239522,0.0,439.95535540761296,236.20612335205078,,0.0,0.0,0.20910763312242703,0.0,0.0,0.0005460727714492889,0.0
1 Channel Hit Rate Req Read Req Write Req AtomicReq EA Read Req EA Write Req EA AtomicReq EA Read Lat - cycles EA Write Lat - cycles EA Atomic Lat - cycles EA Read Stall - IO EA Read Stall - GMI EA Read Stall - DRAM EA Write Stall - IO EA Write Stall - GMI EA Write Stall - DRAM EA Write Stall - Starve
2 16 0.36129577393177476 1.390037776467329 1.3870437644912812 0.0029940119760479044 0.0 1.3862707743387737 0.0014970059880239522 0.0 19295.208471607406 129.39098358154297 0.0 0.0 0.13155908641700972 0.0 0.0 9.696640654238398e-06 0.0
3 17 0.3670100813688908 1.3899731664600488 1.3869791544840007 0.0029940119760479044 0.0 1.3862432034429675 0.0014970059880239522 0.0 436.8734374571566 127.18833923339844 0.0 0.0 0.13534052500467814 0.0 0.0 1.1341300553190493e-05 0.0
4 18 0.608297478227763 1.3922082592627245 1.3892142472866766 0.0029940119760479044 0.0 1.3863165507059612 0.0014970973580183383 0.0 426.6642619888519 132.23951022276472 0.0 0.0 0.15872164971814184 0.0 0.0 1.3088751695827095e-05 0.0
5 19 0.35958077370786723 1.3899583645209581 1.3869643525449102 0.0029940119760479044 0.0 1.3981898530514654 0.0014970059880239522 0.0 434.205416441725 129.4867706298828 0.0 0.0 0.6129189679722586 0.0 0.0 1.694913395864521e-05 0.0
6 20 0.3570187143809455 1.3899802933196108 1.386986281343563 0.0029940119760479044 0.0 1.3862433519192086 0.0014970516730211452 0.0 436.3546912065439 132.9824910738808 0.0 0.0 0.15584175886508234 0.0 0.0 1.239205548863211e-05 0.0
7 21 0.36364641610907317 1.3899890648390718 1.386995052863024 0.0029940119760479044 0.0 1.3862435346591973 0.0014970059880239522 0.0 435.0955386447166 132.51148223876953 0.0 0.0 0.15291472109491955 0.0 0.0 1.4562092855305016e-05 0.0
8 22 0.5089989205486418 1.391265869140625 1.3882718571645771 0.0029940119760479044 0.0 1.3862433519192086 0.0014970516730211452 0.0 546.5651355463219 139.98441362263114 0.0 0.0 0.15386113149677208 0.0 0.0 1.5098891572324102e-05 0.0
9 23 0.36006211284147027 1.3899764557798466 1.3869824438037988 0.0029940119760479044 0.0 1.3862432719704634 0.0014970516730211452 0.0 473.7518057339894 141.2401202355885 0.0 0.0 0.1502354787495322 0.0 0.0 1.613822525846744e-05 0.0
10 24 0.35637714141192556 1.389967136040419 1.3869731240643712 0.0029940119760479044 0.0 1.3862430778092254 0.0014970973580183383 0.0 432.46204587828595 127.7646551724138 0.0 0.0 0.127010139876497 0.0 0.0 9.034208194938249e-06 0.0
11 25 0.36076514135868903 1.3912663374118461 1.3882723254357983 0.0029940119760479044 0.0 1.3862428036992422 0.0014970059880239522 0.0 441.5601837265902 128.66181182861328 0.0 0.0 0.13789650922763846 0.0 0.0 1.1752465527928518e-05 0.0
12 26 0.35616109237090826 1.3899539787612276 1.3869599667851797 0.0029940119760479044 0.0 1.3862428036992422 0.0014970516730211452 0.0 434.1555537390461 132.328748207147 0.0 0.0 0.13790409293717254 0.0 0.0 1.429940412144461e-05 0.0
13 27 0.35549774414245916 1.3914206270686167 1.3884266150925688 0.0029940119760479044 0.0 1.3862697692688353 0.0014970059880239522 0.0 436.5550572295896 230.33299255371094 0.0 0.0 0.1439780960539858 0.0 0.0 0.0005386603806547063 0.0
14 28 0.36065695238662526 1.390006607877994 1.3870125959019461 0.0029940119760479044 0.0 1.3862439001391749 0.0014970059880239522 0.0 449.0258396422935 132.6700668334961 0.0 0.0 0.1758580921652788 0.0 0.0 1.2083681757578593e-05 0.0
15 29 0.3640717800237613 1.3899802933196108 1.386986281343563 0.0029940119760479044 0.0 1.3862433519192086 0.0014970516730211452 0.0 448.2916171462928 132.42044310171198 0.0 0.0 0.16029047252175338 0.0 0.0 9.46821566827283e-06 0.0
16 30 0.4495938970351085 1.390519741766467 1.387525729790419 0.0029940119760479044 0.0 1.3862813732581225 0.0014970059880239522 0.0 430.260458105258 141.56510162353516 0.0 0.0 0.16309032325973055 0.0 0.0 1.5247367813201722e-05 0.0
17 31 0.3569733773132006 1.4027545609160097 1.3997605489399618 0.0029940119760479044 0.0 1.3872548291783133 0.0014970059880239522 0.0 439.95535540761296 236.20612335205078 0.0 0.0 0.20910763312242703 0.0 0.0 0.0005460727714492889 0.0
@@ -0,0 +1,55 @@
Metric,Value,Alias
Wave Life,33761.0,wave_life_
Active CUs,95/120,active_cu_
SALU,47.0,salu_
SMEM,2.0,smem_
VALU,735.0,valu_
MFMA,,mfma_
VMEM,8.0,vmem_
LDS_Per_Workgroup,0.0,lds_
GWS,0.0,gws_
BR,22.0,br_
VGPR,24.0,vgpr_
SGPR,24.0,sgpr_
LDS_Per_Workgroup Allocation,0.0,lds_alloc_
Scratch Allocation,0.0,scratch_alloc_
Wavefronts,67894.0,wavefronts_
Workgroups,16973.0,workgroups_
LDS_Per_Workgroup Req,0.0,lds_req_
IL1 Fetch,163.0,il1_fetch_
IL1 Hit,100.0,il1_hit_
IL1_L2 Rd,0.0,il1_l2_req_
vL1D Rd,2.0,sl1_rd_
vL1D Hit,98.0,sl1_hit_
vL1D_L2 Rd,0.0,sl1_l2_rd_
vL1D_L2 Wr,0.0,sl1_l2_wr_
vL1D_L2 Atomic,0.0,sl1_l2_atom_
VL1 Rd,279.0,vl1_rd_
VL1 Wr,1.0,vl1_wr_
VL1 Atomic,0.0,vl1_atom_
VL1 Hit,21.0,vl1_hit_
VL1 Lat,1501.0,vl1_lat_
VL1_L2 Rd,44.0,vl1_l2_rd_
VL1_L2 Wr,0.0,vl1_l2_wr_
vL1_L2 Atomic,0.0,vl1_l2_atom_
L2 Rd,44.0,l2_rd_
L2 Wr,0.0,l2_wr_
L2 Atomic,0.0,l2_atom_
L2 Hit,0.0,l2_hit_
L2 Rd Lat,732.0,l2_rd_lat_
L2 Wr Lat,332.0,l2_wr_lat_
Fabric Rd Lat,444.0,fabric_rd_lat_
Fabric Wr Lat,145.0,fabric_wr_lat_
Fabric Atomic Lat,,fabric_atom_lat_
Fabric_L2 Rd,44.0,l2_fabric_rd_
Fabric_L2 Wr,0.0,l2_fabric_wr_
Fabric_l2 Atomic,0.0,l2_fabric_atom_
HBM Rd,44.0,hbm_rd_
HBM Wr,0.0,hbm_wr_
LDS_Per_Workgroup Util,0.0,lds_util_
VL1 Coalesce,70.0,vl1_coales_
VL1 Stall,30.0,vl1_stall_
LDS_Per_Workgroup Lat,,lds_lat_
vL1D Lat,,sl1_lat_
IL1 Lat,,il1_lat_
Wave Occupancy,34.0,wave_occ_
1 Metric Value Alias
2 Wave Life 33761.0 wave_life_
3 Active CUs 95/120 active_cu_
4 SALU 47.0 salu_
5 SMEM 2.0 smem_
6 VALU 735.0 valu_
7 MFMA mfma_
8 VMEM 8.0 vmem_
9 LDS_Per_Workgroup 0.0 lds_
10 GWS 0.0 gws_
11 BR 22.0 br_
12 VGPR 24.0 vgpr_
13 SGPR 24.0 sgpr_
14 LDS_Per_Workgroup Allocation 0.0 lds_alloc_
15 Scratch Allocation 0.0 scratch_alloc_
16 Wavefronts 67894.0 wavefronts_
17 Workgroups 16973.0 workgroups_
18 LDS_Per_Workgroup Req 0.0 lds_req_
19 IL1 Fetch 163.0 il1_fetch_
20 IL1 Hit 100.0 il1_hit_
21 IL1_L2 Rd 0.0 il1_l2_req_
22 vL1D Rd 2.0 sl1_rd_
23 vL1D Hit 98.0 sl1_hit_
24 vL1D_L2 Rd 0.0 sl1_l2_rd_
25 vL1D_L2 Wr 0.0 sl1_l2_wr_
26 vL1D_L2 Atomic 0.0 sl1_l2_atom_
27 VL1 Rd 279.0 vl1_rd_
28 VL1 Wr 1.0 vl1_wr_
29 VL1 Atomic 0.0 vl1_atom_
30 VL1 Hit 21.0 vl1_hit_
31 VL1 Lat 1501.0 vl1_lat_
32 VL1_L2 Rd 44.0 vl1_l2_rd_
33 VL1_L2 Wr 0.0 vl1_l2_wr_
34 vL1_L2 Atomic 0.0 vl1_l2_atom_
35 L2 Rd 44.0 l2_rd_
36 L2 Wr 0.0 l2_wr_
37 L2 Atomic 0.0 l2_atom_
38 L2 Hit 0.0 l2_hit_
39 L2 Rd Lat 732.0 l2_rd_lat_
40 L2 Wr Lat 332.0 l2_wr_lat_
41 Fabric Rd Lat 444.0 fabric_rd_lat_
42 Fabric Wr Lat 145.0 fabric_wr_lat_
43 Fabric Atomic Lat fabric_atom_lat_
44 Fabric_L2 Rd 44.0 l2_fabric_rd_
45 Fabric_L2 Wr 0.0 l2_fabric_wr_
46 Fabric_l2 Atomic 0.0 l2_fabric_atom_
47 HBM Rd 44.0 hbm_rd_
48 HBM Wr 0.0 hbm_wr_
49 LDS_Per_Workgroup Util 0.0 lds_util_
50 VL1 Coalesce 70.0 vl1_coales_
51 VL1 Stall 30.0 vl1_stall_
52 LDS_Per_Workgroup Lat lds_lat_
53 vL1D Lat sl1_lat_
54 IL1 Lat il1_lat_
55 Wave Occupancy 34.0 wave_occ_
@@ -0,0 +1,168 @@
Dispatch_ID,Kernel_Name,GPU_ID
0,__amd_rocclr_fillBuffer.kd,0
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0
1 Dispatch_ID Kernel_Name GPU_ID
2 0 __amd_rocclr_fillBuffer.kd 0
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0
5 3 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0
10 8 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0
15 13 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0
20 18 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0
25 23 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0
30 28 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0
35 33 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0
40 38 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0
45 43 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0
50 48 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0
55 53 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0
60 58 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0
65 63 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0
70 68 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0
75 73 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0
80 78 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0
85 83 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0
90 88 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0
95 93 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0
100 98 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0
105 103 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0
110 108 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0
115 113 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0
120 118 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0
125 123 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0
130 128 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0
135 133 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0
140 138 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0
145 143 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0
150 148 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0
155 153 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0
160 158 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0
165 163 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0
@@ -0,0 +1,30 @@
Metric,Value,Unit,Peak,PoP
VALU FLOPs,,Gflops,23070.72,
VALU IOPs,,Gops,23070.72,
MFMA FLOPs (BF16),,Gflops,92282.88,
MFMA FLOPs (F16),,Gflops,184565.76,
MFMA FLOPs (F32),,Gflops,46141.44,
MFMA FLOPs (F64),,Gflops,46141.44,
MFMA IOPs (Int8),,Gops,184565.76,
Active CUs,95,Cus,120,79.16666666666667
SALU Util,2.098901705245223,Pct,100,2.098901705245223
VALU Util,59.49293302260621,Pct,100,59.49293302260621
MFMA Util,,Pct,100,
VALU Active Threads/Wave,63.96757475781579,Threads,64,99.94933555908717
IPC - Issue,0.8437242643821745,Instr/cycle,5,16.874485287643488
LDS_Per_Workgroup BW,0.0,Gb/sec,23070.72,0.0
LDS_Per_Workgroup Bank Conflict,,Conflicts/access,32,
Instr Cache Hit Rate,99.99340470515173,Pct,100,99.99340470515173
Instr Cache BW,1409.2232915418736,Gb/s,4614.144,30.54138083991036
Scalar L1D Cache Hit Rate,99.35620448528866,Pct,100,99.35620448528866
Scalar L1D Cache BW,43.03689407376828,Gb/s,4614.144,0.9327167525280589
Vector L1D Cache Hit Rate,20.508982035928145,Pct,100,20.508982035928145
Vector L1D Cache BW,1217.912507374257,Gb/s,11535.36,10.558079742411655
L2 Cache Hit Rate,0.39296569201373344,Pct,100,0.39296569201373344
L2-Fabric Read BW,837.087019227418,Gb/s,1228.8,68.12231601785628
L2-Fabric Write BW,4.9809517205699905,Gb/s,1228.8,0.40535088871826097
L2-Fabric Read Latency,443.50771438331117,Cycles,,
L2-Fabric Write Latency,145.00192732800434,Cycles,,
Wave Occupancy,3207.535291866078,Wavefronts,4800,66.82365191387663
Instr Fetch BW,686.9122904014298,Gb/s,2307.072,29.774202556375776
Instr Fetch Latency,18.794491301557166,Cycles,,
1 Metric Value Unit Peak PoP
2 VALU FLOPs Gflops 23070.72
3 VALU IOPs Gops 23070.72
4 MFMA FLOPs (BF16) Gflops 92282.88
5 MFMA FLOPs (F16) Gflops 184565.76
6 MFMA FLOPs (F32) Gflops 46141.44
7 MFMA FLOPs (F64) Gflops 46141.44
8 MFMA IOPs (Int8) Gops 184565.76
9 Active CUs 95 Cus 120 79.16666666666667
10 SALU Util 2.098901705245223 Pct 100 2.098901705245223
11 VALU Util 59.49293302260621 Pct 100 59.49293302260621
12 MFMA Util Pct 100
13 VALU Active Threads/Wave 63.96757475781579 Threads 64 99.94933555908717
14 IPC - Issue 0.8437242643821745 Instr/cycle 5 16.874485287643488
15 LDS_Per_Workgroup BW 0.0 Gb/sec 23070.72 0.0
16 LDS_Per_Workgroup Bank Conflict Conflicts/access 32
17 Instr Cache Hit Rate 99.99340470515173 Pct 100 99.99340470515173
18 Instr Cache BW 1409.2232915418736 Gb/s 4614.144 30.54138083991036
19 Scalar L1D Cache Hit Rate 99.35620448528866 Pct 100 99.35620448528866
20 Scalar L1D Cache BW 43.03689407376828 Gb/s 4614.144 0.9327167525280589
21 Vector L1D Cache Hit Rate 20.508982035928145 Pct 100 20.508982035928145
22 Vector L1D Cache BW 1217.912507374257 Gb/s 11535.36 10.558079742411655
23 L2 Cache Hit Rate 0.39296569201373344 Pct 100 0.39296569201373344
24 L2-Fabric Read BW 837.087019227418 Gb/s 1228.8 68.12231601785628
25 L2-Fabric Write BW 4.9809517205699905 Gb/s 1228.8 0.40535088871826097
26 L2-Fabric Read Latency 443.50771438331117 Cycles
27 L2-Fabric Write Latency 145.00192732800434 Cycles
28 Wave Occupancy 3207.535291866078 Wavefronts 4800 66.82365191387663
29 Instr Fetch BW 686.9122904014298 Gb/s 2307.072 29.774202556375776
30 Instr Fetch Latency 18.794491301557166 Cycles
@@ -0,0 +1,9 @@
Metric,Avg,Min,Max,Unit
GPU Busy Cycles,616146.371257485,29293,9090320,Cycles/kernel
CPF Busy,616146.371257485,29293,9090320,Cycles/kernel
CPF Util,100.0,100.0,100.0,Pct
CPF Stall,0.0019823204395161783,0.0,0.05616938981556532,Cycles/kernel
L2Cache Intf Busy,4386.988023952096,4161,6391,Cycles/kernel
L2Cache Intf Util,1.404379490813178,0.062060791098944246,15.699853639381717,Pct
L2Cache Intf Stall,0.0,0.0,0.0,Pct
UTCL1 Stall,8.51497005988024,0,158,Cycles/kernel
1 Metric Avg Min Max Unit
2 GPU Busy Cycles 616146.371257485 29293 9090320 Cycles/kernel
3 CPF Busy 616146.371257485 29293 9090320 Cycles/kernel
4 CPF Util 100.0 100.0 100.0 Pct
5 CPF Stall 0.0019823204395161783 0.0 0.05616938981556532 Cycles/kernel
6 L2Cache Intf Busy 4386.988023952096 4161 6391 Cycles/kernel
7 L2Cache Intf Util 1.404379490813178 0.062060791098944246 15.699853639381717 Pct
8 L2Cache Intf Stall 0.0 0.0 0.0 Pct
9 UTCL1 Stall 8.51497005988024 0 158 Cycles/kernel
@@ -0,0 +1,13 @@
Metric,Avg,Min,Max,Unit
GPU Busy Cycles,616146.371257485,29293,9090320,Cycles
CPC Busy Cycles,610146.2035928144,29293,9027791,Cycles
CPC Util,99.21617356304758,77.92116377287658,100.0,Pct
CPC Stall Cycles,14736.383233532933,11368,71238,Cycles
CPC Stall Rate,4.1380942008462975,0.7890966904306934,40.85959102857338,Pct
CPC Packet Decoding,45402.33532934132,15334,473678,Cycles
SPI Intf Busy Cycles,562546.9401197605,695,8538800,Cycles
SPI Intf Util,89.50763251461059,2.3725804799781516,97.24357747353953,Pct
L2Cache Intf Util,0.23819004988101447,0.011050644826405083,2.175451008135833,Pct
UTCL1 Stall Cycles,2100.868263473054,1943,2817,Cycles
UTCL2 Intf Busy Cycles,2922.9221556886228,2734,3581,Cycles
UTCL2 Intf Util,0.9243258655216366,0.035082444845840825,9.868846874467723,Pct
1 Metric Avg Min Max Unit
2 GPU Busy Cycles 616146.371257485 29293 9090320 Cycles
3 CPC Busy Cycles 610146.2035928144 29293 9027791 Cycles
4 CPC Util 99.21617356304758 77.92116377287658 100.0 Pct
5 CPC Stall Cycles 14736.383233532933 11368 71238 Cycles
6 CPC Stall Rate 4.1380942008462975 0.7890966904306934 40.85959102857338 Pct
7 CPC Packet Decoding 45402.33532934132 15334 473678 Cycles
8 SPI Intf Busy Cycles 562546.9401197605 695 8538800 Cycles
9 SPI Intf Util 89.50763251461059 2.3725804799781516 97.24357747353953 Pct
10 L2Cache Intf Util 0.23819004988101447 0.011050644826405083 2.175451008135833 Pct
11 UTCL1 Stall Cycles 2100.868263473054 1943 2817 Cycles
12 UTCL2 Intf Busy Cycles 2922.9221556886228 2734 3581 Cycles
13 UTCL2 Intf Util 0.9243258655216366 0.035082444845840825 9.868846874467723 Pct
@@ -0,0 +1,9 @@
Metric,Avg,Min,Max,Unit
GPU Busy,616146.371257485,29293,9090320,Cycles
CS Busy,4752399.4850299405,85073,72550739,Cycles
SPI Busy,594966.1856287426,11697,9068910,Cycles
SQ Busy,4724500.143712575,78244,72523793,Cycles
Dispatched Workgroups,16973.413173652694,128,131072,Workgroups
Dispatched Wavefronts,67893.65269461078,512,524288,Wavefronts
Wave Alloc Failed,278359.80239520955,113,1622444,Cycles
Wave Alloc Failed - CS,329556.99401197606,625,999867,Cycles
1 Metric Avg Min Max Unit
2 GPU Busy 616146.371257485 29293 9090320 Cycles
3 CS Busy 4752399.4850299405 85073 72550739 Cycles
4 SPI Busy 594966.1856287426 11697 9068910 Cycles
5 SQ Busy 4724500.143712575 78244 72523793 Cycles
6 Dispatched Workgroups 16973.413173652694 128 131072 Workgroups
7 Dispatched Wavefronts 67893.65269461078 512 524288 Wavefronts
8 Wave Alloc Failed 278359.80239520955 113 1622444 Cycles
9 Wave Alloc Failed - CS 329556.99401197606 625 999867 Cycles
@@ -0,0 +1,15 @@
Metric,Avg,Min,Max,Unit
Wave request Failed (CS),329556.99401197606,625,999867,Cycles
CS Stall,19433.22754491018,0,662810,Cycles
CS Stall Rate,5.222711826919921,0.0,73.76513703882182,Pct
Scratch Stall,0.0,0,0,Cycles
Insufficient SIMD Waveslots,57830.431137724554,0,731049,Simd
Insufficient SIMD VGPRs,568474.6706586826,0,41500307,Simd
Insufficient SIMD SGPRs,0.0,0,0,Simd
Insufficient CU LDS_Per_Workgroup,0.0,0,0,Cu
Insufficient CU Barries,0.0,0,0,Cu
Insufficient Bulky Resource,0.0,0,0,Cu
Reach CU Threadgroups Limit,0.0,0,0,Cycles
Reach CU Wave Limit,0.0,0,0,Cycles
VGPR Writes,4.0,4.0,4.0,Cycles/wave
SGPR Writes,5.005988023952096,5.0,6.0,Cycles/wave
1 Metric Avg Min Max Unit
2 Wave request Failed (CS) 329556.99401197606 625 999867 Cycles
3 CS Stall 19433.22754491018 0 662810 Cycles
4 CS Stall Rate 5.222711826919921 0.0 73.76513703882182 Pct
5 Scratch Stall 0.0 0 0 Cycles
6 Insufficient SIMD Waveslots 57830.431137724554 0 731049 Simd
7 Insufficient SIMD VGPRs 568474.6706586826 0 41500307 Simd
8 Insufficient SIMD SGPRs 0.0 0 0 Simd
9 Insufficient CU LDS_Per_Workgroup 0.0 0 0 Cu
10 Insufficient CU Barries 0.0 0 0 Cu
11 Insufficient Bulky Resource 0.0 0 0 Cu
12 Reach CU Threadgroups Limit 0.0 0 0 Cycles
13 Reach CU Wave Limit 0.0 0 0 Cycles
14 VGPR Writes 4.0 4.0 4.0 Cycles/wave
15 SGPR Writes 5.005988023952096 5.0 6.0 Cycles/wave
@@ -0,0 +1,10 @@
Metric,Avg,Min,Max,Unit
Grid Size,4345193.77245509,32768,33554432,Work items
Workgroup Size,256.0,256,256,Work items
Total Wavefronts,67893.65269461078,512,524288,Wavefronts
Saved Wavefronts,0.0,0,0,Wavefronts
Restored Wavefronts,0.0,0,0,Wavefronts
VGPRs,23.976047904191617,8,36,Registers
SGPRs,24.047904191616766,24,32,Registers
LDS_Per_Workgroup Allocation,0.0,0,0,Bytes
Scratch Allocation,0.0,0,0,Bytes
1 Metric Avg Min Max Unit
2 Grid Size 4345193.77245509 32768 33554432 Work items
3 Workgroup Size 256.0 256 256 Work items
4 Total Wavefronts 67893.65269461078 512 524288 Wavefronts
5 Saved Wavefronts 0.0 0 0 Wavefronts
6 Restored Wavefronts 0.0 0 0 Wavefronts
7 VGPRs 23.976047904191617 8 36 Registers
8 SGPRs 24.047904191616766 24 32 Registers
9 LDS_Per_Workgroup Allocation 0.0 0 0 Bytes
10 Scratch Allocation 0.0 0 0 Bytes
@@ -0,0 +1,9 @@
Metric,Avg,Min,Max,Unit
Kernel Time (Nanosec),395162.04191616765,6400,6055312,Ns
Kernel Time (Cycles),616146.371257485,29293,9090320,Cycle
Instr/wavefront,842.5329341317365,62.0,20596.0,Instr/wavefront
Wave Cycles,33761.37244470105,2805.687400817871,547941.7736816406,Cycles/wave
Dependency Wait Cycles,4420.899736918375,1025.5845947265625,26430.99169921875,Cycles/wave
Issue Wait Cycles,25440.848739167173,131.4296875,443194.7819824219,Cycles/wave
Active Cycles,3899.636050652601,248.0,78316.0,Cycles/wave
Wavefront Occupancy,3207.535291866078,161.93853121967,3951.7584158080263,Wavefronts
1 Metric Avg Min Max Unit
2 Kernel Time (Nanosec) 395162.04191616765 6400 6055312 Ns
3 Kernel Time (Cycles) 616146.371257485 29293 9090320 Cycle
4 Instr/wavefront 842.5329341317365 62.0 20596.0 Instr/wavefront
5 Wave Cycles 33761.37244470105 2805.687400817871 547941.7736816406 Cycles/wave
6 Dependency Wait Cycles 4420.899736918375 1025.5845947265625 26430.99169921875 Cycles/wave
7 Issue Wait Cycles 25440.848739167173 131.4296875 443194.7819824219 Cycles/wave
8 Active Cycles 3899.636050652601 248.0 78316.0 Cycles/wave
9 Wavefront Occupancy 3207.535291866078 161.93853121967 3951.7584158080263 Wavefronts
@@ -0,0 +1,2 @@
workload_name,host_name,host_cpu,host_distro,host_kernel,host_rocmver,date,gpu_soc,numSE,numCU,numSIMD,waveSize,maxWavesPerCU,maxWorkgroupSize,L1,L2,sclk,mclk,cur_sclk,cur_mclk,L2Banks,name,numSQC,numPipes,hbmBW,ip_blocks
dev0,vesuvius,AMD EPYC 7542 32-Core Processor,,4.18.0-240.15.1.el8_3.x86_64,4.2.0-21,Thu Sep 22 11:31:14 2022 (CDT),gfx908,8,120,4,64,40,1024,16,,1502,1200,300,1200,32,mi100,48,4,1228.8,SQ|LDS_Per_Workgroup|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF
1 workload_name host_name host_cpu host_distro host_kernel host_rocmver date gpu_soc numSE numCU numSIMD waveSize maxWavesPerCU maxWorkgroupSize L1 L2 sclk mclk cur_sclk cur_mclk L2Banks name numSQC numPipes hbmBW ip_blocks
2 dev0 vesuvius AMD EPYC 7542 32-Core Processor 4.18.0-240.15.1.el8_3.x86_64 4.2.0-21 Thu Sep 22 11:31:14 2022 (CDT) gfx908 8 120 4 64 40 1024 16 1502 1200 300 1200 32 mi100 48 4 1228.8 SQ|LDS_Per_Workgroup|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF
@@ -0,0 +1,168 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,grd,Workgroup_Size,LDS_Per_Workgroup,scr,vgpr,SGPR,fbar,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"__amd_rocclr_fillBuffer.kd",0,0,0,921580,921585,33554432,256,0,0,8,32,6464,0x0,0x7fc0c2804180,12076328266793044,12076328266837802,12076328267160519,12076328267269900
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,921580,921585,32768,256,0,0,24,24,12480,0x0,0x7fc0c2835100,12076328282132912,12076328282246095,12076328282252495,12076328282258235
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,921580,921585,4194304,256,0,0,24,24,12928,0x7fc1ce3b2900,0x7fc0c2835140,12076328282304692,12076328282317774,12076328282452973,12076328282456624
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,921580,921585,4194304,256,0,0,36,24,13632,0x7fc1ce3b2800,0x7fc0c2835180,12076328282500335,12076328282514412,12076328282757290,12076328282839105
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,921580,921585,4194304,256,0,0,28,24,14080,0x7fc1ce3b2700,0x7fc0c28351c0,12076328282866656,12076328282878089,12076328283120967,12076328283220874
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,921580,921585,4194304,256,0,0,24,24,14528,0x7fc1ce3b2600,0x7fc0c2835200,12076328283248405,12076328283259845,12076328283385284,12076328283388756
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,921580,921585,4194304,256,0,0,24,24,14976,0x7fc1ce3b2500,0x7fc0c2835240,12076328283411038,12076328283422884,12076328283548003,12076328283551288
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,921580,921585,4194304,256,0,0,24,24,15424,0x7fc1ce3b2400,0x7fc0c2835280,12076328283602293,12076328283613762,12076328283737761,12076328283740811
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,921580,921585,4194304,256,0,0,28,24,16128,0x7fc1ce3b2300,0x7fc0c28352c0,12076328283768412,12076328283780801,12076328284062878,12076328284160350
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,921580,921585,4194304,256,0,0,28,24,16832,0x7fc1ce3b2a00,0x7fc0c2835300,12076328284183183,12076328284195517,12076328284440794,12076328284537421
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,921580,921585,4194304,256,0,0,24,24,17536,0x7fc1ce3b2900,0x7fc0c2835340,12076328284559472,12076328284572153,12076328284696792,12076328284700534
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,921580,921585,4194304,256,0,0,24,24,18240,0x7fc1ce3b2800,0x7fc0c2835380,12076328284727935,12076328284739831,12076328284865110,12076328284868647
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,921580,921585,4194304,256,0,0,24,24,18944,0x7fc1ce3b2700,0x7fc0c28353c0,12076328284906737,12076328284918390,12076328285042869,12076328285046106
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,921580,921585,4194304,256,0,0,28,24,19904,0x7fc1ce3b2600,0x7fc0c2835400,12076328285073086,12076328285085268,12076328285336946,12076328285408620
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,921580,921585,4194304,256,0,0,28,24,20608,0x7fc1ce3b2500,0x7fc0c2835440,12076328285430571,12076328285441905,12076328285686702,12076328285753501
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,921580,921585,4194304,256,0,0,24,24,21312,0x7fc1ce3b2400,0x7fc0c2835480,12076328285776674,12076328285788302,12076328285912940,12076328285916494
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,921580,921585,4194304,256,0,0,24,24,22016,0x7fc1ce3b2300,0x7fc0c28354c0,12076328285943133,12076328285955020,12076328286079659,12076328286083084
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,921580,921585,4194304,256,0,0,24,24,22720,0x7fc1ce3b2a00,0x7fc0c2835500,12076328286122036,12076328286134858,12076328286259337,12076328286262497
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,921580,921585,4194304,256,0,0,28,24,23680,0x7fc1ce3b2900,0x7fc0c2835540,12076328286288716,12076328286301257,12076328286581894,12076328286648665
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,921580,921585,4194304,256,0,0,28,24,24384,0x7fc1ce3b2800,0x7fc0c2835580,12076328286669003,12076328286680453,12076328286923491,12076328286990099
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,921580,921585,4194304,256,0,0,24,24,25088,0x7fc1ce3b2700,0x7fc0c28355c0,12076328287022319,12076328287034210,12076328287158849,12076328287161748
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,921580,921585,4194304,256,0,0,24,24,25792,0x7fc1ce3b2600,0x7fc0c2835600,12076328287194309,12076328287206208,12076328287331647,12076328287334990
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,921580,921585,4194304,256,0,0,24,24,26496,0x7fc1ce3b2500,0x7fc0c2835640,12076328287376938,12076328287388286,12076328287511965,12076328287515265
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,921580,921585,4194304,256,0,0,28,24,27712,0x7fc1ce3b2400,0x7fc0c2835680,12076328287546493,12076328287558205,12076328287809402,12076328287875505
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,921580,921585,4194304,256,0,0,28,24,28416,0x7fc1ce3b2300,0x7fc0c28356c0,12076328287902144,12076328287915801,12076328288159799,12076328288259989
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,921580,921585,4194304,256,0,0,24,24,29120,0x7fc1ce3b2a00,0x7fc0c2835700,12076328288281289,12076328288292918,12076328288416757,12076328288420097
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,921580,921585,4194304,256,0,0,24,24,30080,0x7fc1ce3b2900,0x7fc0c2835740,12076328288446927,12076328288458196,12076328288583475,12076328288587197
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,921580,921585,4194304,256,0,0,24,24,30784,0x7fc1ce3b2800,0x7fc0c2835780,12076328288624767,12076328288637555,12076328288762673,12076328288765689
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,921580,921585,4194304,256,0,0,28,24,32000,0x7fc1ce3b2700,0x7fc0c28357c0,12076328288792669,12076328288805873,12076328289056271,12076328289116922
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,921580,921585,4194304,256,0,0,28,24,32960,0x7fc1ce3b2600,0x7fc0c2835800,12076328289139163,12076328289150030,12076328289393547,12076328289471471
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,921580,921585,4194304,256,0,0,24,24,33920,0x7fc1ce3b2500,0x7fc0c2835840,12076328289493542,12076328289505066,12076328289630185,12076328289633502
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,921580,921585,4194304,256,0,0,24,24,34880,0x7fc1ce3b2400,0x7fc0c2835880,12076328289660963,12076328289672265,12076328289797864,12076328289801123
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,921580,921585,4194304,256,0,0,24,24,35840,0x7fc1ce3b2300,0x7fc0c28358c0,12076328289839254,12076328289853543,12076328289978502,12076328289981509
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,921580,921585,4194304,256,0,0,28,24,37312,0x7fc1ce3b2a00,0x7fc0c2835900,12076328290011795,12076328290023942,12076328290273219,12076328290328403
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,921580,921585,4194304,256,0,0,28,24,38272,0x7fc1ce3b2900,0x7fc0c2835940,12076328290350675,12076328290363618,12076328290606816,12076328290661202
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,921580,921585,4194304,256,0,0,24,24,39232,0x7fc1ce3b2800,0x7fc0c2835980,12076328290682592,12076328290695135,12076328290820094,12076328290823453
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,921580,921585,4194304,256,0,0,24,24,40192,0x7fc1ce3b2700,0x7fc0c28359c0,12076328290849432,12076328290860414,12076328290985692,12076328290988941
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,921580,921585,4194304,256,0,0,24,24,41152,0x7fc1ce3b2600,0x7fc0c2835a00,12076328291030689,12076328291042172,12076328291166171,12076328291169607
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,921580,921585,4194304,256,0,0,28,24,42624,0x7fc1ce3b2500,0x7fc0c2835a40,12076328291196156,12076328291207930,12076328291454808,12076328291511642
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,921580,921585,4194304,256,0,0,28,24,43584,0x7fc1ce3b2400,0x7fc0c2835a80,12076328291534896,12076328291547927,12076328291791605,12076328291816539
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,921580,921585,4194304,256,0,0,24,24,44544,0x7fc1ce3b2300,0x7fc0c2835ac0,12076328291840223,12076328291851764,12076328291976563,12076328291979882
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,921580,921585,4194304,256,0,0,24,24,45760,0x7fc1ce3b2a00,0x7fc0c2835b00,12076328292010920,12076328292022803,12076328292148561,12076328292151812
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,921580,921585,4194304,256,0,0,24,24,46720,0x7fc1ce3b2900,0x7fc0c2835b40,12076328292188039,12076328292201201,12076328292325840,12076328292329182
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,921580,921585,4194304,256,0,0,28,24,48448,0x7fc1ce3b2800,0x7fc0c2835b80,12076328292354940,12076328292365999,12076328292617677,12076328292636793
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,921580,921585,4194304,256,0,0,28,24,49408,0x7fc1ce3b2700,0x7fc0c2835bc0,12076328292658373,12076328292669357,12076328292916074,12076328292935699
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,921580,921585,4194304,256,0,0,24,24,50368,0x7fc1ce3b2600,0x7fc0c2835c00,12076328292954734,12076328292965994,12076328293090633,12076328293093873
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,921580,921585,4194304,256,0,0,24,24,51584,0x7fc1ce3b2500,0x7fc0c2835c40,12076328293121103,12076328293131912,12076328293259431,12076328293262406
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,921580,921585,4194304,256,0,0,24,24,52544,0x7fc1ce3b2400,0x7fc0c2835c80,12076328293300567,12076328293311910,12076328293436869,12076328293439926
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,921580,921585,4194304,256,0,0,28,24,54272,0x7fc1ce3b2300,0x7fc0c2835cc0,12076328293466065,12076328293478149,12076328293729347,12076328293752527
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,921580,921585,4194304,256,0,0,28,24,55488,0x7fc1ce3b2a00,0x7fc0c2835d00,12076328293773806,12076328293786306,12076328294031104,12076328294055570
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,921580,921585,4194304,256,0,0,24,24,56704,0x7fc1ce3b2900,0x7fc0c2835d40,12076328294076248,12076328294088703,12076328294213502,12076328294216309
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,921580,921585,4194304,256,0,0,24,24,58176,0x7fc1ce3b2800,0x7fc0c2835d80,12076328294241656,12076328294252862,12076328294379900,12076328294382888
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,921580,921585,4194304,256,0,0,24,24,59392,0x7fc1ce3b2700,0x7fc0c2835dc0,12076328294418545,12076328294431580,12076328294556859,12076328294559737
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,921580,921585,4194304,256,0,0,28,24,61376,0x7fc1ce3b2600,0x7fc0c2835e00,12076328294585285,12076328294598298,12076328294849976,12076328294868801
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,921580,921585,4194304,256,0,0,28,24,62592,0x7fc1ce3b2500,0x7fc0c2835e40,12076328294889520,12076328294902615,12076328295151573,12076328295175802
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,921580,921585,4194304,256,0,0,24,24,63808,0x7fc1ce3b2400,0x7fc0c2835e80,12076328295198935,12076328295211893,12076328295336691,12076328295339857
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,921580,921585,4194304,256,0,0,24,24,65280,0x7fc1ce3b2300,0x7fc0c2835ec0,12076328295366046,12076328295377651,12076328295507410,12076328295510384
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,921580,921585,4194304,256,0,0,24,24,66496,0x7fc1ce3b2a00,0x7fc0c2835f00,12076328295546761,12076328295558289,12076328295683568,12076328295686752
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,921580,921585,4194304,256,0,0,28,24,68480,0x7fc1ce3b2900,0x7fc0c2835f40,12076328295713010,12076328295726128,12076328295989485,12076328296017226
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,921580,921585,4194304,256,0,0,28,24,69696,0x7fc1ce3b2800,0x7fc0c2835f80,12076328296038936,12076328296051885,12076328296296042,12076328296319227
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,921580,921585,4194304,256,0,0,24,24,70912,0x7fc1ce3b2700,0x7fc0c2835fc0,12076328296340867,12076328296353322,12076328296477961,12076328296480927
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,921580,921585,4194304,256,0,0,24,24,72384,0x7fc1ce3b2600,0x7fc0c2836000,12076328296507066,12076328296518280,12076328296654439,12076328296657546
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,921580,921585,4194304,256,0,0,24,24,73600,0x7fc1ce3b2500,0x7fc0c2836040,12076328296695366,12076328296707398,12076328296831877,12076328296834715
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,921580,921585,4194304,256,0,0,28,24,75840,0x7fc1ce3b2400,0x7fc0c2836080,12076328296860693,12076328296872357,12076328297132994,12076328297165039
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,921580,921585,4194304,256,0,0,28,24,77056,0x7fc1ce3b2300,0x7fc0c28360c0,12076328297187260,12076328297199394,12076328297444991,12076328297469595
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,921580,921585,4194304,256,0,0,24,24,78272,0x7fc1ce3b2a00,0x7fc0c2836100,12076328297490253,12076328297502591,12076328297627230,12076328297630223
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,921580,921585,4194304,256,0,0,24,24,80000,0x7fc1ce3b2900,0x7fc0c2836140,12076328297656091,12076328297667389,12076328297809788,12076328297812753
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,921580,921585,4194304,256,0,0,24,24,81216,0x7fc1ce3b2800,0x7fc0c2836180,12076328297849160,12076328297860987,12076328297985946,12076328297989140
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,921580,921585,4194304,256,0,0,28,24,83456,0x7fc1ce3b2700,0x7fc0c28361c0,12076328298020028,12076328298031386,12076328298284983,12076328298311640
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,921580,921585,4194304,256,0,0,28,24,84928,0x7fc1ce3b2600,0x7fc0c2836200,12076328298331847,12076328298343383,12076328298589621,12076328298616817
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,921580,921585,4194304,256,0,0,24,24,86400,0x7fc1ce3b2500,0x7fc0c2836240,12076328298641623,12076328298654260,12076328298780979,12076328298784038
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,921580,921585,4194304,256,0,0,24,24,88128,0x7fc1ce3b2400,0x7fc0c2836280,12076328298808974,12076328298821618,12076328298971377,12076328298974672
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,921580,921585,4194304,256,0,0,24,24,89600,0x7fc1ce3b2300,0x7fc0c28362c0,12076328299030676,12076328299042576,12076328299167695,12076328299171197
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,921580,921585,4194304,256,0,0,28,24,92096,0x7fc1ce3b2a00,0x7fc0c2836300,12076328299197967,12076328299211215,12076328299464812,12076328299487175
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,921580,921585,4194304,256,0,0,28,24,93568,0x7fc1ce3b2900,0x7fc0c2836340,12076328299508584,12076328299521292,12076328299772489,12076328299795878
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,921580,921585,4194304,256,0,0,24,24,95040,0x7fc1ce3b2800,0x7fc0c2836380,12076328299816136,12076328299828489,12076328299954088,12076328299957138
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,921580,921585,4194304,256,0,0,24,24,96768,0x7fc1ce3b2700,0x7fc0c28363c0,12076328299982896,12076328299994247,12076328300152326,12076328300155396
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,921580,921585,4194304,256,0,0,24,24,98240,0x7fc1ce3b2600,0x7fc0c2836400,12076328300192926,12076328300204965,12076328300330244,12076328300333618
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,921580,921585,4194304,256,0,0,28,24,100736,0x7fc1ce3b2500,0x7fc0c2836440,12076328300359496,12076328300370884,12076328300624801,12076328300647090
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,921580,921585,4194304,256,0,0,28,24,102208,0x7fc1ce3b2400,0x7fc0c2836480,12076328300668179,12076328300679681,12076328300927039,12076328300949612
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,921580,921585,4194304,256,0,0,24,24,103680,0x7fc1ce3b2300,0x7fc0c28364c0,12076328300969940,12076328300980958,12076328301106237,12076328301109660
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,921580,921585,4194304,256,0,0,24,24,105664,0x7fc1ce3b2a00,0x7fc0c2836500,12076328301135007,12076328301145916,12076328301310395,12076328301314070
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,921580,921585,4194304,256,0,0,24,24,107136,0x7fc1ce3b2900,0x7fc0c2836540,12076328301349906,12076328301361274,12076328301486553,12076328301489626
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,921580,921585,4194304,256,0,0,28,24,109888,0x7fc1ce3b2800,0x7fc0c2836580,12076328301516135,12076328301528153,12076328301783990,12076328301806735
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,921580,921585,4194304,256,0,0,28,24,111360,0x7fc1ce3b2700,0x7fc0c28365c0,12076328301828015,12076328301841110,12076328302090228,12076328302113816
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,921580,921585,4194304,256,0,0,24,24,112832,0x7fc1ce3b2600,0x7fc0c2836600,12076328302136859,12076328302149427,12076328302275026,12076328302278342
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,921580,921585,4194304,256,0,0,24,24,114816,0x7fc1ce3b2500,0x7fc0c2836640,12076328302303909,12076328302316945,12076328302489104,12076328302492410
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,921580,921585,4194304,256,0,0,24,24,116288,0x7fc1ce3b2400,0x7fc0c2836680,12076328302528587,12076328302541583,12076328302667022,12076328302670280
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,921580,921585,4194304,256,0,0,28,24,119040,0x7fc1ce3b2300,0x7fc0c28366c0,12076328302696369,12076328302707982,12076328302964139,12076328302986678
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,921580,921585,4194304,256,0,0,28,24,120768,0x7fc1ce3b2a00,0x7fc0c2836700,12076328303011745,12076328303023019,12076328303267976,12076328303295001
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,921580,921585,4194304,256,0,0,24,24,122496,0x7fc1ce3b2900,0x7fc0c2836740,12076328303317523,12076328303328936,12076328303454215,12076328303457353
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,921580,921585,4194304,256,0,0,24,24,124736,0x7fc1ce3b2800,0x7fc0c2836780,12076328303482750,12076328303494214,12076328303676293,12076328303679416
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,921580,921585,4194304,256,0,0,24,24,126464,0x7fc1ce3b2700,0x7fc0c28367c0,12076328303715833,12076328303729252,12076328303855491,12076328303858879
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,921580,921585,4194304,256,0,0,20,24,127936,0x7fc1ce3b2600,0x7fc0c2836800,12076328303884727,12076328303897250,12076328304193568,12076328304217075
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,921580,921585,4194304,256,0,0,28,24,129664,0x7fc1ce3b2500,0x7fc0c2836840,12076328304238034,12076328304250687,12076328304496765,12076328304519777
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,921580,921585,4194304,256,0,0,24,24,131392,0x7fc1ce3b2400,0x7fc0c2836880,12076328304542760,12076328304556124,12076328304682523,12076328304686267
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,921580,921585,4194304,256,0,0,24,24,133632,0x7fc1ce3b2300,0x7fc0c28368c0,12076328304712315,12076328304724923,12076328304916601,12076328304919851
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,921580,921585,4194304,256,0,0,24,24,135360,0x7fc1ce3b2a00,0x7fc0c2836900,12076328304956910,12076328304969240,12076328305095799,12076328305099445
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,921580,921585,4194304,256,0,0,20,24,136832,0x7fc1ce3b2900,0x7fc0c2836940,12076328305126014,12076328305139319,12076328305421876,12076328305446179
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,921580,921585,4194304,256,0,0,28,24,138560,0x7fc1ce3b2800,0x7fc0c2836980,12076328305468711,12076328305481555,12076328305732913,12076328305759321
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,921580,921585,4194304,256,0,0,24,24,140288,0x7fc1ce3b2700,0x7fc0c28369c0,12076328305780941,12076328305793393,12076328305918831,12076328305922043
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,921580,921585,4194304,256,0,0,24,24,142784,0x7fc1ce3b2600,0x7fc0c2836a00,12076328305949234,12076328305959791,12076328306169869,12076328306197075
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,921580,921585,4194304,256,0,0,24,24,144768,0x7fc1ce3b2500,0x7fc0c2836a40,12076328306228493,12076328306239948,12076328306370027,12076328306373392
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,921580,921585,4194304,256,0,0,20,24,145728,0x7fc1ce3b2400,0x7fc0c2836a80,12076328306399170,12076328306411307,12076328306718024,12076328306740224
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,921580,921585,4194304,256,0,0,28,24,147712,0x7fc1ce3b2300,0x7fc0c2836ac0,12076328306761123,12076328306772263,12076328307024101,12076328307051893
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,921580,921585,4194304,256,0,0,24,24,149696,0x7fc1ce3b2a00,0x7fc0c2836b00,12076328307073984,12076328307086500,12076328307214019,12076328307217321
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,921580,921585,4194304,256,0,0,24,24,152192,0x7fc1ce3b2900,0x7fc0c2836b40,12076328307242718,12076328307254019,12076328307481057,12076328307507219
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,921580,921585,4194304,256,0,0,24,24,154176,0x7fc1ce3b2800,0x7fc0c2836b80,12076328307538868,12076328307551136,12076328307677535,12076328307680822
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,921580,921585,4194304,256,0,0,20,24,155648,0x7fc1ce3b2700,0x7fc0c2836bc0,12076328307706550,12076328307717854,12076328308046011,12076328308073191
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,921580,921585,4194304,256,0,0,28,24,157632,0x7fc1ce3b2600,0x7fc0c2836c00,12076328308094771,12076328308107451,12076328308359448,12076328308385832
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,921580,921585,4194304,256,0,0,24,24,159616,0x7fc1ce3b2500,0x7fc0c2836c40,12076328308406601,12076328308419448,12076328308547447,12076328308550799
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,921580,921585,4194304,256,0,0,24,24,162368,0x7fc1ce3b2400,0x7fc0c2836c80,12076328308576006,12076328308589366,12076328308832404,12076328308858491
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,921580,921585,4194304,256,0,0,24,24,164608,0x7fc1ce3b2300,0x7fc0c2836cc0,12076328308889107,12076328308902163,12076328309031602,12076328309035229
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,921580,921585,4194304,256,0,0,20,24,166336,0x7fc1ce3b2a00,0x7fc0c2836d00,12076328309060666,12076328309071922,12076328309446638,12076328309476750
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,921580,921585,4194304,256,0,0,28,24,168576,0x7fc1ce3b2900,0x7fc0c2836d40,12076328309498029,12076328309509357,12076328309760075,12076328309786235
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,921580,921585,4194304,256,0,0,24,24,170816,0x7fc1ce3b2800,0x7fc0c2836d80,12076328309808376,12076328309820075,12076328309948873,12076328309952123
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,921580,921585,4194304,256,0,0,24,24,174080,0x7fc1ce3b2700,0x7fc0c2836dc0,12076328309977791,12076328309990473,12076328310268230,12076328310291504
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,921580,921585,4194304,256,0,0,24,24,176576,0x7fc1ce3b2600,0x7fc0c2836e00,12076328310323363,12076328310334790,12076328310470468,12076328310473672
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,921580,921585,4194304,256,0,0,20,24,177792,0x7fc1ce3b2500,0x7fc0c2836e40,12076328310499410,12076328310511268,12076328310933824,12076328310957331
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,921580,921585,4194304,256,0,0,28,24,180288,0x7fc1ce3b2400,0x7fc0c2836e80,12076328310980524,12076328310991423,12076328311257501,12076328311284690
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,921580,921585,4194304,256,0,0,24,24,182784,0x7fc1ce3b2300,0x7fc0c2836ec0,12076328311304076,12076328311315260,12076328311450619,12076328311453844
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,921580,921585,4194304,256,0,0,24,24,186304,0x7fc1ce3b2a00,0x7fc0c2836f00,12076328311481495,12076328311491899,12076328311806136,12076328311832137
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,921580,921585,4194304,256,0,0,24,24,189312,0x7fc1ce3b2900,0x7fc0c2836f40,12076328311865519,12076328311876855,12076328312028694,12076328312032049
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,921580,921585,4194304,256,0,0,20,24,190784,0x7fc1ce3b2800,0x7fc0c2836f80,12076328312058758,12076328312071093,12076328312587568,12076328312613850
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,921580,921585,4194304,256,0,0,28,24,193792,0x7fc1ce3b2700,0x7fc0c2836fc0,12076328312635360,12076328312647728,12076328312949165,12076328312975372
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,921580,921585,4194304,256,0,0,24,24,196800,0x7fc1ce3b2600,0x7fc0c2837000,12076328312995659,12076328313006604,12076328313159883,12076328313163421
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,921580,921585,4194304,256,0,0,24,24,201088,0x7fc1ce3b2500,0x7fc0c2837040,12076328313190341,12076328313204043,12076328313588519,12076328313611744
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,921580,921585,4194304,256,0,0,24,24,204608,0x7fc1ce3b2400,0x7fc0c2837080,12076328313643133,12076328313654438,12076328313829637,12076328313832845
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,921580,921585,4194304,256,0,0,20,24,206080,0x7fc1ce3b2300,0x7fc0c28370c0,12076328313858964,12076328313872516,12076328314481310,12076328314504854
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,921580,921585,4194304,256,0,0,28,24,209600,0x7fc1ce3b2a00,0x7fc0c2837100,12076328314527316,12076328314539550,12076328314869947,12076328314892695
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,921580,921585,4194304,256,0,0,24,24,213120,0x7fc1ce3b2900,0x7fc0c2837140,12076328314916589,12076328314927706,12076328315105785,12076328315109298
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,921580,921585,4194304,256,0,0,24,24,218176,0x7fc1ce3b2800,0x7fc0c2837180,12076328315136568,12076328315147544,12076328315602740,12076328315625367
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,921580,921585,4194304,256,0,0,24,24,222208,0x7fc1ce3b2700,0x7fc0c28371c0,12076328315656605,12076328315669139,12076328315868177,12076328315890389
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,921580,921585,4194304,256,0,0,20,24,223936,0x7fc1ce3b2600,0x7fc0c2837200,12076328315909935,12076328315921137,12076328316623050,12076328316652245
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,921580,921585,4194304,256,0,0,28,24,227968,0x7fc1ce3b2500,0x7fc0c2837240,12076328316674667,12076328316685770,12076328317058246,12076328317085961
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,921580,921585,4194304,256,0,0,24,24,232000,0x7fc1ce3b2400,0x7fc0c2837280,12076328317112040,12076328317123206,12076328317325764,12076328317352116
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,921580,921585,4194304,256,0,0,24,24,237824,0x7fc1ce3b2300,0x7fc0c28372c0,12076328317372964,12076328317384003,12076328317909438,12076328317935410
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,921580,921585,4194304,256,0,0,24,24,242368,0x7fc1ce3b2a00,0x7fc0c2837300,12076328317968030,12076328317979357,12076328318237755,12076328318269951
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,921580,921585,4194304,256,0,0,20,24,243584,0x7fc1ce3b2900,0x7fc0c2837340,12076328318290960,12076328318303034,12076328319100947,12076328319129479
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,921580,921585,4194304,256,0,0,28,24,248128,0x7fc1ce3b2800,0x7fc0c2837380,12076328319154806,12076328319166066,12076328319587502,12076328319613749
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,921580,921585,4194304,256,0,0,24,24,252672,0x7fc1ce3b2700,0x7fc0c28373c0,12076328319637002,12076328319648462,12076328319873100,12076328319898748
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,921580,921585,4194304,256,0,0,24,24,259264,0x7fc1ce3b2600,0x7fc0c2837400,12076328319920669,12076328319932939,12076328320529253,12076328320556331
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,921580,921585,4194304,256,0,0,24,24,264832,0x7fc1ce3b2500,0x7fc0c2837440,12076328320588520,12076328320601253,12076328320871010,12076328320894018
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,921580,921585,4194304,256,0,0,20,24,266304,0x7fc1ce3b2400,0x7fc0c2837480,12076328320915799,12076328320926850,12076328321911160,12076328321941896
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,921580,921585,4194304,256,0,0,28,24,271872,0x7fc1ce3b2300,0x7fc0c28374c0,12076328321962213,12076328321973240,12076328322485715,12076328322513037
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,921580,921585,4194304,256,0,0,24,24,277440,0x7fc1ce3b2a00,0x7fc0c2837500,12076328322538134,12076328322549234,12076328322820432,12076328322842910
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,921580,921585,4194304,256,0,0,12,24,279936,0x7fc1ce3b2900,0x7fc0c2837540,12076328322865682,12076328322877231,12076328323614664,12076328323648066
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,921580,921585,4194304,256,0,0,24,24,286528,0x7fc1ce3b2800,0x7fc0c2837580,12076328323679785,12076328323691303,12076328324006820,12076328324033843
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,921580,921585,4194304,256,0,0,20,24,288000,0x7fc1ce3b2700,0x7fc0c28375c0,12076328324060243,12076328324071620,12076328325242329,12076328325266614
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,921580,921585,4194304,256,0,0,32,24,294592,0x7fc1ce3b2600,0x7fc0c2837600,12076328325292813,12076328325304088,12076328325913202,12076328325936920
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,921580,921585,4194304,256,0,0,24,24,301184,0x7fc1ce3b2500,0x7fc0c2837640,12076328325963039,12076328325975762,12076328326294799,12076328326323589
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,921580,921585,4194304,256,0,0,12,24,304960,0x7fc1ce3b2400,0x7fc0c2837680,12076328326349387,12076328326360398,12076328327238150,12076328327267373
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,921580,921585,4194304,256,0,0,24,24,313600,0x7fc1ce3b2300,0x7fc0c28376c0,12076328327303049,12076328327315909,12076328327724385,12076328327752785
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,921580,921585,4194304,256,0,0,20,24,314816,0x7fc1ce3b2a00,0x7fc0c2837700,12076328327775457,12076328327788385,12076328329338130,12076328329409243
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,921580,921585,4194304,256,0,0,20,24,317568,0x7fc1ce3b2900,0x7fc0c2837740,12076328329433268,12076328329446494,12076328330240888,12076328330315778
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,921580,921585,4194304,256,0,0,12,24,320320,0x7fc1ce3b2800,0x7fc0c2837780,12076328330335795,12076328330349046,12076328330762483,12076328330832368
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,921580,921585,4194304,256,0,0,12,24,324096,0x7fc1ce3b2700,0x7fc0c28377c0,12076328330856042,12076328330867602,12076328332025833,12076328332098802
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,921580,921585,4194304,256,0,0,12,24,328896,0x7fc1ce3b2600,0x7fc0c2837800,12076328332133025,12076328332148552,12076328332933986,12076328333006859
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,921580,921585,4194304,256,0,0,20,24,330112,0x7fc1ce3b2500,0x7fc0c2837840,12076328333028720,12076328333040865,12076328336096201,12076328336166511
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,921580,921585,4194304,256,0,0,20,24,332864,0x7fc1ce3b2400,0x7fc0c2837880,12076328336195776,12076328336207400,12076328337749468,12076328337820415
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,921580,921585,4194304,256,0,0,12,24,335616,0x7fc1ce3b2300,0x7fc0c28378c0,12076328337848287,12076328337860667,12076328338649301,12076328338723804
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,921580,921585,4194304,256,0,0,12,24,339392,0x7fc1ce3b2a00,0x7fc0c2837900,12076328338747668,12076328338759380,12076328341041122,12076328341111622
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,921580,921585,4194304,256,0,0,12,24,344192,0x7fc1ce3b2900,0x7fc0c2837940,12076328341146376,12076328341158241,12076328342692949,12076328342764133
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,921580,921585,4194304,256,0,0,20,24,345408,0x7fc1ce3b2800,0x7fc0c2837980,12076328342787035,12076328342799028,12076328348854340,12076328348924932
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,921580,921585,4194304,256,0,0,20,24,348160,0x7fc1ce3b2700,0x7fc0c28379c0,12076328348949458,12076328348960739,12076328352004075,12076328352077892
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,921580,921585,4194304,256,0,0,12,24,350912,0x7fc1ce3b2600,0x7fc0c2837a00,12076328352100574,12076328352112075,12076328353651102,12076328353722028
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,921580,921585,4194304,256,0,0,12,24,0,0x7fc1ce3b2500,0x7fc0c2837a40,12076328353744509,12076328353758782,12076328358285786,12076328358356250
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid grd Workgroup_Size LDS_Per_Workgroup scr vgpr SGPR fbar sig obj DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 __amd_rocclr_fillBuffer.kd 0 0 0 921580 921585 33554432 256 0 0 8 32 6464 0x0 0x7fc0c2804180 12076328266793044 12076328266837802 12076328267160519 12076328267269900
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 921580 921585 32768 256 0 0 24 24 12480 0x0 0x7fc0c2835100 12076328282132912 12076328282246095 12076328282252495 12076328282258235
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 4 921580 921585 4194304 256 0 0 24 24 12928 0x7fc1ce3b2900 0x7fc0c2835140 12076328282304692 12076328282317774 12076328282452973 12076328282456624
5 3 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 6 921580 921585 4194304 256 0 0 36 24 13632 0x7fc1ce3b2800 0x7fc0c2835180 12076328282500335 12076328282514412 12076328282757290 12076328282839105
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 8 921580 921585 4194304 256 0 0 28 24 14080 0x7fc1ce3b2700 0x7fc0c28351c0 12076328282866656 12076328282878089 12076328283120967 12076328283220874
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 10 921580 921585 4194304 256 0 0 24 24 14528 0x7fc1ce3b2600 0x7fc0c2835200 12076328283248405 12076328283259845 12076328283385284 12076328283388756
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 12 921580 921585 4194304 256 0 0 24 24 14976 0x7fc1ce3b2500 0x7fc0c2835240 12076328283411038 12076328283422884 12076328283548003 12076328283551288
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 14 921580 921585 4194304 256 0 0 24 24 15424 0x7fc1ce3b2400 0x7fc0c2835280 12076328283602293 12076328283613762 12076328283737761 12076328283740811
10 8 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 16 921580 921585 4194304 256 0 0 28 24 16128 0x7fc1ce3b2300 0x7fc0c28352c0 12076328283768412 12076328283780801 12076328284062878 12076328284160350
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 18 921580 921585 4194304 256 0 0 28 24 16832 0x7fc1ce3b2a00 0x7fc0c2835300 12076328284183183 12076328284195517 12076328284440794 12076328284537421
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 20 921580 921585 4194304 256 0 0 24 24 17536 0x7fc1ce3b2900 0x7fc0c2835340 12076328284559472 12076328284572153 12076328284696792 12076328284700534
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 22 921580 921585 4194304 256 0 0 24 24 18240 0x7fc1ce3b2800 0x7fc0c2835380 12076328284727935 12076328284739831 12076328284865110 12076328284868647
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 24 921580 921585 4194304 256 0 0 24 24 18944 0x7fc1ce3b2700 0x7fc0c28353c0 12076328284906737 12076328284918390 12076328285042869 12076328285046106
15 13 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 26 921580 921585 4194304 256 0 0 28 24 19904 0x7fc1ce3b2600 0x7fc0c2835400 12076328285073086 12076328285085268 12076328285336946 12076328285408620
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 28 921580 921585 4194304 256 0 0 28 24 20608 0x7fc1ce3b2500 0x7fc0c2835440 12076328285430571 12076328285441905 12076328285686702 12076328285753501
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 30 921580 921585 4194304 256 0 0 24 24 21312 0x7fc1ce3b2400 0x7fc0c2835480 12076328285776674 12076328285788302 12076328285912940 12076328285916494
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 32 921580 921585 4194304 256 0 0 24 24 22016 0x7fc1ce3b2300 0x7fc0c28354c0 12076328285943133 12076328285955020 12076328286079659 12076328286083084
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 34 921580 921585 4194304 256 0 0 24 24 22720 0x7fc1ce3b2a00 0x7fc0c2835500 12076328286122036 12076328286134858 12076328286259337 12076328286262497
20 18 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 36 921580 921585 4194304 256 0 0 28 24 23680 0x7fc1ce3b2900 0x7fc0c2835540 12076328286288716 12076328286301257 12076328286581894 12076328286648665
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 38 921580 921585 4194304 256 0 0 28 24 24384 0x7fc1ce3b2800 0x7fc0c2835580 12076328286669003 12076328286680453 12076328286923491 12076328286990099
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 40 921580 921585 4194304 256 0 0 24 24 25088 0x7fc1ce3b2700 0x7fc0c28355c0 12076328287022319 12076328287034210 12076328287158849 12076328287161748
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 42 921580 921585 4194304 256 0 0 24 24 25792 0x7fc1ce3b2600 0x7fc0c2835600 12076328287194309 12076328287206208 12076328287331647 12076328287334990
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 44 921580 921585 4194304 256 0 0 24 24 26496 0x7fc1ce3b2500 0x7fc0c2835640 12076328287376938 12076328287388286 12076328287511965 12076328287515265
25 23 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 46 921580 921585 4194304 256 0 0 28 24 27712 0x7fc1ce3b2400 0x7fc0c2835680 12076328287546493 12076328287558205 12076328287809402 12076328287875505
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 48 921580 921585 4194304 256 0 0 28 24 28416 0x7fc1ce3b2300 0x7fc0c28356c0 12076328287902144 12076328287915801 12076328288159799 12076328288259989
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 50 921580 921585 4194304 256 0 0 24 24 29120 0x7fc1ce3b2a00 0x7fc0c2835700 12076328288281289 12076328288292918 12076328288416757 12076328288420097
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 52 921580 921585 4194304 256 0 0 24 24 30080 0x7fc1ce3b2900 0x7fc0c2835740 12076328288446927 12076328288458196 12076328288583475 12076328288587197
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 54 921580 921585 4194304 256 0 0 24 24 30784 0x7fc1ce3b2800 0x7fc0c2835780 12076328288624767 12076328288637555 12076328288762673 12076328288765689
30 28 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 56 921580 921585 4194304 256 0 0 28 24 32000 0x7fc1ce3b2700 0x7fc0c28357c0 12076328288792669 12076328288805873 12076328289056271 12076328289116922
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 58 921580 921585 4194304 256 0 0 28 24 32960 0x7fc1ce3b2600 0x7fc0c2835800 12076328289139163 12076328289150030 12076328289393547 12076328289471471
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 60 921580 921585 4194304 256 0 0 24 24 33920 0x7fc1ce3b2500 0x7fc0c2835840 12076328289493542 12076328289505066 12076328289630185 12076328289633502
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 62 921580 921585 4194304 256 0 0 24 24 34880 0x7fc1ce3b2400 0x7fc0c2835880 12076328289660963 12076328289672265 12076328289797864 12076328289801123
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 64 921580 921585 4194304 256 0 0 24 24 35840 0x7fc1ce3b2300 0x7fc0c28358c0 12076328289839254 12076328289853543 12076328289978502 12076328289981509
35 33 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 66 921580 921585 4194304 256 0 0 28 24 37312 0x7fc1ce3b2a00 0x7fc0c2835900 12076328290011795 12076328290023942 12076328290273219 12076328290328403
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 68 921580 921585 4194304 256 0 0 28 24 38272 0x7fc1ce3b2900 0x7fc0c2835940 12076328290350675 12076328290363618 12076328290606816 12076328290661202
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 70 921580 921585 4194304 256 0 0 24 24 39232 0x7fc1ce3b2800 0x7fc0c2835980 12076328290682592 12076328290695135 12076328290820094 12076328290823453
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 72 921580 921585 4194304 256 0 0 24 24 40192 0x7fc1ce3b2700 0x7fc0c28359c0 12076328290849432 12076328290860414 12076328290985692 12076328290988941
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 74 921580 921585 4194304 256 0 0 24 24 41152 0x7fc1ce3b2600 0x7fc0c2835a00 12076328291030689 12076328291042172 12076328291166171 12076328291169607
40 38 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 76 921580 921585 4194304 256 0 0 28 24 42624 0x7fc1ce3b2500 0x7fc0c2835a40 12076328291196156 12076328291207930 12076328291454808 12076328291511642
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 78 921580 921585 4194304 256 0 0 28 24 43584 0x7fc1ce3b2400 0x7fc0c2835a80 12076328291534896 12076328291547927 12076328291791605 12076328291816539
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 80 921580 921585 4194304 256 0 0 24 24 44544 0x7fc1ce3b2300 0x7fc0c2835ac0 12076328291840223 12076328291851764 12076328291976563 12076328291979882
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 82 921580 921585 4194304 256 0 0 24 24 45760 0x7fc1ce3b2a00 0x7fc0c2835b00 12076328292010920 12076328292022803 12076328292148561 12076328292151812
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 84 921580 921585 4194304 256 0 0 24 24 46720 0x7fc1ce3b2900 0x7fc0c2835b40 12076328292188039 12076328292201201 12076328292325840 12076328292329182
45 43 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 86 921580 921585 4194304 256 0 0 28 24 48448 0x7fc1ce3b2800 0x7fc0c2835b80 12076328292354940 12076328292365999 12076328292617677 12076328292636793
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 88 921580 921585 4194304 256 0 0 28 24 49408 0x7fc1ce3b2700 0x7fc0c2835bc0 12076328292658373 12076328292669357 12076328292916074 12076328292935699
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 90 921580 921585 4194304 256 0 0 24 24 50368 0x7fc1ce3b2600 0x7fc0c2835c00 12076328292954734 12076328292965994 12076328293090633 12076328293093873
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 92 921580 921585 4194304 256 0 0 24 24 51584 0x7fc1ce3b2500 0x7fc0c2835c40 12076328293121103 12076328293131912 12076328293259431 12076328293262406
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 94 921580 921585 4194304 256 0 0 24 24 52544 0x7fc1ce3b2400 0x7fc0c2835c80 12076328293300567 12076328293311910 12076328293436869 12076328293439926
50 48 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 96 921580 921585 4194304 256 0 0 28 24 54272 0x7fc1ce3b2300 0x7fc0c2835cc0 12076328293466065 12076328293478149 12076328293729347 12076328293752527
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 98 921580 921585 4194304 256 0 0 28 24 55488 0x7fc1ce3b2a00 0x7fc0c2835d00 12076328293773806 12076328293786306 12076328294031104 12076328294055570
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 100 921580 921585 4194304 256 0 0 24 24 56704 0x7fc1ce3b2900 0x7fc0c2835d40 12076328294076248 12076328294088703 12076328294213502 12076328294216309
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 102 921580 921585 4194304 256 0 0 24 24 58176 0x7fc1ce3b2800 0x7fc0c2835d80 12076328294241656 12076328294252862 12076328294379900 12076328294382888
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 104 921580 921585 4194304 256 0 0 24 24 59392 0x7fc1ce3b2700 0x7fc0c2835dc0 12076328294418545 12076328294431580 12076328294556859 12076328294559737
55 53 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 106 921580 921585 4194304 256 0 0 28 24 61376 0x7fc1ce3b2600 0x7fc0c2835e00 12076328294585285 12076328294598298 12076328294849976 12076328294868801
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 108 921580 921585 4194304 256 0 0 28 24 62592 0x7fc1ce3b2500 0x7fc0c2835e40 12076328294889520 12076328294902615 12076328295151573 12076328295175802
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 110 921580 921585 4194304 256 0 0 24 24 63808 0x7fc1ce3b2400 0x7fc0c2835e80 12076328295198935 12076328295211893 12076328295336691 12076328295339857
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 112 921580 921585 4194304 256 0 0 24 24 65280 0x7fc1ce3b2300 0x7fc0c2835ec0 12076328295366046 12076328295377651 12076328295507410 12076328295510384
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 114 921580 921585 4194304 256 0 0 24 24 66496 0x7fc1ce3b2a00 0x7fc0c2835f00 12076328295546761 12076328295558289 12076328295683568 12076328295686752
60 58 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 116 921580 921585 4194304 256 0 0 28 24 68480 0x7fc1ce3b2900 0x7fc0c2835f40 12076328295713010 12076328295726128 12076328295989485 12076328296017226
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 118 921580 921585 4194304 256 0 0 28 24 69696 0x7fc1ce3b2800 0x7fc0c2835f80 12076328296038936 12076328296051885 12076328296296042 12076328296319227
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 120 921580 921585 4194304 256 0 0 24 24 70912 0x7fc1ce3b2700 0x7fc0c2835fc0 12076328296340867 12076328296353322 12076328296477961 12076328296480927
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 122 921580 921585 4194304 256 0 0 24 24 72384 0x7fc1ce3b2600 0x7fc0c2836000 12076328296507066 12076328296518280 12076328296654439 12076328296657546
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 124 921580 921585 4194304 256 0 0 24 24 73600 0x7fc1ce3b2500 0x7fc0c2836040 12076328296695366 12076328296707398 12076328296831877 12076328296834715
65 63 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 126 921580 921585 4194304 256 0 0 28 24 75840 0x7fc1ce3b2400 0x7fc0c2836080 12076328296860693 12076328296872357 12076328297132994 12076328297165039
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 128 921580 921585 4194304 256 0 0 28 24 77056 0x7fc1ce3b2300 0x7fc0c28360c0 12076328297187260 12076328297199394 12076328297444991 12076328297469595
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 130 921580 921585 4194304 256 0 0 24 24 78272 0x7fc1ce3b2a00 0x7fc0c2836100 12076328297490253 12076328297502591 12076328297627230 12076328297630223
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 132 921580 921585 4194304 256 0 0 24 24 80000 0x7fc1ce3b2900 0x7fc0c2836140 12076328297656091 12076328297667389 12076328297809788 12076328297812753
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 134 921580 921585 4194304 256 0 0 24 24 81216 0x7fc1ce3b2800 0x7fc0c2836180 12076328297849160 12076328297860987 12076328297985946 12076328297989140
70 68 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 136 921580 921585 4194304 256 0 0 28 24 83456 0x7fc1ce3b2700 0x7fc0c28361c0 12076328298020028 12076328298031386 12076328298284983 12076328298311640
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 138 921580 921585 4194304 256 0 0 28 24 84928 0x7fc1ce3b2600 0x7fc0c2836200 12076328298331847 12076328298343383 12076328298589621 12076328298616817
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 140 921580 921585 4194304 256 0 0 24 24 86400 0x7fc1ce3b2500 0x7fc0c2836240 12076328298641623 12076328298654260 12076328298780979 12076328298784038
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 142 921580 921585 4194304 256 0 0 24 24 88128 0x7fc1ce3b2400 0x7fc0c2836280 12076328298808974 12076328298821618 12076328298971377 12076328298974672
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 144 921580 921585 4194304 256 0 0 24 24 89600 0x7fc1ce3b2300 0x7fc0c28362c0 12076328299030676 12076328299042576 12076328299167695 12076328299171197
75 73 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 146 921580 921585 4194304 256 0 0 28 24 92096 0x7fc1ce3b2a00 0x7fc0c2836300 12076328299197967 12076328299211215 12076328299464812 12076328299487175
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 148 921580 921585 4194304 256 0 0 28 24 93568 0x7fc1ce3b2900 0x7fc0c2836340 12076328299508584 12076328299521292 12076328299772489 12076328299795878
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 150 921580 921585 4194304 256 0 0 24 24 95040 0x7fc1ce3b2800 0x7fc0c2836380 12076328299816136 12076328299828489 12076328299954088 12076328299957138
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 152 921580 921585 4194304 256 0 0 24 24 96768 0x7fc1ce3b2700 0x7fc0c28363c0 12076328299982896 12076328299994247 12076328300152326 12076328300155396
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 154 921580 921585 4194304 256 0 0 24 24 98240 0x7fc1ce3b2600 0x7fc0c2836400 12076328300192926 12076328300204965 12076328300330244 12076328300333618
80 78 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 156 921580 921585 4194304 256 0 0 28 24 100736 0x7fc1ce3b2500 0x7fc0c2836440 12076328300359496 12076328300370884 12076328300624801 12076328300647090
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 158 921580 921585 4194304 256 0 0 28 24 102208 0x7fc1ce3b2400 0x7fc0c2836480 12076328300668179 12076328300679681 12076328300927039 12076328300949612
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 160 921580 921585 4194304 256 0 0 24 24 103680 0x7fc1ce3b2300 0x7fc0c28364c0 12076328300969940 12076328300980958 12076328301106237 12076328301109660
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 162 921580 921585 4194304 256 0 0 24 24 105664 0x7fc1ce3b2a00 0x7fc0c2836500 12076328301135007 12076328301145916 12076328301310395 12076328301314070
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 164 921580 921585 4194304 256 0 0 24 24 107136 0x7fc1ce3b2900 0x7fc0c2836540 12076328301349906 12076328301361274 12076328301486553 12076328301489626
85 83 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 166 921580 921585 4194304 256 0 0 28 24 109888 0x7fc1ce3b2800 0x7fc0c2836580 12076328301516135 12076328301528153 12076328301783990 12076328301806735
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 168 921580 921585 4194304 256 0 0 28 24 111360 0x7fc1ce3b2700 0x7fc0c28365c0 12076328301828015 12076328301841110 12076328302090228 12076328302113816
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 170 921580 921585 4194304 256 0 0 24 24 112832 0x7fc1ce3b2600 0x7fc0c2836600 12076328302136859 12076328302149427 12076328302275026 12076328302278342
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 172 921580 921585 4194304 256 0 0 24 24 114816 0x7fc1ce3b2500 0x7fc0c2836640 12076328302303909 12076328302316945 12076328302489104 12076328302492410
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 174 921580 921585 4194304 256 0 0 24 24 116288 0x7fc1ce3b2400 0x7fc0c2836680 12076328302528587 12076328302541583 12076328302667022 12076328302670280
90 88 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 176 921580 921585 4194304 256 0 0 28 24 119040 0x7fc1ce3b2300 0x7fc0c28366c0 12076328302696369 12076328302707982 12076328302964139 12076328302986678
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 178 921580 921585 4194304 256 0 0 28 24 120768 0x7fc1ce3b2a00 0x7fc0c2836700 12076328303011745 12076328303023019 12076328303267976 12076328303295001
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 180 921580 921585 4194304 256 0 0 24 24 122496 0x7fc1ce3b2900 0x7fc0c2836740 12076328303317523 12076328303328936 12076328303454215 12076328303457353
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 182 921580 921585 4194304 256 0 0 24 24 124736 0x7fc1ce3b2800 0x7fc0c2836780 12076328303482750 12076328303494214 12076328303676293 12076328303679416
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 184 921580 921585 4194304 256 0 0 24 24 126464 0x7fc1ce3b2700 0x7fc0c28367c0 12076328303715833 12076328303729252 12076328303855491 12076328303858879
95 93 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 186 921580 921585 4194304 256 0 0 20 24 127936 0x7fc1ce3b2600 0x7fc0c2836800 12076328303884727 12076328303897250 12076328304193568 12076328304217075
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 188 921580 921585 4194304 256 0 0 28 24 129664 0x7fc1ce3b2500 0x7fc0c2836840 12076328304238034 12076328304250687 12076328304496765 12076328304519777
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 190 921580 921585 4194304 256 0 0 24 24 131392 0x7fc1ce3b2400 0x7fc0c2836880 12076328304542760 12076328304556124 12076328304682523 12076328304686267
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 192 921580 921585 4194304 256 0 0 24 24 133632 0x7fc1ce3b2300 0x7fc0c28368c0 12076328304712315 12076328304724923 12076328304916601 12076328304919851
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 194 921580 921585 4194304 256 0 0 24 24 135360 0x7fc1ce3b2a00 0x7fc0c2836900 12076328304956910 12076328304969240 12076328305095799 12076328305099445
100 98 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 196 921580 921585 4194304 256 0 0 20 24 136832 0x7fc1ce3b2900 0x7fc0c2836940 12076328305126014 12076328305139319 12076328305421876 12076328305446179
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 198 921580 921585 4194304 256 0 0 28 24 138560 0x7fc1ce3b2800 0x7fc0c2836980 12076328305468711 12076328305481555 12076328305732913 12076328305759321
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 200 921580 921585 4194304 256 0 0 24 24 140288 0x7fc1ce3b2700 0x7fc0c28369c0 12076328305780941 12076328305793393 12076328305918831 12076328305922043
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 202 921580 921585 4194304 256 0 0 24 24 142784 0x7fc1ce3b2600 0x7fc0c2836a00 12076328305949234 12076328305959791 12076328306169869 12076328306197075
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 204 921580 921585 4194304 256 0 0 24 24 144768 0x7fc1ce3b2500 0x7fc0c2836a40 12076328306228493 12076328306239948 12076328306370027 12076328306373392
105 103 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 206 921580 921585 4194304 256 0 0 20 24 145728 0x7fc1ce3b2400 0x7fc0c2836a80 12076328306399170 12076328306411307 12076328306718024 12076328306740224
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 208 921580 921585 4194304 256 0 0 28 24 147712 0x7fc1ce3b2300 0x7fc0c2836ac0 12076328306761123 12076328306772263 12076328307024101 12076328307051893
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 210 921580 921585 4194304 256 0 0 24 24 149696 0x7fc1ce3b2a00 0x7fc0c2836b00 12076328307073984 12076328307086500 12076328307214019 12076328307217321
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 212 921580 921585 4194304 256 0 0 24 24 152192 0x7fc1ce3b2900 0x7fc0c2836b40 12076328307242718 12076328307254019 12076328307481057 12076328307507219
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 214 921580 921585 4194304 256 0 0 24 24 154176 0x7fc1ce3b2800 0x7fc0c2836b80 12076328307538868 12076328307551136 12076328307677535 12076328307680822
110 108 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 216 921580 921585 4194304 256 0 0 20 24 155648 0x7fc1ce3b2700 0x7fc0c2836bc0 12076328307706550 12076328307717854 12076328308046011 12076328308073191
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 218 921580 921585 4194304 256 0 0 28 24 157632 0x7fc1ce3b2600 0x7fc0c2836c00 12076328308094771 12076328308107451 12076328308359448 12076328308385832
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 220 921580 921585 4194304 256 0 0 24 24 159616 0x7fc1ce3b2500 0x7fc0c2836c40 12076328308406601 12076328308419448 12076328308547447 12076328308550799
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 222 921580 921585 4194304 256 0 0 24 24 162368 0x7fc1ce3b2400 0x7fc0c2836c80 12076328308576006 12076328308589366 12076328308832404 12076328308858491
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 224 921580 921585 4194304 256 0 0 24 24 164608 0x7fc1ce3b2300 0x7fc0c2836cc0 12076328308889107 12076328308902163 12076328309031602 12076328309035229
115 113 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 226 921580 921585 4194304 256 0 0 20 24 166336 0x7fc1ce3b2a00 0x7fc0c2836d00 12076328309060666 12076328309071922 12076328309446638 12076328309476750
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 228 921580 921585 4194304 256 0 0 28 24 168576 0x7fc1ce3b2900 0x7fc0c2836d40 12076328309498029 12076328309509357 12076328309760075 12076328309786235
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 230 921580 921585 4194304 256 0 0 24 24 170816 0x7fc1ce3b2800 0x7fc0c2836d80 12076328309808376 12076328309820075 12076328309948873 12076328309952123
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 232 921580 921585 4194304 256 0 0 24 24 174080 0x7fc1ce3b2700 0x7fc0c2836dc0 12076328309977791 12076328309990473 12076328310268230 12076328310291504
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 234 921580 921585 4194304 256 0 0 24 24 176576 0x7fc1ce3b2600 0x7fc0c2836e00 12076328310323363 12076328310334790 12076328310470468 12076328310473672
120 118 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 236 921580 921585 4194304 256 0 0 20 24 177792 0x7fc1ce3b2500 0x7fc0c2836e40 12076328310499410 12076328310511268 12076328310933824 12076328310957331
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 238 921580 921585 4194304 256 0 0 28 24 180288 0x7fc1ce3b2400 0x7fc0c2836e80 12076328310980524 12076328310991423 12076328311257501 12076328311284690
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 240 921580 921585 4194304 256 0 0 24 24 182784 0x7fc1ce3b2300 0x7fc0c2836ec0 12076328311304076 12076328311315260 12076328311450619 12076328311453844
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 242 921580 921585 4194304 256 0 0 24 24 186304 0x7fc1ce3b2a00 0x7fc0c2836f00 12076328311481495 12076328311491899 12076328311806136 12076328311832137
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 244 921580 921585 4194304 256 0 0 24 24 189312 0x7fc1ce3b2900 0x7fc0c2836f40 12076328311865519 12076328311876855 12076328312028694 12076328312032049
125 123 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 246 921580 921585 4194304 256 0 0 20 24 190784 0x7fc1ce3b2800 0x7fc0c2836f80 12076328312058758 12076328312071093 12076328312587568 12076328312613850
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 248 921580 921585 4194304 256 0 0 28 24 193792 0x7fc1ce3b2700 0x7fc0c2836fc0 12076328312635360 12076328312647728 12076328312949165 12076328312975372
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 250 921580 921585 4194304 256 0 0 24 24 196800 0x7fc1ce3b2600 0x7fc0c2837000 12076328312995659 12076328313006604 12076328313159883 12076328313163421
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 252 921580 921585 4194304 256 0 0 24 24 201088 0x7fc1ce3b2500 0x7fc0c2837040 12076328313190341 12076328313204043 12076328313588519 12076328313611744
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 254 921580 921585 4194304 256 0 0 24 24 204608 0x7fc1ce3b2400 0x7fc0c2837080 12076328313643133 12076328313654438 12076328313829637 12076328313832845
130 128 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 256 921580 921585 4194304 256 0 0 20 24 206080 0x7fc1ce3b2300 0x7fc0c28370c0 12076328313858964 12076328313872516 12076328314481310 12076328314504854
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 258 921580 921585 4194304 256 0 0 28 24 209600 0x7fc1ce3b2a00 0x7fc0c2837100 12076328314527316 12076328314539550 12076328314869947 12076328314892695
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 260 921580 921585 4194304 256 0 0 24 24 213120 0x7fc1ce3b2900 0x7fc0c2837140 12076328314916589 12076328314927706 12076328315105785 12076328315109298
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 262 921580 921585 4194304 256 0 0 24 24 218176 0x7fc1ce3b2800 0x7fc0c2837180 12076328315136568 12076328315147544 12076328315602740 12076328315625367
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 264 921580 921585 4194304 256 0 0 24 24 222208 0x7fc1ce3b2700 0x7fc0c28371c0 12076328315656605 12076328315669139 12076328315868177 12076328315890389
135 133 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 266 921580 921585 4194304 256 0 0 20 24 223936 0x7fc1ce3b2600 0x7fc0c2837200 12076328315909935 12076328315921137 12076328316623050 12076328316652245
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 268 921580 921585 4194304 256 0 0 28 24 227968 0x7fc1ce3b2500 0x7fc0c2837240 12076328316674667 12076328316685770 12076328317058246 12076328317085961
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 270 921580 921585 4194304 256 0 0 24 24 232000 0x7fc1ce3b2400 0x7fc0c2837280 12076328317112040 12076328317123206 12076328317325764 12076328317352116
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 272 921580 921585 4194304 256 0 0 24 24 237824 0x7fc1ce3b2300 0x7fc0c28372c0 12076328317372964 12076328317384003 12076328317909438 12076328317935410
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 274 921580 921585 4194304 256 0 0 24 24 242368 0x7fc1ce3b2a00 0x7fc0c2837300 12076328317968030 12076328317979357 12076328318237755 12076328318269951
140 138 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 276 921580 921585 4194304 256 0 0 20 24 243584 0x7fc1ce3b2900 0x7fc0c2837340 12076328318290960 12076328318303034 12076328319100947 12076328319129479
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 278 921580 921585 4194304 256 0 0 28 24 248128 0x7fc1ce3b2800 0x7fc0c2837380 12076328319154806 12076328319166066 12076328319587502 12076328319613749
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 280 921580 921585 4194304 256 0 0 24 24 252672 0x7fc1ce3b2700 0x7fc0c28373c0 12076328319637002 12076328319648462 12076328319873100 12076328319898748
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 282 921580 921585 4194304 256 0 0 24 24 259264 0x7fc1ce3b2600 0x7fc0c2837400 12076328319920669 12076328319932939 12076328320529253 12076328320556331
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 284 921580 921585 4194304 256 0 0 24 24 264832 0x7fc1ce3b2500 0x7fc0c2837440 12076328320588520 12076328320601253 12076328320871010 12076328320894018
145 143 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 286 921580 921585 4194304 256 0 0 20 24 266304 0x7fc1ce3b2400 0x7fc0c2837480 12076328320915799 12076328320926850 12076328321911160 12076328321941896
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 288 921580 921585 4194304 256 0 0 28 24 271872 0x7fc1ce3b2300 0x7fc0c28374c0 12076328321962213 12076328321973240 12076328322485715 12076328322513037
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 290 921580 921585 4194304 256 0 0 24 24 277440 0x7fc1ce3b2a00 0x7fc0c2837500 12076328322538134 12076328322549234 12076328322820432 12076328322842910
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 292 921580 921585 4194304 256 0 0 12 24 279936 0x7fc1ce3b2900 0x7fc0c2837540 12076328322865682 12076328322877231 12076328323614664 12076328323648066
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 294 921580 921585 4194304 256 0 0 24 24 286528 0x7fc1ce3b2800 0x7fc0c2837580 12076328323679785 12076328323691303 12076328324006820 12076328324033843
150 148 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 296 921580 921585 4194304 256 0 0 20 24 288000 0x7fc1ce3b2700 0x7fc0c28375c0 12076328324060243 12076328324071620 12076328325242329 12076328325266614
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 298 921580 921585 4194304 256 0 0 32 24 294592 0x7fc1ce3b2600 0x7fc0c2837600 12076328325292813 12076328325304088 12076328325913202 12076328325936920
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 300 921580 921585 4194304 256 0 0 24 24 301184 0x7fc1ce3b2500 0x7fc0c2837640 12076328325963039 12076328325975762 12076328326294799 12076328326323589
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 302 921580 921585 4194304 256 0 0 12 24 304960 0x7fc1ce3b2400 0x7fc0c2837680 12076328326349387 12076328326360398 12076328327238150 12076328327267373
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 304 921580 921585 4194304 256 0 0 24 24 313600 0x7fc1ce3b2300 0x7fc0c28376c0 12076328327303049 12076328327315909 12076328327724385 12076328327752785
155 153 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 306 921580 921585 4194304 256 0 0 20 24 314816 0x7fc1ce3b2a00 0x7fc0c2837700 12076328327775457 12076328327788385 12076328329338130 12076328329409243
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 308 921580 921585 4194304 256 0 0 20 24 317568 0x7fc1ce3b2900 0x7fc0c2837740 12076328329433268 12076328329446494 12076328330240888 12076328330315778
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 310 921580 921585 4194304 256 0 0 12 24 320320 0x7fc1ce3b2800 0x7fc0c2837780 12076328330335795 12076328330349046 12076328330762483 12076328330832368
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 312 921580 921585 4194304 256 0 0 12 24 324096 0x7fc1ce3b2700 0x7fc0c28377c0 12076328330856042 12076328330867602 12076328332025833 12076328332098802
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 314 921580 921585 4194304 256 0 0 12 24 328896 0x7fc1ce3b2600 0x7fc0c2837800 12076328332133025 12076328332148552 12076328332933986 12076328333006859
160 158 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 316 921580 921585 4194304 256 0 0 20 24 330112 0x7fc1ce3b2500 0x7fc0c2837840 12076328333028720 12076328333040865 12076328336096201 12076328336166511
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 318 921580 921585 4194304 256 0 0 20 24 332864 0x7fc1ce3b2400 0x7fc0c2837880 12076328336195776 12076328336207400 12076328337749468 12076328337820415
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 320 921580 921585 4194304 256 0 0 12 24 335616 0x7fc1ce3b2300 0x7fc0c28378c0 12076328337848287 12076328337860667 12076328338649301 12076328338723804
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 322 921580 921585 4194304 256 0 0 12 24 339392 0x7fc1ce3b2a00 0x7fc0c2837900 12076328338747668 12076328338759380 12076328341041122 12076328341111622
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 324 921580 921585 4194304 256 0 0 12 24 344192 0x7fc1ce3b2900 0x7fc0c2837940 12076328341146376 12076328341158241 12076328342692949 12076328342764133
165 163 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 326 921580 921585 4194304 256 0 0 20 24 345408 0x7fc1ce3b2800 0x7fc0c2837980 12076328342787035 12076328342799028 12076328348854340 12076328348924932
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 328 921580 921585 4194304 256 0 0 20 24 348160 0x7fc1ce3b2700 0x7fc0c28379c0 12076328348949458 12076328348960739 12076328352004075 12076328352077892
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 330 921580 921585 4194304 256 0 0 12 24 350912 0x7fc1ce3b2600 0x7fc0c2837a00 12076328352100574 12076328352112075 12076328353651102 12076328353722028
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 332 921580 921585 4194304 256 0 0 12 24 0 0x7fc1ce3b2500 0x7fc0c2837a40 12076328353744509 12076328353758782 12076328358285786 12076328358356250
@@ -0,0 +1,168 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,grd,Workgroup_Size,LDS_Per_Workgroup,scr,vgpr,SGPR,fbar,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"__amd_rocclr_fillBufferAligned.kd",0,0,0,223297,223297,33554432,256,0,0,4,32,4160,0x0,0x7fc57a604280,379284,379284,524288,4718592,681163,76310828,17598097140845,17597387743185,17598246526395,17598246639545
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,223297,223297,32768,256,0,0,12,24,13888,0x0,0x7fc57a623f80,33251,33251,512,8192,6010,679448,17598251787224,17598246526395,17598251919198,17598251924230
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,223297,223297,4194304,256,0,0,12,24,14336,0x7fc57d663380,0x7fc57a623fc0,163594,163594,65536,917504,141997,15950860,17598251961259,17598251919198,17598252301279,17598252303751
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,223297,223297,4194304,256,0,0,16,24,15040,0x7fc57d663200,0x7fc57a624000,310676,310676,65536,1114112,172028,19257004,17598252343430,17598252301279,17598252724159,17598252726940
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,223297,223297,4194304,256,0,0,16,24,15488,0x7fc57d663080,0x7fc57a624040,309020,309020,65536,917504,138926,15550360,17598252763489,17598252724159,17598253136799,17598253139200
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,223297,223297,4194304,256,0,0,12,24,15936,0x7fc57b003f00,0x7fc57a624080,164976,164976,65536,1048576,157741,17738236,17598253175849,17598253136799,17598253450240,17598253452452
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,223297,223297,4194304,256,0,0,12,24,16384,0x7fc57b003d80,0x7fc57a6240c0,163529,163529,65536,983040,148002,16556188,17598253487311,17598253450240,17598253764800,17598253767114
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,223297,223297,4194304,256,0,0,12,24,17088,0x7fc57b003c00,0x7fc57a624100,162196,162196,65536,1114112,162834,18259480,17598253814412,17598253764800,17598254076000,17598254086866
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,223297,223297,4194304,256,0,0,16,24,17792,0x7fc57b003a80,0x7fc57a624140,309800,309800,65536,1310720,206086,23129588,17598254114915,17598254076000,17598254485600,17598254487735
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,223297,223297,4194304,256,0,0,16,24,18496,0x7fc57b003900,0x7fc57a624180,306944,306944,65536,1179648,177127,19842568,17598254522574,17598254485600,17598254905121,17598254906905
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,223297,223297,4194304,256,0,0,16,24,19200,0x7fc57b003780,0x7fc57a6241c0,164084,164084,65536,1245184,189398,21184652,17598254940604,17598254905121,17598255192801,17598255194607
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,223297,223297,4194304,256,0,0,16,24,19904,0x7fc57b003600,0x7fc57a624200,162975,162975,65536,1245184,186637,20929980,17598255228957,17598255192801,17598255477761,17598255479620
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,223297,223297,4194304,256,0,0,12,24,20608,0x7fc57d663480,0x7fc57a624240,163260,163260,65536,1245184,188086,21072920,17598255522339,17598255477761,17598255766241,17598255768043
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,223297,223297,4194304,256,0,0,16,24,21312,0x7fc57d663300,0x7fc57a624280,308005,308005,65536,1441792,215714,24176728,17598255805652,17598255766241,17598256148642,17598256150373
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,223297,223297,4194304,256,0,0,16,24,22016,0x7fc57d663180,0x7fc57a6242c0,308010,308010,65536,1310720,199745,22367996,17598256185452,17598256148642,17598256525122,17598256526884
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,223297,223297,4194304,256,0,0,16,24,22720,0x7fc57d663000,0x7fc57a624300,163878,163878,65536,1376256,206041,23082112,17598256561523,17598256525122,17598256815042,17598256816776
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,223297,223297,4194304,256,0,0,12,24,23424,0x7fc57b003e80,0x7fc57a624340,163340,163340,65536,1441792,217864,24335144,17598256851235,17598256815042,17598257106722,17598257108309
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,223297,223297,4194304,256,0,0,12,24,24128,0x7fc57b003d00,0x7fc57a624380,162064,162064,65536,1310720,196821,22019008,17598257150368,17598257106722,17598257405123,17598257406731
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,223297,223297,4194304,256,0,0,16,24,24832,0x7fc57b003b80,0x7fc57a6243c0,308441,308441,65536,1572864,233127,26082088,17598257442950,17598257405123,17598257779363,17598257781082
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,223297,223297,4194304,256,0,0,16,24,25536,0x7fc57b003a00,0x7fc57a624400,304557,304557,65536,1441792,208665,23365924,17598257815321,17598257779363,17598258155363,17598258157062
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,223297,223297,4194304,256,0,0,12,24,26240,0x7fc57b003880,0x7fc57a624440,162559,162559,65536,1507328,226838,25406660,17598258192311,17598258155363,17598258447363,17598258449185
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,223297,223297,4194304,256,0,0,12,24,26944,0x7fc57b003700,0x7fc57a624480,163057,163057,65536,1638400,243091,27262240,17598258484414,17598258447363,17598258737924,17598258739588
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,223297,223297,4194304,256,0,0,12,24,27648,0x7fc57d663580,0x7fc57a6244c0,161757,161757,65536,1441792,214563,24030252,17598258783146,17598258737924,17598259034244,17598259035990
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,223297,223297,4194304,256,0,0,16,24,28608,0x7fc57d663400,0x7fc57a624500,305217,305217,65536,1703936,252073,28235268,17598259072069,17598259034244,17598259410084,17598259411920
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,223297,223297,4194304,256,0,0,16,24,29312,0x7fc57d663280,0x7fc57a624540,303171,303171,65536,1572864,232908,26123324,17598259447019,17598259410084,17598259783844,17598259785641
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,223297,223297,4194304,256,0,0,12,24,30016,0x7fc57d663100,0x7fc57a624580,161758,161758,65536,1638400,243285,27310660,17598259820640,17598259783844,17598260071845,17598260073763
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,223297,223297,4194304,256,0,0,8,24,30976,0x7fc57b003f80,0x7fc57a6245c0,160538,160538,65536,1835008,270103,30322488,17598260108543,17598260071845,17598260358725,17598260360476
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,223297,223297,4194304,256,0,0,12,24,31680,0x7fc57b003e00,0x7fc57a624600,163862,163862,65536,1507328,224594,25081836,17598260402215,17598260358725,17598260656645,17598260658339
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,223297,223297,4194304,256,0,0,16,24,32640,0x7fc57b003c80,0x7fc57a624640,306084,306084,65536,1835008,271175,30248500,17598260694318,17598260656645,17598261046085,17598261047719
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,223297,223297,4194304,256,0,0,12,24,33600,0x7fc57b003b00,0x7fc57a624680,307380,307380,65536,1703936,249875,27955212,17598261082628,17598261046085,17598261424326,17598261425939
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,223297,223297,4194304,256,0,0,12,24,34560,0x7fc57b003980,0x7fc57a6246c0,163238,163238,65536,1769472,265219,29706488,17598261460008,17598261424326,17598261712486,17598261714362
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,223297,223297,4194304,256,0,0,8,24,35520,0x7fc57b003800,0x7fc57a624700,162860,162860,65536,2031616,303442,33955492,17598261748951,17598261712486,17598262001606,17598262003354
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,223297,223297,4194304,256,0,0,12,24,36224,0x7fc57b003680,0x7fc57a624740,161890,161890,65536,1638400,263222,29471680,17598262044743,17598262001606,17598262297446,17598262299177
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,223297,223297,4194304,256,0,0,12,24,37184,0x7fc57d663500,0x7fc57a624780,304550,304550,65536,1966080,288953,32377204,17598262334206,17598262297446,17598262682727,17598262684327
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,223297,223297,4194304,256,0,0,12,24,38144,0x7fc57d663380,0x7fc57a6247c0,304419,304419,65536,1835008,279877,31253588,17598262719856,17598262682727,17598263061447,17598263063217
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,223297,223297,4194304,256,0,0,12,24,39104,0x7fc57d663200,0x7fc57a624800,162792,162792,65536,1900544,285508,31920360,17598263098776,17598263061447,17598263352487,17598263354190
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,223297,223297,4194304,256,0,0,8,24,40320,0x7fc57d663080,0x7fc57a624840,163607,163607,65536,2228224,346629,38837308,17598263390639,17598263352487,17598263644167,17598263645983
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,223297,223297,4194304,256,0,0,12,24,41280,0x7fc57b003f00,0x7fc57a624880,161512,161512,65536,1703936,258557,28939128,17598263688412,17598263644167,17598263940008,17598263941695
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,223297,223297,4194304,256,0,0,12,24,42240,0x7fc57b003d80,0x7fc57a6248c0,304171,304171,65536,2097152,311294,34802656,17598263978294,17598263940008,17598264318088,17598264320046
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,223297,223297,4194304,256,0,0,12,24,43200,0x7fc57b003c00,0x7fc57a624900,303740,303740,65536,1966080,285331,31960944,17598264354835,17598264318088,17598264698408,17598264699996
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,223297,223297,4194304,256,0,0,8,24,44160,0x7fc57b003a80,0x7fc57a624940,161837,161837,65536,2031616,305326,34228756,17598264734605,17598264698408,17598264988488,17598264990239
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,223297,223297,4194304,256,0,0,12,24,45376,0x7fc57b003900,0x7fc57a624980,163205,163205,65536,2424832,361416,40511376,17598265024908,17598264988488,17598265282729,17598265284531
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,223297,223297,4194304,256,0,0,12,24,46336,0x7fc57b003780,0x7fc57a6249c0,161312,161312,65536,1835008,274162,30739912,17598265326330,17598265282729,17598265578409,17598265580184
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,223297,223297,4194304,256,0,0,12,24,47552,0x7fc57b003600,0x7fc57a624a00,306564,306564,65536,2228224,328050,36721992,17598265616243,17598265578409,17598265955529,17598265957354
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,223297,223297,4194304,256,0,0,12,24,48512,0x7fc57d663480,0x7fc57a624a40,302434,302434,65536,2097152,309303,34586432,17598265992943,17598265955529,17598266337609,17598266339694
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,223297,223297,4194304,256,0,0,8,24,49472,0x7fc57d663300,0x7fc57a624a80,161867,161867,65536,2162688,318107,35667196,17598266374213,17598266337609,17598266627530,17598266629077
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,223297,223297,4194304,256,0,0,12,24,50688,0x7fc57d663180,0x7fc57a624ac0,161314,161314,65536,2621440,397899,44557408,17598266664246,17598266627530,17598266916650,17598266918410
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,223297,223297,4194304,256,0,0,12,24,51648,0x7fc57d663000,0x7fc57a624b00,160569,160569,65536,1966080,292828,32729708,17598266960678,17598266916650,17598267207370,17598267209012
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,223297,223297,4194304,256,0,0,12,24,52864,0x7fc57b003e80,0x7fc57a624b40,303754,303754,65536,2359296,347958,38955816,17598267243241,17598267207370,17598267584010,17598267585722
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,223297,223297,4194304,256,0,0,12,24,54080,0x7fc57b003d00,0x7fc57a624b80,301553,301553,65536,2228224,330564,37009284,17598267620532,17598267584010,17598267968971,17598267970733
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,223297,223297,4194304,256,0,0,8,24,55296,0x7fc57b003b80,0x7fc57a624bc0,161840,161840,65536,2293760,341860,38219528,17598268006032,17598267968971,17598268259851,17598268261575
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,223297,223297,4194304,256,0,0,12,24,56768,0x7fc57b003a00,0x7fc57a624c00,163433,163433,65536,2752512,418160,46830460,17598268297364,17598268259851,17598268553131,17598268555078
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,223297,223297,4194304,256,0,0,12,24,57728,0x7fc57b003880,0x7fc57a624c40,162472,162472,65536,2031616,327412,36578768,17598268597427,17598268553131,17598268849131,17598268850910
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,223297,223297,4194304,256,0,0,12,24,58944,0x7fc57b003700,0x7fc57a624c80,300606,300606,65536,2490368,374186,41850496,17598268885249,17598268849131,17598269224652,17598269226301
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,223297,223297,4194304,256,0,0,12,24,60160,0x7fc57d663580,0x7fc57a624cc0,301210,301210,65536,2359296,349917,39249832,17598269262130,17598269224652,17598269605612,17598269607311
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,223297,223297,4194304,256,0,0,8,24,61376,0x7fc57d663400,0x7fc57a624d00,164759,164759,65536,2424832,402021,45040004,17598269642290,17598269605612,17598269900012,17598269901653
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,223297,223297,4194304,256,0,0,12,24,62848,0x7fc57d663280,0x7fc57a624d40,168038,168038,65536,2949120,441481,49485848,17598269937442,17598269900012,17598270200332,17598270202336
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,223297,223297,4194304,256,0,0,12,24,63808,0x7fc57d663100,0x7fc57a624d80,162222,162222,65536,2162688,326133,36467264,17598270244505,17598270200332,17598270503213,17598270505038
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,223297,223297,4194304,256,0,0,12,24,65024,0x7fc57b003f80,0x7fc57a624dc0,300132,300132,65536,2621440,403067,45203720,17598270542417,17598270503213,17598270879373,17598270881049
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,223297,223297,4194304,256,0,0,12,24,66240,0x7fc57b003e00,0x7fc57a624e00,297342,297342,65536,2490368,363422,40682956,17598270916698,17598270879373,17598271251693,17598271253479
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,223297,223297,4194304,256,0,0,8,24,67456,0x7fc57b003c80,0x7fc57a624e40,161790,161790,65536,2555904,385035,43147484,17598271288108,17598271251693,17598271555373,17598271557111
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,223297,223297,4194304,256,0,0,12,24,68928,0x7fc57b003b00,0x7fc57a624e80,175315,175315,65536,3145728,465475,52218840,17598271592291,17598271555373,17598271857134,17598271858854
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,223297,223297,4194304,256,0,0,12,24,70144,0x7fc57b003980,0x7fc57a624ec0,160832,160832,65536,2228224,327517,36700732,17598271901353,17598271857134,17598272152334,17598272154216
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,223297,223297,4194304,256,0,0,12,24,71616,0x7fc57b003800,0x7fc57a624f00,301078,301078,65536,2752512,406340,45513568,17598272188625,17598272152334,17598272528174,17598272529867
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,223297,223297,4194304,256,0,0,12,24,72832,0x7fc57b003680,0x7fc57a624f40,300842,300842,65536,2621440,390699,43686036,17598272564506,17598272528174,17598272903854,17598272905627
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,223297,223297,4194304,256,0,0,8,24,74048,0x7fc57d663500,0x7fc57a624f80,160830,160830,65536,2686976,395360,44292492,17598272939826,17598272903854,17598273198735,17598273200550
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,223297,223297,4194304,256,0,0,12,24,75776,0x7fc57d663380,0x7fc57a624fc0,182347,182347,65536,3342336,500899,56027040,17598273235849,17598273198735,17598273504975,17598273506752
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,223297,223297,4194304,256,0,0,12,24,76992,0x7fc57d663200,0x7fc57a625000,160788,160788,65536,2359296,351290,39283156,17598273561021,17598273504975,17598273796495,17598273798285
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,223297,223297,4194304,256,0,0,12,24,78464,0x7fc57d663080,0x7fc57a625040,300956,300956,65536,2883584,429814,48155448,17598273834214,17598273796495,17598274177935,17598274180075
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,223297,223297,4194304,256,0,0,12,24,79936,0x7fc57b003f00,0x7fc57a625080,301294,301294,65536,2686976,397384,44563000,17598274216954,17598274177935,17598274566416,17598274568035
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,223297,223297,4194304,256,0,0,8,24,81408,0x7fc57b003d80,0x7fc57a6250c0,161951,161951,65536,2818048,427963,47980996,17598274602984,17598274566416,17598274860656,17598274862508
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,223297,223297,4194304,256,0,0,12,24,83136,0x7fc57b003c00,0x7fc57a625100,192746,192746,65536,3538944,532322,59602316,17598274897647,17598274860656,17598275170736,17598275172540
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,223297,223297,4194304,256,0,0,12,24,84352,0x7fc57b003a80,0x7fc57a625140,161368,161368,65536,2424832,362958,40605932,17598275214489,17598275170736,17598275462896,17598275464632
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,223297,223297,4194304,256,0,0,12,24,85824,0x7fc57b003900,0x7fc57a625180,298410,298410,65536,3014656,455330,51053144,17598275499312,17598275462896,17598275843537,17598275845343
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,223297,223297,4194304,256,0,0,12,24,87296,0x7fc57b003780,0x7fc57a6251c0,299703,299703,65536,2818048,414678,46518540,17598275882412,17598275843537,17598276219537,17598276221333
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,223297,223297,4194304,256,0,0,12,24,88768,0x7fc57b003600,0x7fc57a625200,163032,163032,65536,2949120,440286,49312880,17598276255762,17598276219537,17598276511057,17598276512946
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,223297,223297,4194304,256,0,0,12,24,90752,0x7fc57d663480,0x7fc57a625240,201001,201001,65536,3735552,563175,63022556,17598276548175,17598276511057,17598276828337,17598276830078
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,223297,223297,4194304,256,0,0,12,24,91968,0x7fc57d663300,0x7fc57a625280,160772,160772,65536,2555904,384541,43027336,17598276872717,17598276828337,17598277120498,17598277122240
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,223297,223297,4194304,256,0,0,12,24,93440,0x7fc57d663180,0x7fc57a6252c0,301399,301399,65536,3145728,468135,52410600,17598277157359,17598277120498,17598277502898,17598277504591
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,223297,223297,4194304,256,0,0,12,24,94912,0x7fc57d663000,0x7fc57a625300,298032,298032,65536,2949120,438122,49043508,17598277540630,17598277502898,17598277878898,17598277880551
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,223297,223297,4194304,256,0,0,12,24,96384,0x7fc57b003e80,0x7fc57a625340,161173,161173,65536,3080192,458154,51258132,17598277914490,17598277878898,17598278168978,17598278170684
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,223297,223297,4194304,256,0,0,12,24,98368,0x7fc57b003d00,0x7fc57a625380,210176,210176,65536,3932160,584119,65374800,17598278206013,17598278168978,17598278501139,17598278502945
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,223297,223297,4194304,256,0,0,12,24,99584,0x7fc57b003b80,0x7fc57a6253c0,160977,160977,65536,2621440,400352,44855392,17598278545574,17598278501139,17598278792499,17598278794318
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,223297,223297,4194304,256,0,0,12,24,101312,0x7fc57b003a00,0x7fc57a625400,298340,298340,65536,3276800,486004,54426996,17598278828297,17598278792499,17598279167379,17598279169138
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,223297,223297,4194304,256,0,0,12,24,102784,0x7fc57b003880,0x7fc57a625440,298053,298053,65536,3080192,458075,51352276,17598279204357,17598279167379,17598279543539,17598279545219
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,223297,223297,4194304,256,0,0,12,24,104256,0x7fc57b003700,0x7fc57a625480,160841,160841,65536,3211264,484596,54284288,17598279580298,17598279543539,17598279838260,17598279840021
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,223297,223297,4194304,256,0,0,12,24,106240,0x7fc57d663580,0x7fc57a6254c0,218152,218152,65536,4128768,616431,68878940,17598279875190,17598279838260,17598280167220,17598280168983
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,223297,223297,4194304,256,0,0,12,24,107712,0x7fc57d663400,0x7fc57a625500,160567,160567,65536,2752512,417745,46799652,17598280212322,17598280167220,17598280459380,17598280461125
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,223297,223297,4194304,256,0,0,16,24,109440,0x7fc57d663280,0x7fc57a625540,296492,296492,65536,3407872,505502,56585432,17598280496844,17598280459380,17598280836660,17598280838476
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,223297,223297,4194304,256,0,0,16,24,111168,0x7fc57d663100,0x7fc57a625580,298105,298105,65536,3211264,482413,54009352,17598280872815,17598280836660,17598281216181,17598281217926
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,223297,223297,4194304,256,0,0,8,24,112896,0x7fc57b003f80,0x7fc57a6255c0,161904,161904,65536,3276800,506894,56757116,17598281253465,17598281216181,17598281509781,17598281511629
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,223297,223297,4194304,256,0,0,12,24,115136,0x7fc57b003e00,0x7fc57a625600,229113,229113,65536,4325376,650894,72975492,17598281547028,17598281509781,17598281844821,17598281846640
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,223297,223297,4194304,256,0,0,12,24,116608,0x7fc57b003c80,0x7fc57a625640,160282,160282,65536,2818048,426339,47792836,17598281888169,17598281844821,17598282136981,17598282139263
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,223297,223297,4194304,256,0,0,16,24,118336,0x7fc57b003b00,0x7fc57a625680,295972,295972,65536,3538944,527007,59108996,17598282174272,17598282136981,17598282516502,17598282518193
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,223297,223297,4194304,256,0,0,16,24,120064,0x7fc57b003980,0x7fc57a6256c0,297070,297070,65536,3407872,503507,56377296,17598282553482,17598282516502,17598282895062,17598282896803
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,223297,223297,4194304,256,0,0,12,24,121792,0x7fc57b003800,0x7fc57a625700,164238,164238,65536,3407872,517939,58036956,17598282932012,17598282895062,17598283192022,17598283193786
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,223297,223297,4194304,256,0,0,12,24,124032,0x7fc57b003680,0x7fc57a625740,239990,239990,65536,4521984,674318,75539916,17598283228455,17598283192022,17598283534422,17598283536147
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,223297,223297,4194304,256,0,0,12,24,125504,0x7fc57d663500,0x7fc57a625780,160084,160084,65536,3014656,455348,50937812,17598283578066,17598283534422,17598283832983,17598283834680
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,223297,223297,4194304,256,0,0,12,24,127488,0x7fc57d663380,0x7fc57a6257c0,296176,296176,65536,3801088,570136,63874748,17598283869599,17598283832983,17598284213623,17598284215390
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,223297,223297,4194304,256,0,0,12,24,129216,0x7fc57d663200,0x7fc57a625800,295022,295022,65536,3670016,555402,62225088,17598284251499,17598284213623,17598284589463,17598284591170
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,223297,223297,4194304,256,0,0,12,24,130944,0x7fc57d663080,0x7fc57a625840,169128,169128,65536,3670016,550903,61687964,17598284626840,17598284589463,17598284884983,17598284886903
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,223297,223297,4194304,256,0,0,12,24,133440,0x7fc57b003f00,0x7fc57a625880,257246,257246,65536,4915200,736660,82515752,17598284922352,17598284884983,17598285236344,17598285238084
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,223297,223297,4194304,256,0,0,12,24,134912,0x7fc57b003d80,0x7fc57a6258c0,160272,160272,65536,3145728,466172,52297568,17598285281643,17598285236344,17598285527704,17598285529467
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,223297,223297,4194304,256,0,0,12,24,136896,0x7fc57b003c00,0x7fc57a625900,295110,295110,65536,4063232,616673,68984692,17598285563896,17598285527704,17598285904664,17598285906377
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,223297,223297,4194304,256,0,0,12,24,138880,0x7fc57b003a80,0x7fc57a625940,294604,294604,65536,3932160,591796,66248272,17598285941266,17598285904664,17598286288345,17598286290217
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,223297,223297,4194304,256,0,0,12,24,140864,0x7fc57b003900,0x7fc57a625980,177260,177260,65536,3932160,602053,67358980,17598286325246,17598286288345,17598286599225,17598286600979
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,223297,223297,4194304,256,0,0,12,24,143616,0x7fc57b003780,0x7fc57a6259c0,278792,278792,65536,5308416,794875,88965396,17598286636188,17598286599225,17598286968025,17598286969640
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,223297,223297,4194304,256,0,0,12,24,145344,0x7fc57b003600,0x7fc57a625a00,161506,161506,65536,3342336,505771,56643040,17598287011649,17598286968025,17598287265945,17598287267622
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,223297,223297,4194304,256,0,0,12,24,147584,0x7fc57d663480,0x7fc57a625a40,295276,295276,65536,4325376,651002,72908412,17598287304191,17598287265945,17598287645946,17598287647843
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,223297,223297,4194304,256,0,0,12,24,149568,0x7fc57d663300,0x7fc57a625a80,293808,293808,65536,4194304,625995,70176864,17598287682742,17598287645946,17598288020506,17598288022153
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,223297,223297,4194304,256,0,0,12,24,151552,0x7fc57d663180,0x7fc57a625ac0,186443,186443,65536,4194304,630271,70642760,17598288057092,17598288020506,17598288326586,17598288328415
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,223297,223297,4194304,256,0,0,12,24,154304,0x7fc57d663000,0x7fc57a625b00,299015,299015,65536,5701632,850965,95261900,17598288363704,17598288326586,17598288709466,17598288711106
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,223297,223297,4194304,256,0,0,12,24,156288,0x7fc57b003e80,0x7fc57a625b40,171741,171741,65536,3735552,574939,64440664,17598288753564,17598288709466,17598289014267,17598289015908
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,223297,223297,4194304,256,0,0,12,24,158784,0x7fc57b003d00,0x7fc57a625b80,296283,296283,65536,4849664,751758,84280972,17598289050267,17598289014267,17598289390587,17598289392308
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,223297,223297,4194304,256,0,0,12,24,161024,0x7fc57b003b80,0x7fc57a625bc0,296308,296308,65536,4718592,742455,83196816,17598289426447,17598289390587,17598289776027,17598289777868
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,223297,223297,4194304,256,0,0,12,24,163264,0x7fc57b003a00,0x7fc57a625c00,206779,206779,65536,4718592,727697,81548732,17598289812267,17598289776027,17598290095227,17598290099930
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,223297,223297,4194304,256,0,0,12,24,166528,0x7fc57b003880,0x7fc57a625c40,340221,340221,65536,6488064,972878,108993016,17598290132559,17598290095227,17598290500988,17598290523689
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,223297,223297,4194304,256,0,0,12,24,168512,0x7fc57b003700,0x7fc57a625c80,184260,184260,65536,4128768,613745,68748960,17598290545309,17598290500988,17598290814588,17598290816392
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,223297,223297,4194304,256,0,0,12,24,171264,0x7fc57d663580,0x7fc57a625cc0,295663,295663,65536,5373952,850650,95258960,17598290850901,17598290814588,17598291194108,17598291195942
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,223297,223297,4194304,256,0,0,12,24,173760,0x7fc57d663400,0x7fc57a625d00,295680,295680,65536,5242880,820925,92106848,17598291230841,17598291194108,17598291573949,17598291575513
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,223297,223297,4194304,256,0,0,12,24,176256,0x7fc57d663280,0x7fc57a625d40,225121,225121,65536,5242880,789646,88496888,17598291610022,17598291573949,17598291908829,17598291910534
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,223297,223297,4194304,256,0,0,12,24,179776,0x7fc57d663100,0x7fc57a625d80,379382,379382,65536,7274496,1094455,122617096,17598291945693,17598291908829,17598292340509,17598292361623
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,223297,223297,4194304,256,0,0,12,24,182272,0x7fc57b003f80,0x7fc57a625dc0,210285,210285,65536,4915200,738800,82677044,17598292384942,17598292340509,17598292671869,17598292673465
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,223297,223297,4194304,256,0,0,12,24,185536,0x7fc57b003e00,0x7fc57a625e00,304476,304476,65536,6422528,996530,111553876,17598292708054,17598292671869,17598293063870,17598293065545
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,223297,223297,4194304,256,0,0,12,24,188544,0x7fc57b003c80,0x7fc57a625e40,309795,309795,65536,6291456,1008725,113005204,17598293100184,17598293063870,17598293454270,17598293456575
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,223297,223297,4194304,256,0,0,12,24,191552,0x7fc57b003b00,0x7fc57a625e80,265016,265016,65536,6291456,960955,107642448,17598293490034,17598293454270,17598293808670,17598293810446
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,223297,223297,4194304,256,0,0,12,24,195840,0x7fc57b003980,0x7fc57a625ec0,460468,460468,65536,8847360,1340578,150097020,17598293845135,17598293808670,17598294285151,17598294307633
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,223297,223297,4194304,256,0,0,12,24,198592,0x7fc57b003800,0x7fc57a625f00,244266,244266,65536,5701632,861018,96425368,17598294328973,17598294285151,17598294653791,17598294655415
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,223297,223297,4194304,256,0,0,12,24,202368,0x7fc57b003680,0x7fc57a625f40,333187,333187,65536,7471104,1193904,133725160,17598294690874,17598294653791,17598295059551,17598295104823
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,223297,223297,4194304,256,0,0,12,24,205888,0x7fc57d663500,0x7fc57a625f80,330871,330871,65536,7340032,1159135,129836260,17598295116103,17598295059551,17598295497311,17598295540822
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,223297,223297,4194304,256,0,0,12,24,209408,0x7fc57d663380,0x7fc57a625fc0,305910,305910,65536,7340032,1121399,125509564,17598295551712,17598295497311,17598295908672,17598295910503
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,223297,223297,4194304,256,0,0,12,24,214464,0x7fc57d663200,0x7fc57a626000,542283,542283,65536,10420224,1568783,175813004,17598295945792,17598295908672,17598296439872,17598296482158
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,223297,223297,4194304,256,0,0,12,24,217728,0x7fc57d663080,0x7fc57a626040,272435,272435,65536,6488064,992618,111236844,17598296502797,17598296439872,17598296830912,17598296832689
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,223297,223297,4194304,256,0,0,12,24,222016,0x7fc57b003f00,0x7fc57a626080,364525,364525,65536,8519680,1361388,152365296,17598296869268,17598296830912,17598297256833,17598297299227
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,223297,223297,4194304,256,0,0,12,24,226048,0x7fc57b003d80,0x7fc57a6260c0,367851,367851,65536,8388608,1359359,152227300,17598297310527,17598297256833,17598297709633,17598297727836
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,223297,223297,4194304,256,0,0,12,24,230080,0x7fc57b003c00,0x7fc57a626100,346157,346157,65536,8388608,1297532,145388716,17598297745406,17598297709633,17598298117473,17598298163095
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,223297,223297,4194304,256,0,0,12,24,235904,0x7fc57b003a80,0x7fc57a626140,623057,623057,65536,11993088,1828127,204732500,17598298174855,17598298117473,17598298733954,17598298777430
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,223297,223297,4194304,256,0,0,12,24,239424,0x7fc57b003900,0x7fc57a626180,302787,302787,65536,7274496,1156188,129567956,17598298796769,17598298733954,17598299146914,17598299148690
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,223297,223297,4194304,256,0,0,12,24,244224,0x7fc57b003780,0x7fc57a6261c0,398823,398823,65536,9568256,1491465,167017620,17598299186029,17598299146914,17598299592835,17598299637038
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,223297,223297,4194304,256,0,0,12,24,248768,0x7fc57b003600,0x7fc57a626200,389443,389443,65536,9437184,1456663,163291036,17598299649217,17598299592835,17598300061315,17598300105206
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,223297,223297,4194304,256,0,0,12,24,253312,0x7fc57d663480,0x7fc57a626240,386633,386633,65536,9437184,1464421,163958644,17598300116546,17598300061315,17598300533795,17598300577924
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,223297,223297,4194304,256,0,0,8,24,255552,0x7fc57d663300,0x7fc57a626280,718746,718746,65536,16056320,2308323,258892844,17598300589654,17598300533795,17598301209156,17598301253387
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,223297,223297,4194304,256,0,0,12,24,259840,0x7fc57d663180,0x7fc57a6262c0,363190,363190,65536,8847360,1367371,153164760,17598301273886,17598301209156,17598301657636,17598301702005
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,223297,223297,4194304,256,0,0,12,24,265664,0x7fc57d663000,0x7fc57a626300,468855,468855,65536,11665408,1840693,206045152,17598301713865,17598301657636,17598302184677,17598302229022
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,223297,223297,4194304,256,0,0,12,24,271232,0x7fc57b003e80,0x7fc57a626340,471122,471122,65536,11468800,1835596,205579460,17598302240842,17598302184677,17598302714277,17598302758459
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,223297,223297,4194304,256,0,0,8,24,273216,0x7fc57b003d00,0x7fc57a626380,482691,482691,65536,14090240,2021655,226289536,17598302769468,17598302714277,17598303239557,17598303283735
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,223297,223297,4194304,256,0,0,8,24,275712,0x7fc57b003b80,0x7fc57a6263c0,879198,879198,65536,19202048,2757838,308615396,17598303295945,17598303239557,17598304018598,17598304060306
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,223297,223297,4194304,256,0,0,12,24,280768,0x7fc57b003a00,0x7fc57a626400,425606,425606,65536,10420224,1600707,179444132,17598304080715,17598304018598,17598304502758,17598304545083
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,223297,223297,4194304,256,0,0,12,24,287616,0x7fc57b003880,0x7fc57a626440,547968,547968,65536,13762560,2143950,240064628,17598304556993,17598304502758,17598305074599,17598305116809
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,223297,223297,4194304,256,0,0,12,24,294208,0x7fc57b003700,0x7fc57a626480,549766,549766,65536,13565952,2169986,243035864,17598305129159,17598305074599,17598305644199,17598305686654
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,223297,223297,4194304,256,0,0,8,24,296960,0x7fc57d663580,0x7fc57a6264c0,563418,563418,65536,15466496,2228340,249472868,17598305698124,17598305644199,17598306218120,17598306262830
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,223297,223297,4194304,256,0,0,8,24,299968,0x7fc57d663400,0x7fc57a626500,1043564,1043564,65536,22347776,3211811,359803404,17598306275119,17598306218120,17598307109960,17598307153547
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,223297,223297,4194304,256,0,0,8,24,302720,0x7fc57d663280,0x7fc57a626540,722110,722110,65536,20250624,2910147,325967960,17598307174287,17598307109960,17598307781481,17598307825580
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,223297,223297,4194304,256,0,0,12,24,305472,0x7fc57d663100,0x7fc57a626580,723565,723565,65536,20447232,2935970,328866128,17598307836850,17598307781481,17598308479401,17598308521872
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,223297,223297,4194304,256,0,0,12,24,308224,0x7fc57b003f80,0x7fc57a6265c0,721500,721500,65536,19595264,2814676,315453276,17598308533312,17598308479225,17598309162745,17598309208785
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,223297,223297,4194304,256,0,0,8,24,310976,0x7fc57b003e00,0x7fc57a626600,726076,726076,65536,20381696,2936476,328942212,17598309219944,17598309162745,17598309838265,17598309881097
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,223297,223297,4194304,256,0,0,8,24,313216,0x7fc57b003c80,0x7fc57a626640,1366825,1366825,65536,31522816,4514898,505583912,17598309891967,17598309838265,17598310928665,17598310975270
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,223297,223297,4194304,256,0,0,8,24,315968,0x7fc57b003b00,0x7fc57a626680,1371641,1371641,65536,38993920,5589029,626214956,17598310996489,17598310928665,17598312012346,17598312056892
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,223297,223297,4194304,256,0,0,12,24,318720,0x7fc57b003980,0x7fc57a6266c0,1372673,1372673,65536,39124992,5608013,627989248,17598312068272,17598312012346,17598313119226,17598313184094
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,223297,223297,4194304,256,0,0,12,24,321472,0x7fc57b003800,0x7fc57a626700,1370411,1370411,65536,38469632,5519358,617861312,17598313195153,17598313119226,17598314243227,17598314312425
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,223297,223297,4194304,256,0,0,8,24,324224,0x7fc57b003680,0x7fc57a626740,1375071,1375071,65536,39059456,5597910,626915124,17598314324455,17598314243227,17598315372347,17598315439636
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,223297,223297,4194304,256,0,0,8,24,326464,0x7fc57d663500,0x7fc57a626780,2664520,2664520,65536,60489728,8660095,969801984,17598315451946,17598315372347,17598317343388,17598317410306
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,223297,223297,4194304,256,0,0,8,24,329216,0x7fc57d663380,0x7fc57a6267c0,2666822,2666822,65536,77266944,11060008,1238260984,17598317430076,17598317343388,17598319273789,17598319343217
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,223297,223297,4194304,256,0,0,12,24,331968,0x7fc57d663200,0x7fc57a626800,2671085,2671085,65536,77398016,11073139,1240205108,17598319355797,17598319273789,17598321268189,17598321335786
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,223297,223297,4194304,256,0,0,12,24,334720,0x7fc57d663080,0x7fc57a626840,2668714,2668714,65536,76218368,10914634,1222575476,17598321348676,17598321268189,17598323245470,17598323317666
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,223297,223297,4194304,256,0,0,8,24,337472,0x7fc57b003f00,0x7fc57a626880,2674890,2674890,65536,77332480,11062184,1239088008,17598323330526,17598323245470,17598325194911,17598325263067
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,223297,223297,4194304,256,0,0,8,24,0,0x7fc57b003d80,0x7fc57a6268c0,5255732,5255732,65536,120258560,17190583,1925804324,17598325275167,17598325194911,17598328815713,17598328885995
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid grd Workgroup_Size LDS_Per_Workgroup scr vgpr SGPR fbar sig obj GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 __amd_rocclr_fillBufferAligned.kd 0 0 0 223297 223297 33554432 256 0 0 4 32 4160 0x0 0x7fc57a604280 379284 379284 524288 4718592 681163 76310828 17598097140845 17597387743185 17598246526395 17598246639545
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 223297 223297 32768 256 0 0 12 24 13888 0x0 0x7fc57a623f80 33251 33251 512 8192 6010 679448 17598251787224 17598246526395 17598251919198 17598251924230
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 5 223297 223297 4194304 256 0 0 12 24 14336 0x7fc57d663380 0x7fc57a623fc0 163594 163594 65536 917504 141997 15950860 17598251961259 17598251919198 17598252301279 17598252303751
5 3 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 8 223297 223297 4194304 256 0 0 16 24 15040 0x7fc57d663200 0x7fc57a624000 310676 310676 65536 1114112 172028 19257004 17598252343430 17598252301279 17598252724159 17598252726940
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 11 223297 223297 4194304 256 0 0 16 24 15488 0x7fc57d663080 0x7fc57a624040 309020 309020 65536 917504 138926 15550360 17598252763489 17598252724159 17598253136799 17598253139200
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 14 223297 223297 4194304 256 0 0 12 24 15936 0x7fc57b003f00 0x7fc57a624080 164976 164976 65536 1048576 157741 17738236 17598253175849 17598253136799 17598253450240 17598253452452
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 17 223297 223297 4194304 256 0 0 12 24 16384 0x7fc57b003d80 0x7fc57a6240c0 163529 163529 65536 983040 148002 16556188 17598253487311 17598253450240 17598253764800 17598253767114
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 20 223297 223297 4194304 256 0 0 12 24 17088 0x7fc57b003c00 0x7fc57a624100 162196 162196 65536 1114112 162834 18259480 17598253814412 17598253764800 17598254076000 17598254086866
10 8 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 23 223297 223297 4194304 256 0 0 16 24 17792 0x7fc57b003a80 0x7fc57a624140 309800 309800 65536 1310720 206086 23129588 17598254114915 17598254076000 17598254485600 17598254487735
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 26 223297 223297 4194304 256 0 0 16 24 18496 0x7fc57b003900 0x7fc57a624180 306944 306944 65536 1179648 177127 19842568 17598254522574 17598254485600 17598254905121 17598254906905
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 29 223297 223297 4194304 256 0 0 16 24 19200 0x7fc57b003780 0x7fc57a6241c0 164084 164084 65536 1245184 189398 21184652 17598254940604 17598254905121 17598255192801 17598255194607
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 32 223297 223297 4194304 256 0 0 16 24 19904 0x7fc57b003600 0x7fc57a624200 162975 162975 65536 1245184 186637 20929980 17598255228957 17598255192801 17598255477761 17598255479620
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 35 223297 223297 4194304 256 0 0 12 24 20608 0x7fc57d663480 0x7fc57a624240 163260 163260 65536 1245184 188086 21072920 17598255522339 17598255477761 17598255766241 17598255768043
15 13 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 38 223297 223297 4194304 256 0 0 16 24 21312 0x7fc57d663300 0x7fc57a624280 308005 308005 65536 1441792 215714 24176728 17598255805652 17598255766241 17598256148642 17598256150373
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 41 223297 223297 4194304 256 0 0 16 24 22016 0x7fc57d663180 0x7fc57a6242c0 308010 308010 65536 1310720 199745 22367996 17598256185452 17598256148642 17598256525122 17598256526884
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 44 223297 223297 4194304 256 0 0 16 24 22720 0x7fc57d663000 0x7fc57a624300 163878 163878 65536 1376256 206041 23082112 17598256561523 17598256525122 17598256815042 17598256816776
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 47 223297 223297 4194304 256 0 0 12 24 23424 0x7fc57b003e80 0x7fc57a624340 163340 163340 65536 1441792 217864 24335144 17598256851235 17598256815042 17598257106722 17598257108309
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 50 223297 223297 4194304 256 0 0 12 24 24128 0x7fc57b003d00 0x7fc57a624380 162064 162064 65536 1310720 196821 22019008 17598257150368 17598257106722 17598257405123 17598257406731
20 18 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 53 223297 223297 4194304 256 0 0 16 24 24832 0x7fc57b003b80 0x7fc57a6243c0 308441 308441 65536 1572864 233127 26082088 17598257442950 17598257405123 17598257779363 17598257781082
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 56 223297 223297 4194304 256 0 0 16 24 25536 0x7fc57b003a00 0x7fc57a624400 304557 304557 65536 1441792 208665 23365924 17598257815321 17598257779363 17598258155363 17598258157062
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 59 223297 223297 4194304 256 0 0 12 24 26240 0x7fc57b003880 0x7fc57a624440 162559 162559 65536 1507328 226838 25406660 17598258192311 17598258155363 17598258447363 17598258449185
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 62 223297 223297 4194304 256 0 0 12 24 26944 0x7fc57b003700 0x7fc57a624480 163057 163057 65536 1638400 243091 27262240 17598258484414 17598258447363 17598258737924 17598258739588
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 65 223297 223297 4194304 256 0 0 12 24 27648 0x7fc57d663580 0x7fc57a6244c0 161757 161757 65536 1441792 214563 24030252 17598258783146 17598258737924 17598259034244 17598259035990
25 23 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 68 223297 223297 4194304 256 0 0 16 24 28608 0x7fc57d663400 0x7fc57a624500 305217 305217 65536 1703936 252073 28235268 17598259072069 17598259034244 17598259410084 17598259411920
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 71 223297 223297 4194304 256 0 0 16 24 29312 0x7fc57d663280 0x7fc57a624540 303171 303171 65536 1572864 232908 26123324 17598259447019 17598259410084 17598259783844 17598259785641
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 74 223297 223297 4194304 256 0 0 12 24 30016 0x7fc57d663100 0x7fc57a624580 161758 161758 65536 1638400 243285 27310660 17598259820640 17598259783844 17598260071845 17598260073763
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 77 223297 223297 4194304 256 0 0 8 24 30976 0x7fc57b003f80 0x7fc57a6245c0 160538 160538 65536 1835008 270103 30322488 17598260108543 17598260071845 17598260358725 17598260360476
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 80 223297 223297 4194304 256 0 0 12 24 31680 0x7fc57b003e00 0x7fc57a624600 163862 163862 65536 1507328 224594 25081836 17598260402215 17598260358725 17598260656645 17598260658339
30 28 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 83 223297 223297 4194304 256 0 0 16 24 32640 0x7fc57b003c80 0x7fc57a624640 306084 306084 65536 1835008 271175 30248500 17598260694318 17598260656645 17598261046085 17598261047719
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 86 223297 223297 4194304 256 0 0 12 24 33600 0x7fc57b003b00 0x7fc57a624680 307380 307380 65536 1703936 249875 27955212 17598261082628 17598261046085 17598261424326 17598261425939
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 89 223297 223297 4194304 256 0 0 12 24 34560 0x7fc57b003980 0x7fc57a6246c0 163238 163238 65536 1769472 265219 29706488 17598261460008 17598261424326 17598261712486 17598261714362
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 92 223297 223297 4194304 256 0 0 8 24 35520 0x7fc57b003800 0x7fc57a624700 162860 162860 65536 2031616 303442 33955492 17598261748951 17598261712486 17598262001606 17598262003354
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 95 223297 223297 4194304 256 0 0 12 24 36224 0x7fc57b003680 0x7fc57a624740 161890 161890 65536 1638400 263222 29471680 17598262044743 17598262001606 17598262297446 17598262299177
35 33 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 98 223297 223297 4194304 256 0 0 12 24 37184 0x7fc57d663500 0x7fc57a624780 304550 304550 65536 1966080 288953 32377204 17598262334206 17598262297446 17598262682727 17598262684327
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 101 223297 223297 4194304 256 0 0 12 24 38144 0x7fc57d663380 0x7fc57a6247c0 304419 304419 65536 1835008 279877 31253588 17598262719856 17598262682727 17598263061447 17598263063217
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 104 223297 223297 4194304 256 0 0 12 24 39104 0x7fc57d663200 0x7fc57a624800 162792 162792 65536 1900544 285508 31920360 17598263098776 17598263061447 17598263352487 17598263354190
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 107 223297 223297 4194304 256 0 0 8 24 40320 0x7fc57d663080 0x7fc57a624840 163607 163607 65536 2228224 346629 38837308 17598263390639 17598263352487 17598263644167 17598263645983
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 110 223297 223297 4194304 256 0 0 12 24 41280 0x7fc57b003f00 0x7fc57a624880 161512 161512 65536 1703936 258557 28939128 17598263688412 17598263644167 17598263940008 17598263941695
40 38 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 113 223297 223297 4194304 256 0 0 12 24 42240 0x7fc57b003d80 0x7fc57a6248c0 304171 304171 65536 2097152 311294 34802656 17598263978294 17598263940008 17598264318088 17598264320046
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 116 223297 223297 4194304 256 0 0 12 24 43200 0x7fc57b003c00 0x7fc57a624900 303740 303740 65536 1966080 285331 31960944 17598264354835 17598264318088 17598264698408 17598264699996
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 119 223297 223297 4194304 256 0 0 8 24 44160 0x7fc57b003a80 0x7fc57a624940 161837 161837 65536 2031616 305326 34228756 17598264734605 17598264698408 17598264988488 17598264990239
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 122 223297 223297 4194304 256 0 0 12 24 45376 0x7fc57b003900 0x7fc57a624980 163205 163205 65536 2424832 361416 40511376 17598265024908 17598264988488 17598265282729 17598265284531
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 125 223297 223297 4194304 256 0 0 12 24 46336 0x7fc57b003780 0x7fc57a6249c0 161312 161312 65536 1835008 274162 30739912 17598265326330 17598265282729 17598265578409 17598265580184
45 43 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 128 223297 223297 4194304 256 0 0 12 24 47552 0x7fc57b003600 0x7fc57a624a00 306564 306564 65536 2228224 328050 36721992 17598265616243 17598265578409 17598265955529 17598265957354
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 131 223297 223297 4194304 256 0 0 12 24 48512 0x7fc57d663480 0x7fc57a624a40 302434 302434 65536 2097152 309303 34586432 17598265992943 17598265955529 17598266337609 17598266339694
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 134 223297 223297 4194304 256 0 0 8 24 49472 0x7fc57d663300 0x7fc57a624a80 161867 161867 65536 2162688 318107 35667196 17598266374213 17598266337609 17598266627530 17598266629077
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 137 223297 223297 4194304 256 0 0 12 24 50688 0x7fc57d663180 0x7fc57a624ac0 161314 161314 65536 2621440 397899 44557408 17598266664246 17598266627530 17598266916650 17598266918410
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 140 223297 223297 4194304 256 0 0 12 24 51648 0x7fc57d663000 0x7fc57a624b00 160569 160569 65536 1966080 292828 32729708 17598266960678 17598266916650 17598267207370 17598267209012
50 48 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 143 223297 223297 4194304 256 0 0 12 24 52864 0x7fc57b003e80 0x7fc57a624b40 303754 303754 65536 2359296 347958 38955816 17598267243241 17598267207370 17598267584010 17598267585722
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 146 223297 223297 4194304 256 0 0 12 24 54080 0x7fc57b003d00 0x7fc57a624b80 301553 301553 65536 2228224 330564 37009284 17598267620532 17598267584010 17598267968971 17598267970733
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 149 223297 223297 4194304 256 0 0 8 24 55296 0x7fc57b003b80 0x7fc57a624bc0 161840 161840 65536 2293760 341860 38219528 17598268006032 17598267968971 17598268259851 17598268261575
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 152 223297 223297 4194304 256 0 0 12 24 56768 0x7fc57b003a00 0x7fc57a624c00 163433 163433 65536 2752512 418160 46830460 17598268297364 17598268259851 17598268553131 17598268555078
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 155 223297 223297 4194304 256 0 0 12 24 57728 0x7fc57b003880 0x7fc57a624c40 162472 162472 65536 2031616 327412 36578768 17598268597427 17598268553131 17598268849131 17598268850910
55 53 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 158 223297 223297 4194304 256 0 0 12 24 58944 0x7fc57b003700 0x7fc57a624c80 300606 300606 65536 2490368 374186 41850496 17598268885249 17598268849131 17598269224652 17598269226301
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 161 223297 223297 4194304 256 0 0 12 24 60160 0x7fc57d663580 0x7fc57a624cc0 301210 301210 65536 2359296 349917 39249832 17598269262130 17598269224652 17598269605612 17598269607311
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 164 223297 223297 4194304 256 0 0 8 24 61376 0x7fc57d663400 0x7fc57a624d00 164759 164759 65536 2424832 402021 45040004 17598269642290 17598269605612 17598269900012 17598269901653
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 167 223297 223297 4194304 256 0 0 12 24 62848 0x7fc57d663280 0x7fc57a624d40 168038 168038 65536 2949120 441481 49485848 17598269937442 17598269900012 17598270200332 17598270202336
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 170 223297 223297 4194304 256 0 0 12 24 63808 0x7fc57d663100 0x7fc57a624d80 162222 162222 65536 2162688 326133 36467264 17598270244505 17598270200332 17598270503213 17598270505038
60 58 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 173 223297 223297 4194304 256 0 0 12 24 65024 0x7fc57b003f80 0x7fc57a624dc0 300132 300132 65536 2621440 403067 45203720 17598270542417 17598270503213 17598270879373 17598270881049
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 176 223297 223297 4194304 256 0 0 12 24 66240 0x7fc57b003e00 0x7fc57a624e00 297342 297342 65536 2490368 363422 40682956 17598270916698 17598270879373 17598271251693 17598271253479
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 179 223297 223297 4194304 256 0 0 8 24 67456 0x7fc57b003c80 0x7fc57a624e40 161790 161790 65536 2555904 385035 43147484 17598271288108 17598271251693 17598271555373 17598271557111
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 182 223297 223297 4194304 256 0 0 12 24 68928 0x7fc57b003b00 0x7fc57a624e80 175315 175315 65536 3145728 465475 52218840 17598271592291 17598271555373 17598271857134 17598271858854
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 185 223297 223297 4194304 256 0 0 12 24 70144 0x7fc57b003980 0x7fc57a624ec0 160832 160832 65536 2228224 327517 36700732 17598271901353 17598271857134 17598272152334 17598272154216
65 63 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 188 223297 223297 4194304 256 0 0 12 24 71616 0x7fc57b003800 0x7fc57a624f00 301078 301078 65536 2752512 406340 45513568 17598272188625 17598272152334 17598272528174 17598272529867
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 191 223297 223297 4194304 256 0 0 12 24 72832 0x7fc57b003680 0x7fc57a624f40 300842 300842 65536 2621440 390699 43686036 17598272564506 17598272528174 17598272903854 17598272905627
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 194 223297 223297 4194304 256 0 0 8 24 74048 0x7fc57d663500 0x7fc57a624f80 160830 160830 65536 2686976 395360 44292492 17598272939826 17598272903854 17598273198735 17598273200550
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 197 223297 223297 4194304 256 0 0 12 24 75776 0x7fc57d663380 0x7fc57a624fc0 182347 182347 65536 3342336 500899 56027040 17598273235849 17598273198735 17598273504975 17598273506752
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 200 223297 223297 4194304 256 0 0 12 24 76992 0x7fc57d663200 0x7fc57a625000 160788 160788 65536 2359296 351290 39283156 17598273561021 17598273504975 17598273796495 17598273798285
70 68 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 203 223297 223297 4194304 256 0 0 12 24 78464 0x7fc57d663080 0x7fc57a625040 300956 300956 65536 2883584 429814 48155448 17598273834214 17598273796495 17598274177935 17598274180075
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 206 223297 223297 4194304 256 0 0 12 24 79936 0x7fc57b003f00 0x7fc57a625080 301294 301294 65536 2686976 397384 44563000 17598274216954 17598274177935 17598274566416 17598274568035
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 209 223297 223297 4194304 256 0 0 8 24 81408 0x7fc57b003d80 0x7fc57a6250c0 161951 161951 65536 2818048 427963 47980996 17598274602984 17598274566416 17598274860656 17598274862508
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 212 223297 223297 4194304 256 0 0 12 24 83136 0x7fc57b003c00 0x7fc57a625100 192746 192746 65536 3538944 532322 59602316 17598274897647 17598274860656 17598275170736 17598275172540
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 215 223297 223297 4194304 256 0 0 12 24 84352 0x7fc57b003a80 0x7fc57a625140 161368 161368 65536 2424832 362958 40605932 17598275214489 17598275170736 17598275462896 17598275464632
75 73 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 218 223297 223297 4194304 256 0 0 12 24 85824 0x7fc57b003900 0x7fc57a625180 298410 298410 65536 3014656 455330 51053144 17598275499312 17598275462896 17598275843537 17598275845343
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 221 223297 223297 4194304 256 0 0 12 24 87296 0x7fc57b003780 0x7fc57a6251c0 299703 299703 65536 2818048 414678 46518540 17598275882412 17598275843537 17598276219537 17598276221333
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 224 223297 223297 4194304 256 0 0 12 24 88768 0x7fc57b003600 0x7fc57a625200 163032 163032 65536 2949120 440286 49312880 17598276255762 17598276219537 17598276511057 17598276512946
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 227 223297 223297 4194304 256 0 0 12 24 90752 0x7fc57d663480 0x7fc57a625240 201001 201001 65536 3735552 563175 63022556 17598276548175 17598276511057 17598276828337 17598276830078
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 230 223297 223297 4194304 256 0 0 12 24 91968 0x7fc57d663300 0x7fc57a625280 160772 160772 65536 2555904 384541 43027336 17598276872717 17598276828337 17598277120498 17598277122240
80 78 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 233 223297 223297 4194304 256 0 0 12 24 93440 0x7fc57d663180 0x7fc57a6252c0 301399 301399 65536 3145728 468135 52410600 17598277157359 17598277120498 17598277502898 17598277504591
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 236 223297 223297 4194304 256 0 0 12 24 94912 0x7fc57d663000 0x7fc57a625300 298032 298032 65536 2949120 438122 49043508 17598277540630 17598277502898 17598277878898 17598277880551
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 239 223297 223297 4194304 256 0 0 12 24 96384 0x7fc57b003e80 0x7fc57a625340 161173 161173 65536 3080192 458154 51258132 17598277914490 17598277878898 17598278168978 17598278170684
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 242 223297 223297 4194304 256 0 0 12 24 98368 0x7fc57b003d00 0x7fc57a625380 210176 210176 65536 3932160 584119 65374800 17598278206013 17598278168978 17598278501139 17598278502945
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 245 223297 223297 4194304 256 0 0 12 24 99584 0x7fc57b003b80 0x7fc57a6253c0 160977 160977 65536 2621440 400352 44855392 17598278545574 17598278501139 17598278792499 17598278794318
85 83 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 248 223297 223297 4194304 256 0 0 12 24 101312 0x7fc57b003a00 0x7fc57a625400 298340 298340 65536 3276800 486004 54426996 17598278828297 17598278792499 17598279167379 17598279169138
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 251 223297 223297 4194304 256 0 0 12 24 102784 0x7fc57b003880 0x7fc57a625440 298053 298053 65536 3080192 458075 51352276 17598279204357 17598279167379 17598279543539 17598279545219
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 254 223297 223297 4194304 256 0 0 12 24 104256 0x7fc57b003700 0x7fc57a625480 160841 160841 65536 3211264 484596 54284288 17598279580298 17598279543539 17598279838260 17598279840021
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 257 223297 223297 4194304 256 0 0 12 24 106240 0x7fc57d663580 0x7fc57a6254c0 218152 218152 65536 4128768 616431 68878940 17598279875190 17598279838260 17598280167220 17598280168983
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 260 223297 223297 4194304 256 0 0 12 24 107712 0x7fc57d663400 0x7fc57a625500 160567 160567 65536 2752512 417745 46799652 17598280212322 17598280167220 17598280459380 17598280461125
90 88 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 263 223297 223297 4194304 256 0 0 16 24 109440 0x7fc57d663280 0x7fc57a625540 296492 296492 65536 3407872 505502 56585432 17598280496844 17598280459380 17598280836660 17598280838476
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 266 223297 223297 4194304 256 0 0 16 24 111168 0x7fc57d663100 0x7fc57a625580 298105 298105 65536 3211264 482413 54009352 17598280872815 17598280836660 17598281216181 17598281217926
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 269 223297 223297 4194304 256 0 0 8 24 112896 0x7fc57b003f80 0x7fc57a6255c0 161904 161904 65536 3276800 506894 56757116 17598281253465 17598281216181 17598281509781 17598281511629
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 272 223297 223297 4194304 256 0 0 12 24 115136 0x7fc57b003e00 0x7fc57a625600 229113 229113 65536 4325376 650894 72975492 17598281547028 17598281509781 17598281844821 17598281846640
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 275 223297 223297 4194304 256 0 0 12 24 116608 0x7fc57b003c80 0x7fc57a625640 160282 160282 65536 2818048 426339 47792836 17598281888169 17598281844821 17598282136981 17598282139263
95 93 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 278 223297 223297 4194304 256 0 0 16 24 118336 0x7fc57b003b00 0x7fc57a625680 295972 295972 65536 3538944 527007 59108996 17598282174272 17598282136981 17598282516502 17598282518193
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 281 223297 223297 4194304 256 0 0 16 24 120064 0x7fc57b003980 0x7fc57a6256c0 297070 297070 65536 3407872 503507 56377296 17598282553482 17598282516502 17598282895062 17598282896803
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 284 223297 223297 4194304 256 0 0 12 24 121792 0x7fc57b003800 0x7fc57a625700 164238 164238 65536 3407872 517939 58036956 17598282932012 17598282895062 17598283192022 17598283193786
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 287 223297 223297 4194304 256 0 0 12 24 124032 0x7fc57b003680 0x7fc57a625740 239990 239990 65536 4521984 674318 75539916 17598283228455 17598283192022 17598283534422 17598283536147
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 290 223297 223297 4194304 256 0 0 12 24 125504 0x7fc57d663500 0x7fc57a625780 160084 160084 65536 3014656 455348 50937812 17598283578066 17598283534422 17598283832983 17598283834680
100 98 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 293 223297 223297 4194304 256 0 0 12 24 127488 0x7fc57d663380 0x7fc57a6257c0 296176 296176 65536 3801088 570136 63874748 17598283869599 17598283832983 17598284213623 17598284215390
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 296 223297 223297 4194304 256 0 0 12 24 129216 0x7fc57d663200 0x7fc57a625800 295022 295022 65536 3670016 555402 62225088 17598284251499 17598284213623 17598284589463 17598284591170
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 299 223297 223297 4194304 256 0 0 12 24 130944 0x7fc57d663080 0x7fc57a625840 169128 169128 65536 3670016 550903 61687964 17598284626840 17598284589463 17598284884983 17598284886903
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 302 223297 223297 4194304 256 0 0 12 24 133440 0x7fc57b003f00 0x7fc57a625880 257246 257246 65536 4915200 736660 82515752 17598284922352 17598284884983 17598285236344 17598285238084
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 305 223297 223297 4194304 256 0 0 12 24 134912 0x7fc57b003d80 0x7fc57a6258c0 160272 160272 65536 3145728 466172 52297568 17598285281643 17598285236344 17598285527704 17598285529467
105 103 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 308 223297 223297 4194304 256 0 0 12 24 136896 0x7fc57b003c00 0x7fc57a625900 295110 295110 65536 4063232 616673 68984692 17598285563896 17598285527704 17598285904664 17598285906377
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 311 223297 223297 4194304 256 0 0 12 24 138880 0x7fc57b003a80 0x7fc57a625940 294604 294604 65536 3932160 591796 66248272 17598285941266 17598285904664 17598286288345 17598286290217
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 314 223297 223297 4194304 256 0 0 12 24 140864 0x7fc57b003900 0x7fc57a625980 177260 177260 65536 3932160 602053 67358980 17598286325246 17598286288345 17598286599225 17598286600979
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 317 223297 223297 4194304 256 0 0 12 24 143616 0x7fc57b003780 0x7fc57a6259c0 278792 278792 65536 5308416 794875 88965396 17598286636188 17598286599225 17598286968025 17598286969640
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 320 223297 223297 4194304 256 0 0 12 24 145344 0x7fc57b003600 0x7fc57a625a00 161506 161506 65536 3342336 505771 56643040 17598287011649 17598286968025 17598287265945 17598287267622
110 108 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 323 223297 223297 4194304 256 0 0 12 24 147584 0x7fc57d663480 0x7fc57a625a40 295276 295276 65536 4325376 651002 72908412 17598287304191 17598287265945 17598287645946 17598287647843
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 326 223297 223297 4194304 256 0 0 12 24 149568 0x7fc57d663300 0x7fc57a625a80 293808 293808 65536 4194304 625995 70176864 17598287682742 17598287645946 17598288020506 17598288022153
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 329 223297 223297 4194304 256 0 0 12 24 151552 0x7fc57d663180 0x7fc57a625ac0 186443 186443 65536 4194304 630271 70642760 17598288057092 17598288020506 17598288326586 17598288328415
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 332 223297 223297 4194304 256 0 0 12 24 154304 0x7fc57d663000 0x7fc57a625b00 299015 299015 65536 5701632 850965 95261900 17598288363704 17598288326586 17598288709466 17598288711106
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 335 223297 223297 4194304 256 0 0 12 24 156288 0x7fc57b003e80 0x7fc57a625b40 171741 171741 65536 3735552 574939 64440664 17598288753564 17598288709466 17598289014267 17598289015908
115 113 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 338 223297 223297 4194304 256 0 0 12 24 158784 0x7fc57b003d00 0x7fc57a625b80 296283 296283 65536 4849664 751758 84280972 17598289050267 17598289014267 17598289390587 17598289392308
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 341 223297 223297 4194304 256 0 0 12 24 161024 0x7fc57b003b80 0x7fc57a625bc0 296308 296308 65536 4718592 742455 83196816 17598289426447 17598289390587 17598289776027 17598289777868
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 344 223297 223297 4194304 256 0 0 12 24 163264 0x7fc57b003a00 0x7fc57a625c00 206779 206779 65536 4718592 727697 81548732 17598289812267 17598289776027 17598290095227 17598290099930
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 347 223297 223297 4194304 256 0 0 12 24 166528 0x7fc57b003880 0x7fc57a625c40 340221 340221 65536 6488064 972878 108993016 17598290132559 17598290095227 17598290500988 17598290523689
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 350 223297 223297 4194304 256 0 0 12 24 168512 0x7fc57b003700 0x7fc57a625c80 184260 184260 65536 4128768 613745 68748960 17598290545309 17598290500988 17598290814588 17598290816392
120 118 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 353 223297 223297 4194304 256 0 0 12 24 171264 0x7fc57d663580 0x7fc57a625cc0 295663 295663 65536 5373952 850650 95258960 17598290850901 17598290814588 17598291194108 17598291195942
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 356 223297 223297 4194304 256 0 0 12 24 173760 0x7fc57d663400 0x7fc57a625d00 295680 295680 65536 5242880 820925 92106848 17598291230841 17598291194108 17598291573949 17598291575513
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 359 223297 223297 4194304 256 0 0 12 24 176256 0x7fc57d663280 0x7fc57a625d40 225121 225121 65536 5242880 789646 88496888 17598291610022 17598291573949 17598291908829 17598291910534
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 362 223297 223297 4194304 256 0 0 12 24 179776 0x7fc57d663100 0x7fc57a625d80 379382 379382 65536 7274496 1094455 122617096 17598291945693 17598291908829 17598292340509 17598292361623
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 365 223297 223297 4194304 256 0 0 12 24 182272 0x7fc57b003f80 0x7fc57a625dc0 210285 210285 65536 4915200 738800 82677044 17598292384942 17598292340509 17598292671869 17598292673465
125 123 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 368 223297 223297 4194304 256 0 0 12 24 185536 0x7fc57b003e00 0x7fc57a625e00 304476 304476 65536 6422528 996530 111553876 17598292708054 17598292671869 17598293063870 17598293065545
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 371 223297 223297 4194304 256 0 0 12 24 188544 0x7fc57b003c80 0x7fc57a625e40 309795 309795 65536 6291456 1008725 113005204 17598293100184 17598293063870 17598293454270 17598293456575
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 374 223297 223297 4194304 256 0 0 12 24 191552 0x7fc57b003b00 0x7fc57a625e80 265016 265016 65536 6291456 960955 107642448 17598293490034 17598293454270 17598293808670 17598293810446
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 377 223297 223297 4194304 256 0 0 12 24 195840 0x7fc57b003980 0x7fc57a625ec0 460468 460468 65536 8847360 1340578 150097020 17598293845135 17598293808670 17598294285151 17598294307633
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 380 223297 223297 4194304 256 0 0 12 24 198592 0x7fc57b003800 0x7fc57a625f00 244266 244266 65536 5701632 861018 96425368 17598294328973 17598294285151 17598294653791 17598294655415
130 128 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 383 223297 223297 4194304 256 0 0 12 24 202368 0x7fc57b003680 0x7fc57a625f40 333187 333187 65536 7471104 1193904 133725160 17598294690874 17598294653791 17598295059551 17598295104823
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 386 223297 223297 4194304 256 0 0 12 24 205888 0x7fc57d663500 0x7fc57a625f80 330871 330871 65536 7340032 1159135 129836260 17598295116103 17598295059551 17598295497311 17598295540822
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 389 223297 223297 4194304 256 0 0 12 24 209408 0x7fc57d663380 0x7fc57a625fc0 305910 305910 65536 7340032 1121399 125509564 17598295551712 17598295497311 17598295908672 17598295910503
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 392 223297 223297 4194304 256 0 0 12 24 214464 0x7fc57d663200 0x7fc57a626000 542283 542283 65536 10420224 1568783 175813004 17598295945792 17598295908672 17598296439872 17598296482158
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 395 223297 223297 4194304 256 0 0 12 24 217728 0x7fc57d663080 0x7fc57a626040 272435 272435 65536 6488064 992618 111236844 17598296502797 17598296439872 17598296830912 17598296832689
135 133 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 398 223297 223297 4194304 256 0 0 12 24 222016 0x7fc57b003f00 0x7fc57a626080 364525 364525 65536 8519680 1361388 152365296 17598296869268 17598296830912 17598297256833 17598297299227
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 401 223297 223297 4194304 256 0 0 12 24 226048 0x7fc57b003d80 0x7fc57a6260c0 367851 367851 65536 8388608 1359359 152227300 17598297310527 17598297256833 17598297709633 17598297727836
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 404 223297 223297 4194304 256 0 0 12 24 230080 0x7fc57b003c00 0x7fc57a626100 346157 346157 65536 8388608 1297532 145388716 17598297745406 17598297709633 17598298117473 17598298163095
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 407 223297 223297 4194304 256 0 0 12 24 235904 0x7fc57b003a80 0x7fc57a626140 623057 623057 65536 11993088 1828127 204732500 17598298174855 17598298117473 17598298733954 17598298777430
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 410 223297 223297 4194304 256 0 0 12 24 239424 0x7fc57b003900 0x7fc57a626180 302787 302787 65536 7274496 1156188 129567956 17598298796769 17598298733954 17598299146914 17598299148690
140 138 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 413 223297 223297 4194304 256 0 0 12 24 244224 0x7fc57b003780 0x7fc57a6261c0 398823 398823 65536 9568256 1491465 167017620 17598299186029 17598299146914 17598299592835 17598299637038
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 416 223297 223297 4194304 256 0 0 12 24 248768 0x7fc57b003600 0x7fc57a626200 389443 389443 65536 9437184 1456663 163291036 17598299649217 17598299592835 17598300061315 17598300105206
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 419 223297 223297 4194304 256 0 0 12 24 253312 0x7fc57d663480 0x7fc57a626240 386633 386633 65536 9437184 1464421 163958644 17598300116546 17598300061315 17598300533795 17598300577924
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 422 223297 223297 4194304 256 0 0 8 24 255552 0x7fc57d663300 0x7fc57a626280 718746 718746 65536 16056320 2308323 258892844 17598300589654 17598300533795 17598301209156 17598301253387
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 425 223297 223297 4194304 256 0 0 12 24 259840 0x7fc57d663180 0x7fc57a6262c0 363190 363190 65536 8847360 1367371 153164760 17598301273886 17598301209156 17598301657636 17598301702005
145 143 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 428 223297 223297 4194304 256 0 0 12 24 265664 0x7fc57d663000 0x7fc57a626300 468855 468855 65536 11665408 1840693 206045152 17598301713865 17598301657636 17598302184677 17598302229022
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 431 223297 223297 4194304 256 0 0 12 24 271232 0x7fc57b003e80 0x7fc57a626340 471122 471122 65536 11468800 1835596 205579460 17598302240842 17598302184677 17598302714277 17598302758459
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 434 223297 223297 4194304 256 0 0 8 24 273216 0x7fc57b003d00 0x7fc57a626380 482691 482691 65536 14090240 2021655 226289536 17598302769468 17598302714277 17598303239557 17598303283735
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 437 223297 223297 4194304 256 0 0 8 24 275712 0x7fc57b003b80 0x7fc57a6263c0 879198 879198 65536 19202048 2757838 308615396 17598303295945 17598303239557 17598304018598 17598304060306
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 440 223297 223297 4194304 256 0 0 12 24 280768 0x7fc57b003a00 0x7fc57a626400 425606 425606 65536 10420224 1600707 179444132 17598304080715 17598304018598 17598304502758 17598304545083
150 148 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 443 223297 223297 4194304 256 0 0 12 24 287616 0x7fc57b003880 0x7fc57a626440 547968 547968 65536 13762560 2143950 240064628 17598304556993 17598304502758 17598305074599 17598305116809
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 446 223297 223297 4194304 256 0 0 12 24 294208 0x7fc57b003700 0x7fc57a626480 549766 549766 65536 13565952 2169986 243035864 17598305129159 17598305074599 17598305644199 17598305686654
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 449 223297 223297 4194304 256 0 0 8 24 296960 0x7fc57d663580 0x7fc57a6264c0 563418 563418 65536 15466496 2228340 249472868 17598305698124 17598305644199 17598306218120 17598306262830
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 452 223297 223297 4194304 256 0 0 8 24 299968 0x7fc57d663400 0x7fc57a626500 1043564 1043564 65536 22347776 3211811 359803404 17598306275119 17598306218120 17598307109960 17598307153547
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 455 223297 223297 4194304 256 0 0 8 24 302720 0x7fc57d663280 0x7fc57a626540 722110 722110 65536 20250624 2910147 325967960 17598307174287 17598307109960 17598307781481 17598307825580
155 153 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 458 223297 223297 4194304 256 0 0 12 24 305472 0x7fc57d663100 0x7fc57a626580 723565 723565 65536 20447232 2935970 328866128 17598307836850 17598307781481 17598308479401 17598308521872
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 461 223297 223297 4194304 256 0 0 12 24 308224 0x7fc57b003f80 0x7fc57a6265c0 721500 721500 65536 19595264 2814676 315453276 17598308533312 17598308479225 17598309162745 17598309208785
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 464 223297 223297 4194304 256 0 0 8 24 310976 0x7fc57b003e00 0x7fc57a626600 726076 726076 65536 20381696 2936476 328942212 17598309219944 17598309162745 17598309838265 17598309881097
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 467 223297 223297 4194304 256 0 0 8 24 313216 0x7fc57b003c80 0x7fc57a626640 1366825 1366825 65536 31522816 4514898 505583912 17598309891967 17598309838265 17598310928665 17598310975270
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 470 223297 223297 4194304 256 0 0 8 24 315968 0x7fc57b003b00 0x7fc57a626680 1371641 1371641 65536 38993920 5589029 626214956 17598310996489 17598310928665 17598312012346 17598312056892
160 158 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 473 223297 223297 4194304 256 0 0 12 24 318720 0x7fc57b003980 0x7fc57a6266c0 1372673 1372673 65536 39124992 5608013 627989248 17598312068272 17598312012346 17598313119226 17598313184094
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 476 223297 223297 4194304 256 0 0 12 24 321472 0x7fc57b003800 0x7fc57a626700 1370411 1370411 65536 38469632 5519358 617861312 17598313195153 17598313119226 17598314243227 17598314312425
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 479 223297 223297 4194304 256 0 0 8 24 324224 0x7fc57b003680 0x7fc57a626740 1375071 1375071 65536 39059456 5597910 626915124 17598314324455 17598314243227 17598315372347 17598315439636
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 482 223297 223297 4194304 256 0 0 8 24 326464 0x7fc57d663500 0x7fc57a626780 2664520 2664520 65536 60489728 8660095 969801984 17598315451946 17598315372347 17598317343388 17598317410306
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 485 223297 223297 4194304 256 0 0 8 24 329216 0x7fc57d663380 0x7fc57a6267c0 2666822 2666822 65536 77266944 11060008 1238260984 17598317430076 17598317343388 17598319273789 17598319343217
165 163 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 488 223297 223297 4194304 256 0 0 12 24 331968 0x7fc57d663200 0x7fc57a626800 2671085 2671085 65536 77398016 11073139 1240205108 17598319355797 17598319273789 17598321268189 17598321335786
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 491 223297 223297 4194304 256 0 0 12 24 334720 0x7fc57d663080 0x7fc57a626840 2668714 2668714 65536 76218368 10914634 1222575476 17598321348676 17598321268189 17598323245470 17598323317666
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 494 223297 223297 4194304 256 0 0 8 24 337472 0x7fc57b003f00 0x7fc57a626880 2674890 2674890 65536 77332480 11062184 1239088008 17598323330526 17598323245470 17598325194911 17598325263067
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 497 223297 223297 4194304 256 0 0 8 24 0 0x7fc57b003d80 0x7fc57a6268c0 5255732 5255732 65536 120258560 17190583 1925804324 17598325275167 17598325194911 17598328815713 17598328885995
@@ -0,0 +1,168 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,grd,Workgroup_Size,LDS_Per_Workgroup,scr,vgpr,SGPR,fbar,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"__amd_rocclr_fillBufferAligned.kd",0,0,0,225145,225145,33554432,256,0,0,4,32,4160,0x0,0x7f6011204280,0,0,0,17617373642292,17616657358066,17617521510730,17617521624110
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,225145,225145,32768,256,0,0,12,24,13888,0x0,0x7f6011223f80,0,0,0,17617526822058,17617521510730,17617526949772,17617526954185
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,225145,225145,4194304,256,0,0,12,24,14336,0x7f601422d380,0x7f6011223fc0,0,0,0,17617526989654,17617526949772,17617527316172,17617527318486
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,225145,225145,4194304,256,0,0,16,24,15040,0x7f601422d200,0x7f6011224000,0,0,0,17617527355035,17617527316172,17617527717452,17617527719416
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,225145,225145,4194304,256,0,0,16,24,15488,0x7f601422d080,0x7f6011224040,0,0,0,17617527752475,17617527717452,17617528112172,17617528114156
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,225145,225145,4194304,256,0,0,12,24,15936,0x7f6011acdf00,0x7f6011224080,0,0,0,17617528147005,17617528112172,17617528419052,17617528421068
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,225145,225145,4194304,256,0,0,12,24,16384,0x7f6011acdd80,0x7f60112240c0,0,0,0,17617528454017,17617528419052,17617528719692,17617528721660
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,225145,225145,4194304,256,0,0,12,24,17088,0x7f6011acdc00,0x7f6011224100,0,0,0,17617528765359,17617528719692,17617529019052,17617529020973
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,225145,225145,4194304,256,0,0,16,24,17792,0x7f6011acda80,0x7f6011224140,0,0,0,17617529052832,17617529019052,17617529407373,17617529409783
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,225145,225145,4194304,256,0,0,16,24,18496,0x7f6011acd900,0x7f6011224180,0,0,0,17617529441212,17617529407373,17617529796653,17617529798663
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,225145,225145,4194304,256,0,0,16,24,19200,0x7f6011acd780,0x7f60112241c0,0,0,0,17617529830222,17617529796653,17617530116173,17617530118345
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,225145,225145,4194304,256,0,0,16,24,19904,0x7f6011acd600,0x7f6011224200,0,0,0,17617530150604,17617530116173,17617530428653,17617530431017
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,225145,225145,4194304,256,0,0,12,24,20608,0x7f601422d480,0x7f6011224240,0,0,0,17617530470706,17617530428653,17617530725293,17617530726820
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,225145,225145,4194304,256,0,0,16,24,21312,0x7f601422d300,0x7f6011224280,0,0,0,17617530760449,17617530725293,17617531089293,17617531090840
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,225145,225145,4194304,256,0,0,16,24,22016,0x7f601422d180,0x7f60112242c0,0,0,0,17617531123289,17617531089293,17617531450573,17617531452141
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,225145,225145,4194304,256,0,0,16,24,22720,0x7f601422d000,0x7f6011224300,0,0,0,17617531484590,17617531450573,17617531725294,17617531726804
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,225145,225145,4194304,256,0,0,12,24,23424,0x7f6011acde80,0x7f6011224340,0,0,0,17617531758603,17617531725294,17617532009454,17617532010787
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,225145,225145,4194304,256,0,0,12,24,24128,0x7f6011acdd00,0x7f6011224380,0,0,0,17617532049466,17617532009454,17617532284334,17617532285800
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,225145,225145,4194304,256,0,0,16,24,24832,0x7f6011acdb80,0x7f60112243c0,0,0,0,17617532318189,17617532284334,17617532646094,17617532647451
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,225145,225145,4194304,256,0,0,16,24,25536,0x7f6011acda00,0x7f6011224400,0,0,0,17617532679750,17617532646094,17617533007054,17617533008542
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,225145,225145,4194304,256,0,0,12,24,26240,0x7f6011acd880,0x7f6011224440,0,0,0,17617533040051,17617533007054,17617533285134,17617533286845
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,225145,225145,4194304,256,0,0,12,24,26944,0x7f6011acd700,0x7f6011224480,0,0,0,17617533318864,17617533285134,17617533556334,17617533557708
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,225145,225145,4194304,256,0,0,12,24,27648,0x7f601422d580,0x7f60112244c0,0,0,0,17617533596337,17617533556334,17617533827534,17617533829061
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,225145,225145,4194304,256,0,0,16,24,28608,0x7f601422d400,0x7f6011224500,0,0,0,17617533860670,17617533827534,17617534189615,17617534191042
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,225145,225145,4194304,256,0,0,16,24,29312,0x7f601422d280,0x7f6011224540,0,0,0,17617534223531,17617534189615,17617534552495,17617534553882
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,225145,225145,4194304,256,0,0,12,24,30016,0x7f601422d100,0x7f6011224580,0,0,0,17617534584972,17617534552495,17617534828655,17617534830085
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,225145,225145,4194304,256,0,0,8,24,30976,0x7f6011acdf80,0x7f60112245c0,0,0,0,17617534862085,17617534828655,17617535102895,17617535104478
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,225145,225145,4194304,256,0,0,12,24,31680,0x7f6011acde00,0x7f6011224600,0,0,0,17617535143677,17617535102895,17617535374575,17617535376091
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,225145,225145,4194304,256,0,0,16,24,32640,0x7f6011acdc80,0x7f6011224640,0,0,0,17617535409341,17617535374575,17617535731695,17617535733162
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,225145,225145,4194304,256,0,0,12,24,33600,0x7f6011acdb00,0x7f6011224680,0,0,0,17617535764342,17617535731695,17617536088655,17617536090333
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,225145,225145,4194304,256,0,0,12,24,34560,0x7f6011acd980,0x7f60112246c0,0,0,0,17617536122022,17617536088655,17617536365455,17617536367116
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,225145,225145,4194304,256,0,0,8,24,35520,0x7f6011acd800,0x7f6011224700,0,0,0,17617536398155,17617536365455,17617536651375,17617536652909
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,225145,225145,4194304,256,0,0,12,24,36224,0x7f6011acd680,0x7f6011224740,0,0,0,17617536690968,17617536651375,17617536927696,17617536929142
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,225145,225145,4194304,256,0,0,12,24,37184,0x7f601422d500,0x7f6011224780,0,0,0,17617536961961,17617536927696,17617537287856,17617537289353
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,225145,225145,4194304,256,0,0,12,24,38144,0x7f601422d380,0x7f60112247c0,0,0,0,17617537321362,17617537287856,17617537650096,17617537651613
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,225145,225145,4194304,256,0,0,12,24,39104,0x7f601422d200,0x7f6011224800,0,0,0,17617537683823,17617537650096,17617537925136,17617537926746
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,225145,225145,4194304,256,0,0,8,24,40320,0x7f601422d080,0x7f6011224840,0,0,0,17617537958656,17617537925136,17617538207696,17617538209129
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,225145,225145,4194304,256,0,0,12,24,41280,0x7f6011acdf00,0x7f6011224880,0,0,0,17617538249708,17617538207696,17617538484016,17617538485432
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,225145,225145,4194304,256,0,0,12,24,42240,0x7f6011acdd80,0x7f60112248c0,0,0,0,17617538518491,17617538484016,17617538844656,17617538846203
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,225145,225145,4194304,256,0,0,12,24,43200,0x7f6011acdc00,0x7f6011224900,0,0,0,17617538877072,17617538844656,17617539208177,17617539209674
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,225145,225145,4194304,256,0,0,8,24,44160,0x7f6011acda80,0x7f6011224940,0,0,0,17617539241083,17617539208177,17617539478897,17617539480317
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,225145,225145,4194304,256,0,0,12,24,45376,0x7f6011acd900,0x7f6011224980,0,0,0,17617539511686,17617539478897,17617539750257,17617539751870
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,225145,225145,4194304,256,0,0,12,24,46336,0x7f6011acd780,0x7f60112249c0,0,0,0,17617539789489,17617539750257,17617540025137,17617540026513
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,225145,225145,4194304,256,0,0,12,24,47552,0x7f6011acd600,0x7f6011224a00,0,0,0,17617540058182,17617540025137,17617540381137,17617540382644
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,225145,225145,4194304,256,0,0,12,24,48512,0x7f601422d480,0x7f6011224a40,0,0,0,17617540414813,17617540381137,17617540740017,17617540741505
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,225145,225145,4194304,256,0,0,8,24,49472,0x7f601422d300,0x7f6011224a80,0,0,0,17617540773014,17617540740017,17617541012337,17617541013728
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,225145,225145,4194304,256,0,0,12,24,50688,0x7f601422d180,0x7f6011224ac0,0,0,0,17617541045667,17617541012337,17617541284337,17617541285751
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,225145,225145,4194304,256,0,0,12,24,51648,0x7f601422d000,0x7f6011224b00,0,0,0,17617541323680,17617541284337,17617541559057,17617541560504
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,225145,225145,4194304,256,0,0,12,24,52864,0x7f6011acde80,0x7f6011224b40,0,0,0,17617541591823,17617541559057,17617541918258,17617541919735
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,225145,225145,4194304,256,0,0,12,24,54080,0x7f6011acdd00,0x7f6011224b80,0,0,0,17617541953424,17617541918258,17617542290898,17617542292496
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,225145,225145,4194304,256,0,0,8,24,55296,0x7f6011acdb80,0x7f6011224bc0,0,0,0,17617542323815,17617542290898,17617542565458,17617542566939
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,225145,225145,4194304,256,0,0,12,24,56768,0x7f6011acda00,0x7f6011224c00,0,0,0,17617542597968,17617542565458,17617542837618,17617542839042
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,225145,225145,4194304,256,0,0,12,24,57728,0x7f6011acd880,0x7f6011224c40,0,0,0,17617542877741,17617542837618,17617543111858,17617543113295
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,225145,225145,4194304,256,0,0,12,24,58944,0x7f6011acd700,0x7f6011224c80,0,0,0,17617543145394,17617543111858,17617543469778,17617543471166
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,225145,225145,4194304,256,0,0,12,24,60160,0x7f601422d580,0x7f6011224cc0,0,0,0,17617543502855,17617543469778,17617543828978,17617543830397
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,225145,225145,4194304,256,0,0,8,24,61376,0x7f601422d400,0x7f6011224d00,0,0,0,17617543861706,17617543828978,17617544099698,17617544101090
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,225145,225145,4194304,256,0,0,12,24,62848,0x7f601422d280,0x7f6011224d40,0,0,0,17617544133159,17617544099698,17617544376659,17617544377983
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,225145,225145,4194304,256,0,0,12,24,63808,0x7f601422d100,0x7f6011224d80,0,0,0,17617544417452,17617544376659,17617544656339,17617544657766
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,225145,225145,4194304,256,0,0,12,24,65024,0x7f6011acdf80,0x7f6011224dc0,0,0,0,17617544689525,17617544656339,17617545017299,17617545018867
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,225145,225145,4194304,256,0,0,12,24,66240,0x7f6011acde00,0x7f6011224e00,0,0,0,17617545050856,17617545017299,17617545372979,17617545374468
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,225145,225145,4194304,256,0,0,8,24,67456,0x7f6011acdc80,0x7f6011224e40,0,0,0,17617545405597,17617545372979,17617545643379,17617545644811
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,225145,225145,4194304,256,0,0,12,24,68928,0x7f6011acdb00,0x7f6011224e80,0,0,0,17617545676170,17617545643379,17617545929939,17617545931253
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,225145,225145,4194304,256,0,0,12,24,70144,0x7f6011acd980,0x7f6011224ec0,0,0,0,17617545968743,17617545929939,17617546210739,17617546212246
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,225145,225145,4194304,256,0,0,12,24,71616,0x7f6011acd800,0x7f6011224f00,0,0,0,17617546243966,17617546210739,17617546575059,17617546576377
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,225145,225145,4194304,256,0,0,12,24,72832,0x7f6011acd680,0x7f6011224f40,0,0,0,17617546608446,17617546575059,17617546935380,17617546936818
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,225145,225145,4194304,256,0,0,8,24,74048,0x7f601422d500,0x7f6011224f80,0,0,0,17617546967947,17617546935380,17617547207060,17617547208651
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,225145,225145,4194304,256,0,0,12,24,75776,0x7f601422d380,0x7f6011224fc0,0,0,0,17617547239860,17617547207060,17617547494420,17617547495814
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,225145,225145,4194304,256,0,0,12,24,76992,0x7f601422d200,0x7f6011225000,0,0,0,17617547534863,17617547494420,17617547767380,17617547768937
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,225145,225145,4194304,256,0,0,12,24,78464,0x7f601422d080,0x7f6011225040,0,0,0,17617547800396,17617547767380,17617548131540,17617548133078
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,225145,225145,4194304,256,0,0,12,24,79936,0x7f6011acdf00,0x7f6011225080,0,0,0,17617548165057,17617548131540,17617548492340,17617548493869
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,225145,225145,4194304,256,0,0,8,24,81408,0x7f6011acdd80,0x7f60112250c0,0,0,0,17617548525858,17617548492340,17617548768980,17617548770372
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,225145,225145,4194304,256,0,0,12,24,83136,0x7f6011acdc00,0x7f6011225100,0,0,0,17617548801051,17617548768980,17617549062900,17617549064304
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,225145,225145,4194304,256,0,0,12,24,84352,0x7f6011acda80,0x7f6011225140,0,0,0,17617549113433,17617549062900,17617549337461,17617549338857
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,225145,225145,4194304,256,0,0,12,24,85824,0x7f6011acd900,0x7f6011225180,0,0,0,17617549370096,17617549337461,17617549710741,17617549712198
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,225145,225145,4194304,256,0,0,12,24,87296,0x7f6011acd780,0x7f60112251c0,0,0,0,17617549743687,17617549710741,17617550072021,17617550073539
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,225145,225145,4194304,256,0,0,12,24,88768,0x7f6011acd600,0x7f6011225200,0,0,0,17617550105618,17617550072021,17617550350581,17617550352101
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,225145,225145,4194304,256,0,0,12,24,90752,0x7f601422d480,0x7f6011225240,0,0,0,17617550383471,17617550350581,17617550650901,17617550652284
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,225145,225145,4194304,256,0,0,12,24,91968,0x7f601422d300,0x7f6011225280,0,0,0,17617550690823,17617550650901,17617550932981,17617550934397
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,225145,225145,4194304,256,0,0,12,24,93440,0x7f601422d180,0x7f60112252c0,0,0,0,17617550966226,17617550932981,17617551295541,17617551297107
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,225145,225145,4194304,256,0,0,12,24,94912,0x7f601422d000,0x7f6011225300,0,0,0,17617551329177,17617551295541,17617551658901,17617551660368
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,225145,225145,4194304,256,0,0,12,24,96384,0x7f6011acde80,0x7f6011225340,0,0,0,17617551692067,17617551658901,17617551933622,17617551935011
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,225145,225145,4194304,256,0,0,12,24,98368,0x7f6011acdd00,0x7f6011225380,0,0,0,17617551966931,17617551933622,17617552237142,17617552238644
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,225145,225145,4194304,256,0,0,12,24,99584,0x7f6011acdb80,0x7f60112253c0,0,0,0,17617552277203,17617552237142,17617552509782,17617552511337
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,225145,225145,4194304,256,0,0,12,24,101312,0x7f6011acda00,0x7f6011225400,0,0,0,17617552542106,17617552509782,17617552865622,17617552867108
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,225145,225145,4194304,256,0,0,12,24,102784,0x7f6011acd880,0x7f6011225440,0,0,0,17617552898317,17617552865622,17617553224182,17617553225649
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,225145,225145,4194304,256,0,0,12,24,104256,0x7f6011acd700,0x7f6011225480,0,0,0,17617553257078,17617553224182,17617553497782,17617553499362
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,225145,225145,4194304,256,0,0,12,24,106240,0x7f601422d580,0x7f60112254c0,0,0,0,17617553530831,17617553497782,17617553821462,17617553823013
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,225145,225145,4194304,256,0,0,12,24,107712,0x7f601422d400,0x7f6011225500,0,0,0,17617553861702,17617553821462,17617554100662,17617554102266
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,225145,225145,4194304,256,0,0,16,24,109440,0x7f601422d280,0x7f6011225540,0,0,0,17617554135076,17617554100662,17617554466263,17617554467857
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,225145,225145,4194304,256,0,0,16,24,111168,0x7f601422d100,0x7f6011225580,0,0,0,17617554500836,17617554466263,17617554826423,17617554827978
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,225145,225145,4194304,256,0,0,8,24,112896,0x7f6011acdf80,0x7f60112255c0,0,0,0,17617554859567,17617554826423,17617555100023,17617555101551
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,225145,225145,4194304,256,0,0,12,24,115136,0x7f6011acde00,0x7f6011225600,0,0,0,17617555132730,17617555100023,17617555414583,17617555416003
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,225145,225145,4194304,256,0,0,12,24,116608,0x7f6011acdc80,0x7f6011225640,0,0,0,17617555454622,17617555414583,17617555687383,17617555688946
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,225145,225145,4194304,256,0,0,16,24,118336,0x7f6011acdb00,0x7f6011225680,0,0,0,17617555719795,17617555687383,17617556043703,17617556045387
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,225145,225145,4194304,256,0,0,16,24,120064,0x7f6011acd980,0x7f60112256c0,0,0,0,17617556076296,17617556043703,17617556403223,17617556404758
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,225145,225145,4194304,256,0,0,12,24,121792,0x7f6011acd800,0x7f6011225700,0,0,0,17617556436007,17617556403223,17617556677303,17617556678691
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,225145,225145,4194304,256,0,0,12,24,124032,0x7f6011acd680,0x7f6011225740,0,0,0,17617556709920,17617556677303,17617557004184,17617557005703
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,225145,225145,4194304,256,0,0,12,24,125504,0x7f601422d500,0x7f6011225780,0,0,0,17617557047552,17617557004184,17617557277464,17617557278956
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,225145,225145,4194304,256,0,0,12,24,127488,0x7f601422d380,0x7f60112257c0,0,0,0,17617557310195,17617557277464,17617557635384,17617557636777
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,225145,225145,4194304,256,0,0,12,24,129216,0x7f601422d200,0x7f6011225800,0,0,0,17617557669036,17617557635384,17617557992984,17617557994588
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,225145,225145,4194304,256,0,0,12,24,130944,0x7f601422d080,0x7f6011225840,0,0,0,17617558025727,17617557992984,17617558284184,17617558285720
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,225145,225145,4194304,256,0,0,12,24,133440,0x7f6011acdf00,0x7f6011225880,0,0,0,17617558317880,17617558284184,17617558624184,17617558625842
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,225145,225145,4194304,256,0,0,12,24,134912,0x7f6011acdd80,0x7f60112258c0,0,0,0,17617558664591,17617558624184,17617558896344,17617558897775
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,225145,225145,4194304,256,0,0,12,24,136896,0x7f6011acdc00,0x7f6011225900,0,0,0,17617558928904,17617558896344,17617559254424,17617559255826
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,225145,225145,4194304,256,0,0,12,24,138880,0x7f6011acda80,0x7f6011225940,0,0,0,17617559287155,17617559254424,17617559610425,17617559611857
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,225145,225145,4194304,256,0,0,12,24,140864,0x7f6011acd900,0x7f6011225980,0,0,0,17617559643026,17617559610425,17617559891865,17617559893430
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,225145,225145,4194304,256,0,0,12,24,143616,0x7f6011acd780,0x7f60112259c0,0,0,0,17617559924479,17617559891865,17617560241785,17617560243271
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,225145,225145,4194304,256,0,0,12,24,145344,0x7f6011acd600,0x7f6011225a00,0,0,0,17617560281790,17617560241785,17617560516825,17617560518504
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,225145,225145,4194304,256,0,0,12,24,147584,0x7f601422d480,0x7f6011225a40,0,0,0,17617560549803,17617560516825,17617560875385,17617560876855
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,225145,225145,4194304,256,0,0,12,24,149568,0x7f601422d300,0x7f6011225a80,0,0,0,17617560909014,17617560875385,17617561232505,17617561233876
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,225145,225145,4194304,256,0,0,12,24,151552,0x7f601422d180,0x7f6011225ac0,0,0,0,17617561265565,17617561232505,17617561520345,17617561522008
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,225145,225145,4194304,256,0,0,12,24,154304,0x7f601422d000,0x7f6011225b00,0,0,0,17617561553348,17617561520345,17617561879546,17617561881059
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,225145,225145,4194304,256,0,0,12,24,156288,0x7f6011acde80,0x7f6011225b40,0,0,0,17617561919758,17617561879546,17617562161306,17617562162862
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,225145,225145,4194304,256,0,0,12,24,158784,0x7f6011acdd00,0x7f6011225b80,0,0,0,17617562196041,17617562161306,17617562526106,17617562527573
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,225145,225145,4194304,256,0,0,12,24,161024,0x7f6011acdb80,0x7f6011225bc0,0,0,0,17617562559762,17617562526106,17617562886266,17617562887624
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,225145,225145,4194304,256,0,0,12,24,163264,0x7f6011acda00,0x7f6011225c00,0,0,0,17617562919813,17617562886266,17617563195706,17617563197286
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,225145,225145,4194304,256,0,0,12,24,166528,0x7f6011acd880,0x7f6011225c40,0,0,0,17617563228415,17617563195706,17617563581306,17617563627295
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,225145,225145,4194304,256,0,0,12,24,168512,0x7f6011acd700,0x7f6011225c80,0,0,0,17617563645865,17617563581306,17617563906906,17617563908268
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,225145,225145,4194304,256,0,0,12,24,171264,0x7f601422d580,0x7f6011225cc0,0,0,0,17617563940177,17617563906906,17617564270746,17617564272239
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,225145,225145,4194304,256,0,0,12,24,173760,0x7f601422d400,0x7f6011225d00,0,0,0,17617564304178,17617564270746,17617564635067,17617564636509
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,225145,225145,4194304,256,0,0,12,24,176256,0x7f601422d280,0x7f6011225d40,0,0,0,17617564668449,17617564635067,17617564949147,17617564950451
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,225145,225145,4194304,256,0,0,12,24,179776,0x7f601422d100,0x7f6011225d80,0,0,0,17617564981881,17617564949147,17617565360347,17617565403230
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,225145,225145,4194304,256,0,0,12,24,182272,0x7f6011acdf80,0x7f6011225dc0,0,0,0,17617565422010,17617565360347,17617565711707,17617565713132
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,225145,225145,4194304,256,0,0,12,24,185536,0x7f6011acde00,0x7f6011225e00,0,0,0,17617565744121,17617565711707,17617566084027,17617566086623
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,225145,225145,4194304,256,0,0,12,24,188544,0x7f6011acdc80,0x7f6011225e40,0,0,0,17617566118272,17617566084027,17617566462427,17617566485903
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,225145,225145,4194304,256,0,0,12,24,191552,0x7f6011acdb00,0x7f6011225e80,0,0,0,17617566498042,17617566462427,17617566818588,17617566820094
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,225145,225145,4194304,256,0,0,12,24,195840,0x7f6011acd980,0x7f6011225ec0,0,0,0,17617566851333,17617566818588,17617567281308,17617567302392
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,225145,225145,4194304,256,0,0,12,24,198592,0x7f6011acd800,0x7f6011225f00,0,0,0,17617567321261,17617567281308,17617567617788,17617567619214
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,225145,225145,4194304,256,0,0,12,24,202368,0x7f6011acd680,0x7f6011225f40,0,0,0,17617567650873,17617567617788,17617568009468,17617568029683
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,225145,225145,4194304,256,0,0,12,24,205888,0x7f601422d500,0x7f6011225f80,0,0,0,17617568043053,17617568009468,17617568402268,17617568422443
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,225145,225145,4194304,256,0,0,12,24,209408,0x7f601422d380,0x7f6011225fc0,0,0,0,17617568435943,17617568402268,17617568776508,17617568777964
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,225145,225145,4194304,256,0,0,12,24,214464,0x7f601422d200,0x7f6011226000,0,0,0,17617568809754,17617568776508,17617569293468,17617569313371
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,225145,225145,4194304,256,0,0,12,24,217728,0x7f601422d080,0x7f6011226040,0,0,0,17617569334100,17617569293468,17617569646909,17617569648382
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,225145,225145,4194304,256,0,0,12,24,222016,0x7f6011acdf00,0x7f6011226080,0,0,0,17617569679902,17617569646909,17617570058429,17617570097621
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,225145,225145,4194304,256,0,0,12,24,226048,0x7f6011acdd80,0x7f60112260c0,0,0,0,17617570110081,17617570058429,17617570504989,17617570550000
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,225145,225145,4194304,256,0,0,12,24,230080,0x7f6011acdc00,0x7f6011226100,0,0,0,17617570562439,17617570504989,17617570931389,17617570978869
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,225145,225145,4194304,256,0,0,12,24,235904,0x7f6011acda80,0x7f6011226140,0,0,0,17617570991138,17617570931389,17617571531229,17617571573424
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,225145,225145,4194304,256,0,0,12,24,239424,0x7f6011acd900,0x7f6011226180,0,0,0,17617571592223,17617571531229,17617571925630,17617571927005
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,225145,225145,4194304,256,0,0,12,24,244224,0x7f6011acd780,0x7f60112261c0,0,0,0,17617571958424,17617571925630,17617572356030,17617572399003
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,225145,225145,4194304,256,0,0,12,24,248768,0x7f6011acd600,0x7f6011226200,0,0,0,17617572411482,17617572356030,17617572817150,17617572859911
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,225145,225145,4194304,256,0,0,12,24,253312,0x7f601422d480,0x7f6011226240,0,0,0,17617572871331,17617572817150,17617573264350,17617573306480
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,225145,225145,4194304,256,0,0,8,24,255552,0x7f601422d300,0x7f6011226280,0,0,0,17617573318479,17617573264350,17617573927710,17617573947643
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,225145,225145,4194304,256,0,0,12,24,259840,0x7f601422d180,0x7f60112262c0,0,0,0,17617573969173,17617573927710,17617574344190,17617574391252
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,225145,225145,4194304,256,0,0,12,24,265664,0x7f601422d000,0x7f6011226300,0,0,0,17617574403462,17617574344190,17617574861471,17617574905879
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,225145,225145,4194304,256,0,0,12,24,271232,0x7f6011acde80,0x7f6011226340,0,0,0,17617574916769,17617574861471,17617575376831,17617575423176
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,225145,225145,4194304,256,0,0,8,24,273216,0x7f6011acdd00,0x7f6011226380,0,0,0,17617575434706,17617575376831,17617575887391,17617575929613
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,225145,225145,4194304,256,0,0,8,24,275712,0x7f6011acdb80,0x7f60112263c0,0,0,0,17617575941063,17617575887391,17617576653151,17617576695054
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,225145,225145,4194304,256,0,0,12,24,280768,0x7f6011acda00,0x7f6011226400,0,0,0,17617576714243,17617576653151,17617577129312,17617577171232
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,225145,225145,4194304,256,0,0,12,24,287616,0x7f6011acd880,0x7f6011226440,0,0,0,17617577183371,17617577129312,17617577690112,17617577732907
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,225145,225145,4194304,256,0,0,12,24,294208,0x7f6011acd700,0x7f6011226480,0,0,0,17617577745047,17617577690112,17617578253792,17617578298543
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,225145,225145,4194304,256,0,0,8,24,296960,0x7f601422d580,0x7f60112264c0,0,0,0,17617578311273,17617578253792,17617578819872,17617578863899
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,225145,225145,4194304,256,0,0,8,24,299968,0x7f601422d400,0x7f6011226500,0,0,0,17617578875309,17617578819872,17617579692193,17617579737037
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,225145,225145,4194304,256,0,0,8,24,302720,0x7f601422d280,0x7f6011226540,0,0,0,17617579756256,17617579692193,17617580351713,17617580394280
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,225145,225145,4194304,256,0,0,12,24,305472,0x7f601422d100,0x7f6011226580,0,0,0,17617580405870,17617580351713,17617581023713,17617581066433
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,225145,225145,4194304,256,0,0,12,24,308224,0x7f6011acdf80,0x7f60112265c0,0,0,0,17617581077973,17617581023713,17617581700033,17617581742536
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,225145,225145,4194304,256,0,0,8,24,310976,0x7f6011acde00,0x7f6011226600,0,0,0,17617581753926,17617581700033,17617582360674,17617582407249
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,225145,225145,4194304,256,0,0,8,24,313216,0x7f6011acdc80,0x7f6011226640,0,0,0,17617582419829,17617582360674,17617583457634,17617583504071
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,225145,225145,4194304,256,0,0,8,24,315968,0x7f6011acdb00,0x7f6011226680,0,0,0,17617583524191,17617583457473,17617584555073,17617584626223
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,225145,225145,4194304,256,0,0,12,24,318720,0x7f6011acd980,0x7f60112266c0,0,0,0,17617584637902,17617584555073,17617585691233,17617585755844
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,225145,225145,4194304,256,0,0,12,24,321472,0x7f6011acd800,0x7f6011226700,0,0,0,17617585768084,17617585691233,17617586817153,17617586888225
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,225145,225145,4194304,256,0,0,8,24,324224,0x7f6011acd680,0x7f6011226740,0,0,0,17617586900485,17617586817153,17617587936353,17617588002997
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,225145,225145,4194304,256,0,0,8,24,326464,0x7f601422d500,0x7f6011226780,0,0,0,17617588015017,17617587936353,17617589885633,17617589953588
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,225145,225145,4194304,256,0,0,8,24,329216,0x7f601422d380,0x7f60112267c0,0,0,0,17617589973427,17617589885633,17617591812033,17617591884639
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,225145,225145,4194304,256,0,0,12,24,331968,0x7f601422d200,0x7f6011226800,0,0,0,17617591896388,17617591812033,17617593803073,17617593868648
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,225145,225145,4194304,256,0,0,12,24,334720,0x7f601422d080,0x7f6011226840,0,0,0,17617593880348,17617593803073,17617595765953,17617595838408
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,225145,225145,4194304,256,0,0,8,24,337472,0x7f6011acdf00,0x7f6011226880,0,0,0,17617595851508,17617595765953,17617597700514,17617597768509
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,225145,225145,4194304,256,0,0,8,24,0,0x7f6011acdd80,0x7f60112268c0,0,0,0,17617597780579,17617597700514,17617601308354,17617601387817
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid grd Workgroup_Size LDS_Per_Workgroup scr vgpr SGPR fbar sig obj SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 __amd_rocclr_fillBufferAligned.kd 0 0 0 225145 225145 33554432 256 0 0 4 32 4160 0x0 0x7f6011204280 0 0 0 17617373642292 17616657358066 17617521510730 17617521624110
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 225145 225145 32768 256 0 0 12 24 13888 0x0 0x7f6011223f80 0 0 0 17617526822058 17617521510730 17617526949772 17617526954185
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 5 225145 225145 4194304 256 0 0 12 24 14336 0x7f601422d380 0x7f6011223fc0 0 0 0 17617526989654 17617526949772 17617527316172 17617527318486
5 3 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 8 225145 225145 4194304 256 0 0 16 24 15040 0x7f601422d200 0x7f6011224000 0 0 0 17617527355035 17617527316172 17617527717452 17617527719416
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 11 225145 225145 4194304 256 0 0 16 24 15488 0x7f601422d080 0x7f6011224040 0 0 0 17617527752475 17617527717452 17617528112172 17617528114156
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 14 225145 225145 4194304 256 0 0 12 24 15936 0x7f6011acdf00 0x7f6011224080 0 0 0 17617528147005 17617528112172 17617528419052 17617528421068
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 17 225145 225145 4194304 256 0 0 12 24 16384 0x7f6011acdd80 0x7f60112240c0 0 0 0 17617528454017 17617528419052 17617528719692 17617528721660
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 20 225145 225145 4194304 256 0 0 12 24 17088 0x7f6011acdc00 0x7f6011224100 0 0 0 17617528765359 17617528719692 17617529019052 17617529020973
10 8 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 23 225145 225145 4194304 256 0 0 16 24 17792 0x7f6011acda80 0x7f6011224140 0 0 0 17617529052832 17617529019052 17617529407373 17617529409783
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 26 225145 225145 4194304 256 0 0 16 24 18496 0x7f6011acd900 0x7f6011224180 0 0 0 17617529441212 17617529407373 17617529796653 17617529798663
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 29 225145 225145 4194304 256 0 0 16 24 19200 0x7f6011acd780 0x7f60112241c0 0 0 0 17617529830222 17617529796653 17617530116173 17617530118345
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 32 225145 225145 4194304 256 0 0 16 24 19904 0x7f6011acd600 0x7f6011224200 0 0 0 17617530150604 17617530116173 17617530428653 17617530431017
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 35 225145 225145 4194304 256 0 0 12 24 20608 0x7f601422d480 0x7f6011224240 0 0 0 17617530470706 17617530428653 17617530725293 17617530726820
15 13 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 38 225145 225145 4194304 256 0 0 16 24 21312 0x7f601422d300 0x7f6011224280 0 0 0 17617530760449 17617530725293 17617531089293 17617531090840
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 41 225145 225145 4194304 256 0 0 16 24 22016 0x7f601422d180 0x7f60112242c0 0 0 0 17617531123289 17617531089293 17617531450573 17617531452141
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 44 225145 225145 4194304 256 0 0 16 24 22720 0x7f601422d000 0x7f6011224300 0 0 0 17617531484590 17617531450573 17617531725294 17617531726804
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 47 225145 225145 4194304 256 0 0 12 24 23424 0x7f6011acde80 0x7f6011224340 0 0 0 17617531758603 17617531725294 17617532009454 17617532010787
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 50 225145 225145 4194304 256 0 0 12 24 24128 0x7f6011acdd00 0x7f6011224380 0 0 0 17617532049466 17617532009454 17617532284334 17617532285800
20 18 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 53 225145 225145 4194304 256 0 0 16 24 24832 0x7f6011acdb80 0x7f60112243c0 0 0 0 17617532318189 17617532284334 17617532646094 17617532647451
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 56 225145 225145 4194304 256 0 0 16 24 25536 0x7f6011acda00 0x7f6011224400 0 0 0 17617532679750 17617532646094 17617533007054 17617533008542
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 59 225145 225145 4194304 256 0 0 12 24 26240 0x7f6011acd880 0x7f6011224440 0 0 0 17617533040051 17617533007054 17617533285134 17617533286845
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 62 225145 225145 4194304 256 0 0 12 24 26944 0x7f6011acd700 0x7f6011224480 0 0 0 17617533318864 17617533285134 17617533556334 17617533557708
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 65 225145 225145 4194304 256 0 0 12 24 27648 0x7f601422d580 0x7f60112244c0 0 0 0 17617533596337 17617533556334 17617533827534 17617533829061
25 23 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 68 225145 225145 4194304 256 0 0 16 24 28608 0x7f601422d400 0x7f6011224500 0 0 0 17617533860670 17617533827534 17617534189615 17617534191042
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 71 225145 225145 4194304 256 0 0 16 24 29312 0x7f601422d280 0x7f6011224540 0 0 0 17617534223531 17617534189615 17617534552495 17617534553882
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 74 225145 225145 4194304 256 0 0 12 24 30016 0x7f601422d100 0x7f6011224580 0 0 0 17617534584972 17617534552495 17617534828655 17617534830085
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 77 225145 225145 4194304 256 0 0 8 24 30976 0x7f6011acdf80 0x7f60112245c0 0 0 0 17617534862085 17617534828655 17617535102895 17617535104478
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 80 225145 225145 4194304 256 0 0 12 24 31680 0x7f6011acde00 0x7f6011224600 0 0 0 17617535143677 17617535102895 17617535374575 17617535376091
30 28 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 83 225145 225145 4194304 256 0 0 16 24 32640 0x7f6011acdc80 0x7f6011224640 0 0 0 17617535409341 17617535374575 17617535731695 17617535733162
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 86 225145 225145 4194304 256 0 0 12 24 33600 0x7f6011acdb00 0x7f6011224680 0 0 0 17617535764342 17617535731695 17617536088655 17617536090333
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 89 225145 225145 4194304 256 0 0 12 24 34560 0x7f6011acd980 0x7f60112246c0 0 0 0 17617536122022 17617536088655 17617536365455 17617536367116
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 92 225145 225145 4194304 256 0 0 8 24 35520 0x7f6011acd800 0x7f6011224700 0 0 0 17617536398155 17617536365455 17617536651375 17617536652909
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 95 225145 225145 4194304 256 0 0 12 24 36224 0x7f6011acd680 0x7f6011224740 0 0 0 17617536690968 17617536651375 17617536927696 17617536929142
35 33 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 98 225145 225145 4194304 256 0 0 12 24 37184 0x7f601422d500 0x7f6011224780 0 0 0 17617536961961 17617536927696 17617537287856 17617537289353
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 101 225145 225145 4194304 256 0 0 12 24 38144 0x7f601422d380 0x7f60112247c0 0 0 0 17617537321362 17617537287856 17617537650096 17617537651613
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 104 225145 225145 4194304 256 0 0 12 24 39104 0x7f601422d200 0x7f6011224800 0 0 0 17617537683823 17617537650096 17617537925136 17617537926746
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 107 225145 225145 4194304 256 0 0 8 24 40320 0x7f601422d080 0x7f6011224840 0 0 0 17617537958656 17617537925136 17617538207696 17617538209129
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 110 225145 225145 4194304 256 0 0 12 24 41280 0x7f6011acdf00 0x7f6011224880 0 0 0 17617538249708 17617538207696 17617538484016 17617538485432
40 38 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 113 225145 225145 4194304 256 0 0 12 24 42240 0x7f6011acdd80 0x7f60112248c0 0 0 0 17617538518491 17617538484016 17617538844656 17617538846203
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 116 225145 225145 4194304 256 0 0 12 24 43200 0x7f6011acdc00 0x7f6011224900 0 0 0 17617538877072 17617538844656 17617539208177 17617539209674
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 119 225145 225145 4194304 256 0 0 8 24 44160 0x7f6011acda80 0x7f6011224940 0 0 0 17617539241083 17617539208177 17617539478897 17617539480317
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 122 225145 225145 4194304 256 0 0 12 24 45376 0x7f6011acd900 0x7f6011224980 0 0 0 17617539511686 17617539478897 17617539750257 17617539751870
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 125 225145 225145 4194304 256 0 0 12 24 46336 0x7f6011acd780 0x7f60112249c0 0 0 0 17617539789489 17617539750257 17617540025137 17617540026513
45 43 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 128 225145 225145 4194304 256 0 0 12 24 47552 0x7f6011acd600 0x7f6011224a00 0 0 0 17617540058182 17617540025137 17617540381137 17617540382644
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 131 225145 225145 4194304 256 0 0 12 24 48512 0x7f601422d480 0x7f6011224a40 0 0 0 17617540414813 17617540381137 17617540740017 17617540741505
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 134 225145 225145 4194304 256 0 0 8 24 49472 0x7f601422d300 0x7f6011224a80 0 0 0 17617540773014 17617540740017 17617541012337 17617541013728
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 137 225145 225145 4194304 256 0 0 12 24 50688 0x7f601422d180 0x7f6011224ac0 0 0 0 17617541045667 17617541012337 17617541284337 17617541285751
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 140 225145 225145 4194304 256 0 0 12 24 51648 0x7f601422d000 0x7f6011224b00 0 0 0 17617541323680 17617541284337 17617541559057 17617541560504
50 48 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 143 225145 225145 4194304 256 0 0 12 24 52864 0x7f6011acde80 0x7f6011224b40 0 0 0 17617541591823 17617541559057 17617541918258 17617541919735
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 146 225145 225145 4194304 256 0 0 12 24 54080 0x7f6011acdd00 0x7f6011224b80 0 0 0 17617541953424 17617541918258 17617542290898 17617542292496
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 149 225145 225145 4194304 256 0 0 8 24 55296 0x7f6011acdb80 0x7f6011224bc0 0 0 0 17617542323815 17617542290898 17617542565458 17617542566939
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 152 225145 225145 4194304 256 0 0 12 24 56768 0x7f6011acda00 0x7f6011224c00 0 0 0 17617542597968 17617542565458 17617542837618 17617542839042
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 155 225145 225145 4194304 256 0 0 12 24 57728 0x7f6011acd880 0x7f6011224c40 0 0 0 17617542877741 17617542837618 17617543111858 17617543113295
55 53 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 158 225145 225145 4194304 256 0 0 12 24 58944 0x7f6011acd700 0x7f6011224c80 0 0 0 17617543145394 17617543111858 17617543469778 17617543471166
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 161 225145 225145 4194304 256 0 0 12 24 60160 0x7f601422d580 0x7f6011224cc0 0 0 0 17617543502855 17617543469778 17617543828978 17617543830397
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 164 225145 225145 4194304 256 0 0 8 24 61376 0x7f601422d400 0x7f6011224d00 0 0 0 17617543861706 17617543828978 17617544099698 17617544101090
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 167 225145 225145 4194304 256 0 0 12 24 62848 0x7f601422d280 0x7f6011224d40 0 0 0 17617544133159 17617544099698 17617544376659 17617544377983
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 170 225145 225145 4194304 256 0 0 12 24 63808 0x7f601422d100 0x7f6011224d80 0 0 0 17617544417452 17617544376659 17617544656339 17617544657766
60 58 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 173 225145 225145 4194304 256 0 0 12 24 65024 0x7f6011acdf80 0x7f6011224dc0 0 0 0 17617544689525 17617544656339 17617545017299 17617545018867
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 176 225145 225145 4194304 256 0 0 12 24 66240 0x7f6011acde00 0x7f6011224e00 0 0 0 17617545050856 17617545017299 17617545372979 17617545374468
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 179 225145 225145 4194304 256 0 0 8 24 67456 0x7f6011acdc80 0x7f6011224e40 0 0 0 17617545405597 17617545372979 17617545643379 17617545644811
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 182 225145 225145 4194304 256 0 0 12 24 68928 0x7f6011acdb00 0x7f6011224e80 0 0 0 17617545676170 17617545643379 17617545929939 17617545931253
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 185 225145 225145 4194304 256 0 0 12 24 70144 0x7f6011acd980 0x7f6011224ec0 0 0 0 17617545968743 17617545929939 17617546210739 17617546212246
65 63 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 188 225145 225145 4194304 256 0 0 12 24 71616 0x7f6011acd800 0x7f6011224f00 0 0 0 17617546243966 17617546210739 17617546575059 17617546576377
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 191 225145 225145 4194304 256 0 0 12 24 72832 0x7f6011acd680 0x7f6011224f40 0 0 0 17617546608446 17617546575059 17617546935380 17617546936818
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 194 225145 225145 4194304 256 0 0 8 24 74048 0x7f601422d500 0x7f6011224f80 0 0 0 17617546967947 17617546935380 17617547207060 17617547208651
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 197 225145 225145 4194304 256 0 0 12 24 75776 0x7f601422d380 0x7f6011224fc0 0 0 0 17617547239860 17617547207060 17617547494420 17617547495814
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 200 225145 225145 4194304 256 0 0 12 24 76992 0x7f601422d200 0x7f6011225000 0 0 0 17617547534863 17617547494420 17617547767380 17617547768937
70 68 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 203 225145 225145 4194304 256 0 0 12 24 78464 0x7f601422d080 0x7f6011225040 0 0 0 17617547800396 17617547767380 17617548131540 17617548133078
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 206 225145 225145 4194304 256 0 0 12 24 79936 0x7f6011acdf00 0x7f6011225080 0 0 0 17617548165057 17617548131540 17617548492340 17617548493869
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 209 225145 225145 4194304 256 0 0 8 24 81408 0x7f6011acdd80 0x7f60112250c0 0 0 0 17617548525858 17617548492340 17617548768980 17617548770372
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 212 225145 225145 4194304 256 0 0 12 24 83136 0x7f6011acdc00 0x7f6011225100 0 0 0 17617548801051 17617548768980 17617549062900 17617549064304
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 215 225145 225145 4194304 256 0 0 12 24 84352 0x7f6011acda80 0x7f6011225140 0 0 0 17617549113433 17617549062900 17617549337461 17617549338857
75 73 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 218 225145 225145 4194304 256 0 0 12 24 85824 0x7f6011acd900 0x7f6011225180 0 0 0 17617549370096 17617549337461 17617549710741 17617549712198
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 221 225145 225145 4194304 256 0 0 12 24 87296 0x7f6011acd780 0x7f60112251c0 0 0 0 17617549743687 17617549710741 17617550072021 17617550073539
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 224 225145 225145 4194304 256 0 0 12 24 88768 0x7f6011acd600 0x7f6011225200 0 0 0 17617550105618 17617550072021 17617550350581 17617550352101
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 227 225145 225145 4194304 256 0 0 12 24 90752 0x7f601422d480 0x7f6011225240 0 0 0 17617550383471 17617550350581 17617550650901 17617550652284
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 230 225145 225145 4194304 256 0 0 12 24 91968 0x7f601422d300 0x7f6011225280 0 0 0 17617550690823 17617550650901 17617550932981 17617550934397
80 78 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 233 225145 225145 4194304 256 0 0 12 24 93440 0x7f601422d180 0x7f60112252c0 0 0 0 17617550966226 17617550932981 17617551295541 17617551297107
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 236 225145 225145 4194304 256 0 0 12 24 94912 0x7f601422d000 0x7f6011225300 0 0 0 17617551329177 17617551295541 17617551658901 17617551660368
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 239 225145 225145 4194304 256 0 0 12 24 96384 0x7f6011acde80 0x7f6011225340 0 0 0 17617551692067 17617551658901 17617551933622 17617551935011
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 242 225145 225145 4194304 256 0 0 12 24 98368 0x7f6011acdd00 0x7f6011225380 0 0 0 17617551966931 17617551933622 17617552237142 17617552238644
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 245 225145 225145 4194304 256 0 0 12 24 99584 0x7f6011acdb80 0x7f60112253c0 0 0 0 17617552277203 17617552237142 17617552509782 17617552511337
85 83 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 248 225145 225145 4194304 256 0 0 12 24 101312 0x7f6011acda00 0x7f6011225400 0 0 0 17617552542106 17617552509782 17617552865622 17617552867108
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 251 225145 225145 4194304 256 0 0 12 24 102784 0x7f6011acd880 0x7f6011225440 0 0 0 17617552898317 17617552865622 17617553224182 17617553225649
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 254 225145 225145 4194304 256 0 0 12 24 104256 0x7f6011acd700 0x7f6011225480 0 0 0 17617553257078 17617553224182 17617553497782 17617553499362
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 257 225145 225145 4194304 256 0 0 12 24 106240 0x7f601422d580 0x7f60112254c0 0 0 0 17617553530831 17617553497782 17617553821462 17617553823013
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 260 225145 225145 4194304 256 0 0 12 24 107712 0x7f601422d400 0x7f6011225500 0 0 0 17617553861702 17617553821462 17617554100662 17617554102266
90 88 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 263 225145 225145 4194304 256 0 0 16 24 109440 0x7f601422d280 0x7f6011225540 0 0 0 17617554135076 17617554100662 17617554466263 17617554467857
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 266 225145 225145 4194304 256 0 0 16 24 111168 0x7f601422d100 0x7f6011225580 0 0 0 17617554500836 17617554466263 17617554826423 17617554827978
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 269 225145 225145 4194304 256 0 0 8 24 112896 0x7f6011acdf80 0x7f60112255c0 0 0 0 17617554859567 17617554826423 17617555100023 17617555101551
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 272 225145 225145 4194304 256 0 0 12 24 115136 0x7f6011acde00 0x7f6011225600 0 0 0 17617555132730 17617555100023 17617555414583 17617555416003
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 275 225145 225145 4194304 256 0 0 12 24 116608 0x7f6011acdc80 0x7f6011225640 0 0 0 17617555454622 17617555414583 17617555687383 17617555688946
95 93 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 278 225145 225145 4194304 256 0 0 16 24 118336 0x7f6011acdb00 0x7f6011225680 0 0 0 17617555719795 17617555687383 17617556043703 17617556045387
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 281 225145 225145 4194304 256 0 0 16 24 120064 0x7f6011acd980 0x7f60112256c0 0 0 0 17617556076296 17617556043703 17617556403223 17617556404758
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 284 225145 225145 4194304 256 0 0 12 24 121792 0x7f6011acd800 0x7f6011225700 0 0 0 17617556436007 17617556403223 17617556677303 17617556678691
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 287 225145 225145 4194304 256 0 0 12 24 124032 0x7f6011acd680 0x7f6011225740 0 0 0 17617556709920 17617556677303 17617557004184 17617557005703
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 290 225145 225145 4194304 256 0 0 12 24 125504 0x7f601422d500 0x7f6011225780 0 0 0 17617557047552 17617557004184 17617557277464 17617557278956
100 98 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 293 225145 225145 4194304 256 0 0 12 24 127488 0x7f601422d380 0x7f60112257c0 0 0 0 17617557310195 17617557277464 17617557635384 17617557636777
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 296 225145 225145 4194304 256 0 0 12 24 129216 0x7f601422d200 0x7f6011225800 0 0 0 17617557669036 17617557635384 17617557992984 17617557994588
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 299 225145 225145 4194304 256 0 0 12 24 130944 0x7f601422d080 0x7f6011225840 0 0 0 17617558025727 17617557992984 17617558284184 17617558285720
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 302 225145 225145 4194304 256 0 0 12 24 133440 0x7f6011acdf00 0x7f6011225880 0 0 0 17617558317880 17617558284184 17617558624184 17617558625842
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 305 225145 225145 4194304 256 0 0 12 24 134912 0x7f6011acdd80 0x7f60112258c0 0 0 0 17617558664591 17617558624184 17617558896344 17617558897775
105 103 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 308 225145 225145 4194304 256 0 0 12 24 136896 0x7f6011acdc00 0x7f6011225900 0 0 0 17617558928904 17617558896344 17617559254424 17617559255826
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 311 225145 225145 4194304 256 0 0 12 24 138880 0x7f6011acda80 0x7f6011225940 0 0 0 17617559287155 17617559254424 17617559610425 17617559611857
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 314 225145 225145 4194304 256 0 0 12 24 140864 0x7f6011acd900 0x7f6011225980 0 0 0 17617559643026 17617559610425 17617559891865 17617559893430
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 317 225145 225145 4194304 256 0 0 12 24 143616 0x7f6011acd780 0x7f60112259c0 0 0 0 17617559924479 17617559891865 17617560241785 17617560243271
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 320 225145 225145 4194304 256 0 0 12 24 145344 0x7f6011acd600 0x7f6011225a00 0 0 0 17617560281790 17617560241785 17617560516825 17617560518504
110 108 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 323 225145 225145 4194304 256 0 0 12 24 147584 0x7f601422d480 0x7f6011225a40 0 0 0 17617560549803 17617560516825 17617560875385 17617560876855
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 326 225145 225145 4194304 256 0 0 12 24 149568 0x7f601422d300 0x7f6011225a80 0 0 0 17617560909014 17617560875385 17617561232505 17617561233876
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 329 225145 225145 4194304 256 0 0 12 24 151552 0x7f601422d180 0x7f6011225ac0 0 0 0 17617561265565 17617561232505 17617561520345 17617561522008
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 332 225145 225145 4194304 256 0 0 12 24 154304 0x7f601422d000 0x7f6011225b00 0 0 0 17617561553348 17617561520345 17617561879546 17617561881059
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 335 225145 225145 4194304 256 0 0 12 24 156288 0x7f6011acde80 0x7f6011225b40 0 0 0 17617561919758 17617561879546 17617562161306 17617562162862
115 113 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 338 225145 225145 4194304 256 0 0 12 24 158784 0x7f6011acdd00 0x7f6011225b80 0 0 0 17617562196041 17617562161306 17617562526106 17617562527573
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 341 225145 225145 4194304 256 0 0 12 24 161024 0x7f6011acdb80 0x7f6011225bc0 0 0 0 17617562559762 17617562526106 17617562886266 17617562887624
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 344 225145 225145 4194304 256 0 0 12 24 163264 0x7f6011acda00 0x7f6011225c00 0 0 0 17617562919813 17617562886266 17617563195706 17617563197286
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 347 225145 225145 4194304 256 0 0 12 24 166528 0x7f6011acd880 0x7f6011225c40 0 0 0 17617563228415 17617563195706 17617563581306 17617563627295
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 350 225145 225145 4194304 256 0 0 12 24 168512 0x7f6011acd700 0x7f6011225c80 0 0 0 17617563645865 17617563581306 17617563906906 17617563908268
120 118 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 353 225145 225145 4194304 256 0 0 12 24 171264 0x7f601422d580 0x7f6011225cc0 0 0 0 17617563940177 17617563906906 17617564270746 17617564272239
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 356 225145 225145 4194304 256 0 0 12 24 173760 0x7f601422d400 0x7f6011225d00 0 0 0 17617564304178 17617564270746 17617564635067 17617564636509
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 359 225145 225145 4194304 256 0 0 12 24 176256 0x7f601422d280 0x7f6011225d40 0 0 0 17617564668449 17617564635067 17617564949147 17617564950451
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 362 225145 225145 4194304 256 0 0 12 24 179776 0x7f601422d100 0x7f6011225d80 0 0 0 17617564981881 17617564949147 17617565360347 17617565403230
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 365 225145 225145 4194304 256 0 0 12 24 182272 0x7f6011acdf80 0x7f6011225dc0 0 0 0 17617565422010 17617565360347 17617565711707 17617565713132
125 123 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 368 225145 225145 4194304 256 0 0 12 24 185536 0x7f6011acde00 0x7f6011225e00 0 0 0 17617565744121 17617565711707 17617566084027 17617566086623
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 371 225145 225145 4194304 256 0 0 12 24 188544 0x7f6011acdc80 0x7f6011225e40 0 0 0 17617566118272 17617566084027 17617566462427 17617566485903
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 374 225145 225145 4194304 256 0 0 12 24 191552 0x7f6011acdb00 0x7f6011225e80 0 0 0 17617566498042 17617566462427 17617566818588 17617566820094
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 377 225145 225145 4194304 256 0 0 12 24 195840 0x7f6011acd980 0x7f6011225ec0 0 0 0 17617566851333 17617566818588 17617567281308 17617567302392
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 380 225145 225145 4194304 256 0 0 12 24 198592 0x7f6011acd800 0x7f6011225f00 0 0 0 17617567321261 17617567281308 17617567617788 17617567619214
130 128 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 383 225145 225145 4194304 256 0 0 12 24 202368 0x7f6011acd680 0x7f6011225f40 0 0 0 17617567650873 17617567617788 17617568009468 17617568029683
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 386 225145 225145 4194304 256 0 0 12 24 205888 0x7f601422d500 0x7f6011225f80 0 0 0 17617568043053 17617568009468 17617568402268 17617568422443
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 389 225145 225145 4194304 256 0 0 12 24 209408 0x7f601422d380 0x7f6011225fc0 0 0 0 17617568435943 17617568402268 17617568776508 17617568777964
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 392 225145 225145 4194304 256 0 0 12 24 214464 0x7f601422d200 0x7f6011226000 0 0 0 17617568809754 17617568776508 17617569293468 17617569313371
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 395 225145 225145 4194304 256 0 0 12 24 217728 0x7f601422d080 0x7f6011226040 0 0 0 17617569334100 17617569293468 17617569646909 17617569648382
135 133 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 398 225145 225145 4194304 256 0 0 12 24 222016 0x7f6011acdf00 0x7f6011226080 0 0 0 17617569679902 17617569646909 17617570058429 17617570097621
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 401 225145 225145 4194304 256 0 0 12 24 226048 0x7f6011acdd80 0x7f60112260c0 0 0 0 17617570110081 17617570058429 17617570504989 17617570550000
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 404 225145 225145 4194304 256 0 0 12 24 230080 0x7f6011acdc00 0x7f6011226100 0 0 0 17617570562439 17617570504989 17617570931389 17617570978869
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 407 225145 225145 4194304 256 0 0 12 24 235904 0x7f6011acda80 0x7f6011226140 0 0 0 17617570991138 17617570931389 17617571531229 17617571573424
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 410 225145 225145 4194304 256 0 0 12 24 239424 0x7f6011acd900 0x7f6011226180 0 0 0 17617571592223 17617571531229 17617571925630 17617571927005
140 138 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 413 225145 225145 4194304 256 0 0 12 24 244224 0x7f6011acd780 0x7f60112261c0 0 0 0 17617571958424 17617571925630 17617572356030 17617572399003
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 416 225145 225145 4194304 256 0 0 12 24 248768 0x7f6011acd600 0x7f6011226200 0 0 0 17617572411482 17617572356030 17617572817150 17617572859911
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 419 225145 225145 4194304 256 0 0 12 24 253312 0x7f601422d480 0x7f6011226240 0 0 0 17617572871331 17617572817150 17617573264350 17617573306480
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 422 225145 225145 4194304 256 0 0 8 24 255552 0x7f601422d300 0x7f6011226280 0 0 0 17617573318479 17617573264350 17617573927710 17617573947643
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 425 225145 225145 4194304 256 0 0 12 24 259840 0x7f601422d180 0x7f60112262c0 0 0 0 17617573969173 17617573927710 17617574344190 17617574391252
145 143 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 428 225145 225145 4194304 256 0 0 12 24 265664 0x7f601422d000 0x7f6011226300 0 0 0 17617574403462 17617574344190 17617574861471 17617574905879
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 431 225145 225145 4194304 256 0 0 12 24 271232 0x7f6011acde80 0x7f6011226340 0 0 0 17617574916769 17617574861471 17617575376831 17617575423176
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 434 225145 225145 4194304 256 0 0 8 24 273216 0x7f6011acdd00 0x7f6011226380 0 0 0 17617575434706 17617575376831 17617575887391 17617575929613
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 437 225145 225145 4194304 256 0 0 8 24 275712 0x7f6011acdb80 0x7f60112263c0 0 0 0 17617575941063 17617575887391 17617576653151 17617576695054
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 440 225145 225145 4194304 256 0 0 12 24 280768 0x7f6011acda00 0x7f6011226400 0 0 0 17617576714243 17617576653151 17617577129312 17617577171232
150 148 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 443 225145 225145 4194304 256 0 0 12 24 287616 0x7f6011acd880 0x7f6011226440 0 0 0 17617577183371 17617577129312 17617577690112 17617577732907
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 446 225145 225145 4194304 256 0 0 12 24 294208 0x7f6011acd700 0x7f6011226480 0 0 0 17617577745047 17617577690112 17617578253792 17617578298543
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 449 225145 225145 4194304 256 0 0 8 24 296960 0x7f601422d580 0x7f60112264c0 0 0 0 17617578311273 17617578253792 17617578819872 17617578863899
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 452 225145 225145 4194304 256 0 0 8 24 299968 0x7f601422d400 0x7f6011226500 0 0 0 17617578875309 17617578819872 17617579692193 17617579737037
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 455 225145 225145 4194304 256 0 0 8 24 302720 0x7f601422d280 0x7f6011226540 0 0 0 17617579756256 17617579692193 17617580351713 17617580394280
155 153 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 458 225145 225145 4194304 256 0 0 12 24 305472 0x7f601422d100 0x7f6011226580 0 0 0 17617580405870 17617580351713 17617581023713 17617581066433
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 461 225145 225145 4194304 256 0 0 12 24 308224 0x7f6011acdf80 0x7f60112265c0 0 0 0 17617581077973 17617581023713 17617581700033 17617581742536
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 464 225145 225145 4194304 256 0 0 8 24 310976 0x7f6011acde00 0x7f6011226600 0 0 0 17617581753926 17617581700033 17617582360674 17617582407249
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 467 225145 225145 4194304 256 0 0 8 24 313216 0x7f6011acdc80 0x7f6011226640 0 0 0 17617582419829 17617582360674 17617583457634 17617583504071
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 470 225145 225145 4194304 256 0 0 8 24 315968 0x7f6011acdb00 0x7f6011226680 0 0 0 17617583524191 17617583457473 17617584555073 17617584626223
160 158 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 473 225145 225145 4194304 256 0 0 12 24 318720 0x7f6011acd980 0x7f60112266c0 0 0 0 17617584637902 17617584555073 17617585691233 17617585755844
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 476 225145 225145 4194304 256 0 0 12 24 321472 0x7f6011acd800 0x7f6011226700 0 0 0 17617585768084 17617585691233 17617586817153 17617586888225
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 479 225145 225145 4194304 256 0 0 8 24 324224 0x7f6011acd680 0x7f6011226740 0 0 0 17617586900485 17617586817153 17617587936353 17617588002997
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 482 225145 225145 4194304 256 0 0 8 24 326464 0x7f601422d500 0x7f6011226780 0 0 0 17617588015017 17617587936353 17617589885633 17617589953588
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 485 225145 225145 4194304 256 0 0 8 24 329216 0x7f601422d380 0x7f60112267c0 0 0 0 17617589973427 17617589885633 17617591812033 17617591884639
165 163 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 488 225145 225145 4194304 256 0 0 12 24 331968 0x7f601422d200 0x7f6011226800 0 0 0 17617591896388 17617591812033 17617593803073 17617593868648
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 491 225145 225145 4194304 256 0 0 12 24 334720 0x7f601422d080 0x7f6011226840 0 0 0 17617593880348 17617593803073 17617595765953 17617595838408
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 494 225145 225145 4194304 256 0 0 8 24 337472 0x7f6011acdf00 0x7f6011226880 0 0 0 17617595851508 17617595765953 17617597700514 17617597768509
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 497 225145 225145 4194304 256 0 0 8 24 0 0x7f6011acdd80 0x7f60112268c0 0 0 0 17617597780579 17617597700514 17617601308354 17617601387817
@@ -0,0 +1,168 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,grd,Workgroup_Size,LDS_Per_Workgroup,scr,vgpr,SGPR,fbar,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"__amd_rocclr_fillBufferAligned.kd",0,0,0,223075,223075,33554432,256,0,0,4,32,4160,0x0,0x7f931ec04280,3670016,2924224,327281248,17597154367976,17588719430319,17597306738811,17597306856651
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,223075,223075,32768,256,0,0,12,24,13888,0x0,0x7f931ec23f80,512,96990,10865032,17597311964571,17597306738811,17597312097854,17597312102767
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,223075,223075,4194304,256,0,0,12,24,14336,0x7f9321c13380,0x7f931ec23fc0,65536,635542,71138720,17597312138116,17597312097854,17597312468574,17597312471268
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,223075,223075,4194304,256,0,0,16,24,15040,0x7f9321c13200,0x7f931ec24000,65536,668954,74844872,17597312508957,17597312468574,17597312880734,17597312883107
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,223075,223075,4194304,256,0,0,16,24,15488,0x7f9321c13080,0x7f931ec24040,65536,665030,74552216,17597312916436,17597312880734,17597313280574,17597313282907
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,223075,223075,4194304,256,0,0,12,24,15936,0x7f931f46df00,0x7f931ec24080,65536,664266,74264696,17597313316306,17597313280574,17597313587455,17597313589829
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,223075,223075,4194304,256,0,0,12,24,16384,0x7f931f46dd80,0x7f931ec240c0,65536,662688,74184792,17597313622909,17597313587455,17597313898815,17597313901412
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,223075,223075,4194304,256,0,0,12,24,17088,0x7f931f46dc00,0x7f931ec24100,131072,674174,75457840,17597313946930,17597313898815,17597314213215,17597314215744
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,223075,223075,4194304,256,0,0,16,24,17792,0x7f931f46da80,0x7f931ec24140,131072,726098,81306128,17597314248903,17597314213215,17597314618655,17597314621123
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,223075,223075,4194304,256,0,0,16,24,18496,0x7f931f46d900,0x7f931ec24180,65536,679034,76165256,17597314652482,17597314618655,17597315014976,17597315017543
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,223075,223075,4194304,256,0,0,16,24,19200,0x7f931f46d780,0x7f931ec241c0,131072,712554,79823496,17597315047612,17597315014976,17597315336576,17597315338935
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,223075,223075,4194304,256,0,0,16,24,19904,0x7f931f46d600,0x7f931ec24200,131072,703346,78696448,17597315372044,17597315336576,17597315646976,17597315649507
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,223075,223075,4194304,256,0,0,12,24,20608,0x7f9321c13480,0x7f931ec24240,131072,704280,78756160,17597315689836,17597315646976,17597315959136,17597315961459
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,223075,223075,4194304,256,0,0,16,24,21312,0x7f9321c13300,0x7f931ec24280,131072,714192,79980280,17597315994668,17597315959136,17597316355616,17597316358149
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,223075,223075,4194304,256,0,0,16,24,22016,0x7f9321c13180,0x7f931ec242c0,65536,674066,75458304,17597316390698,17597316355616,17597316750817,17597316753269
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,223075,223075,4194304,256,0,0,16,24,22720,0x7f9321c13000,0x7f931ec24300,131072,706866,79057552,17597316786328,17597316750817,17597317057377,17597317059851
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,223075,223075,4194304,256,0,0,12,24,23424,0x7f931f46de80,0x7f931ec24340,131072,718248,80420472,17597317091891,17597317057377,17597317362657,17597317365124
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,223075,223075,4194304,256,0,0,12,24,24128,0x7f931f46dd00,0x7f931ec24380,131072,703250,78853504,17597317404783,17597317362657,17597317667937,17597317670476
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,223075,223075,4194304,256,0,0,16,24,24832,0x7f931f46db80,0x7f931ec243c0,131072,714636,79960808,17597317703385,17597317667937,17597318060577,17597318062946
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,223075,223075,4194304,256,0,0,16,24,25536,0x7f931f46da00,0x7f931ec24400,65536,630326,70626920,17597318105805,17597318060577,17597318506178,17597318508775
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,223075,223075,4194304,256,0,0,12,24,26240,0x7f931f46d880,0x7f931ec24440,131072,715790,80058024,17597318540724,17597318506178,17597318813698,17597318816247
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,223075,223075,4194304,256,0,0,12,24,26944,0x7f931f46d700,0x7f931ec24480,131072,691454,77402272,17597318850086,17597318813698,17597319118178,17597319120109
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,223075,223075,4194304,256,0,0,12,24,27648,0x7f9321c13580,0x7f931ec244c0,131072,669112,74898928,17597319159448,17597319118178,17597319397378,17597319399412
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,223075,223075,4194304,256,0,0,16,24,28608,0x7f9321c13400,0x7f931ec24500,131072,708748,79261640,17597319432951,17597319397378,17597319761858,17597319763613
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,223075,223075,4194304,256,0,0,16,24,29312,0x7f9321c13280,0x7f931ec24540,65536,688240,77087656,17597319796522,17597319761858,17597320130979,17597320132803
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,223075,223075,4194304,256,0,0,12,24,30016,0x7f9321c13100,0x7f931ec24580,131072,678180,75974336,17597320165302,17597320130979,17597320407939,17597320410176
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,223075,223075,4194304,256,0,0,8,24,30976,0x7f931f46df80,0x7f931ec245c0,131072,660320,74001800,17597320442495,17597320407939,17597320685539,17597320687419
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,223075,223075,4194304,256,0,0,12,24,31680,0x7f931f46de00,0x7f931ec24600,131072,694760,77826152,17597320725998,17597320685539,17597320971939,17597320973862
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,223075,223075,4194304,256,0,0,16,24,32640,0x7f931f46dc80,0x7f931ec24640,131072,652222,73024600,17597321006161,17597320971939,17597321339779,17597321341672
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,223075,223075,4194304,256,0,0,12,24,33600,0x7f931f46db00,0x7f931ec24680,65536,644760,72175248,17597321373252,17597321339779,17597321712100,17597321713953
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,223075,223075,4194304,256,0,0,12,24,34560,0x7f931f46d980,0x7f931ec246c0,131072,697950,78224064,17597321744992,17597321712100,17597321996580,17597321998466
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,223075,223075,4194304,256,0,0,8,24,35520,0x7f931f46d800,0x7f931ec24700,131072,715062,80079536,17597322030445,17597321996580,17597322285540,17597322287398
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,223075,223075,4194304,256,0,0,12,24,36224,0x7f931f46d680,0x7f931ec24740,131072,697808,78194000,17597322326607,17597322285540,17597322567620,17597322569481
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,223075,223075,4194304,256,0,0,12,24,37184,0x7f9321c13500,0x7f931ec24780,131072,682792,76451232,17597322600290,17597322567620,17597322935940,17597322937742
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,223075,223075,4194304,256,0,0,12,24,38144,0x7f9321c13380,0x7f931ec247c0,65536,664222,74436624,17597322970181,17597322935940,17597323304901,17597323306962
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,223075,223075,4194304,256,0,0,12,24,39104,0x7f9321c13200,0x7f931ec24800,131072,735872,82313560,17597323338562,17597323304901,17597323584421,17597323586475
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,223075,223075,4194304,256,0,0,8,24,40320,0x7f9321c13080,0x7f931ec24840,131072,697810,78129336,17597323618265,17597323584421,17597323864421,17597323866248
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,223075,223075,4194304,256,0,0,12,24,41280,0x7f931f46df00,0x7f931ec24880,131072,694898,77830464,17597323905857,17597323864421,17597324147781,17597324149601
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,223075,223075,4194304,256,0,0,12,24,42240,0x7f931f46dd80,0x7f931ec248c0,131072,702560,78715112,17597324181220,17597324147781,17597324518021,17597324519812
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,223075,223075,4194304,256,0,0,12,24,43200,0x7f931f46dc00,0x7f931ec24900,65536,634644,70977992,17597324551461,17597324518021,17597324889862,17597324891632
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,223075,223075,4194304,256,0,0,8,24,44160,0x7f931f46da80,0x7f931ec24940,131072,697140,78131152,17597324922462,17597324889862,17597325169382,17597325171185
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,223075,223075,4194304,256,0,0,12,24,45376,0x7f931f46d900,0x7f931ec24980,131072,697980,78084744,17597325203334,17597325169382,17597325449542,17597325451328
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,223075,223075,4194304,256,0,0,12,24,46336,0x7f931f46d780,0x7f931ec249c0,131072,696226,78049968,17597325489587,17597325449542,17597325728582,17597325730501
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,223075,223075,4194304,256,0,0,12,24,47552,0x7f931f46d600,0x7f931ec24a00,131072,702108,78737352,17597325762170,17597325728582,17597326091302,17597326093172
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,223075,223075,4194304,256,0,0,12,24,48512,0x7f9321c13480,0x7f931ec24a40,65536,666410,74655072,17597326126661,17597326091302,17597326462503,17597326464312
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,223075,223075,4194304,256,0,0,8,24,49472,0x7f9321c13300,0x7f931ec24a80,131072,673530,75430064,17597326496362,17597326462503,17597326746023,17597326747925
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,223075,223075,4194304,256,0,0,12,24,50688,0x7f9321c13180,0x7f931ec24ac0,131072,667014,74670760,17597326780364,17597326746023,17597327028903,17597327030658
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,223075,223075,4194304,256,0,0,12,24,51648,0x7f9321c13000,0x7f931ec24b00,131072,671252,75264880,17597327069437,17597327028903,17597327319143,17597327320991
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,223075,223075,4194304,256,0,0,12,24,52864,0x7f931f46de80,0x7f931ec24b40,131072,712228,79799792,17597327352480,17597327319143,17597327684743,17597327686711
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,223075,223075,4194304,256,0,0,12,24,54080,0x7f931f46dd00,0x7f931ec24b80,65536,658750,73677624,17597327718170,17597327684743,17597328048424,17597328050372
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,223075,223075,4194304,256,0,0,8,24,55296,0x7f931f46db80,0x7f931ec24bc0,131072,697100,78223472,17597328081711,17597328048424,17597328327144,17597328329005
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,223075,223075,4194304,256,0,0,12,24,56768,0x7f931f46da00,0x7f931ec24c00,131072,710644,79686320,17597328361274,17597328327144,17597328610504,17597328612358
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,223075,223075,4194304,256,0,0,12,24,57728,0x7f931f46d880,0x7f931ec24c40,131072,710408,79587520,17597328651187,17597328610504,17597328889224,17597328891190
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,223075,223075,4194304,256,0,0,12,24,58944,0x7f931f46d700,0x7f931ec24c80,131072,672038,75223808,17597328922200,17597328889224,17597329257704,17597329259461
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,223075,223075,4194304,256,0,0,12,24,60160,0x7f9321c13580,0x7f931ec24cc0,65536,662710,74304592,17597329291530,17597329257704,17597329622665,17597329624542
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,223075,223075,4194304,256,0,0,8,24,61376,0x7f9321c13400,0x7f931ec24d00,131072,706096,79082776,17597329656121,17597329622665,17597329903945,17597329905965
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,223075,223075,4194304,256,0,0,12,24,62848,0x7f9321c13280,0x7f931ec24d40,131072,702730,78712760,17597329937524,17597329903945,17597330201385,17597330203447
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,223075,223075,4194304,256,0,0,12,24,63808,0x7f9321c13100,0x7f931ec24d80,131072,716614,80258024,17597330242846,17597330201385,17597330484425,17597330486270
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,223075,223075,4194304,256,0,0,12,24,65024,0x7f931f46df80,0x7f931ec24dc0,131072,656912,73598504,17597330519099,17597330484425,17597330848105,17597330850041
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,223075,223075,4194304,256,0,0,12,24,66240,0x7f931f46de00,0x7f931ec24e00,65536,633070,70869888,17597330882520,17597330848105,17597331212106,17597331213981
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,223075,223075,4194304,256,0,0,8,24,67456,0x7f931f46dc80,0x7f931ec24e40,131072,705818,79022760,17597331245461,17597331212106,17597331490506,17597331492484
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,223075,223075,4194304,256,0,0,12,24,68928,0x7f931f46db00,0x7f931ec24e80,131072,718288,80554376,17597331523804,17597331490506,17597331778346,17597331780317
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,223075,223075,4194304,256,0,0,12,24,70144,0x7f931f46d980,0x7f931ec24ec0,131072,661874,74136848,17597331818476,17597331778346,17597332056586,17597332058540
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,223075,223075,4194304,256,0,0,12,24,71616,0x7f931f46d800,0x7f931ec24f00,131072,703060,78572800,17597332089789,17597332056586,17597332424266,17597332426101
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,223075,223075,4194304,256,0,0,12,24,72832,0x7f931f46d680,0x7f931ec24f40,65536,662214,74344912,17597332457410,17597332424266,17597332790346,17597332792111
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,223075,223075,4194304,256,0,0,8,24,74048,0x7f9321c13500,0x7f931ec24f80,131072,667848,74811800,17597332823461,17597332790346,17597333076107,17597333078104
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,223075,223075,4194304,256,0,0,12,24,75776,0x7f9321c13380,0x7f931ec24fc0,131072,670202,75058656,17597333109323,17597333076107,17597333368267,17597333370227
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,223075,223075,4194304,256,0,0,12,24,76992,0x7f9321c13200,0x7f931ec25000,131072,708088,79246456,17597333409146,17597333368267,17597333653547,17597333655430
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,223075,223075,4194304,256,0,0,12,24,78464,0x7f9321c13080,0x7f931ec25040,131072,704406,78916808,17597333688409,17597333653547,17597334019627,17597334021430
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,223075,223075,4194304,256,0,0,12,24,79936,0x7f931f46df00,0x7f931ec25080,65536,676510,75787792,17597334053709,17597334019627,17597334404587,17597334406740
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,223075,223075,4194304,256,0,0,8,24,81408,0x7f931f46dd80,0x7f931ec250c0,131072,708676,79361680,17597334438370,17597334404587,17597334688428,17597334690223
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,223075,223075,4194304,256,0,0,12,24,83136,0x7f931f46dc00,0x7f931ec25100,131072,703188,78758032,17597334721262,17597334688428,17597334986828,17597334988716
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,223075,223075,4194304,256,0,0,12,24,84352,0x7f931f46da80,0x7f931ec25140,131072,711374,79750704,17597335038064,17597334986828,17597335266988,17597335269488
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,223075,223075,4194304,256,0,0,12,24,85824,0x7f931f46d900,0x7f931ec25180,131072,709356,79350424,17597335302398,17597335266988,17597335641228,17597335643189
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,223075,223075,4194304,256,0,0,12,24,87296,0x7f931f46d780,0x7f931ec251c0,65536,665750,74682744,17597335674408,17597335641228,17597336012428,17597336014399
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,223075,223075,4194304,256,0,0,12,24,88768,0x7f931f46d600,0x7f931ec25200,131072,692582,77599992,17597336045289,17597336012428,17597336290989,17597336293122
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,223075,223075,4194304,256,0,0,12,24,90752,0x7f9321c13480,0x7f931ec25240,131072,702280,78569912,17597336324782,17597336290989,17597336592269,17597336594275
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,223075,223075,4194304,256,0,0,12,24,91968,0x7f9321c13300,0x7f931ec25280,131072,693860,77791912,17597336633174,17597336592269,17597336871629,17597336873568
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,223075,223075,4194304,256,0,0,12,24,93440,0x7f9321c13180,0x7f931ec252c0,131072,706080,79064344,17597336905237,17597336871629,17597337239629,17597337241428
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,223075,223075,4194304,256,0,0,12,24,94912,0x7f9321c13000,0x7f931ec25300,65536,666258,74630208,17597337273267,17597337239629,17597337603309,17597337605369
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,223075,223075,4194304,256,0,0,12,24,96384,0x7f931f46de80,0x7f931ec25340,131072,710070,79682480,17597337636328,17597337603309,17597337882670,17597337884502
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,223075,223075,4194304,256,0,0,12,24,98368,0x7f931f46dd00,0x7f931ec25380,131072,702104,78648408,17597337916431,17597337882670,17597338197070,17597338198944
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,223075,223075,4194304,256,0,0,12,24,99584,0x7f931f46db80,0x7f931ec253c0,131072,700538,78454816,17597338239503,17597338197070,17597338489870,17597338491926
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,223075,223075,4194304,256,0,0,12,24,101312,0x7f931f46da00,0x7f931ec25400,131072,666856,74761672,17597338524835,17597338489870,17597338860910,17597338862717
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,223075,223075,4194304,256,0,0,12,24,102784,0x7f931f46d880,0x7f931ec25440,65536,659098,73784752,17597338894486,17597338860910,17597339223950,17597339225938
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,223075,223075,4194304,256,0,0,12,24,104256,0x7f931f46d700,0x7f931ec25480,131072,662732,74236680,17597339257507,17597339223950,17597339502511,17597339504391
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,223075,223075,4194304,256,0,0,12,24,106240,0x7f9321c13580,0x7f931ec254c0,131072,667880,74684280,17597339536040,17597339502511,17597339817871,17597339819773
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,223075,223075,4194304,256,0,0,12,24,107712,0x7f9321c13400,0x7f931ec25500,131072,661066,74072560,17597339859702,17597339817871,17597340101391,17597340103275
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,223075,223075,4194304,256,0,0,16,24,109440,0x7f9321c13280,0x7f931ec25540,131072,710230,79482104,17597340135205,17597340101391,17597340468591,17597340470596
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,223075,223075,4194304,256,0,0,16,24,111168,0x7f9321c13100,0x7f931ec25580,65536,661678,74174808,17597340502315,17597340468591,17597340835951,17597340838057
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,223075,223075,4194304,256,0,0,8,24,112896,0x7f931f46df80,0x7f931ec255c0,131072,707212,79293872,17597340870236,17597340835951,17597341117872,17597341119770
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,223075,223075,4194304,256,0,0,12,24,115136,0x7f931f46de00,0x7f931ec25600,131072,699874,78369792,17597341151399,17597341117872,17597341439152,17597341441202
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,223075,223075,4194304,256,0,0,12,24,116608,0x7f931f46dc80,0x7f931ec25640,131072,725092,81096840,17597341479951,17597341439152,17597341719312,17597341721264
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,223075,223075,4194304,256,0,0,16,24,118336,0x7f931f46db00,0x7f931ec25680,131072,698688,78273480,17597341752264,17597341719312,17597342088272,17597342090355
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,223075,223075,4194304,256,0,0,16,24,120064,0x7f931f46d980,0x7f931ec256c0,65536,656586,73608176,17597342122474,17597342088272,17597342457712,17597342459566
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,223075,223075,4194304,256,0,0,12,24,121792,0x7f931f46d800,0x7f931ec25700,131072,698516,78338248,17597342490885,17597342457712,17597342740273,17597342742229
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,223075,223075,4194304,256,0,0,12,24,124032,0x7f931f46d680,0x7f931ec25740,131072,700370,78477592,17597342773698,17597342740273,17597343068753,17597343070740
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,223075,223075,4194304,256,0,0,12,24,125504,0x7f9321c13500,0x7f931ec25780,131072,730982,81860504,17597343108739,17597343068753,17597343346033,17597343347943
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,223075,223075,4194304,256,0,0,12,24,127488,0x7f9321c13380,0x7f931ec257c0,131072,703298,78797712,17597343380002,17597343346033,17597343712593,17597343714574
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,223075,223075,4194304,256,0,0,12,24,129216,0x7f9321c13200,0x7f931ec25800,65536,665594,74649432,17597343746363,17597343712593,17597344077713,17597344079695
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,223075,223075,4194304,256,0,0,12,24,130944,0x7f9321c13080,0x7f931ec25840,131072,660658,73990392,17597344110364,17597344077713,17597344363314,17597344365207
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,223075,223075,4194304,256,0,0,12,24,133440,0x7f931f46df00,0x7f931ec25880,131072,666714,74697072,17597344396947,17597344363314,17597344708914,17597344710799
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,223075,223075,4194304,256,0,0,12,24,134912,0x7f931f46dd80,0x7f931ec258c0,131072,1038386,116257656,17597344749948,17597344708914,17597345001554,17597345003581
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,223075,223075,4194304,256,0,0,12,24,136896,0x7f931f46dc00,0x7f931ec25900,131072,670534,75076112,17597345033950,17597345001554,17597345368114,17597345370072
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,223075,223075,4194304,256,0,0,12,24,138880,0x7f931f46da80,0x7f931ec25940,65536,666894,74621088,17597345400881,17597345368114,17597345735794,17597345737533
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,223075,223075,4194304,256,0,0,12,24,140864,0x7f931f46d900,0x7f931ec25980,131072,718126,80443832,17597345769252,17597345735794,17597346028915,17597346030965
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,223075,223075,4194304,256,0,0,12,24,143616,0x7f931f46d780,0x7f931ec259c0,131072,697842,78253680,17597346062644,17597346028915,17597346391315,17597346393496
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,223075,223075,4194304,256,0,0,12,24,145344,0x7f931f46d600,0x7f931ec25a00,131072,1031090,115861136,17597346433055,17597346391315,17597346675795,17597346677779
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,223075,223075,4194304,256,0,0,12,24,147584,0x7f9321c13480,0x7f931ec25a40,131072,705648,79054560,17597346708888,17597346675795,17597347044435,17597347046459
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,223075,223075,4194304,256,0,0,12,24,149568,0x7f9321c13300,0x7f931ec25a80,65536,670954,75064088,17597347078618,17597347044435,17597347409715,17597347411750
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,223075,223075,4194304,256,0,0,12,24,151552,0x7f9321c13180,0x7f931ec25ac0,131072,663496,74294224,17597347443289,17597347409715,17597347707476,17597347709542
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,223075,223075,4194304,256,0,0,12,24,154304,0x7f9321c13000,0x7f931ec25b00,131072,668400,74793240,17597347741332,17597347707476,17597348082676,17597348084693
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,223075,223075,4194304,256,0,0,12,24,156288,0x7f931f46de80,0x7f931ec25b40,131072,1026636,114897616,17597348123932,17597348082676,17597348373556,17597348375415
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,223075,223075,4194304,256,0,0,12,24,158784,0x7f931f46dd00,0x7f931ec25b80,131072,698430,78182680,17597348407765,17597348373556,17597348741236,17597348743166
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,223075,223075,4194304,256,0,0,12,24,161024,0x7f931f46db80,0x7f931ec25bc0,65536,683402,76514448,17597348774895,17597348741236,17597349113237,17597349115207
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,223075,223075,4194304,256,0,0,12,24,163264,0x7f931f46da00,0x7f931ec25c00,131072,672808,75413400,17597349146026,17597349113237,17597349420437,17597349422399
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,223075,223075,4194304,256,0,0,12,24,166528,0x7f931f46d880,0x7f931ec25c40,131072,671530,75195136,17597349454338,17597349420437,17597349812757,17597349833198
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,223075,223075,4194304,256,0,0,12,24,168512,0x7f931f46d700,0x7f931ec25c80,131072,1032970,115454920,17597349854798,17597349812757,17597350118357,17597350120291
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,223075,223075,4194304,256,0,0,12,24,171264,0x7f9321c13580,0x7f931ec25cc0,131072,676368,75721968,17597350151800,17597350118357,17597350490517,17597350492541
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,223075,223075,4194304,256,0,0,12,24,173760,0x7f9321c13400,0x7f931ec25d00,65536,669610,74897784,17597350524561,17597350490517,17597350858518,17597350860582
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,223075,223075,4194304,256,0,0,12,24,176256,0x7f9321c13280,0x7f931ec25d40,131072,668750,74900584,17597350892281,17597350858518,17597351182358,17597351184154
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,223075,223075,4194304,256,0,0,12,24,179776,0x7f9321c13100,0x7f931ec25d80,131072,670176,75023824,17597351216313,17597351182358,17597351598518,17597351620443
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,223075,223075,4194304,256,0,0,12,24,182272,0x7f931f46df80,0x7f931ec25dc0,131072,1001158,111996720,17597351639712,17597351598518,17597351922358,17597351924465
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,223075,223075,4194304,256,0,0,12,24,185536,0x7f931f46de00,0x7f931ec25e00,131072,697152,78221344,17597351955654,17597351922358,17597352300919,17597352304986
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,223075,223075,4194304,256,0,0,12,24,188544,0x7f931f46dc80,0x7f931ec25e40,65536,672452,75382408,17597352334805,17597352300919,17597352682039,17597352703415
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,223075,223075,4194304,256,0,0,12,24,191552,0x7f931f46db00,0x7f931ec25e80,131072,672120,75272112,17597352714855,17597352682039,17597353037559,17597353039557
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,223075,223075,4194304,256,0,0,12,24,195840,0x7f931f46d980,0x7f931ec25ec0,131072,670680,75082576,17597353070026,17597353037559,17597353507319,17597353526105
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,223075,223075,4194304,256,0,0,12,24,198592,0x7f931f46d800,0x7f931ec25f00,131072,1040348,116659016,17597353549374,17597353507319,17597353851959,17597353853856
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,223075,223075,4194304,256,0,0,12,24,202368,0x7f931f46d680,0x7f931ec25f40,131072,1006542,112700832,17597353885225,17597353851959,17597354245720,17597354269046
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,223075,223075,4194304,256,0,0,12,24,205888,0x7f9321c13500,0x7f931ec25f80,65536,671122,75258728,17597354281075,17597354245720,17597354660920,17597354680075
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,223075,223075,4194304,256,0,0,12,24,209408,0x7f9321c13380,0x7f931ec25fc0,131072,653696,73301256,17597354694815,17597354660920,17597355044280,17597355046316
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,223075,223075,4194304,256,0,0,12,24,214464,0x7f9321c13200,0x7f931ec26000,131072,666582,74693536,17597355078635,17597355044280,17597355565881,17597355608712
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,223075,223075,4194304,256,0,0,12,24,217728,0x7f9321c13080,0x7f931ec26040,131072,1041874,116597504,17597355629221,17597355565881,17597355946361,17597355948133
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,223075,223075,4194304,256,0,0,12,24,222016,0x7f931f46df00,0x7f931ec26080,131072,1032236,115775712,17597355980002,17597355946361,17597356360441,17597356403071
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,223075,223075,4194304,256,0,0,12,24,226048,0x7f931f46dd80,0x7f931ec260c0,65536,665294,74496584,17597356415051,17597356360441,17597356807481,17597356826960
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,223075,223075,4194304,256,0,0,12,24,230080,0x7f931f46dc00,0x7f931ec26100,131072,664030,74379976,17597356840870,17597356807481,17597357213242,17597357230970
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,223075,223075,4194304,256,0,0,12,24,235904,0x7f931f46da80,0x7f931ec26140,131072,681610,76317440,17597357247050,17597357213242,17597357791962,17597357810505
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,223075,223075,4194304,256,0,0,12,24,239424,0x7f931f46d900,0x7f931ec26180,131072,1042806,116904424,17597357833835,17597357791962,17597358175322,17597358177346
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,223075,223075,4194304,256,0,0,12,24,244224,0x7f931f46d780,0x7f931ec261c0,131072,1011952,113558168,17597358208925,17597358175322,17597358622682,17597358669334
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,223075,223075,4194304,256,0,0,12,24,248768,0x7f931f46d600,0x7f931ec26200,65536,664286,74368744,17597358681623,17597358622682,17597359095643,17597359137992
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,223075,223075,4194304,256,0,0,12,24,253312,0x7f9321c13480,0x7f931ec26240,131072,666756,74648400,17597359149211,17597359095643,17597359551643,17597359594280
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,223075,223075,4194304,256,0,0,8,24,255552,0x7f9321c13300,0x7f931ec26280,131072,1038062,116465224,17597359606080,17597359551643,17597360223003,17597360265703
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,223075,223075,4194304,256,0,0,12,24,259840,0x7f9321c13180,0x7f931ec262c0,131072,1045256,117014992,17597360286333,17597360223003,17597360665244,17597360707782
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,223075,223075,4194304,256,0,0,12,24,265664,0x7f9321c13000,0x7f931ec26300,131072,1007058,112558008,17597360719592,17597360665244,17597361182524,17597361224979
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,223075,223075,4194304,256,0,0,12,24,271232,0x7f931f46de80,0x7f931ec26340,65536,657532,73680936,17597361237358,17597361182524,17597361699164,17597361717576
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,223075,223075,4194304,256,0,0,8,24,273216,0x7f931f46dd00,0x7f931ec26380,131072,1005954,112684560,17597361732206,17597361699164,17597362190845,17597362239043
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,223075,223075,4194304,256,0,0,8,24,275712,0x7f931f46db80,0x7f931ec263c0,131072,1042374,116961312,17597362251443,17597362190845,17597362972445,17597363015383
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,223075,223075,4194304,256,0,0,12,24,280768,0x7f931f46da00,0x7f931ec26400,131072,1064520,119203776,17597363035773,17597362972445,17597363460285,17597363504371
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,223075,223075,4194304,256,0,0,12,24,287616,0x7f931f46d880,0x7f931ec26440,131072,1042964,116718240,17597363515870,17597363460285,17597364027806,17597364070626
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,223075,223075,4194304,256,0,0,12,24,294208,0x7f931f46d700,0x7f931ec26480,65536,663618,74381656,17597364083626,17597364027806,17597364592766,17597364635562
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,223075,223075,4194304,256,0,0,8,24,296960,0x7f9321c13580,0x7f931ec264c0,131072,1000220,112098968,17597364647432,17597364592766,17597365157886,17597365200478
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,223075,223075,4194304,256,0,0,8,24,299968,0x7f9321c13400,0x7f931ec26500,131072,1043906,116970336,17597365212197,17597365157886,17597366032927,17597366080735
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,223075,223075,4194304,256,0,0,8,24,302720,0x7f9321c13280,0x7f931ec26540,131072,1039030,116234576,17597366103624,17597366032927,17597366708287,17597366753068
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,223075,223075,4194304,256,0,0,12,24,305472,0x7f9321c13100,0x7f931ec26580,131072,1029336,115203056,17597366765068,17597366708287,17597367397408,17597367439831
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,223075,223075,4194304,256,0,0,12,24,308224,0x7f931f46df80,0x7f931ec265c0,65536,676850,75914936,17597367452270,17597367397408,17597368079328,17597368123053
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,223075,223075,4194304,256,0,0,8,24,310976,0x7f931f46de00,0x7f931ec26600,131072,1030904,115374280,17597368134303,17597368079328,17597368745249,17597368788626
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,223075,223075,4194304,256,0,0,8,24,313216,0x7f931f46dc80,0x7f931ec26640,131072,1030312,115314640,17597368800216,17597368745099,17597369840139,17597369888059
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,223075,223075,4194304,256,0,0,8,24,315968,0x7f931f46db00,0x7f931ec26680,131072,1030648,115399864,17597369908628,17597369840139,17597370924619,17597370974181
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,223075,223075,4194304,256,0,0,12,24,318720,0x7f931f46d980,0x7f931ec266c0,131072,1028750,115070680,17597370986871,17597370924619,17597372057579,17597372122792
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,223075,223075,4194304,256,0,0,12,24,321472,0x7f931f46d800,0x7f931ec26700,65536,667858,74772640,17597372135112,17597372057579,17597373192780,17597373258383
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,223075,223075,4194304,256,0,0,8,24,324224,0x7f931f46d680,0x7f931ec26740,131072,1048612,117538728,17597373270383,17597373192780,17597374307340,17597374377395
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,223075,223075,4194304,256,0,0,8,24,326464,0x7f9321c13500,0x7f931ec26780,131072,1042638,117104624,17597374390544,17597374307340,17597376275021,17597376340695
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,223075,223075,4194304,256,0,0,8,24,329216,0x7f9321c13380,0x7f931ec267c0,131072,1030956,115495896,17597376361114,17597376275021,17597378203661,17597378279105
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,223075,223075,4194304,256,0,0,12,24,331968,0x7f9321c13200,0x7f931ec26800,131072,1032982,115519584,17597378292145,17597378203661,17597380199502,17597380268425
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,223075,223075,4194304,256,0,0,12,24,334720,0x7f9321c13080,0x7f931ec26840,65536,672240,75212416,17597380281674,17597380199502,17597382174223,17597382243035
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,223075,223075,4194304,256,0,0,8,24,337472,0x7f931f46df00,0x7f931ec26880,131072,1041268,116482736,17597382255654,17597382174223,17597384122543,17597384191705
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,223075,223075,4194304,256,0,0,8,24,0,0x7f931f46dd80,0x7f931ec268c0,131072,1045480,116818840,17597384204405,17597384122543,17597387742704,17597387818633
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid grd Workgroup_Size LDS_Per_Workgroup scr vgpr SGPR fbar sig obj SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 __amd_rocclr_fillBufferAligned.kd 0 0 0 223075 223075 33554432 256 0 0 4 32 4160 0x0 0x7f931ec04280 3670016 2924224 327281248 17597154367976 17588719430319 17597306738811 17597306856651
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 223075 223075 32768 256 0 0 12 24 13888 0x0 0x7f931ec23f80 512 96990 10865032 17597311964571 17597306738811 17597312097854 17597312102767
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 5 223075 223075 4194304 256 0 0 12 24 14336 0x7f9321c13380 0x7f931ec23fc0 65536 635542 71138720 17597312138116 17597312097854 17597312468574 17597312471268
5 3 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 8 223075 223075 4194304 256 0 0 16 24 15040 0x7f9321c13200 0x7f931ec24000 65536 668954 74844872 17597312508957 17597312468574 17597312880734 17597312883107
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 11 223075 223075 4194304 256 0 0 16 24 15488 0x7f9321c13080 0x7f931ec24040 65536 665030 74552216 17597312916436 17597312880734 17597313280574 17597313282907
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 14 223075 223075 4194304 256 0 0 12 24 15936 0x7f931f46df00 0x7f931ec24080 65536 664266 74264696 17597313316306 17597313280574 17597313587455 17597313589829
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 17 223075 223075 4194304 256 0 0 12 24 16384 0x7f931f46dd80 0x7f931ec240c0 65536 662688 74184792 17597313622909 17597313587455 17597313898815 17597313901412
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 20 223075 223075 4194304 256 0 0 12 24 17088 0x7f931f46dc00 0x7f931ec24100 131072 674174 75457840 17597313946930 17597313898815 17597314213215 17597314215744
10 8 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 23 223075 223075 4194304 256 0 0 16 24 17792 0x7f931f46da80 0x7f931ec24140 131072 726098 81306128 17597314248903 17597314213215 17597314618655 17597314621123
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 26 223075 223075 4194304 256 0 0 16 24 18496 0x7f931f46d900 0x7f931ec24180 65536 679034 76165256 17597314652482 17597314618655 17597315014976 17597315017543
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 29 223075 223075 4194304 256 0 0 16 24 19200 0x7f931f46d780 0x7f931ec241c0 131072 712554 79823496 17597315047612 17597315014976 17597315336576 17597315338935
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 32 223075 223075 4194304 256 0 0 16 24 19904 0x7f931f46d600 0x7f931ec24200 131072 703346 78696448 17597315372044 17597315336576 17597315646976 17597315649507
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 35 223075 223075 4194304 256 0 0 12 24 20608 0x7f9321c13480 0x7f931ec24240 131072 704280 78756160 17597315689836 17597315646976 17597315959136 17597315961459
15 13 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 38 223075 223075 4194304 256 0 0 16 24 21312 0x7f9321c13300 0x7f931ec24280 131072 714192 79980280 17597315994668 17597315959136 17597316355616 17597316358149
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 41 223075 223075 4194304 256 0 0 16 24 22016 0x7f9321c13180 0x7f931ec242c0 65536 674066 75458304 17597316390698 17597316355616 17597316750817 17597316753269
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 44 223075 223075 4194304 256 0 0 16 24 22720 0x7f9321c13000 0x7f931ec24300 131072 706866 79057552 17597316786328 17597316750817 17597317057377 17597317059851
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 47 223075 223075 4194304 256 0 0 12 24 23424 0x7f931f46de80 0x7f931ec24340 131072 718248 80420472 17597317091891 17597317057377 17597317362657 17597317365124
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 50 223075 223075 4194304 256 0 0 12 24 24128 0x7f931f46dd00 0x7f931ec24380 131072 703250 78853504 17597317404783 17597317362657 17597317667937 17597317670476
20 18 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 53 223075 223075 4194304 256 0 0 16 24 24832 0x7f931f46db80 0x7f931ec243c0 131072 714636 79960808 17597317703385 17597317667937 17597318060577 17597318062946
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 56 223075 223075 4194304 256 0 0 16 24 25536 0x7f931f46da00 0x7f931ec24400 65536 630326 70626920 17597318105805 17597318060577 17597318506178 17597318508775
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 59 223075 223075 4194304 256 0 0 12 24 26240 0x7f931f46d880 0x7f931ec24440 131072 715790 80058024 17597318540724 17597318506178 17597318813698 17597318816247
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 62 223075 223075 4194304 256 0 0 12 24 26944 0x7f931f46d700 0x7f931ec24480 131072 691454 77402272 17597318850086 17597318813698 17597319118178 17597319120109
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 65 223075 223075 4194304 256 0 0 12 24 27648 0x7f9321c13580 0x7f931ec244c0 131072 669112 74898928 17597319159448 17597319118178 17597319397378 17597319399412
25 23 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 68 223075 223075 4194304 256 0 0 16 24 28608 0x7f9321c13400 0x7f931ec24500 131072 708748 79261640 17597319432951 17597319397378 17597319761858 17597319763613
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 71 223075 223075 4194304 256 0 0 16 24 29312 0x7f9321c13280 0x7f931ec24540 65536 688240 77087656 17597319796522 17597319761858 17597320130979 17597320132803
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 74 223075 223075 4194304 256 0 0 12 24 30016 0x7f9321c13100 0x7f931ec24580 131072 678180 75974336 17597320165302 17597320130979 17597320407939 17597320410176
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 77 223075 223075 4194304 256 0 0 8 24 30976 0x7f931f46df80 0x7f931ec245c0 131072 660320 74001800 17597320442495 17597320407939 17597320685539 17597320687419
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 80 223075 223075 4194304 256 0 0 12 24 31680 0x7f931f46de00 0x7f931ec24600 131072 694760 77826152 17597320725998 17597320685539 17597320971939 17597320973862
30 28 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 83 223075 223075 4194304 256 0 0 16 24 32640 0x7f931f46dc80 0x7f931ec24640 131072 652222 73024600 17597321006161 17597320971939 17597321339779 17597321341672
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 86 223075 223075 4194304 256 0 0 12 24 33600 0x7f931f46db00 0x7f931ec24680 65536 644760 72175248 17597321373252 17597321339779 17597321712100 17597321713953
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 89 223075 223075 4194304 256 0 0 12 24 34560 0x7f931f46d980 0x7f931ec246c0 131072 697950 78224064 17597321744992 17597321712100 17597321996580 17597321998466
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 92 223075 223075 4194304 256 0 0 8 24 35520 0x7f931f46d800 0x7f931ec24700 131072 715062 80079536 17597322030445 17597321996580 17597322285540 17597322287398
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 95 223075 223075 4194304 256 0 0 12 24 36224 0x7f931f46d680 0x7f931ec24740 131072 697808 78194000 17597322326607 17597322285540 17597322567620 17597322569481
35 33 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 98 223075 223075 4194304 256 0 0 12 24 37184 0x7f9321c13500 0x7f931ec24780 131072 682792 76451232 17597322600290 17597322567620 17597322935940 17597322937742
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 101 223075 223075 4194304 256 0 0 12 24 38144 0x7f9321c13380 0x7f931ec247c0 65536 664222 74436624 17597322970181 17597322935940 17597323304901 17597323306962
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 104 223075 223075 4194304 256 0 0 12 24 39104 0x7f9321c13200 0x7f931ec24800 131072 735872 82313560 17597323338562 17597323304901 17597323584421 17597323586475
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 107 223075 223075 4194304 256 0 0 8 24 40320 0x7f9321c13080 0x7f931ec24840 131072 697810 78129336 17597323618265 17597323584421 17597323864421 17597323866248
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 110 223075 223075 4194304 256 0 0 12 24 41280 0x7f931f46df00 0x7f931ec24880 131072 694898 77830464 17597323905857 17597323864421 17597324147781 17597324149601
40 38 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 113 223075 223075 4194304 256 0 0 12 24 42240 0x7f931f46dd80 0x7f931ec248c0 131072 702560 78715112 17597324181220 17597324147781 17597324518021 17597324519812
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 116 223075 223075 4194304 256 0 0 12 24 43200 0x7f931f46dc00 0x7f931ec24900 65536 634644 70977992 17597324551461 17597324518021 17597324889862 17597324891632
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 119 223075 223075 4194304 256 0 0 8 24 44160 0x7f931f46da80 0x7f931ec24940 131072 697140 78131152 17597324922462 17597324889862 17597325169382 17597325171185
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 122 223075 223075 4194304 256 0 0 12 24 45376 0x7f931f46d900 0x7f931ec24980 131072 697980 78084744 17597325203334 17597325169382 17597325449542 17597325451328
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 125 223075 223075 4194304 256 0 0 12 24 46336 0x7f931f46d780 0x7f931ec249c0 131072 696226 78049968 17597325489587 17597325449542 17597325728582 17597325730501
45 43 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 128 223075 223075 4194304 256 0 0 12 24 47552 0x7f931f46d600 0x7f931ec24a00 131072 702108 78737352 17597325762170 17597325728582 17597326091302 17597326093172
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 131 223075 223075 4194304 256 0 0 12 24 48512 0x7f9321c13480 0x7f931ec24a40 65536 666410 74655072 17597326126661 17597326091302 17597326462503 17597326464312
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 134 223075 223075 4194304 256 0 0 8 24 49472 0x7f9321c13300 0x7f931ec24a80 131072 673530 75430064 17597326496362 17597326462503 17597326746023 17597326747925
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 137 223075 223075 4194304 256 0 0 12 24 50688 0x7f9321c13180 0x7f931ec24ac0 131072 667014 74670760 17597326780364 17597326746023 17597327028903 17597327030658
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 140 223075 223075 4194304 256 0 0 12 24 51648 0x7f9321c13000 0x7f931ec24b00 131072 671252 75264880 17597327069437 17597327028903 17597327319143 17597327320991
50 48 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 143 223075 223075 4194304 256 0 0 12 24 52864 0x7f931f46de80 0x7f931ec24b40 131072 712228 79799792 17597327352480 17597327319143 17597327684743 17597327686711
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 146 223075 223075 4194304 256 0 0 12 24 54080 0x7f931f46dd00 0x7f931ec24b80 65536 658750 73677624 17597327718170 17597327684743 17597328048424 17597328050372
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 149 223075 223075 4194304 256 0 0 8 24 55296 0x7f931f46db80 0x7f931ec24bc0 131072 697100 78223472 17597328081711 17597328048424 17597328327144 17597328329005
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 152 223075 223075 4194304 256 0 0 12 24 56768 0x7f931f46da00 0x7f931ec24c00 131072 710644 79686320 17597328361274 17597328327144 17597328610504 17597328612358
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 155 223075 223075 4194304 256 0 0 12 24 57728 0x7f931f46d880 0x7f931ec24c40 131072 710408 79587520 17597328651187 17597328610504 17597328889224 17597328891190
55 53 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 158 223075 223075 4194304 256 0 0 12 24 58944 0x7f931f46d700 0x7f931ec24c80 131072 672038 75223808 17597328922200 17597328889224 17597329257704 17597329259461
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 161 223075 223075 4194304 256 0 0 12 24 60160 0x7f9321c13580 0x7f931ec24cc0 65536 662710 74304592 17597329291530 17597329257704 17597329622665 17597329624542
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 164 223075 223075 4194304 256 0 0 8 24 61376 0x7f9321c13400 0x7f931ec24d00 131072 706096 79082776 17597329656121 17597329622665 17597329903945 17597329905965
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 167 223075 223075 4194304 256 0 0 12 24 62848 0x7f9321c13280 0x7f931ec24d40 131072 702730 78712760 17597329937524 17597329903945 17597330201385 17597330203447
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 170 223075 223075 4194304 256 0 0 12 24 63808 0x7f9321c13100 0x7f931ec24d80 131072 716614 80258024 17597330242846 17597330201385 17597330484425 17597330486270
60 58 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 173 223075 223075 4194304 256 0 0 12 24 65024 0x7f931f46df80 0x7f931ec24dc0 131072 656912 73598504 17597330519099 17597330484425 17597330848105 17597330850041
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 176 223075 223075 4194304 256 0 0 12 24 66240 0x7f931f46de00 0x7f931ec24e00 65536 633070 70869888 17597330882520 17597330848105 17597331212106 17597331213981
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 179 223075 223075 4194304 256 0 0 8 24 67456 0x7f931f46dc80 0x7f931ec24e40 131072 705818 79022760 17597331245461 17597331212106 17597331490506 17597331492484
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 182 223075 223075 4194304 256 0 0 12 24 68928 0x7f931f46db00 0x7f931ec24e80 131072 718288 80554376 17597331523804 17597331490506 17597331778346 17597331780317
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 185 223075 223075 4194304 256 0 0 12 24 70144 0x7f931f46d980 0x7f931ec24ec0 131072 661874 74136848 17597331818476 17597331778346 17597332056586 17597332058540
65 63 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 188 223075 223075 4194304 256 0 0 12 24 71616 0x7f931f46d800 0x7f931ec24f00 131072 703060 78572800 17597332089789 17597332056586 17597332424266 17597332426101
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 191 223075 223075 4194304 256 0 0 12 24 72832 0x7f931f46d680 0x7f931ec24f40 65536 662214 74344912 17597332457410 17597332424266 17597332790346 17597332792111
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 194 223075 223075 4194304 256 0 0 8 24 74048 0x7f9321c13500 0x7f931ec24f80 131072 667848 74811800 17597332823461 17597332790346 17597333076107 17597333078104
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 197 223075 223075 4194304 256 0 0 12 24 75776 0x7f9321c13380 0x7f931ec24fc0 131072 670202 75058656 17597333109323 17597333076107 17597333368267 17597333370227
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 200 223075 223075 4194304 256 0 0 12 24 76992 0x7f9321c13200 0x7f931ec25000 131072 708088 79246456 17597333409146 17597333368267 17597333653547 17597333655430
70 68 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 203 223075 223075 4194304 256 0 0 12 24 78464 0x7f9321c13080 0x7f931ec25040 131072 704406 78916808 17597333688409 17597333653547 17597334019627 17597334021430
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 206 223075 223075 4194304 256 0 0 12 24 79936 0x7f931f46df00 0x7f931ec25080 65536 676510 75787792 17597334053709 17597334019627 17597334404587 17597334406740
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 209 223075 223075 4194304 256 0 0 8 24 81408 0x7f931f46dd80 0x7f931ec250c0 131072 708676 79361680 17597334438370 17597334404587 17597334688428 17597334690223
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 212 223075 223075 4194304 256 0 0 12 24 83136 0x7f931f46dc00 0x7f931ec25100 131072 703188 78758032 17597334721262 17597334688428 17597334986828 17597334988716
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 215 223075 223075 4194304 256 0 0 12 24 84352 0x7f931f46da80 0x7f931ec25140 131072 711374 79750704 17597335038064 17597334986828 17597335266988 17597335269488
75 73 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 218 223075 223075 4194304 256 0 0 12 24 85824 0x7f931f46d900 0x7f931ec25180 131072 709356 79350424 17597335302398 17597335266988 17597335641228 17597335643189
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 221 223075 223075 4194304 256 0 0 12 24 87296 0x7f931f46d780 0x7f931ec251c0 65536 665750 74682744 17597335674408 17597335641228 17597336012428 17597336014399
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 224 223075 223075 4194304 256 0 0 12 24 88768 0x7f931f46d600 0x7f931ec25200 131072 692582 77599992 17597336045289 17597336012428 17597336290989 17597336293122
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 227 223075 223075 4194304 256 0 0 12 24 90752 0x7f9321c13480 0x7f931ec25240 131072 702280 78569912 17597336324782 17597336290989 17597336592269 17597336594275
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 230 223075 223075 4194304 256 0 0 12 24 91968 0x7f9321c13300 0x7f931ec25280 131072 693860 77791912 17597336633174 17597336592269 17597336871629 17597336873568
80 78 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 233 223075 223075 4194304 256 0 0 12 24 93440 0x7f9321c13180 0x7f931ec252c0 131072 706080 79064344 17597336905237 17597336871629 17597337239629 17597337241428
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 236 223075 223075 4194304 256 0 0 12 24 94912 0x7f9321c13000 0x7f931ec25300 65536 666258 74630208 17597337273267 17597337239629 17597337603309 17597337605369
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 239 223075 223075 4194304 256 0 0 12 24 96384 0x7f931f46de80 0x7f931ec25340 131072 710070 79682480 17597337636328 17597337603309 17597337882670 17597337884502
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 242 223075 223075 4194304 256 0 0 12 24 98368 0x7f931f46dd00 0x7f931ec25380 131072 702104 78648408 17597337916431 17597337882670 17597338197070 17597338198944
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 245 223075 223075 4194304 256 0 0 12 24 99584 0x7f931f46db80 0x7f931ec253c0 131072 700538 78454816 17597338239503 17597338197070 17597338489870 17597338491926
85 83 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 248 223075 223075 4194304 256 0 0 12 24 101312 0x7f931f46da00 0x7f931ec25400 131072 666856 74761672 17597338524835 17597338489870 17597338860910 17597338862717
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 251 223075 223075 4194304 256 0 0 12 24 102784 0x7f931f46d880 0x7f931ec25440 65536 659098 73784752 17597338894486 17597338860910 17597339223950 17597339225938
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 254 223075 223075 4194304 256 0 0 12 24 104256 0x7f931f46d700 0x7f931ec25480 131072 662732 74236680 17597339257507 17597339223950 17597339502511 17597339504391
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 257 223075 223075 4194304 256 0 0 12 24 106240 0x7f9321c13580 0x7f931ec254c0 131072 667880 74684280 17597339536040 17597339502511 17597339817871 17597339819773
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 260 223075 223075 4194304 256 0 0 12 24 107712 0x7f9321c13400 0x7f931ec25500 131072 661066 74072560 17597339859702 17597339817871 17597340101391 17597340103275
90 88 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 263 223075 223075 4194304 256 0 0 16 24 109440 0x7f9321c13280 0x7f931ec25540 131072 710230 79482104 17597340135205 17597340101391 17597340468591 17597340470596
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 266 223075 223075 4194304 256 0 0 16 24 111168 0x7f9321c13100 0x7f931ec25580 65536 661678 74174808 17597340502315 17597340468591 17597340835951 17597340838057
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 269 223075 223075 4194304 256 0 0 8 24 112896 0x7f931f46df80 0x7f931ec255c0 131072 707212 79293872 17597340870236 17597340835951 17597341117872 17597341119770
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 272 223075 223075 4194304 256 0 0 12 24 115136 0x7f931f46de00 0x7f931ec25600 131072 699874 78369792 17597341151399 17597341117872 17597341439152 17597341441202
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 275 223075 223075 4194304 256 0 0 12 24 116608 0x7f931f46dc80 0x7f931ec25640 131072 725092 81096840 17597341479951 17597341439152 17597341719312 17597341721264
95 93 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 278 223075 223075 4194304 256 0 0 16 24 118336 0x7f931f46db00 0x7f931ec25680 131072 698688 78273480 17597341752264 17597341719312 17597342088272 17597342090355
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 281 223075 223075 4194304 256 0 0 16 24 120064 0x7f931f46d980 0x7f931ec256c0 65536 656586 73608176 17597342122474 17597342088272 17597342457712 17597342459566
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 284 223075 223075 4194304 256 0 0 12 24 121792 0x7f931f46d800 0x7f931ec25700 131072 698516 78338248 17597342490885 17597342457712 17597342740273 17597342742229
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 287 223075 223075 4194304 256 0 0 12 24 124032 0x7f931f46d680 0x7f931ec25740 131072 700370 78477592 17597342773698 17597342740273 17597343068753 17597343070740
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 290 223075 223075 4194304 256 0 0 12 24 125504 0x7f9321c13500 0x7f931ec25780 131072 730982 81860504 17597343108739 17597343068753 17597343346033 17597343347943
100 98 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 293 223075 223075 4194304 256 0 0 12 24 127488 0x7f9321c13380 0x7f931ec257c0 131072 703298 78797712 17597343380002 17597343346033 17597343712593 17597343714574
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 296 223075 223075 4194304 256 0 0 12 24 129216 0x7f9321c13200 0x7f931ec25800 65536 665594 74649432 17597343746363 17597343712593 17597344077713 17597344079695
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 299 223075 223075 4194304 256 0 0 12 24 130944 0x7f9321c13080 0x7f931ec25840 131072 660658 73990392 17597344110364 17597344077713 17597344363314 17597344365207
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 302 223075 223075 4194304 256 0 0 12 24 133440 0x7f931f46df00 0x7f931ec25880 131072 666714 74697072 17597344396947 17597344363314 17597344708914 17597344710799
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 305 223075 223075 4194304 256 0 0 12 24 134912 0x7f931f46dd80 0x7f931ec258c0 131072 1038386 116257656 17597344749948 17597344708914 17597345001554 17597345003581
105 103 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 308 223075 223075 4194304 256 0 0 12 24 136896 0x7f931f46dc00 0x7f931ec25900 131072 670534 75076112 17597345033950 17597345001554 17597345368114 17597345370072
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 311 223075 223075 4194304 256 0 0 12 24 138880 0x7f931f46da80 0x7f931ec25940 65536 666894 74621088 17597345400881 17597345368114 17597345735794 17597345737533
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 314 223075 223075 4194304 256 0 0 12 24 140864 0x7f931f46d900 0x7f931ec25980 131072 718126 80443832 17597345769252 17597345735794 17597346028915 17597346030965
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 317 223075 223075 4194304 256 0 0 12 24 143616 0x7f931f46d780 0x7f931ec259c0 131072 697842 78253680 17597346062644 17597346028915 17597346391315 17597346393496
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 320 223075 223075 4194304 256 0 0 12 24 145344 0x7f931f46d600 0x7f931ec25a00 131072 1031090 115861136 17597346433055 17597346391315 17597346675795 17597346677779
110 108 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 323 223075 223075 4194304 256 0 0 12 24 147584 0x7f9321c13480 0x7f931ec25a40 131072 705648 79054560 17597346708888 17597346675795 17597347044435 17597347046459
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 326 223075 223075 4194304 256 0 0 12 24 149568 0x7f9321c13300 0x7f931ec25a80 65536 670954 75064088 17597347078618 17597347044435 17597347409715 17597347411750
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 329 223075 223075 4194304 256 0 0 12 24 151552 0x7f9321c13180 0x7f931ec25ac0 131072 663496 74294224 17597347443289 17597347409715 17597347707476 17597347709542
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 332 223075 223075 4194304 256 0 0 12 24 154304 0x7f9321c13000 0x7f931ec25b00 131072 668400 74793240 17597347741332 17597347707476 17597348082676 17597348084693
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 335 223075 223075 4194304 256 0 0 12 24 156288 0x7f931f46de80 0x7f931ec25b40 131072 1026636 114897616 17597348123932 17597348082676 17597348373556 17597348375415
115 113 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 338 223075 223075 4194304 256 0 0 12 24 158784 0x7f931f46dd00 0x7f931ec25b80 131072 698430 78182680 17597348407765 17597348373556 17597348741236 17597348743166
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 341 223075 223075 4194304 256 0 0 12 24 161024 0x7f931f46db80 0x7f931ec25bc0 65536 683402 76514448 17597348774895 17597348741236 17597349113237 17597349115207
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 344 223075 223075 4194304 256 0 0 12 24 163264 0x7f931f46da00 0x7f931ec25c00 131072 672808 75413400 17597349146026 17597349113237 17597349420437 17597349422399
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 347 223075 223075 4194304 256 0 0 12 24 166528 0x7f931f46d880 0x7f931ec25c40 131072 671530 75195136 17597349454338 17597349420437 17597349812757 17597349833198
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 350 223075 223075 4194304 256 0 0 12 24 168512 0x7f931f46d700 0x7f931ec25c80 131072 1032970 115454920 17597349854798 17597349812757 17597350118357 17597350120291
120 118 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 353 223075 223075 4194304 256 0 0 12 24 171264 0x7f9321c13580 0x7f931ec25cc0 131072 676368 75721968 17597350151800 17597350118357 17597350490517 17597350492541
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 356 223075 223075 4194304 256 0 0 12 24 173760 0x7f9321c13400 0x7f931ec25d00 65536 669610 74897784 17597350524561 17597350490517 17597350858518 17597350860582
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 359 223075 223075 4194304 256 0 0 12 24 176256 0x7f9321c13280 0x7f931ec25d40 131072 668750 74900584 17597350892281 17597350858518 17597351182358 17597351184154
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 362 223075 223075 4194304 256 0 0 12 24 179776 0x7f9321c13100 0x7f931ec25d80 131072 670176 75023824 17597351216313 17597351182358 17597351598518 17597351620443
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 365 223075 223075 4194304 256 0 0 12 24 182272 0x7f931f46df80 0x7f931ec25dc0 131072 1001158 111996720 17597351639712 17597351598518 17597351922358 17597351924465
125 123 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 368 223075 223075 4194304 256 0 0 12 24 185536 0x7f931f46de00 0x7f931ec25e00 131072 697152 78221344 17597351955654 17597351922358 17597352300919 17597352304986
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 371 223075 223075 4194304 256 0 0 12 24 188544 0x7f931f46dc80 0x7f931ec25e40 65536 672452 75382408 17597352334805 17597352300919 17597352682039 17597352703415
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 374 223075 223075 4194304 256 0 0 12 24 191552 0x7f931f46db00 0x7f931ec25e80 131072 672120 75272112 17597352714855 17597352682039 17597353037559 17597353039557
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 377 223075 223075 4194304 256 0 0 12 24 195840 0x7f931f46d980 0x7f931ec25ec0 131072 670680 75082576 17597353070026 17597353037559 17597353507319 17597353526105
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 380 223075 223075 4194304 256 0 0 12 24 198592 0x7f931f46d800 0x7f931ec25f00 131072 1040348 116659016 17597353549374 17597353507319 17597353851959 17597353853856
130 128 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 383 223075 223075 4194304 256 0 0 12 24 202368 0x7f931f46d680 0x7f931ec25f40 131072 1006542 112700832 17597353885225 17597353851959 17597354245720 17597354269046
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 386 223075 223075 4194304 256 0 0 12 24 205888 0x7f9321c13500 0x7f931ec25f80 65536 671122 75258728 17597354281075 17597354245720 17597354660920 17597354680075
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 389 223075 223075 4194304 256 0 0 12 24 209408 0x7f9321c13380 0x7f931ec25fc0 131072 653696 73301256 17597354694815 17597354660920 17597355044280 17597355046316
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 392 223075 223075 4194304 256 0 0 12 24 214464 0x7f9321c13200 0x7f931ec26000 131072 666582 74693536 17597355078635 17597355044280 17597355565881 17597355608712
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 395 223075 223075 4194304 256 0 0 12 24 217728 0x7f9321c13080 0x7f931ec26040 131072 1041874 116597504 17597355629221 17597355565881 17597355946361 17597355948133
135 133 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 398 223075 223075 4194304 256 0 0 12 24 222016 0x7f931f46df00 0x7f931ec26080 131072 1032236 115775712 17597355980002 17597355946361 17597356360441 17597356403071
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 401 223075 223075 4194304 256 0 0 12 24 226048 0x7f931f46dd80 0x7f931ec260c0 65536 665294 74496584 17597356415051 17597356360441 17597356807481 17597356826960
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 404 223075 223075 4194304 256 0 0 12 24 230080 0x7f931f46dc00 0x7f931ec26100 131072 664030 74379976 17597356840870 17597356807481 17597357213242 17597357230970
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 407 223075 223075 4194304 256 0 0 12 24 235904 0x7f931f46da80 0x7f931ec26140 131072 681610 76317440 17597357247050 17597357213242 17597357791962 17597357810505
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 410 223075 223075 4194304 256 0 0 12 24 239424 0x7f931f46d900 0x7f931ec26180 131072 1042806 116904424 17597357833835 17597357791962 17597358175322 17597358177346
140 138 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 413 223075 223075 4194304 256 0 0 12 24 244224 0x7f931f46d780 0x7f931ec261c0 131072 1011952 113558168 17597358208925 17597358175322 17597358622682 17597358669334
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 416 223075 223075 4194304 256 0 0 12 24 248768 0x7f931f46d600 0x7f931ec26200 65536 664286 74368744 17597358681623 17597358622682 17597359095643 17597359137992
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 419 223075 223075 4194304 256 0 0 12 24 253312 0x7f9321c13480 0x7f931ec26240 131072 666756 74648400 17597359149211 17597359095643 17597359551643 17597359594280
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 422 223075 223075 4194304 256 0 0 8 24 255552 0x7f9321c13300 0x7f931ec26280 131072 1038062 116465224 17597359606080 17597359551643 17597360223003 17597360265703
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 425 223075 223075 4194304 256 0 0 12 24 259840 0x7f9321c13180 0x7f931ec262c0 131072 1045256 117014992 17597360286333 17597360223003 17597360665244 17597360707782
145 143 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 428 223075 223075 4194304 256 0 0 12 24 265664 0x7f9321c13000 0x7f931ec26300 131072 1007058 112558008 17597360719592 17597360665244 17597361182524 17597361224979
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 431 223075 223075 4194304 256 0 0 12 24 271232 0x7f931f46de80 0x7f931ec26340 65536 657532 73680936 17597361237358 17597361182524 17597361699164 17597361717576
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 434 223075 223075 4194304 256 0 0 8 24 273216 0x7f931f46dd00 0x7f931ec26380 131072 1005954 112684560 17597361732206 17597361699164 17597362190845 17597362239043
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 437 223075 223075 4194304 256 0 0 8 24 275712 0x7f931f46db80 0x7f931ec263c0 131072 1042374 116961312 17597362251443 17597362190845 17597362972445 17597363015383
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 440 223075 223075 4194304 256 0 0 12 24 280768 0x7f931f46da00 0x7f931ec26400 131072 1064520 119203776 17597363035773 17597362972445 17597363460285 17597363504371
150 148 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 443 223075 223075 4194304 256 0 0 12 24 287616 0x7f931f46d880 0x7f931ec26440 131072 1042964 116718240 17597363515870 17597363460285 17597364027806 17597364070626
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 446 223075 223075 4194304 256 0 0 12 24 294208 0x7f931f46d700 0x7f931ec26480 65536 663618 74381656 17597364083626 17597364027806 17597364592766 17597364635562
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 449 223075 223075 4194304 256 0 0 8 24 296960 0x7f9321c13580 0x7f931ec264c0 131072 1000220 112098968 17597364647432 17597364592766 17597365157886 17597365200478
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 452 223075 223075 4194304 256 0 0 8 24 299968 0x7f9321c13400 0x7f931ec26500 131072 1043906 116970336 17597365212197 17597365157886 17597366032927 17597366080735
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 455 223075 223075 4194304 256 0 0 8 24 302720 0x7f9321c13280 0x7f931ec26540 131072 1039030 116234576 17597366103624 17597366032927 17597366708287 17597366753068
155 153 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 458 223075 223075 4194304 256 0 0 12 24 305472 0x7f9321c13100 0x7f931ec26580 131072 1029336 115203056 17597366765068 17597366708287 17597367397408 17597367439831
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 461 223075 223075 4194304 256 0 0 12 24 308224 0x7f931f46df80 0x7f931ec265c0 65536 676850 75914936 17597367452270 17597367397408 17597368079328 17597368123053
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 464 223075 223075 4194304 256 0 0 8 24 310976 0x7f931f46de00 0x7f931ec26600 131072 1030904 115374280 17597368134303 17597368079328 17597368745249 17597368788626
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 467 223075 223075 4194304 256 0 0 8 24 313216 0x7f931f46dc80 0x7f931ec26640 131072 1030312 115314640 17597368800216 17597368745099 17597369840139 17597369888059
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 470 223075 223075 4194304 256 0 0 8 24 315968 0x7f931f46db00 0x7f931ec26680 131072 1030648 115399864 17597369908628 17597369840139 17597370924619 17597370974181
160 158 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 473 223075 223075 4194304 256 0 0 12 24 318720 0x7f931f46d980 0x7f931ec266c0 131072 1028750 115070680 17597370986871 17597370924619 17597372057579 17597372122792
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 476 223075 223075 4194304 256 0 0 12 24 321472 0x7f931f46d800 0x7f931ec26700 65536 667858 74772640 17597372135112 17597372057579 17597373192780 17597373258383
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 479 223075 223075 4194304 256 0 0 8 24 324224 0x7f931f46d680 0x7f931ec26740 131072 1048612 117538728 17597373270383 17597373192780 17597374307340 17597374377395
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 482 223075 223075 4194304 256 0 0 8 24 326464 0x7f9321c13500 0x7f931ec26780 131072 1042638 117104624 17597374390544 17597374307340 17597376275021 17597376340695
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 485 223075 223075 4194304 256 0 0 8 24 329216 0x7f9321c13380 0x7f931ec267c0 131072 1030956 115495896 17597376361114 17597376275021 17597378203661 17597378279105
165 163 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 488 223075 223075 4194304 256 0 0 12 24 331968 0x7f9321c13200 0x7f931ec26800 131072 1032982 115519584 17597378292145 17597378203661 17597380199502 17597380268425
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 491 223075 223075 4194304 256 0 0 12 24 334720 0x7f9321c13080 0x7f931ec26840 65536 672240 75212416 17597380281674 17597380199502 17597382174223 17597382243035
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 494 223075 223075 4194304 256 0 0 8 24 337472 0x7f931f46df00 0x7f931ec26880 131072 1041268 116482736 17597382255654 17597382174223 17597384122543 17597384191705
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 497 223075 223075 4194304 256 0 0 8 24 0 0x7f931f46dd80 0x7f931ec268c0 131072 1045480 116818840 17597384204405 17597384122543 17597387742704 17597387818633
@@ -0,0 +1,168 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,grd,Workgroup_Size,LDS_Per_Workgroup,scr,vgpr,SGPR,fbar,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"__amd_rocclr_fillBufferAligned.kd",0,0,0,224923,224923,33554432,256,0,0,4,32,4160,0x0,0x7f6676804280,524288,5433099,608528124,17616429017287,17614162329648,17616578244180,17616578354430
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,224923,224923,32768,256,0,0,12,24,13888,0x0,0x7f6676823f80,4096,42285,4736872,17616583510399,17616578244180,17616583637143,17616583641776
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,224923,224923,4194304,256,0,0,12,24,14336,0x7f66798a9380,0x7f6676823fc0,524288,10680424,1196193368,17616583675735,17616583637143,17616584007223,17616584009546
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,224923,224923,4194304,256,0,0,16,24,15040,0x7f66798a9200,0x7f6676824000,524288,11460754,1283570552,17616584045545,17616584007223,17616584406103,17616584408176
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,224923,224923,4194304,256,0,0,16,24,15488,0x7f66798a9080,0x7f6676824040,524288,11434216,1280587960,17616584439935,17616584406103,17616584800663,17616584802576
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,224923,224923,4194304,256,0,0,12,24,15936,0x7f6677207f00,0x7f6676824080,524288,10725172,1201188584,17616584835485,17616584800663,17616585101303,17616585103359
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,224923,224923,4194304,256,0,0,12,24,16384,0x7f6677207d80,0x7f66768240c0,524288,10820892,1211882656,17616585134888,17616585101303,17616585400504,17616585402521
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,224923,224923,4194304,256,0,0,12,24,17088,0x7f6677207c00,0x7f6676824100,524288,11264600,1261602676,17616585446060,17616585400504,17616585705624,17616585707533
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,224923,224923,4194304,256,0,0,16,24,17792,0x7f6677207a80,0x7f6676824140,524288,11459579,1283453140,17616585738492,17616585705624,17616586089944,17616586105043
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,224923,224923,4194304,256,0,0,16,24,18496,0x7f6677207900,0x7f6676824180,524288,11636886,1303310512,17616586123853,17616586089944,17616586494264,17616586496113
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,224923,224923,4194304,256,0,0,16,24,19200,0x7f6677207780,0x7f66768241c0,524288,11006422,1232696024,17616586526353,17616586494264,17616586788824,17616586790096
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,224923,224923,4194304,256,0,0,16,24,19904,0x7f6677207600,0x7f6676824200,524288,11011983,1233291564,17616586820495,17616586788824,17616587064345,17616587066029
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,224923,224923,4194304,256,0,0,12,24,20608,0x7f66798a9480,0x7f6676824240,524288,10884992,1219065644,17616587105378,17616587064345,17616587338585,17616587340112
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,224923,224923,4194304,256,0,0,16,24,21312,0x7f66798a9300,0x7f6676824280,524288,11486594,1286494744,17616587371061,17616587338585,17616587697785,17616587699073
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,224923,224923,4194304,256,0,0,16,24,22016,0x7f66798a9180,0x7f66768242c0,524288,11447281,1282107568,17616587730422,17616587697785,17616588057305,17616588058734
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,224923,224923,4194304,256,0,0,16,24,22720,0x7f66798a9000,0x7f6676824300,524288,11340196,1270047532,17616588090153,17616588057305,17616588328665,17616588330047
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,224923,224923,4194304,256,0,0,12,24,23424,0x7f6677207e80,0x7f6676824340,524288,11235643,1258366196,17616588361016,17616588328665,17616588598905,17616588600380
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,224923,224923,4194304,256,0,0,12,24,24128,0x7f6677207d00,0x7f6676824380,524288,11212984,1255863520,17616588638479,17616588598905,17616588872026,17616588873363
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,224923,224923,4194304,256,0,0,16,24,24832,0x7f6677207b80,0x7f66768243c0,524288,11475817,1285277324,17616588905152,17616588872026,17616589229946,17616589231314
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,224923,224923,4194304,256,0,0,16,24,25536,0x7f6677207a00,0x7f6676824400,524288,11565969,1295363756,17616589261653,17616589229946,17616589594266,17616589595715
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,224923,224923,4194304,256,0,0,12,24,26240,0x7f6677207880,0x7f6676824440,524288,11124985,1245916360,17616589626254,17616589594266,17616589866746,17616589868168
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,224923,224923,4194304,256,0,0,12,24,26944,0x7f6677207700,0x7f6676824480,524288,10914456,1222388864,17616589898867,17616589866746,17616590140346,17616590141681
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,224923,224923,4194304,256,0,0,12,24,27648,0x7f66798a9580,0x7f66768244c0,524288,11122668,1245696596,17616590181100,17616590140346,17616590418107,17616590419434
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,224923,224923,4194304,256,0,0,16,24,28608,0x7f66798a9400,0x7f6676824500,524288,11374860,1273944156,17616590449703,17616590418107,17616590776187,17616590777725
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,224923,224923,4194304,256,0,0,16,24,29312,0x7f66798a9280,0x7f6676824540,524288,11410133,1277927640,17616590808744,17616590776187,17616591134907,17616591136306
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,224923,224923,4194304,256,0,0,12,24,30016,0x7f66798a9100,0x7f6676824580,524288,10954631,1226946540,17616591168025,17616591134907,17616591406907,17616591408309
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,224923,224923,4194304,256,0,0,8,24,30976,0x7f6677207f80,0x7f66768245c0,524288,10617058,1189110872,17616591439468,17616591406907,17616591681947,17616591683512
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,224923,224923,4194304,256,0,0,12,24,31680,0x7f6677207e00,0x7f6676824600,524288,11108853,1244240284,17616591720561,17616591681947,17616591955707,17616591957015
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,224923,224923,4194304,256,0,0,16,24,32640,0x7f6677207c80,0x7f6676824640,524288,11568683,1295664164,17616591987614,17616591955707,17616592319708,17616592321145
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,224923,224923,4194304,256,0,0,12,24,33600,0x7f6677207b00,0x7f6676824680,524288,11530782,1291418292,17616592351345,17616592319708,17616592677308,17616592678706
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,224923,224923,4194304,256,0,0,12,24,34560,0x7f6677207980,0x7f66768246c0,524288,10659903,1193847880,17616592709545,17616592677308,17616592948668,17616592949999
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,224923,224923,4194304,256,0,0,8,24,35520,0x7f6677207800,0x7f6676824700,524288,10442292,1169501476,17616592980148,17616592948668,17616593230108,17616593231572
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,224923,224923,4194304,256,0,0,12,24,36224,0x7f6677207680,0x7f6676824740,524288,10884366,1218958024,17616593269151,17616593230108,17616593502108,17616593503775
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,224923,224923,4194304,256,0,0,12,24,37184,0x7f66798a9500,0x7f6676824780,524288,11449817,1282334924,17616593534774,17616593502108,17616593861469,17616593862736
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,224923,224923,4194304,256,0,0,12,24,38144,0x7f66798a9380,0x7f66768247c0,524288,11342802,1270360984,17616593893635,17616593861469,17616594217629,17616594219287
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,224923,224923,4194304,256,0,0,12,24,39104,0x7f66798a9200,0x7f6676824800,524288,10697145,1198148552,17616594251286,17616594217629,17616594493629,17616594495230
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,224923,224923,4194304,256,0,0,8,24,40320,0x7f66798a9080,0x7f6676824840,524288,9998816,1119848052,17616594525979,17616594493629,17616594764829,17616594766313
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,224923,224923,4194304,256,0,0,12,24,41280,0x7f6677207f00,0x7f6676824880,524288,10622469,1189645616,17616594804622,17616594764829,17616595045629,17616595046936
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,224923,224923,4194304,256,0,0,12,24,42240,0x7f6677207d80,0x7f66768248c0,524288,11504704,1288527952,17616595077105,17616595045629,17616595404669,17616595406117
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,224923,224923,4194304,256,0,0,12,24,43200,0x7f6677207c00,0x7f6676824900,524288,11459692,1283406788,17616595437476,17616595404669,17616595760190,17616595761558
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,224923,224923,4194304,256,0,0,8,24,44160,0x7f6677207a80,0x7f6676824940,524288,10636268,1191276784,17616595791687,17616595760190,17616596029310,17616596030861
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,224923,224923,4194304,256,0,0,12,24,45376,0x7f6677207900,0x7f6676824980,524288,9540413,1068487148,17616596061170,17616596029310,17616596298910,17616596300374
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,224923,224923,4194304,256,0,0,12,24,46336,0x7f6677207780,0x7f66768249c0,524288,11005247,1232547252,17616596338123,17616596298910,17616596569150,17616596570477
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,224923,224923,4194304,256,0,0,12,24,47552,0x7f6677207600,0x7f6676824a00,524288,11291528,1264664408,17616596601337,17616596569150,17616596924670,17616596925898
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,224923,224923,4194304,256,0,0,12,24,48512,0x7f66798a9480,0x7f6676824a40,524288,11464293,1283976936,17616596957847,17616596924670,17616597283551,17616597285029
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,224923,224923,4194304,256,0,0,8,24,49472,0x7f66798a9300,0x7f6676824a80,524288,10351349,1159310736,17616597315118,17616597283551,17616597552031,17616597553652
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,224923,224923,4194304,256,0,0,12,24,50688,0x7f66798a9180,0x7f6676824ac0,524288,9189592,1029270056,17616597584822,17616597552031,17616597829471,17616597830875
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,224923,224923,4194304,256,0,0,12,24,51648,0x7f66798a9000,0x7f6676824b00,524288,10490920,1175044172,17616597869014,17616597829471,17616598098591,17616598100079
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,224923,224923,4194304,256,0,0,12,24,52864,0x7f6677207e80,0x7f6676824b40,524288,11243719,1259288068,17616598130938,17616598098591,17616598459871,17616598461469
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,224923,224923,4194304,256,0,0,12,24,54080,0x7f6677207d00,0x7f6676824b80,524288,11333427,1269354784,17616598491949,17616598459871,17616598818751,17616598820110
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,224923,224923,4194304,256,0,0,8,24,55296,0x7f6677207b80,0x7f6676824bc0,524288,10311900,1154881916,17616598850270,17616598818751,17616599088352,17616599089833
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,224923,224923,4194304,256,0,0,12,24,56768,0x7f6677207a00,0x7f6676824c00,524288,7660962,858033416,17616599121143,17616599088352,17616599357472,17616599358907
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,224923,224923,4194304,256,0,0,12,24,57728,0x7f6677207880,0x7f6676824c40,524288,10668081,1194805792,17616599396086,17616599357472,17616599629632,17616599631100
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,224923,224923,4194304,256,0,0,12,24,58944,0x7f6677207700,0x7f6676824c80,524288,11332260,1269208508,17616599661319,17616599629632,17616599989312,17616599990621
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,224923,224923,4194304,256,0,0,12,24,60160,0x7f66798a9580,0x7f6676824cc0,524288,11364999,1272870852,17616600022310,17616599989312,17616600344512,17616600345982
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,224923,224923,4194304,256,0,0,8,24,61376,0x7f66798a9400,0x7f6676824d00,524288,10103502,1131538196,17616600376871,17616600344512,17616600619553,17616600620975
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,224923,224923,4194304,256,0,0,12,24,62848,0x7f66798a9280,0x7f6676824d40,524288,6112177,684580832,17616600652174,17616600619553,17616600895873,17616600897318
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,224923,224923,4194304,256,0,0,12,24,63808,0x7f66798a9100,0x7f6676824d80,524288,10015600,1121741252,17616600935627,17616600895873,17616601170113,17616601171441
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,224923,224923,4194304,256,0,0,12,24,65024,0x7f6677207f80,0x7f6676824dc0,524288,11187710,1253001024,17616601203690,17616601170113,17616601526273,17616601527682
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,224923,224923,4194304,256,0,0,12,24,66240,0x7f6677207e00,0x7f6676824e00,524288,11315916,1267348760,17616601558741,17616601526273,17616601881633,17616601882923
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,224923,224923,4194304,256,0,0,8,24,67456,0x7f6677207c80,0x7f6676824e40,524288,10029985,1123285696,17616601912862,17616601881633,17616602150913,17616602152566
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,224923,224923,4194304,256,0,0,12,24,68928,0x7f6677207b00,0x7f6676824e80,524288,5583246,625324888,17616602184665,17616602150913,17616602441474,17616602442938
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,224923,224923,4194304,256,0,0,12,24,70144,0x7f6677207980,0x7f6676824ec0,524288,10215409,1144096892,17616602480957,17616602441474,17616602716034,17616602717501
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,224923,224923,4194304,256,0,0,12,24,71616,0x7f6677207800,0x7f6676824f00,524288,11359905,1272281852,17616602748221,17616602716034,17616603075714,17616603077082
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,224923,224923,4194304,256,0,0,12,24,72832,0x7f6677207680,0x7f6676824f40,524288,11350178,1271157244,17616603107072,17616603075714,17616603438114,17616603439493
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,224923,224923,4194304,256,0,0,8,24,74048,0x7f66798a9500,0x7f6676824f80,524288,9917994,1110808992,17616603470322,17616603438114,17616603707234,17616603708736
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,224923,224923,4194304,256,0,0,12,24,75776,0x7f66798a9380,0x7f6676824fc0,524288,4863112,544688836,17616603739946,17616603707234,17616603989634,17616603991009
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,224923,224923,4194304,256,0,0,12,24,76992,0x7f66798a9200,0x7f6676825000,524288,10380466,1162561880,17616604029308,17616603989634,17616604262115,17616604263672
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,224923,224923,4194304,256,0,0,12,24,78464,0x7f66798a9080,0x7f6676825040,524288,11179716,1252099184,17616604295032,17616604262115,17616604619395,17616604620833
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,224923,224923,4194304,256,0,0,12,24,79936,0x7f6677207f00,0x7f6676825080,524288,11305869,1266268936,17616604652082,17616604619395,17616604974755,17616604976134
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,224923,224923,4194304,256,0,0,8,24,81408,0x7f6677207d80,0x7f66768250c0,524288,9799511,1097505924,17616605006363,17616604974755,17616605244195,17616605245757
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,224923,224923,4194304,256,0,0,12,24,83136,0x7f6677207c00,0x7f6676825100,524288,4119811,461354636,17616605276557,17616605244195,17616605532515,17616605534080
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,224923,224923,4194304,256,0,0,12,24,84352,0x7f6677207a80,0x7f6676825140,524288,10632933,1190898012,17616605584079,17616605532515,17616605816516,17616605818093
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,224923,224923,4194304,256,0,0,12,24,85824,0x7f6677207900,0x7f6676825180,524288,11260095,1261108360,17616605848142,17616605816516,17616606179716,17616606181284
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,224923,224923,4194304,256,0,0,12,24,87296,0x7f6677207780,0x7f66768251c0,524288,11284094,1263783392,17616606213333,17616606179716,17616606548836,17616606550334
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,224923,224923,4194304,256,0,0,12,24,88768,0x7f6677207600,0x7f6676825200,524288,9414519,1054351792,17616606580284,17616606548836,17616606818756,17616606820058
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,224923,224923,4194304,256,0,0,12,24,90752,0x7f66798a9480,0x7f6676825240,524288,3844270,430570732,17616606850577,17616606818756,17616607113476,17616607114940
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,224923,224923,4194304,256,0,0,12,24,91968,0x7f66798a9300,0x7f6676825280,524288,9868269,1105240528,17616607153569,17616607113476,17616607384516,17616607385923
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,224923,224923,4194304,256,0,0,12,24,93440,0x7f66798a9180,0x7f66768252c0,524288,10983926,1230189044,17616607416802,17616607384516,17616607738597,17616607739874
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,224923,224923,4194304,256,0,0,12,24,94912,0x7f66798a9000,0x7f6676825300,524288,11307938,1266435696,17616607771423,17616607738597,17616608093477,17616608094815
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,224923,224923,4194304,256,0,0,12,24,96384,0x7f6677207e80,0x7f6676825340,524288,9182374,1028407768,17616608125164,17616608093477,17616608364677,17616608366088
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,224923,224923,4194304,256,0,0,12,24,98368,0x7f6677207d00,0x7f6676825380,524288,3582117,401235424,17616608396868,17616608364677,17616608665477,17616608666791
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,224923,224923,4194304,256,0,0,12,24,99584,0x7f6677207b80,0x7f66768253c0,524288,9846286,1102658072,17616608704860,17616608665477,17616608934277,17616608935814
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,224923,224923,4194304,256,0,0,12,24,101312,0x7f6677207a00,0x7f6676825400,524288,11230912,1257866024,17616608966603,17616608934277,17616609294758,17616609296185
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,224923,224923,4194304,256,0,0,12,24,102784,0x7f6677207880,0x7f6676825440,524288,11195118,1253816412,17616609325994,17616609294758,17616609649638,17616609651126
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,224923,224923,4194304,256,0,0,12,24,104256,0x7f6677207700,0x7f6676825480,524288,8846911,990893700,17616609680985,17616609649638,17616609917958,17616609919339
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,224923,224923,4194304,256,0,0,12,24,106240,0x7f66798a9580,0x7f66768254c0,524288,3226468,361341948,17616609950348,17616609917958,17616610230278,17616610231731
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,224923,224923,4194304,256,0,0,12,24,107712,0x7f66798a9400,0x7f6676825500,524288,9896332,1108337416,17616610270730,17616610230278,17616610503078,17616610504414
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,224923,224923,4194304,256,0,0,16,24,109440,0x7f66798a9280,0x7f6676825540,524288,11267814,1261933520,17616610535683,17616610503078,17616610859559,17616610860995
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,224923,224923,4194304,256,0,0,16,24,111168,0x7f66798a9100,0x7f6676825580,524288,11205376,1254971684,17616610891814,17616610859559,17616611215719,17616611217136
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,224923,224923,4194304,256,0,0,8,24,112896,0x7f6677207f80,0x7f66768255c0,524288,8112508,908551692,17616611248415,17616611215719,17616611485639,17616611487089
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,224923,224923,4194304,256,0,0,12,24,115136,0x7f6677207e00,0x7f6676825600,524288,2989363,334767632,17616611519188,17616611485639,17616611798119,17616611799431
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,224923,224923,4194304,256,0,0,12,24,116608,0x7f6677207c80,0x7f6676825640,524288,9377872,1050296924,17616611837240,17616611798119,17616612079879,17616612081324
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,224923,224923,4194304,256,0,0,16,24,118336,0x7f6677207b00,0x7f6676825680,524288,11095753,1242725200,17616612112023,17616612079879,17616612435399,17616612436885
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,224923,224923,4194304,256,0,0,16,24,120064,0x7f6677207980,0x7f66768256c0,524288,11132157,1246737332,17616612467294,17616612435399,17616612790760,17616612792196
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,224923,224923,4194304,256,0,0,12,24,121792,0x7f6677207800,0x7f6676825700,524288,6908138,773635240,17616612822435,17616612790760,17616613064040,17616613065519
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,224923,224923,4194304,256,0,0,12,24,124032,0x7f6677207680,0x7f6676825740,524288,2987033,334521784,17616613095598,17616613064040,17616613382920,17616613384501
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,224923,224923,4194304,256,0,0,12,24,125504,0x7f66798a9500,0x7f6676825780,524288,9068751,1015804156,17616613422400,17616613382920,17616613655720,17616613657144
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,224923,224923,4194304,256,0,0,12,24,127488,0x7f66798a9380,0x7f66768257c0,524288,11119819,1245382156,17616613687593,17616613655720,17616614016520,17616614017935
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,224923,224923,4194304,256,0,0,12,24,129216,0x7f66798a9200,0x7f6676825800,524288,10959202,1227400204,17616614048924,17616614016520,17616614380681,17616614382106
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,224923,224923,4194304,256,0,0,12,24,130944,0x7f66798a9080,0x7f6676825840,524288,6223078,696978252,17616614413155,17616614380681,17616614661481,17616614662849
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,224923,224923,4194304,256,0,0,12,24,133440,0x7f6677207f00,0x7f6676825880,524288,2991887,335059936,17616614694488,17616614661481,17616614999081,17616615000450
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,224923,224923,4194304,256,0,0,12,24,134912,0x7f6677207d80,0x7f66768258c0,524288,8477557,949405576,17616615039199,17616614999081,17616615276681,17616615278123
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,224923,224923,4194304,256,0,0,12,24,136896,0x7f6677207c00,0x7f6676825900,524288,10943848,1225678540,17616615308762,17616615276681,17616615631081,17616615632404
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,224923,224923,4194304,256,0,0,12,24,138880,0x7f6677207a80,0x7f6676825940,524288,10998557,1231810156,17616615662823,17616615631081,17616615986922,17616615988555
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,224923,224923,4194304,256,0,0,12,24,140864,0x7f6677207900,0x7f6676825980,524288,4725550,529208156,17616616018834,17616615986922,17616616267882,17616616269328
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,224923,224923,4194304,256,0,0,12,24,143616,0x7f6677207780,0x7f66768259c0,524288,2902808,324987836,17616616300067,17616616267882,17616616611242,17616616612659
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,224923,224923,4194304,256,0,0,12,24,145344,0x7f6677207600,0x7f6676825a00,524288,7477208,837384588,17616616650638,17616616611242,17616616881962,17616616883472
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,224923,224923,4194304,256,0,0,12,24,147584,0x7f66798a9480,0x7f6676825a40,524288,10829654,1212904504,17616616913502,17616616881962,17616617236522,17616617237883
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,224923,224923,4194304,256,0,0,12,24,149568,0x7f66798a9300,0x7f6676825a80,524288,10920320,1223034384,17616617268913,17616617236522,17616617590602,17616617592085
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,224923,224923,4194304,256,0,0,12,24,151552,0x7f66798a9180,0x7f6676825ac0,524288,4021691,450387048,17616617623654,17616617590602,17616617881003,17616617882447
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,224923,224923,4194304,256,0,0,12,24,154304,0x7f66798a9000,0x7f6676825b00,524288,2874412,321960140,17616617912676,17616617881003,17616618240523,17616618242108
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,224923,224923,4194304,256,0,0,12,24,156288,0x7f6677207e80,0x7f6676825b40,524288,5539451,620398736,17616618280487,17616618240523,17616618525163,17616618526791
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,224923,224923,4194304,256,0,0,12,24,158784,0x7f6677207d00,0x7f6676825b80,524288,9956863,1115156680,17616618557630,17616618525163,17616618884523,17616618885892
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,224923,224923,4194304,256,0,0,12,24,161024,0x7f6677207b80,0x7f6676825bc0,524288,10933613,1224586852,17616618916561,17616618884523,17616619252523,17616619253912
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,224923,224923,4194304,256,0,0,12,24,163264,0x7f6677207a00,0x7f6676825c00,524288,3567210,399614228,17616619284452,17616619252523,17616619551244,17616619552705
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,224923,224923,4194304,256,0,0,12,24,166528,0x7f6677207880,0x7f6676825c40,524288,2876201,322135468,17616619583364,17616619551244,17616619932844,17616619978274
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,224923,224923,4194304,256,0,0,12,24,168512,0x7f6677207700,0x7f6676825c80,524288,4051321,453714604,17616619997054,17616619932844,17616620256524,17616620258007
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,224923,224923,4194304,256,0,0,12,24,171264,0x7f66798a9580,0x7f6676825cc0,524288,9834752,1101495352,17616620288956,17616620256524,17616620614924,17616620616318
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,224923,224923,4194304,256,0,0,12,24,173760,0x7f66798a9400,0x7f6676825d00,524288,10166230,1138591316,17616620648857,17616620614924,17616620980524,17616620981909
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,224923,224923,4194304,256,0,0,12,24,176256,0x7f66798a9280,0x7f6676825d40,524288,2839065,317840060,17616621012708,17616620980524,17616621291245,17616621292721
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,224923,224923,4194304,256,0,0,12,24,179776,0x7f66798a9100,0x7f6676825d80,524288,2868542,321310272,17616621323460,17616621291245,17616621697965,17616621716970
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,224923,224923,4194304,256,0,0,12,24,182272,0x7f6677207f80,0x7f6676825dc0,524288,3142293,351892544,17616621737729,17616621697965,17616622008045,17616622009613
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,224923,224923,4194304,256,0,0,12,24,185536,0x7f6677207e00,0x7f6676825e00,524288,7901702,884915708,17616622039702,17616622008045,17616622379245,17616622426112
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,224923,224923,4194304,256,0,0,12,24,188544,0x7f6677207c80,0x7f6676825e40,524288,7658330,857675848,17616622437902,17616622379245,17616622786125,17616622832242
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,224923,224923,4194304,256,0,0,12,24,191552,0x7f6677207b00,0x7f6676825e80,524288,2892246,323848616,17616622843621,17616622786125,17616623157646,17616623159153
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,224923,224923,4194304,256,0,0,12,24,195840,0x7f6677207980,0x7f6676825ec0,524288,2874932,321983312,17616623189973,17616623157646,17616623616206,17616623662361
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,224923,224923,4194304,256,0,0,12,24,198592,0x7f6677207800,0x7f6676825f00,524288,2760412,309111604,17616623681380,17616623616206,17616623974286,17616623975763
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,224923,224923,4194304,256,0,0,12,24,202368,0x7f6677207680,0x7f6676825f40,524288,6818540,763656772,17616624006222,17616623974286,17616624363086,17616624405312
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,224923,224923,4194304,256,0,0,12,24,205888,0x7f66798a9500,0x7f6676825f80,524288,6479153,725637932,17616624416932,17616624363086,17616624781167,17616624822921
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,224923,224923,4194304,256,0,0,12,24,209408,0x7f66798a9380,0x7f6676825fc0,524288,2830352,316894428,17616624833051,17616624781167,17616625172207,17616625173662
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,224923,224923,4194304,256,0,0,12,24,214464,0x7f66798a9200,0x7f6676826000,524288,2922189,327196460,17616625204752,17616625172207,17616625682127,17616625700439
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,224923,224923,4194304,256,0,0,12,24,217728,0x7f66798a9080,0x7f6676826040,524288,2772757,310435048,17616625722508,17616625682127,17616626034287,17616626035721
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,224923,224923,4194304,256,0,0,12,24,222016,0x7f6677207f00,0x7f6676826080,524288,5927465,663861336,17616626067170,17616626034287,17616626472048,17616626515438
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,224923,224923,4194304,256,0,0,12,24,226048,0x7f6677207d80,0x7f66768260c0,524288,5195047,581774056,17616626526338,17616626472048,17616626911088,17616626954027
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,224923,224923,4194304,256,0,0,12,24,230080,0x7f6677207c00,0x7f6676826100,524288,2775539,310824656,17616626965047,17616626911088,17616627330928,17616627372237
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,224923,224923,4194304,256,0,0,12,24,235904,0x7f6677207a80,0x7f6676826140,524288,2907403,325623936,17616627383526,17616627330928,17616627923728,17616627965152
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,224923,224923,4194304,256,0,0,12,24,239424,0x7f6677207900,0x7f6676826180,524288,2824851,316356620,17616627983991,17616627923728,17616628323729,17616628325262
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,224923,224923,4194304,256,0,0,12,24,244224,0x7f6677207780,0x7f66768261c0,524288,5254947,588580672,17616628355832,17616628323729,17616628753489,17616628796461
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,224923,224923,4194304,256,0,0,12,24,248768,0x7f6677207600,0x7f6676826200,524288,3327874,372708560,17616628807600,17616628753489,17616629213009,17616629234139
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,224923,224923,4194304,256,0,0,12,24,253312,0x7f66798a9480,0x7f6676826240,524288,2746430,307470164,17616629245669,17616629213009,17616629634769,17616629654779
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,224923,224923,4194304,256,0,0,8,24,255552,0x7f66798a9300,0x7f6676826280,524288,2365006,264887664,17616629667448,17616629634769,17616630273170,17616630295683
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,224923,224923,4194304,256,0,0,12,24,259840,0x7f66798a9180,0x7f66768262c0,524288,2756045,308607552,17616630314482,17616630273170,17616630690290,17616630711832
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,224923,224923,4194304,256,0,0,12,24,265664,0x7f66798a9000,0x7f6676826300,524288,3302571,369846340,17616630722592,17616630690290,17616631177330,17616631197970
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,224923,224923,4194304,256,0,0,12,24,271232,0x7f6677207e80,0x7f6676826340,524288,3735777,418344800,17616631209439,17616631177330,17616631664211,17616631681227
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,224923,224923,4194304,256,0,0,8,24,273216,0x7f6677207d00,0x7f6676826380,524288,2402299,269019148,17616631696597,17616631664211,17616632140851,17616632157905
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,224923,224923,4194304,256,0,0,8,24,275712,0x7f6677207b80,0x7f66768263c0,524288,2385700,267232156,17616632172865,17616632140851,17616632882451,17616632899677
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,224923,224923,4194304,256,0,0,12,24,280768,0x7f6677207a00,0x7f6676826400,524288,2640985,295764608,17616632922216,17616632882451,17616633333972,17616633350265
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,224923,224923,4194304,256,0,0,12,24,287616,0x7f6677207880,0x7f6676826440,524288,3499100,391889656,17616633365955,17616633333972,17616633865652,17616633882802
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,224923,224923,4194304,256,0,0,12,24,294208,0x7f6677207700,0x7f6676826480,524288,3364047,376719280,17616633900411,17616633865652,17616634397492,17616634416018
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,224923,224923,4194304,256,0,0,8,24,296960,0x7f66798a9580,0x7f66768264c0,524288,2392923,268005112,17616634429828,17616634397492,17616634932053,17616634975704
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,224923,224923,4194304,256,0,0,8,24,299968,0x7f66798a9400,0x7f6676826500,524288,2402295,268992960,17616634987064,17616634932053,17616635800053,17616635841962
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,224923,224923,4194304,256,0,0,8,24,302720,0x7f66798a9280,0x7f6676826540,524288,2387243,267343680,17616635860891,17616635800053,17616636459093,17616636500825
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,224923,224923,4194304,256,0,0,12,24,305472,0x7f66798a9100,0x7f6676826580,524288,2587729,289762244,17616636512105,17616636459093,17616637131734,17616637173178
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,224923,224923,4194304,256,0,0,12,24,308224,0x7f6677207f80,0x7f66768265c0,524288,2599045,291156548,17616637185288,17616637131734,17616637798614,17616637840301
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,224923,224923,4194304,256,0,0,8,24,310976,0x7f6677207e00,0x7f6676826600,524288,2397271,268489716,17616637850871,17616637798614,17616638457815,17616638503664
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,224923,224923,4194304,256,0,0,8,24,313216,0x7f6677207c80,0x7f6676826640,524288,2418107,270776944,17616638515954,17616638457815,17616639559575,17616639605156
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,224923,224923,4194304,256,0,0,8,24,315968,0x7f6677207b00,0x7f6676826680,524288,2443554,273735728,17616639625056,17616639559575,17616640638136,17616640683119
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,224923,224923,4194304,256,0,0,12,24,318720,0x7f6677207980,0x7f66768266c0,524288,2586330,289622392,17616640694219,17616640637960,17616641744200,17616641813000
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,224923,224923,4194304,256,0,0,12,24,321472,0x7f6677207800,0x7f6676826700,524288,2613802,292684248,17616641824460,17616641744200,17616642871560,17616642942701
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,224923,224923,4194304,256,0,0,8,24,324224,0x7f6677207680,0x7f6676826740,524288,2435966,272804852,17616642953751,17616642871560,17616643985480,17616644051093
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,224923,224923,4194304,256,0,0,8,24,326464,0x7f66798a9500,0x7f6676826780,524288,2466561,276190448,17616644062383,17616643985480,17616645930441,17616645996534
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,224923,224923,4194304,256,0,0,8,24,329216,0x7f66798a9380,0x7f66768267c0,524288,2453031,274691816,17616646015123,17616645930441,17616647856041,17616647925465
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,224923,224923,4194304,256,0,0,12,24,331968,0x7f66798a9200,0x7f6676826800,524288,2617755,293159780,17616647936565,17616647856041,17616649843881,17616649907945
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,224923,224923,4194304,256,0,0,12,24,334720,0x7f66798a9080,0x7f6676826840,524288,2629177,294473224,17616649918805,17616649843881,17616651822922,17616651893654
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,224923,224923,4194304,256,0,0,8,24,337472,0x7f6677207f00,0x7f6676826880,524288,2456642,275183732,17616651905794,17616651822922,17616653754602,17616653820396
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,224923,224923,4194304,256,0,0,8,24,0,0x7f6677207d80,0x7f66768268c0,524288,2466163,276223040,17616653831885,17616653754602,17616657357483,17616657478993
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid grd Workgroup_Size LDS_Per_Workgroup scr vgpr SGPR fbar sig obj SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 __amd_rocclr_fillBufferAligned.kd 0 0 0 224923 224923 33554432 256 0 0 4 32 4160 0x0 0x7f6676804280 524288 5433099 608528124 17616429017287 17614162329648 17616578244180 17616578354430
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 224923 224923 32768 256 0 0 12 24 13888 0x0 0x7f6676823f80 4096 42285 4736872 17616583510399 17616578244180 17616583637143 17616583641776
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 5 224923 224923 4194304 256 0 0 12 24 14336 0x7f66798a9380 0x7f6676823fc0 524288 10680424 1196193368 17616583675735 17616583637143 17616584007223 17616584009546
5 3 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 8 224923 224923 4194304 256 0 0 16 24 15040 0x7f66798a9200 0x7f6676824000 524288 11460754 1283570552 17616584045545 17616584007223 17616584406103 17616584408176
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 11 224923 224923 4194304 256 0 0 16 24 15488 0x7f66798a9080 0x7f6676824040 524288 11434216 1280587960 17616584439935 17616584406103 17616584800663 17616584802576
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 14 224923 224923 4194304 256 0 0 12 24 15936 0x7f6677207f00 0x7f6676824080 524288 10725172 1201188584 17616584835485 17616584800663 17616585101303 17616585103359
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 17 224923 224923 4194304 256 0 0 12 24 16384 0x7f6677207d80 0x7f66768240c0 524288 10820892 1211882656 17616585134888 17616585101303 17616585400504 17616585402521
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 20 224923 224923 4194304 256 0 0 12 24 17088 0x7f6677207c00 0x7f6676824100 524288 11264600 1261602676 17616585446060 17616585400504 17616585705624 17616585707533
10 8 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 23 224923 224923 4194304 256 0 0 16 24 17792 0x7f6677207a80 0x7f6676824140 524288 11459579 1283453140 17616585738492 17616585705624 17616586089944 17616586105043
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 26 224923 224923 4194304 256 0 0 16 24 18496 0x7f6677207900 0x7f6676824180 524288 11636886 1303310512 17616586123853 17616586089944 17616586494264 17616586496113
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 29 224923 224923 4194304 256 0 0 16 24 19200 0x7f6677207780 0x7f66768241c0 524288 11006422 1232696024 17616586526353 17616586494264 17616586788824 17616586790096
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 32 224923 224923 4194304 256 0 0 16 24 19904 0x7f6677207600 0x7f6676824200 524288 11011983 1233291564 17616586820495 17616586788824 17616587064345 17616587066029
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 35 224923 224923 4194304 256 0 0 12 24 20608 0x7f66798a9480 0x7f6676824240 524288 10884992 1219065644 17616587105378 17616587064345 17616587338585 17616587340112
15 13 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 38 224923 224923 4194304 256 0 0 16 24 21312 0x7f66798a9300 0x7f6676824280 524288 11486594 1286494744 17616587371061 17616587338585 17616587697785 17616587699073
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 41 224923 224923 4194304 256 0 0 16 24 22016 0x7f66798a9180 0x7f66768242c0 524288 11447281 1282107568 17616587730422 17616587697785 17616588057305 17616588058734
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 44 224923 224923 4194304 256 0 0 16 24 22720 0x7f66798a9000 0x7f6676824300 524288 11340196 1270047532 17616588090153 17616588057305 17616588328665 17616588330047
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 47 224923 224923 4194304 256 0 0 12 24 23424 0x7f6677207e80 0x7f6676824340 524288 11235643 1258366196 17616588361016 17616588328665 17616588598905 17616588600380
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 50 224923 224923 4194304 256 0 0 12 24 24128 0x7f6677207d00 0x7f6676824380 524288 11212984 1255863520 17616588638479 17616588598905 17616588872026 17616588873363
20 18 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 53 224923 224923 4194304 256 0 0 16 24 24832 0x7f6677207b80 0x7f66768243c0 524288 11475817 1285277324 17616588905152 17616588872026 17616589229946 17616589231314
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 56 224923 224923 4194304 256 0 0 16 24 25536 0x7f6677207a00 0x7f6676824400 524288 11565969 1295363756 17616589261653 17616589229946 17616589594266 17616589595715
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 59 224923 224923 4194304 256 0 0 12 24 26240 0x7f6677207880 0x7f6676824440 524288 11124985 1245916360 17616589626254 17616589594266 17616589866746 17616589868168
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 62 224923 224923 4194304 256 0 0 12 24 26944 0x7f6677207700 0x7f6676824480 524288 10914456 1222388864 17616589898867 17616589866746 17616590140346 17616590141681
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 65 224923 224923 4194304 256 0 0 12 24 27648 0x7f66798a9580 0x7f66768244c0 524288 11122668 1245696596 17616590181100 17616590140346 17616590418107 17616590419434
25 23 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 68 224923 224923 4194304 256 0 0 16 24 28608 0x7f66798a9400 0x7f6676824500 524288 11374860 1273944156 17616590449703 17616590418107 17616590776187 17616590777725
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 71 224923 224923 4194304 256 0 0 16 24 29312 0x7f66798a9280 0x7f6676824540 524288 11410133 1277927640 17616590808744 17616590776187 17616591134907 17616591136306
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 74 224923 224923 4194304 256 0 0 12 24 30016 0x7f66798a9100 0x7f6676824580 524288 10954631 1226946540 17616591168025 17616591134907 17616591406907 17616591408309
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 77 224923 224923 4194304 256 0 0 8 24 30976 0x7f6677207f80 0x7f66768245c0 524288 10617058 1189110872 17616591439468 17616591406907 17616591681947 17616591683512
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 80 224923 224923 4194304 256 0 0 12 24 31680 0x7f6677207e00 0x7f6676824600 524288 11108853 1244240284 17616591720561 17616591681947 17616591955707 17616591957015
30 28 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 83 224923 224923 4194304 256 0 0 16 24 32640 0x7f6677207c80 0x7f6676824640 524288 11568683 1295664164 17616591987614 17616591955707 17616592319708 17616592321145
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 86 224923 224923 4194304 256 0 0 12 24 33600 0x7f6677207b00 0x7f6676824680 524288 11530782 1291418292 17616592351345 17616592319708 17616592677308 17616592678706
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 89 224923 224923 4194304 256 0 0 12 24 34560 0x7f6677207980 0x7f66768246c0 524288 10659903 1193847880 17616592709545 17616592677308 17616592948668 17616592949999
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 92 224923 224923 4194304 256 0 0 8 24 35520 0x7f6677207800 0x7f6676824700 524288 10442292 1169501476 17616592980148 17616592948668 17616593230108 17616593231572
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 95 224923 224923 4194304 256 0 0 12 24 36224 0x7f6677207680 0x7f6676824740 524288 10884366 1218958024 17616593269151 17616593230108 17616593502108 17616593503775
35 33 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 98 224923 224923 4194304 256 0 0 12 24 37184 0x7f66798a9500 0x7f6676824780 524288 11449817 1282334924 17616593534774 17616593502108 17616593861469 17616593862736
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 101 224923 224923 4194304 256 0 0 12 24 38144 0x7f66798a9380 0x7f66768247c0 524288 11342802 1270360984 17616593893635 17616593861469 17616594217629 17616594219287
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 104 224923 224923 4194304 256 0 0 12 24 39104 0x7f66798a9200 0x7f6676824800 524288 10697145 1198148552 17616594251286 17616594217629 17616594493629 17616594495230
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 107 224923 224923 4194304 256 0 0 8 24 40320 0x7f66798a9080 0x7f6676824840 524288 9998816 1119848052 17616594525979 17616594493629 17616594764829 17616594766313
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 110 224923 224923 4194304 256 0 0 12 24 41280 0x7f6677207f00 0x7f6676824880 524288 10622469 1189645616 17616594804622 17616594764829 17616595045629 17616595046936
40 38 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 113 224923 224923 4194304 256 0 0 12 24 42240 0x7f6677207d80 0x7f66768248c0 524288 11504704 1288527952 17616595077105 17616595045629 17616595404669 17616595406117
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 116 224923 224923 4194304 256 0 0 12 24 43200 0x7f6677207c00 0x7f6676824900 524288 11459692 1283406788 17616595437476 17616595404669 17616595760190 17616595761558
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 119 224923 224923 4194304 256 0 0 8 24 44160 0x7f6677207a80 0x7f6676824940 524288 10636268 1191276784 17616595791687 17616595760190 17616596029310 17616596030861
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 122 224923 224923 4194304 256 0 0 12 24 45376 0x7f6677207900 0x7f6676824980 524288 9540413 1068487148 17616596061170 17616596029310 17616596298910 17616596300374
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 125 224923 224923 4194304 256 0 0 12 24 46336 0x7f6677207780 0x7f66768249c0 524288 11005247 1232547252 17616596338123 17616596298910 17616596569150 17616596570477
45 43 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 128 224923 224923 4194304 256 0 0 12 24 47552 0x7f6677207600 0x7f6676824a00 524288 11291528 1264664408 17616596601337 17616596569150 17616596924670 17616596925898
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 131 224923 224923 4194304 256 0 0 12 24 48512 0x7f66798a9480 0x7f6676824a40 524288 11464293 1283976936 17616596957847 17616596924670 17616597283551 17616597285029
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 134 224923 224923 4194304 256 0 0 8 24 49472 0x7f66798a9300 0x7f6676824a80 524288 10351349 1159310736 17616597315118 17616597283551 17616597552031 17616597553652
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 137 224923 224923 4194304 256 0 0 12 24 50688 0x7f66798a9180 0x7f6676824ac0 524288 9189592 1029270056 17616597584822 17616597552031 17616597829471 17616597830875
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 140 224923 224923 4194304 256 0 0 12 24 51648 0x7f66798a9000 0x7f6676824b00 524288 10490920 1175044172 17616597869014 17616597829471 17616598098591 17616598100079
50 48 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 143 224923 224923 4194304 256 0 0 12 24 52864 0x7f6677207e80 0x7f6676824b40 524288 11243719 1259288068 17616598130938 17616598098591 17616598459871 17616598461469
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 146 224923 224923 4194304 256 0 0 12 24 54080 0x7f6677207d00 0x7f6676824b80 524288 11333427 1269354784 17616598491949 17616598459871 17616598818751 17616598820110
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 149 224923 224923 4194304 256 0 0 8 24 55296 0x7f6677207b80 0x7f6676824bc0 524288 10311900 1154881916 17616598850270 17616598818751 17616599088352 17616599089833
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 152 224923 224923 4194304 256 0 0 12 24 56768 0x7f6677207a00 0x7f6676824c00 524288 7660962 858033416 17616599121143 17616599088352 17616599357472 17616599358907
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 155 224923 224923 4194304 256 0 0 12 24 57728 0x7f6677207880 0x7f6676824c40 524288 10668081 1194805792 17616599396086 17616599357472 17616599629632 17616599631100
55 53 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 158 224923 224923 4194304 256 0 0 12 24 58944 0x7f6677207700 0x7f6676824c80 524288 11332260 1269208508 17616599661319 17616599629632 17616599989312 17616599990621
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 161 224923 224923 4194304 256 0 0 12 24 60160 0x7f66798a9580 0x7f6676824cc0 524288 11364999 1272870852 17616600022310 17616599989312 17616600344512 17616600345982
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 164 224923 224923 4194304 256 0 0 8 24 61376 0x7f66798a9400 0x7f6676824d00 524288 10103502 1131538196 17616600376871 17616600344512 17616600619553 17616600620975
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 167 224923 224923 4194304 256 0 0 12 24 62848 0x7f66798a9280 0x7f6676824d40 524288 6112177 684580832 17616600652174 17616600619553 17616600895873 17616600897318
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 170 224923 224923 4194304 256 0 0 12 24 63808 0x7f66798a9100 0x7f6676824d80 524288 10015600 1121741252 17616600935627 17616600895873 17616601170113 17616601171441
60 58 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 173 224923 224923 4194304 256 0 0 12 24 65024 0x7f6677207f80 0x7f6676824dc0 524288 11187710 1253001024 17616601203690 17616601170113 17616601526273 17616601527682
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 176 224923 224923 4194304 256 0 0 12 24 66240 0x7f6677207e00 0x7f6676824e00 524288 11315916 1267348760 17616601558741 17616601526273 17616601881633 17616601882923
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 179 224923 224923 4194304 256 0 0 8 24 67456 0x7f6677207c80 0x7f6676824e40 524288 10029985 1123285696 17616601912862 17616601881633 17616602150913 17616602152566
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 182 224923 224923 4194304 256 0 0 12 24 68928 0x7f6677207b00 0x7f6676824e80 524288 5583246 625324888 17616602184665 17616602150913 17616602441474 17616602442938
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 185 224923 224923 4194304 256 0 0 12 24 70144 0x7f6677207980 0x7f6676824ec0 524288 10215409 1144096892 17616602480957 17616602441474 17616602716034 17616602717501
65 63 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 188 224923 224923 4194304 256 0 0 12 24 71616 0x7f6677207800 0x7f6676824f00 524288 11359905 1272281852 17616602748221 17616602716034 17616603075714 17616603077082
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 191 224923 224923 4194304 256 0 0 12 24 72832 0x7f6677207680 0x7f6676824f40 524288 11350178 1271157244 17616603107072 17616603075714 17616603438114 17616603439493
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 194 224923 224923 4194304 256 0 0 8 24 74048 0x7f66798a9500 0x7f6676824f80 524288 9917994 1110808992 17616603470322 17616603438114 17616603707234 17616603708736
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 197 224923 224923 4194304 256 0 0 12 24 75776 0x7f66798a9380 0x7f6676824fc0 524288 4863112 544688836 17616603739946 17616603707234 17616603989634 17616603991009
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 200 224923 224923 4194304 256 0 0 12 24 76992 0x7f66798a9200 0x7f6676825000 524288 10380466 1162561880 17616604029308 17616603989634 17616604262115 17616604263672
70 68 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 203 224923 224923 4194304 256 0 0 12 24 78464 0x7f66798a9080 0x7f6676825040 524288 11179716 1252099184 17616604295032 17616604262115 17616604619395 17616604620833
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 206 224923 224923 4194304 256 0 0 12 24 79936 0x7f6677207f00 0x7f6676825080 524288 11305869 1266268936 17616604652082 17616604619395 17616604974755 17616604976134
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 209 224923 224923 4194304 256 0 0 8 24 81408 0x7f6677207d80 0x7f66768250c0 524288 9799511 1097505924 17616605006363 17616604974755 17616605244195 17616605245757
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 212 224923 224923 4194304 256 0 0 12 24 83136 0x7f6677207c00 0x7f6676825100 524288 4119811 461354636 17616605276557 17616605244195 17616605532515 17616605534080
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 215 224923 224923 4194304 256 0 0 12 24 84352 0x7f6677207a80 0x7f6676825140 524288 10632933 1190898012 17616605584079 17616605532515 17616605816516 17616605818093
75 73 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 218 224923 224923 4194304 256 0 0 12 24 85824 0x7f6677207900 0x7f6676825180 524288 11260095 1261108360 17616605848142 17616605816516 17616606179716 17616606181284
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 221 224923 224923 4194304 256 0 0 12 24 87296 0x7f6677207780 0x7f66768251c0 524288 11284094 1263783392 17616606213333 17616606179716 17616606548836 17616606550334
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 224 224923 224923 4194304 256 0 0 12 24 88768 0x7f6677207600 0x7f6676825200 524288 9414519 1054351792 17616606580284 17616606548836 17616606818756 17616606820058
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 227 224923 224923 4194304 256 0 0 12 24 90752 0x7f66798a9480 0x7f6676825240 524288 3844270 430570732 17616606850577 17616606818756 17616607113476 17616607114940
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 230 224923 224923 4194304 256 0 0 12 24 91968 0x7f66798a9300 0x7f6676825280 524288 9868269 1105240528 17616607153569 17616607113476 17616607384516 17616607385923
80 78 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 233 224923 224923 4194304 256 0 0 12 24 93440 0x7f66798a9180 0x7f66768252c0 524288 10983926 1230189044 17616607416802 17616607384516 17616607738597 17616607739874
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 236 224923 224923 4194304 256 0 0 12 24 94912 0x7f66798a9000 0x7f6676825300 524288 11307938 1266435696 17616607771423 17616607738597 17616608093477 17616608094815
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 239 224923 224923 4194304 256 0 0 12 24 96384 0x7f6677207e80 0x7f6676825340 524288 9182374 1028407768 17616608125164 17616608093477 17616608364677 17616608366088
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 242 224923 224923 4194304 256 0 0 12 24 98368 0x7f6677207d00 0x7f6676825380 524288 3582117 401235424 17616608396868 17616608364677 17616608665477 17616608666791
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 245 224923 224923 4194304 256 0 0 12 24 99584 0x7f6677207b80 0x7f66768253c0 524288 9846286 1102658072 17616608704860 17616608665477 17616608934277 17616608935814
85 83 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 248 224923 224923 4194304 256 0 0 12 24 101312 0x7f6677207a00 0x7f6676825400 524288 11230912 1257866024 17616608966603 17616608934277 17616609294758 17616609296185
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 251 224923 224923 4194304 256 0 0 12 24 102784 0x7f6677207880 0x7f6676825440 524288 11195118 1253816412 17616609325994 17616609294758 17616609649638 17616609651126
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 254 224923 224923 4194304 256 0 0 12 24 104256 0x7f6677207700 0x7f6676825480 524288 8846911 990893700 17616609680985 17616609649638 17616609917958 17616609919339
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 257 224923 224923 4194304 256 0 0 12 24 106240 0x7f66798a9580 0x7f66768254c0 524288 3226468 361341948 17616609950348 17616609917958 17616610230278 17616610231731
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 260 224923 224923 4194304 256 0 0 12 24 107712 0x7f66798a9400 0x7f6676825500 524288 9896332 1108337416 17616610270730 17616610230278 17616610503078 17616610504414
90 88 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 263 224923 224923 4194304 256 0 0 16 24 109440 0x7f66798a9280 0x7f6676825540 524288 11267814 1261933520 17616610535683 17616610503078 17616610859559 17616610860995
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 266 224923 224923 4194304 256 0 0 16 24 111168 0x7f66798a9100 0x7f6676825580 524288 11205376 1254971684 17616610891814 17616610859559 17616611215719 17616611217136
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 269 224923 224923 4194304 256 0 0 8 24 112896 0x7f6677207f80 0x7f66768255c0 524288 8112508 908551692 17616611248415 17616611215719 17616611485639 17616611487089
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 272 224923 224923 4194304 256 0 0 12 24 115136 0x7f6677207e00 0x7f6676825600 524288 2989363 334767632 17616611519188 17616611485639 17616611798119 17616611799431
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 275 224923 224923 4194304 256 0 0 12 24 116608 0x7f6677207c80 0x7f6676825640 524288 9377872 1050296924 17616611837240 17616611798119 17616612079879 17616612081324
95 93 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 278 224923 224923 4194304 256 0 0 16 24 118336 0x7f6677207b00 0x7f6676825680 524288 11095753 1242725200 17616612112023 17616612079879 17616612435399 17616612436885
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 281 224923 224923 4194304 256 0 0 16 24 120064 0x7f6677207980 0x7f66768256c0 524288 11132157 1246737332 17616612467294 17616612435399 17616612790760 17616612792196
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 284 224923 224923 4194304 256 0 0 12 24 121792 0x7f6677207800 0x7f6676825700 524288 6908138 773635240 17616612822435 17616612790760 17616613064040 17616613065519
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 287 224923 224923 4194304 256 0 0 12 24 124032 0x7f6677207680 0x7f6676825740 524288 2987033 334521784 17616613095598 17616613064040 17616613382920 17616613384501
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 290 224923 224923 4194304 256 0 0 12 24 125504 0x7f66798a9500 0x7f6676825780 524288 9068751 1015804156 17616613422400 17616613382920 17616613655720 17616613657144
100 98 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 293 224923 224923 4194304 256 0 0 12 24 127488 0x7f66798a9380 0x7f66768257c0 524288 11119819 1245382156 17616613687593 17616613655720 17616614016520 17616614017935
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 296 224923 224923 4194304 256 0 0 12 24 129216 0x7f66798a9200 0x7f6676825800 524288 10959202 1227400204 17616614048924 17616614016520 17616614380681 17616614382106
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 299 224923 224923 4194304 256 0 0 12 24 130944 0x7f66798a9080 0x7f6676825840 524288 6223078 696978252 17616614413155 17616614380681 17616614661481 17616614662849
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 302 224923 224923 4194304 256 0 0 12 24 133440 0x7f6677207f00 0x7f6676825880 524288 2991887 335059936 17616614694488 17616614661481 17616614999081 17616615000450
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 305 224923 224923 4194304 256 0 0 12 24 134912 0x7f6677207d80 0x7f66768258c0 524288 8477557 949405576 17616615039199 17616614999081 17616615276681 17616615278123
105 103 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 308 224923 224923 4194304 256 0 0 12 24 136896 0x7f6677207c00 0x7f6676825900 524288 10943848 1225678540 17616615308762 17616615276681 17616615631081 17616615632404
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 311 224923 224923 4194304 256 0 0 12 24 138880 0x7f6677207a80 0x7f6676825940 524288 10998557 1231810156 17616615662823 17616615631081 17616615986922 17616615988555
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 314 224923 224923 4194304 256 0 0 12 24 140864 0x7f6677207900 0x7f6676825980 524288 4725550 529208156 17616616018834 17616615986922 17616616267882 17616616269328
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 317 224923 224923 4194304 256 0 0 12 24 143616 0x7f6677207780 0x7f66768259c0 524288 2902808 324987836 17616616300067 17616616267882 17616616611242 17616616612659
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 320 224923 224923 4194304 256 0 0 12 24 145344 0x7f6677207600 0x7f6676825a00 524288 7477208 837384588 17616616650638 17616616611242 17616616881962 17616616883472
110 108 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 323 224923 224923 4194304 256 0 0 12 24 147584 0x7f66798a9480 0x7f6676825a40 524288 10829654 1212904504 17616616913502 17616616881962 17616617236522 17616617237883
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 326 224923 224923 4194304 256 0 0 12 24 149568 0x7f66798a9300 0x7f6676825a80 524288 10920320 1223034384 17616617268913 17616617236522 17616617590602 17616617592085
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 329 224923 224923 4194304 256 0 0 12 24 151552 0x7f66798a9180 0x7f6676825ac0 524288 4021691 450387048 17616617623654 17616617590602 17616617881003 17616617882447
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 332 224923 224923 4194304 256 0 0 12 24 154304 0x7f66798a9000 0x7f6676825b00 524288 2874412 321960140 17616617912676 17616617881003 17616618240523 17616618242108
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 335 224923 224923 4194304 256 0 0 12 24 156288 0x7f6677207e80 0x7f6676825b40 524288 5539451 620398736 17616618280487 17616618240523 17616618525163 17616618526791
115 113 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 338 224923 224923 4194304 256 0 0 12 24 158784 0x7f6677207d00 0x7f6676825b80 524288 9956863 1115156680 17616618557630 17616618525163 17616618884523 17616618885892
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 341 224923 224923 4194304 256 0 0 12 24 161024 0x7f6677207b80 0x7f6676825bc0 524288 10933613 1224586852 17616618916561 17616618884523 17616619252523 17616619253912
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 344 224923 224923 4194304 256 0 0 12 24 163264 0x7f6677207a00 0x7f6676825c00 524288 3567210 399614228 17616619284452 17616619252523 17616619551244 17616619552705
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 347 224923 224923 4194304 256 0 0 12 24 166528 0x7f6677207880 0x7f6676825c40 524288 2876201 322135468 17616619583364 17616619551244 17616619932844 17616619978274
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 350 224923 224923 4194304 256 0 0 12 24 168512 0x7f6677207700 0x7f6676825c80 524288 4051321 453714604 17616619997054 17616619932844 17616620256524 17616620258007
120 118 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 353 224923 224923 4194304 256 0 0 12 24 171264 0x7f66798a9580 0x7f6676825cc0 524288 9834752 1101495352 17616620288956 17616620256524 17616620614924 17616620616318
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 356 224923 224923 4194304 256 0 0 12 24 173760 0x7f66798a9400 0x7f6676825d00 524288 10166230 1138591316 17616620648857 17616620614924 17616620980524 17616620981909
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 359 224923 224923 4194304 256 0 0 12 24 176256 0x7f66798a9280 0x7f6676825d40 524288 2839065 317840060 17616621012708 17616620980524 17616621291245 17616621292721
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 362 224923 224923 4194304 256 0 0 12 24 179776 0x7f66798a9100 0x7f6676825d80 524288 2868542 321310272 17616621323460 17616621291245 17616621697965 17616621716970
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 365 224923 224923 4194304 256 0 0 12 24 182272 0x7f6677207f80 0x7f6676825dc0 524288 3142293 351892544 17616621737729 17616621697965 17616622008045 17616622009613
125 123 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 368 224923 224923 4194304 256 0 0 12 24 185536 0x7f6677207e00 0x7f6676825e00 524288 7901702 884915708 17616622039702 17616622008045 17616622379245 17616622426112
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 371 224923 224923 4194304 256 0 0 12 24 188544 0x7f6677207c80 0x7f6676825e40 524288 7658330 857675848 17616622437902 17616622379245 17616622786125 17616622832242
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 374 224923 224923 4194304 256 0 0 12 24 191552 0x7f6677207b00 0x7f6676825e80 524288 2892246 323848616 17616622843621 17616622786125 17616623157646 17616623159153
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 377 224923 224923 4194304 256 0 0 12 24 195840 0x7f6677207980 0x7f6676825ec0 524288 2874932 321983312 17616623189973 17616623157646 17616623616206 17616623662361
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 380 224923 224923 4194304 256 0 0 12 24 198592 0x7f6677207800 0x7f6676825f00 524288 2760412 309111604 17616623681380 17616623616206 17616623974286 17616623975763
130 128 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 383 224923 224923 4194304 256 0 0 12 24 202368 0x7f6677207680 0x7f6676825f40 524288 6818540 763656772 17616624006222 17616623974286 17616624363086 17616624405312
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 386 224923 224923 4194304 256 0 0 12 24 205888 0x7f66798a9500 0x7f6676825f80 524288 6479153 725637932 17616624416932 17616624363086 17616624781167 17616624822921
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 389 224923 224923 4194304 256 0 0 12 24 209408 0x7f66798a9380 0x7f6676825fc0 524288 2830352 316894428 17616624833051 17616624781167 17616625172207 17616625173662
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 392 224923 224923 4194304 256 0 0 12 24 214464 0x7f66798a9200 0x7f6676826000 524288 2922189 327196460 17616625204752 17616625172207 17616625682127 17616625700439
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 395 224923 224923 4194304 256 0 0 12 24 217728 0x7f66798a9080 0x7f6676826040 524288 2772757 310435048 17616625722508 17616625682127 17616626034287 17616626035721
135 133 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 398 224923 224923 4194304 256 0 0 12 24 222016 0x7f6677207f00 0x7f6676826080 524288 5927465 663861336 17616626067170 17616626034287 17616626472048 17616626515438
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 401 224923 224923 4194304 256 0 0 12 24 226048 0x7f6677207d80 0x7f66768260c0 524288 5195047 581774056 17616626526338 17616626472048 17616626911088 17616626954027
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 404 224923 224923 4194304 256 0 0 12 24 230080 0x7f6677207c00 0x7f6676826100 524288 2775539 310824656 17616626965047 17616626911088 17616627330928 17616627372237
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 407 224923 224923 4194304 256 0 0 12 24 235904 0x7f6677207a80 0x7f6676826140 524288 2907403 325623936 17616627383526 17616627330928 17616627923728 17616627965152
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 410 224923 224923 4194304 256 0 0 12 24 239424 0x7f6677207900 0x7f6676826180 524288 2824851 316356620 17616627983991 17616627923728 17616628323729 17616628325262
140 138 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 413 224923 224923 4194304 256 0 0 12 24 244224 0x7f6677207780 0x7f66768261c0 524288 5254947 588580672 17616628355832 17616628323729 17616628753489 17616628796461
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 416 224923 224923 4194304 256 0 0 12 24 248768 0x7f6677207600 0x7f6676826200 524288 3327874 372708560 17616628807600 17616628753489 17616629213009 17616629234139
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 419 224923 224923 4194304 256 0 0 12 24 253312 0x7f66798a9480 0x7f6676826240 524288 2746430 307470164 17616629245669 17616629213009 17616629634769 17616629654779
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 422 224923 224923 4194304 256 0 0 8 24 255552 0x7f66798a9300 0x7f6676826280 524288 2365006 264887664 17616629667448 17616629634769 17616630273170 17616630295683
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 425 224923 224923 4194304 256 0 0 12 24 259840 0x7f66798a9180 0x7f66768262c0 524288 2756045 308607552 17616630314482 17616630273170 17616630690290 17616630711832
145 143 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 428 224923 224923 4194304 256 0 0 12 24 265664 0x7f66798a9000 0x7f6676826300 524288 3302571 369846340 17616630722592 17616630690290 17616631177330 17616631197970
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 431 224923 224923 4194304 256 0 0 12 24 271232 0x7f6677207e80 0x7f6676826340 524288 3735777 418344800 17616631209439 17616631177330 17616631664211 17616631681227
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 434 224923 224923 4194304 256 0 0 8 24 273216 0x7f6677207d00 0x7f6676826380 524288 2402299 269019148 17616631696597 17616631664211 17616632140851 17616632157905
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 437 224923 224923 4194304 256 0 0 8 24 275712 0x7f6677207b80 0x7f66768263c0 524288 2385700 267232156 17616632172865 17616632140851 17616632882451 17616632899677
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 440 224923 224923 4194304 256 0 0 12 24 280768 0x7f6677207a00 0x7f6676826400 524288 2640985 295764608 17616632922216 17616632882451 17616633333972 17616633350265
150 148 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 443 224923 224923 4194304 256 0 0 12 24 287616 0x7f6677207880 0x7f6676826440 524288 3499100 391889656 17616633365955 17616633333972 17616633865652 17616633882802
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 446 224923 224923 4194304 256 0 0 12 24 294208 0x7f6677207700 0x7f6676826480 524288 3364047 376719280 17616633900411 17616633865652 17616634397492 17616634416018
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 449 224923 224923 4194304 256 0 0 8 24 296960 0x7f66798a9580 0x7f66768264c0 524288 2392923 268005112 17616634429828 17616634397492 17616634932053 17616634975704
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 452 224923 224923 4194304 256 0 0 8 24 299968 0x7f66798a9400 0x7f6676826500 524288 2402295 268992960 17616634987064 17616634932053 17616635800053 17616635841962
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 455 224923 224923 4194304 256 0 0 8 24 302720 0x7f66798a9280 0x7f6676826540 524288 2387243 267343680 17616635860891 17616635800053 17616636459093 17616636500825
155 153 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 458 224923 224923 4194304 256 0 0 12 24 305472 0x7f66798a9100 0x7f6676826580 524288 2587729 289762244 17616636512105 17616636459093 17616637131734 17616637173178
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 461 224923 224923 4194304 256 0 0 12 24 308224 0x7f6677207f80 0x7f66768265c0 524288 2599045 291156548 17616637185288 17616637131734 17616637798614 17616637840301
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 464 224923 224923 4194304 256 0 0 8 24 310976 0x7f6677207e00 0x7f6676826600 524288 2397271 268489716 17616637850871 17616637798614 17616638457815 17616638503664
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 467 224923 224923 4194304 256 0 0 8 24 313216 0x7f6677207c80 0x7f6676826640 524288 2418107 270776944 17616638515954 17616638457815 17616639559575 17616639605156
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 470 224923 224923 4194304 256 0 0 8 24 315968 0x7f6677207b00 0x7f6676826680 524288 2443554 273735728 17616639625056 17616639559575 17616640638136 17616640683119
160 158 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 473 224923 224923 4194304 256 0 0 12 24 318720 0x7f6677207980 0x7f66768266c0 524288 2586330 289622392 17616640694219 17616640637960 17616641744200 17616641813000
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 476 224923 224923 4194304 256 0 0 12 24 321472 0x7f6677207800 0x7f6676826700 524288 2613802 292684248 17616641824460 17616641744200 17616642871560 17616642942701
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 479 224923 224923 4194304 256 0 0 8 24 324224 0x7f6677207680 0x7f6676826740 524288 2435966 272804852 17616642953751 17616642871560 17616643985480 17616644051093
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 482 224923 224923 4194304 256 0 0 8 24 326464 0x7f66798a9500 0x7f6676826780 524288 2466561 276190448 17616644062383 17616643985480 17616645930441 17616645996534
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 485 224923 224923 4194304 256 0 0 8 24 329216 0x7f66798a9380 0x7f66768267c0 524288 2453031 274691816 17616646015123 17616645930441 17616647856041 17616647925465
165 163 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 488 224923 224923 4194304 256 0 0 12 24 331968 0x7f66798a9200 0x7f6676826800 524288 2617755 293159780 17616647936565 17616647856041 17616649843881 17616649907945
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 491 224923 224923 4194304 256 0 0 12 24 334720 0x7f66798a9080 0x7f6676826840 524288 2629177 294473224 17616649918805 17616649843881 17616651822922 17616651893654
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 494 224923 224923 4194304 256 0 0 8 24 337472 0x7f6677207f00 0x7f6676826880 524288 2456642 275183732 17616651905794 17616651822922 17616653754602 17616653820396
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 497 224923 224923 4194304 256 0 0 8 24 0 0x7f6677207d80 0x7f66768268c0 524288 2466163 276223040 17616653831885 17616653754602 17616657357483 17616657478993
@@ -0,0 +1,168 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,grd,Workgroup_Size,LDS_Per_Workgroup,scr,vgpr,SGPR,fbar,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"__amd_rocclr_fillBufferAligned.kd",0,0,0,223519,223519,33554432,256,0,0,4,32,4160,0x0,0x7f1ce5804280,387094,387094,8680,3096760,524288,245771477,3011216,0,999328548,17599035568236,17598328816642,17599185813205,17599185923274
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,223519,223519,32768,256,0,0,12,24,13888,0x0,0x7f1ce5823f80,33003,33003,29549,264032,512,1739044,167125,0,6969744,17599191082624,17599185813205,17599191227446,17599191232450
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,223519,223519,4194304,256,0,0,12,24,14336,0x7f1ce8890380,0x7f1ce5823fc0,164050,164050,13444,1312408,65536,80869811,1211279,0,325210296,17599191275709,17599191227446,17599191628886,17599191631540
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,223519,223519,4194304,256,0,0,16,24,15040,0x7f1ce8890200,0x7f1ce5824000,311255,311255,23766,2490048,65536,228598662,2391429,0,916123524,17599191677268,17599191628886,17599192061846,17599192064219
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,223519,223519,4194304,256,0,0,16,24,15488,0x7f1ce8890080,0x7f1ce5824040,308986,308986,23354,2471896,65536,214366751,2367416,0,859195568,17599192106057,17599192061846,17599192489046,17599192491478
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,223519,223519,4194304,256,0,0,12,24,15936,0x7f1ce60edf00,0x7f1ce5824080,164229,164229,13653,1313840,65536,79739799,1213367,0,320688912,17599192533847,17599192489046,17599192819766,17599192822219
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,223519,223519,4194304,256,0,0,12,24,16384,0x7f1ce60edd80,0x7f1ce58240c0,164270,164270,13901,1314168,65536,85085195,1213013,0,342069648,17599192862578,17599192819766,17599193152407,17599193154691
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,223519,223519,4194304,256,0,0,12,24,17088,0x7f1ce60edc00,0x7f1ce5824100,163629,163629,14731,1309040,65536,101700322,1209658,0,408527388,17599193208009,17599193152407,17599193479927,17599193482142
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,223519,223519,4194304,256,0,0,16,24,17792,0x7f1ce60eda80,0x7f1ce5824140,309902,309902,24313,2479224,65536,231331788,2381450,0,927056496,17599193522181,17599193479927,17599193913527,17599193915851
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,223519,223519,4194304,256,0,0,16,24,18496,0x7f1ce60ed900,0x7f1ce5824180,308147,308147,20797,2465184,65536,223234065,2366125,0,894661804,17599193956680,17599193913527,17599194343127,17599194345870
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,223519,223519,4194304,256,0,0,16,24,19200,0x7f1ce60ed780,0x7f1ce58241c0,164420,164420,14978,1315368,65536,107801666,1219890,0,432931588,17599194385889,17599194343127,17599194681207,17599194683762
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,223519,223519,4194304,256,0,0,16,24,19904,0x7f1ce60ed600,0x7f1ce5824200,163850,163850,14054,1310808,65536,95767506,1210869,0,384799188,17599194725201,17599194681207,17599195007127,17599195008974
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,223519,223519,4194304,256,0,0,12,24,20608,0x7f1ce8890480,0x7f1ce5824240,163455,163455,15069,1307648,65536,101466803,1209268,0,407590804,17599195059352,17599195007127,17599195307927,17599195309736
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,223519,223519,4194304,256,0,0,16,24,21312,0x7f1ce8890300,0x7f1ce5824280,311296,311296,24891,2490376,65536,223027785,2383286,0,893843148,17599195357015,17599195307927,17599195716887,17599195718836
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,223519,223519,4194304,256,0,0,16,24,22016,0x7f1ce8890180,0x7f1ce58242c0,307413,307413,21313,2459312,65536,220377875,2358693,0,883239532,17599195762984,17599195716887,17599196109847,17599196111616
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,223519,223519,4194304,256,0,0,16,24,22720,0x7f1ce8890000,0x7f1ce5824300,163860,163860,14357,1310888,65536,86177672,1212931,0,346446296,17599196153195,17599196109847,17599196415287,17599196417118
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,223519,223519,4194304,256,0,0,12,24,23424,0x7f1ce60ede80,0x7f1ce5824340,164511,164511,14669,1316096,65536,101894090,1212423,0,409304048,17599196458717,17599196415287,17599196715448,17599196717250
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,223519,223519,4194304,256,0,0,12,24,24128,0x7f1ce60edd00,0x7f1ce5824380,162566,162566,15450,1300536,65536,99198555,1201088,0,398516296,17599196765099,17599196715448,17599197022328,17599197024232
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,223519,223519,4194304,256,0,0,16,24,24832,0x7f1ce60edb80,0x7f1ce58243c0,308486,308486,24663,2467896,65536,229072215,2363677,0,918017676,17599197068781,17599197022328,17599197411768,17599197413713
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,223519,223519,4194304,256,0,0,16,24,25536,0x7f1ce60eda00,0x7f1ce5824400,306838,306838,20483,2454712,65536,210761440,2347060,0,844777756,17599197455062,17599197411768,17599197800408,17599197802393
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,223519,223519,4194304,256,0,0,12,24,26240,0x7f1ce60ed880,0x7f1ce5824440,162963,162963,14416,1303712,65536,102793107,1207484,0,412900652,17599197843782,17599197800408,17599198102808,17599198104865
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,223519,223519,4194304,256,0,0,12,24,26944,0x7f1ce60ed700,0x7f1ce5824480,162934,162934,14706,1303480,65536,96090233,1205611,0,386088624,17599198146734,17599198102808,17599198410648,17599198412477
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,223519,223519,4194304,256,0,0,12,24,27648,0x7f1ce8890580,0x7f1ce58244c0,162859,162859,15238,1302880,65536,107652555,1202144,0,432340532,17599198460616,17599198410648,17599198715448,17599198717769
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,223519,223519,4194304,256,0,0,16,24,28608,0x7f1ce8890400,0x7f1ce5824500,308990,308990,23423,2471928,65536,228161252,2373553,0,914374868,17599198760228,17599198715448,17599199109368,17599199111219
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,223519,223519,4194304,256,0,0,16,24,29312,0x7f1ce8890280,0x7f1ce5824540,306147,306147,20151,2449184,65536,209050543,2343388,0,837930064,17599199154828,17599199109368,17599199502008,17599199504109
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,223519,223519,4194304,256,0,0,12,24,30016,0x7f1ce8890100,0x7f1ce5824580,162202,162202,14765,1297624,65536,103659410,1202611,0,416368760,17599199546568,17599199502008,17599199803928,17599199805552
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,223519,223519,4194304,256,0,0,8,24,30976,0x7f1ce60edf80,0x7f1ce58245c0,163079,163079,14477,1304640,65536,92718497,1200483,0,372605996,17599199847341,17599199803928,17599200104729,17599200106534
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,223519,223519,4194304,256,0,0,12,24,31680,0x7f1ce60ede00,0x7f1ce5824600,162400,162400,15348,1299208,65536,103841820,1202899,0,417091548,17599200155193,17599200104729,17599200404889,17599200406786
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,223519,223519,4194304,256,0,0,16,24,32640,0x7f1ce60edc80,0x7f1ce5824640,306398,306398,23515,2451192,65536,223314085,2344298,0,894986284,17599200448415,17599200404889,17599200808089,17599200809996
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,223519,223519,4194304,256,0,0,12,24,33600,0x7f1ce60edb00,0x7f1ce5824680,307952,307952,21104,2463624,65536,224650082,2360765,0,900327932,17599200852475,17599200808089,17599201203769,17599201205546
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,223519,223519,4194304,256,0,0,12,24,34560,0x7f1ce60ed980,0x7f1ce58246c0,164008,164008,14762,1312072,65536,103895188,1212089,0,417308724,17599201248205,17599201203769,17599201510649,17599201512478
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,223519,223519,4194304,256,0,0,8,24,35520,0x7f1ce60ed800,0x7f1ce5824700,163010,163010,14494,1304088,65536,91860289,1202289,0,369166104,17599201553217,17599201510649,17599201813689,17599201815460
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,223519,223519,4194304,256,0,0,12,24,36224,0x7f1ce60ed680,0x7f1ce5824740,162473,162473,14752,1299792,65536,103696532,1200924,0,416512052,17599201863219,17599201813689,17599202114969,17599202117173
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,223519,223519,4194304,256,0,0,12,24,37184,0x7f1ce8890500,0x7f1ce5824780,305506,305506,23301,2444056,65536,228169266,2345763,0,914408976,17599202157842,17599202114969,17599202506969,17599202508773
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,223519,223519,4194304,256,0,0,12,24,38144,0x7f1ce8890380,0x7f1ce58247c0,305717,305717,23005,2445744,65536,218981174,2346926,0,877653892,17599202549452,17599202506969,17599202897049,17599202898983
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,223519,223519,4194304,256,0,0,12,24,39104,0x7f1ce8890200,0x7f1ce5824800,162681,162681,14041,1301456,65536,91860945,1201279,0,369175496,17599202940142,17599202897049,17599203203449,17599203205385
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,223519,223519,4194304,256,0,0,8,24,40320,0x7f1ce8890080,0x7f1ce5824840,163191,163191,15242,1305536,65536,90365610,1203195,0,363194352,17599203245884,17599203203449,17599203506809,17599203508637
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,223519,223519,4194304,256,0,0,12,24,41280,0x7f1ce60edf00,0x7f1ce5824880,161859,161859,13858,1294880,65536,95579670,1195909,0,384043028,17599203556696,17599203506809,17599203817210,17599203819140
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,223519,223519,4194304,256,0,0,12,24,42240,0x7f1ce60edd80,0x7f1ce58248c0,305636,305636,23779,2445096,65536,226682733,2348095,0,908461292,17599203859599,17599203817210,17599204207610,17599204209530
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,223519,223519,4194304,256,0,0,12,24,43200,0x7f1ce60edc00,0x7f1ce5824900,305030,305030,22101,2440248,65536,221200829,2340228,0,886532660,17599204255839,17599204207610,17599204600730,17599204602530
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,223519,223519,4194304,256,0,0,8,24,44160,0x7f1ce60eda80,0x7f1ce5824940,162587,162587,14434,1300704,65536,99405729,1197980,0,399347716,17599204643099,17599204600730,17599204904250,17599204906362
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,223519,223519,4194304,256,0,0,12,24,45376,0x7f1ce60ed900,0x7f1ce5824980,163091,163091,15330,1304736,65536,97276801,1204513,0,390833256,17599204946401,17599204904250,17599205207130,17599205208974
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,223519,223519,4194304,256,0,0,12,24,46336,0x7f1ce60ed780,0x7f1ce58249c0,161124,161124,14416,1289000,65536,100075238,1192158,0,402025064,17599205257133,17599205207130,17599205522330,17599205524216
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,223519,223519,4194304,256,0,0,12,24,47552,0x7f1ce60ed600,0x7f1ce5824a00,303879,303879,23298,2431040,65536,219789456,2327008,0,880886488,17599205564615,17599205522330,17599205912090,17599205914126
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,223519,223519,4194304,256,0,0,12,24,48512,0x7f1ce8890480,0x7f1ce5824a40,302284,302284,20793,2418280,65536,213011727,2317029,0,853773992,17599205956235,17599205912090,17599206310490,17599206312506
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,223519,223519,4194304,256,0,0,8,24,49472,0x7f1ce8890300,0x7f1ce5824a80,161795,161795,14420,1294368,65536,91035453,1195696,0,365874580,17599206353075,17599206310490,17599206621530,17599206623439
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,223519,223519,4194304,256,0,0,12,24,50688,0x7f1ce8890180,0x7f1ce5824ac0,162106,162106,16119,1296856,65536,98051476,1192092,0,393944684,17599206664607,17599206621530,17599206925850,17599206927641
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,223519,223519,4194304,256,0,0,12,24,51648,0x7f1ce8890000,0x7f1ce5824b00,162005,162005,15343,1296048,65536,93865820,1188512,0,377192988,17599206975550,17599206925850,17599207236091,17599207238053
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,223519,223519,4194304,256,0,0,12,24,52864,0x7f1ce60ede80,0x7f1ce5824b40,301396,301396,22283,2411176,65536,216674007,2310551,0,868426856,17599207279362,17599207236091,17599207626971,17599207628953
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,223519,223519,4194304,256,0,0,12,24,54080,0x7f1ce60edd00,0x7f1ce5824b80,299539,299539,19642,2396320,65536,206194038,2294934,0,826505180,17599207675052,17599207626971,17599208024891,17599208026693
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,223519,223519,4194304,256,0,0,8,24,55296,0x7f1ce60edb80,0x7f1ce5824bc0,162125,162125,14190,1297008,65536,92278615,1195744,0,370838364,17599208066542,17599208024891,17599208327611,17599208329595
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,223519,223519,4194304,256,0,0,12,24,56768,0x7f1ce60eda00,0x7f1ce5824c00,162214,162214,15205,1297720,65536,99118282,1195610,0,398203984,17599208369894,17599208327611,17599208635931,17599208637747
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,223519,223519,4194304,256,0,0,12,24,57728,0x7f1ce60ed880,0x7f1ce5824c40,161613,161613,14120,1292912,65536,94041848,1195216,0,377893920,17599208685976,17599208635931,17599208945211,17599208947010
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,223519,223519,4194304,256,0,0,12,24,58944,0x7f1ce60ed700,0x7f1ce5824c80,303465,303465,23759,2427728,65536,222226826,2324855,0,890641624,17599208987999,17599208945211,17599209336891,17599209338770
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,223519,223519,4194304,256,0,0,12,24,60160,0x7f1ce8890580,0x7f1ce5824cc0,300746,300746,20912,2405976,65536,213737641,2304791,0,856677840,17599209378479,17599209336891,17599209726171,17599209727870
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,223519,223519,4194304,256,0,0,8,24,61376,0x7f1ce8890400,0x7f1ce5824d00,163757,163757,14773,1310064,65536,92688980,1207571,0,372498780,17599209768679,17599209726171,17599210032251,17599210034002
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,223519,223519,4194304,256,0,0,12,24,62848,0x7f1ce8890280,0x7f1ce5824d40,168983,168983,15942,1351872,65536,107111514,1248405,0,430178284,17599210073981,17599210032251,17599210352411,17599210354654
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,223519,223519,4194304,256,0,0,12,24,63808,0x7f1ce8890100,0x7f1ce5824d80,161745,161745,14451,1293968,65536,91622561,1194499,0,368211260,17599210402933,17599210352411,17599210656892,17599210658776
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,223519,223519,4194304,256,0,0,12,24,65024,0x7f1ce60edf80,0x7f1ce5824dc0,302236,302236,22091,2417896,65536,223073394,2317704,0,894026480,17599210699905,17599210656892,17599211043932,17599211045686
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,223519,223519,4194304,256,0,0,12,24,66240,0x7f1ce60ede00,0x7f1ce5824e00,298968,298968,20392,2391752,65536,214210680,2293417,0,858573496,17599211085865,17599211043932,17599211432732,17599211434506
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,223519,223519,4194304,256,0,0,8,24,67456,0x7f1ce60edc80,0x7f1ce5824e40,162020,162020,14214,1296168,65536,84657719,1193390,0,340358196,17599211474565,17599211432732,17599211734652,17599211736449
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,223519,223519,4194304,256,0,0,12,24,68928,0x7f1ce60edb00,0x7f1ce5824e80,176643,176643,16123,1413152,65536,101640233,1310164,0,408295768,17599211776988,17599211734652,17599212049372,17599212051331
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,223519,223519,4194304,256,0,0,12,24,70144,0x7f1ce60ed980,0x7f1ce5824ec0,160200,160200,14521,1281608,65536,91774639,1182297,0,368831804,17599212099949,17599212049372,17599212357212,17599212359093
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,223519,223519,4194304,256,0,0,12,24,71616,0x7f1ce60ed800,0x7f1ce5824f00,300790,300790,22942,2406328,65536,221184750,2307117,0,886468016,17599212400082,17599212357212,17599212751612,17599212753523
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,223519,223519,4194304,256,0,0,12,24,72832,0x7f1ce60ed680,0x7f1ce5824f40,303214,303214,22979,2425720,65536,222476360,2321620,0,891634332,17599212794032,17599212751612,17599213140412,17599213142303
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,223519,223519,4194304,256,0,0,8,24,74048,0x7f1ce8890500,0x7f1ce5824f80,161576,161576,15002,1292616,65536,93329451,1194379,0,375045880,17599213183432,17599213140412,17599213444252,17599213446165
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,223519,223519,4194304,256,0,0,12,24,75776,0x7f1ce8890380,0x7f1ce5824fc0,181529,181529,16342,1452240,65536,114055396,1352505,0,457967400,17599213487164,17599213444252,17599213760092,17599213762087
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,223519,223519,4194304,256,0,0,12,24,76992,0x7f1ce8890200,0x7f1ce5825000,160547,160547,14019,1284384,65536,93572627,1185461,0,376026100,17599213822025,17599213760092,17599214066012,17599214067799
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,223519,223519,4194304,256,0,0,12,24,78464,0x7f1ce8890080,0x7f1ce5825040,302277,302277,23450,2418224,65536,217494928,2312009,0,871710180,17599214122088,17599214066012,17599214472573,17599214474469
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,223519,223519,4194304,256,0,0,12,24,79936,0x7f1ce60edf00,0x7f1ce5825080,300853,300853,22552,2406832,65536,218269792,2309166,0,874808368,17599214515098,17599214472573,17599214869213,17599214871149
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,223519,223519,4194304,256,0,0,8,24,81408,0x7f1ce60edd80,0x7f1ce58250c0,161705,161705,14563,1293648,65536,89960658,1192520,0,361574908,17599214911058,17599214869213,17599215179133,17599215181001
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,223519,223519,4194304,256,0,0,12,24,83136,0x7f1ce60edc00,0x7f1ce5825100,189879,189879,17280,1519040,65536,121152417,1416318,0,486350000,17599215221200,17599215179133,17599215500893,17599215502703
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,223519,223519,4194304,256,0,0,12,24,84352,0x7f1ce60eda80,0x7f1ce5825140,161595,161595,14563,1292768,65536,90832627,1194715,0,365068304,17599215550182,17599215500893,17599215809853,17599215811795
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,223519,223519,4194304,256,0,0,12,24,85824,0x7f1ce60ed900,0x7f1ce5825180,304373,304373,23948,2434992,65536,223154907,2330830,0,894352844,17599215852234,17599215809853,17599216202173,17599216204095
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,223519,223519,4194304,256,0,0,12,24,87296,0x7f1ce60ed780,0x7f1ce58251c0,302025,302025,23949,2416208,65536,217635570,2314395,0,872271164,17599216245874,17599216202173,17599216596253,17599216598185
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,223519,223519,4194304,256,0,0,12,24,88768,0x7f1ce60ed600,0x7f1ce5825200,164231,164231,15505,1313856,65536,95391188,1208938,0,383297012,17599216637724,17599216596253,17599216905213,17599216907147
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,223519,223519,4194304,256,0,0,12,24,90752,0x7f1ce8890480,0x7f1ce5825240,201157,201157,18060,1609264,65536,132808019,1502674,0,532976100,17599216946956,17599216905213,17599217238173,17599217240109
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,223519,223519,4194304,256,0,0,12,24,91968,0x7f1ce8890300,0x7f1ce5825280,161439,161439,15055,1291520,65536,90394810,1183386,0,363313524,17599217287948,17599217238173,17599217542653,17599217544551
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,223519,223519,4194304,256,0,0,12,24,93440,0x7f1ce8890180,0x7f1ce58252c0,301599,301599,23523,2412800,65536,215903820,2308263,0,865345476,17599217591970,17599217542653,17599217943454,17599217945341
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,223519,223519,4194304,256,0,0,12,24,94912,0x7f1ce8890000,0x7f1ce5825300,299893,299893,21400,2399152,65536,213209361,2302281,0,854568564,17599217988350,17599217943454,17599218342974,17599218345131
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,223519,223519,4194304,256,0,0,12,24,96384,0x7f1ce60ede80,0x7f1ce5825340,161857,161857,15079,1294864,65536,95410546,1195944,0,383376428,17599218384950,17599218342974,17599218651454,17599218653103
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,223519,223519,4194304,256,0,0,12,24,98368,0x7f1ce60edd00,0x7f1ce5825380,210961,210961,18726,1687696,65536,122671910,1573016,0,492430000,17599218693772,17599218651454,17599218984894,17599218986714
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,223519,223519,4194304,256,0,0,12,24,99584,0x7f1ce60edb80,0x7f1ce58253c0,160722,160722,14786,1285784,65536,94041126,1188643,0,377898620,17599219034443,17599218984894,17599219287454,17599219289297
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,223519,223519,4194304,256,0,0,12,24,101312,0x7f1ce60eda00,0x7f1ce5825400,297215,297215,22381,2377728,65536,217376199,2272933,0,871240176,17599219330136,17599219287454,17599219682174,17599219684177
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,223519,223519,4194304,256,0,0,12,24,102784,0x7f1ce60ed880,0x7f1ce5825440,301892,301892,23159,2415144,65536,215777482,2310252,0,864839608,17599219724166,17599219682174,17599220073374,17599220075207
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,223519,223519,4194304,256,0,0,12,24,104256,0x7f1ce60ed700,0x7f1ce5825480,160875,160875,15512,1287008,65536,99935082,1186832,0,401477760,17599220115886,17599220073374,17599220377214,17599220378979
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,223519,223519,4194304,256,0,0,12,24,106240,0x7f1ce8890580,0x7f1ce58254c0,218300,218300,18735,1746408,65536,142545557,1643475,0,571929752,17599220419158,17599220377214,17599220715934,17599220717570
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,223519,223519,4194304,256,0,0,12,24,107712,0x7f1ce8890400,0x7f1ce5825500,160809,160809,14981,1286480,65536,93024188,1185194,0,373830336,17599220765819,17599220715934,17599221020254,17599221022052
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,223519,223519,4194304,256,0,0,16,24,109440,0x7f1ce8890280,0x7f1ce5825540,295522,295522,20151,2364184,65536,200099648,2263590,0,802131380,17599221063171,17599221020254,17599221406975,17599221408643
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,223519,223519,4194304,256,0,0,16,24,111168,0x7f1ce8890100,0x7f1ce5825580,299497,299497,21829,2395984,65536,209498979,2296410,0,839727244,17599221450281,17599221406975,17599221798175,17599221800103
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,223519,223519,4194304,256,0,0,8,24,112896,0x7f1ce60edf80,0x7f1ce58255c0,162801,162801,15814,1302416,65536,103762745,1199482,0,416787216,17599221840192,17599221798175,17599222108415,17599222110135
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,223519,223519,4194304,256,0,0,12,24,115136,0x7f1ce60ede00,0x7f1ce5825600,229107,229107,19573,1832864,65536,144180621,1723384,0,578468672,17599222150574,17599222108415,17599222461055,17599222463096
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,223519,223519,4194304,256,0,0,12,24,116608,0x7f1ce60edc80,0x7f1ce5825640,160681,160681,14462,1285456,65536,88587366,1188462,0,356082704,17599222510745,17599222461055,17599222765375,17599222767318
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,223519,223519,4194304,256,0,0,16,24,118336,0x7f1ce60edb00,0x7f1ce5825680,297135,297135,21739,2377088,65536,215165967,2275049,0,862398400,17599222807817,17599222765375,17599223152895,17599223154718
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,223519,223519,4194304,256,0,0,16,24,120064,0x7f1ce60ed980,0x7f1ce58256c0,297121,297121,20305,2376976,65536,207446767,2276839,0,831518832,17599223194867,17599223152895,17599223543295,17599223545098
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,223519,223519,4194304,256,0,0,12,24,121792,0x7f1ce60ed800,0x7f1ce5825700,163001,163001,15187,1304016,65536,101362097,1204674,0,407182516,17599223585347,17599223543295,17599223848415,17599223850391
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,223519,223519,4194304,256,0,0,12,24,124032,0x7f1ce60ed680,0x7f1ce5825740,239925,239925,19579,1919408,65536,146470535,1808793,0,587628928,17599223889670,17599223848415,17599224205695,17599224207662
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,223519,223519,4194304,256,0,0,12,24,125504,0x7f1ce8890500,0x7f1ce5825780,161045,161045,14978,1288368,65536,97847558,1190238,0,393119288,17599224255930,17599224205695,17599224515615,17599224517514
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,223519,223519,4194304,256,0,0,12,24,127488,0x7f1ce8890380,0x7f1ce58257c0,295651,295651,19251,2365216,65536,206874185,2267595,0,829232996,17599224559303,17599224515615,17599224902816,17599224904564
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,223519,223519,4194304,256,0,0,12,24,129216,0x7f1ce8890200,0x7f1ce5825800,297826,297826,19792,2382616,65536,195167844,2278001,0,782408712,17599224945893,17599224902816,17599225291616,17599225293464
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,223519,223519,4194304,256,0,0,12,24,130944,0x7f1ce8890080,0x7f1ce5825840,169599,169599,15760,1356800,65536,105285452,1254879,0,422889800,17599225333593,17599225291616,17599225601376,17599225603426
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,223519,223519,4194304,256,0,0,12,24,133440,0x7f1ce60edf00,0x7f1ce5825880,258737,258737,20664,2069904,65536,175156884,1963536,0,702375908,17599225644165,17599225601376,17599225965696,17599225967437
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,223519,223519,4194304,256,0,0,12,24,134912,0x7f1ce60edd80,0x7f1ce58258c0,161133,161133,14947,1289072,65536,99668799,1191612,0,400406652,17599226015586,17599225965696,17599226278336,17599226280129
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,223519,223519,4194304,256,0,0,12,24,136896,0x7f1ce60edc00,0x7f1ce5825900,296613,296613,19851,2372912,65536,211958812,2274899,0,849585212,17599226320258,17599226278336,17599226674976,17599226676669
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,223519,223519,4194304,256,0,0,12,24,138880,0x7f1ce60eda80,0x7f1ce5825940,296549,296549,20612,2372400,65536,215890509,2271918,0,865297144,17599226716468,17599226674976,17599227064736,17599227066609
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,223519,223519,4194304,256,0,0,12,24,140864,0x7f1ce60ed900,0x7f1ce5825980,177585,177585,16300,1420688,65536,111061850,1320744,0,445990508,17599227106748,17599227064736,17599227379776,17599227381681
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,223519,223519,4194304,256,0,0,12,24,143616,0x7f1ce60ed780,0x7f1ce58259c0,279463,279463,22603,2235712,65536,197343747,2128046,0,791123128,17599227421940,17599227379776,17599227754656,17599227756442
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,223519,223519,4194304,256,0,0,12,24,145344,0x7f1ce60ed600,0x7f1ce5825a00,161081,161081,15306,1288656,65536,99456610,1190651,0,399561276,17599227807350,17599227754656,17599228061216,17599228063134
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,223519,223519,4194304,256,0,0,12,24,147584,0x7f1ce8890480,0x7f1ce5825a40,296477,296477,21328,2371824,65536,210194267,2268497,0,842536848,17599228103923,17599228061216,17599228449377,17599228451204
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,223519,223519,4194304,256,0,0,12,24,149568,0x7f1ce8890300,0x7f1ce5825a80,295165,295165,20099,2361328,65536,201808227,2257080,0,808969600,17599228491953,17599228449377,17599228839137,17599228841014
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,223519,223519,4194304,256,0,0,12,24,151552,0x7f1ce8890180,0x7f1ce5825ac0,186107,186107,16970,1488864,65536,111191723,1383831,0,446514828,17599228881633,17599228839137,17599229164257,17599229166026
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,223519,223519,4194304,256,0,0,12,24,154304,0x7f1ce8890000,0x7f1ce5825b00,298821,298821,22956,2390576,65536,206564441,2285325,0,828009164,17599229206785,17599229164257,17599229559937,17599229561796
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,223519,223519,4194304,256,0,0,12,24,156288,0x7f1ce60ede80,0x7f1ce5825b40,170807,170807,16146,1366464,65536,109618243,1269968,0,440209784,17599229610025,17599229559937,17599229873537,17599229875448
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,223519,223519,4194304,256,0,0,12,24,158784,0x7f1ce60edd00,0x7f1ce5825b80,297260,297260,19673,2378088,65536,197640121,2268866,0,792318656,17599229916137,17599229873537,17599230277377,17599230279218
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,223519,223519,4194304,256,0,0,12,24,161024,0x7f1ce60edb80,0x7f1ce5825bc0,296572,296572,19642,2372584,65536,194914504,2267424,0,781405500,17599230321996,17599230277377,17599230673697,17599230675577
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,223519,223519,4194304,256,0,0,12,24,163264,0x7f1ce60eda00,0x7f1ce5825c00,204886,204886,17647,1639096,65536,129298815,1534522,0,518943612,17599230716236,17599230673697,17599231008737,17599231010679
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,223519,223519,4194304,256,0,0,12,24,166528,0x7f1ce60ed880,0x7f1ce5825c40,339686,339686,25283,2717496,65536,242270464,2610005,0,970841356,17599231050558,17599231008737,17599231425377,17599231471227
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,223519,223519,4194304,256,0,0,12,24,168512,0x7f1ce60ed700,0x7f1ce5825c80,185664,185664,17222,1485320,65536,99311144,1372031,0,398988988,17599231490727,17599231425377,17599231779778,17599231781749
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,223519,223519,4194304,256,0,0,12,24,171264,0x7f1ce8890580,0x7f1ce5825cc0,297130,297130,19433,2377048,65536,168980440,2248208,0,677690108,17599231823418,17599231779778,17599232174178,17599232175999
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,223519,223519,4194304,256,0,0,12,24,173760,0x7f1ce8890400,0x7f1ce5825d00,297218,297218,19703,2377752,65536,185841999,2256938,0,745121804,17599232217538,17599232174178,17599232566018,17599232567829
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,223519,223519,4194304,256,0,0,12,24,176256,0x7f1ce8890280,0x7f1ce5825d40,224070,224070,19255,1792568,65536,154540594,1688496,0,619907912,17599232608188,17599232566018,17599232912098,17599232914040
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,223519,223519,4194304,256,0,0,12,24,179776,0x7f1ce8890100,0x7f1ce5825d80,379408,379408,27524,3035272,65536,280912538,2929123,0,1125410688,17599232955209,17599232912098,17599233355938,17599233375539
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,223519,223519,4194304,256,0,0,12,24,182272,0x7f1ce60edf80,0x7f1ce5825dc0,210274,210274,18456,1682200,65536,134166152,1577796,0,538415380,17599233406918,17599233355938,17599233698658,17599233700550
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,223519,223519,4194304,256,0,0,12,24,185536,0x7f1ce60ede00,0x7f1ce5825e00,305566,305566,22879,2444536,65536,187311519,2330912,0,751005704,17599233741359,17599233698658,17599234099938,17599234122930
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,223519,223519,4194304,256,0,0,12,24,188544,0x7f1ce60edc80,0x7f1ce5825e40,311488,311488,20664,2491912,65536,175379827,2359463,0,703290192,17599234141379,17599234099938,17599234521698,17599234542609
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,223519,223519,4194304,256,0,0,12,24,191552,0x7f1ce60edb00,0x7f1ce5825e80,265298,265298,21716,2122392,65536,189167497,2016701,0,758434840,17599234564818,17599234521698,17599234894818,17599234896660
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,223519,223519,4194304,256,0,0,12,24,195840,0x7f1ce60ed980,0x7f1ce5825ec0,460424,460424,31007,3683400,65536,345057397,3579176,0,1381993856,17599234937179,17599234894818,17599235386979,17599235407387
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,223519,223519,4194304,256,0,0,12,24,198592,0x7f1ce60ed800,0x7f1ce5825f00,243092,243092,20413,1944744,65536,159122048,1834807,0,638237984,17599235437666,17599235386979,17599235748579,17599235750578
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,223519,223519,4194304,256,0,0,12,24,202368,0x7f1ce60ed680,0x7f1ce5825f40,335827,335827,22384,2686624,65536,210448050,2567232,0,843565464,17599235791957,17599235748579,17599236170179,17599236187327
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,223519,223519,4194304,256,0,0,12,24,205888,0x7f1ce8890500,0x7f1ce5825f80,331346,331346,22209,2650776,65536,198664952,2529289,0,796429876,17599236212287,17599236170179,17599236590339,17599236607707
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,223519,223519,4194304,256,0,0,12,24,209408,0x7f1ce8890380,0x7f1ce5825fc0,305461,305461,22903,2443696,65536,221925267,2342350,0,889461912,17599236633026,17599236590339,17599236995139,17599236996897
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,223519,223519,4194304,256,0,0,12,24,214464,0x7f1ce8890200,0x7f1ce5826000,541098,541098,35284,4328792,65536,409061131,4223430,0,1638009952,17599237038946,17599236995139,17599237539139,17599237556653
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,223519,223519,4194304,256,0,0,12,24,217728,0x7f1ce8890080,0x7f1ce5826040,272959,272959,21652,2183680,65536,178872300,2075612,0,717253708,17599237590162,17599237539139,17599237917699,17599237919603
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,223519,223519,4194304,256,0,0,12,24,222016,0x7f1ce60edf00,0x7f1ce5826080,364250,364250,25231,2914008,65536,239595938,2797370,0,960166628,17599237960842,17599237917699,17599238367779,17599238389651
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,223519,223519,4194304,256,0,0,12,24,226048,0x7f1ce60edd80,0x7f1ce58260c0,361051,361051,27014,2888416,65536,250347820,2778101,0,1003159244,17599238410891,17599238367779,17599238811939,17599238830550
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,223519,223519,4194304,256,0,0,12,24,230080,0x7f1ce60edc00,0x7f1ce5826100,346530,346530,25136,2772248,65536,244408330,2664140,0,979393744,17599238853770,17599238811939,17599239233540,17599239275419
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,223519,223519,4194304,256,0,0,12,24,235904,0x7f1ce60eda80,0x7f1ce5826140,623342,623342,39540,4986744,65536,471218885,4874374,0,1886645808,17599239286438,17599239233540,17599239849060,17599239890713
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,223519,223519,4194304,256,0,0,12,24,239424,0x7f1ce60ed900,0x7f1ce5826180,302245,302245,22652,2417968,65536,211097802,2315171,0,846156844,17599239909623,17599239849060,17599240271140,17599240272963
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,223519,223519,4194304,256,0,0,12,24,244224,0x7f1ce60ed780,0x7f1ce58261c0,398016,398016,27369,3184136,65536,275015593,3079684,0,1101844828,17599240314332,17599240271140,17599240730980,17599240773121
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,223519,223519,4194304,256,0,0,12,24,248768,0x7f1ce60ed600,0x7f1ce5826200,390013,390013,27492,3120112,65536,291609356,3017706,0,1168212064,17599240783620,17599240730980,17599241209380,17599241250958
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,223519,223519,4194304,256,0,0,12,24,253312,0x7f1ce8890480,0x7f1ce5826240,387234,387234,27184,3097880,65536,282987002,2990575,0,1133715156,17599241261508,17599241209380,17599241679140,17599241696477
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,223519,223519,4194304,256,0,0,8,24,255552,0x7f1ce8890300,0x7f1ce5826280,717821,717821,44413,5742576,65536,546838363,5632697,0,2189093020,17599241722076,17599241679140,17599242343780,17599242387169
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,223519,223519,4194304,256,0,0,12,24,259840,0x7f1ce8890180,0x7f1ce58262c0,364617,364617,26978,2916944,65536,260693479,2797452,0,1044537040,17599242407419,17599242343780,17599242803461,17599242846368
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,223519,223519,4194304,256,0,0,12,24,265664,0x7f1ce8890000,0x7f1ce5826300,469179,469179,31717,3753440,65536,353955504,3646651,0,1417608640,17599242858207,17599242803461,17599243334021,17599243375194
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,223519,223519,4194304,256,0,0,12,24,271232,0x7f1ce60ede80,0x7f1ce5826340,471620,471620,31455,3772968,65536,345981677,3668790,0,1385710812,17599243386094,17599243334021,17599243868101,17599243909021
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,223519,223519,4194304,256,0,0,8,24,273216,0x7f1ce60edd00,0x7f1ce5826380,482209,482209,32420,3857680,65536,354559889,3749819,0,1419981536,17599243920091,17599243868101,17599244393061,17599244434278
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,223519,223519,4194304,256,0,0,8,24,275712,0x7f1ce60edb80,0x7f1ce58263c0,880176,880176,52084,7041416,65536,681498431,6923810,0,2727736368,17599244445347,17599244393061,17599245177381,17599245219388
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,223519,223519,4194304,256,0,0,12,24,280768,0x7f1ce60eda00,0x7f1ce5826400,425683,425683,29165,3405472,65536,316443620,3299976,0,1267551264,17599245239757,17599245177381,17599245674661,17599245715875
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,223519,223519,4194304,256,0,0,12,24,287616,0x7f1ce60ed880,0x7f1ce5826440,548412,548412,35509,4387304,65536,413610552,4276643,0,1656223928,17599245726375,17599245674661,17599246252902,17599246298150
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,223519,223519,4194304,256,0,0,12,24,294208,0x7f1ce60ed700,0x7f1ce5826480,552445,552445,36131,4419568,65536,417015369,4310800,0,1669847868,17599246309380,17599246252902,17599246841702,17599246885505
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,223519,223519,4194304,256,0,0,8,24,296960,0x7f1ce8890580,0x7f1ce58264c0,563006,563006,36733,4504056,65536,424308773,4389098,0,1698977668,17599246896825,17599246841702,17599247423782,17599247465411
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,223519,223519,4194304,256,0,0,8,24,299968,0x7f1ce8890400,0x7f1ce5826500,1040093,1040093,60372,8320752,65536,810548879,8216909,0,3243938040,17599247476150,17599247423782,17599248319942,17599248366608
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,223519,223519,4194304,256,0,0,8,24,302720,0x7f1ce8890280,0x7f1ce5826540,721316,721316,43820,5770536,65536,547642350,5655562,0,2192311268,17599248385817,17599248320010,17599249006890,17599249054840
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,223519,223519,4194304,256,0,0,12,24,305472,0x7f1ce8890100,0x7f1ce5826580,723963,723963,44643,5791712,65536,552976262,5675103,0,2213647452,17599249066990,17599249006890,17599249730090,17599249773812
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,223519,223519,4194304,256,0,0,12,24,308224,0x7f1ce60edf80,0x7f1ce58265c0,722060,722060,44378,5776488,65536,542615241,5659951,0,2172201896,17599249785422,17599249730090,17599250439850,17599250485594
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,223519,223519,4194304,256,0,0,8,24,310976,0x7f1ce60ede00,0x7f1ce5826600,726898,726898,45383,5815192,65536,561271847,5695667,0,2246829592,17599250497754,17599250439850,17599251146250,17599251191836
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,223519,223519,4194304,256,0,0,8,24,313216,0x7f1ce60edc80,0x7f1ce5826640,1366597,1366597,77082,10932784,65536,1065672643,10816229,0,4264431668,17599251202856,17599251146250,17599252263051,17599252307888
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,223519,223519,4194304,256,0,0,8,24,315968,0x7f1ce60edb00,0x7f1ce5826680,1372024,1372024,77782,10976200,65536,1078387006,10851064,0,4315289956,17599252326697,17599252263051,17599253373931,17599253438249
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,223519,223519,4194304,256,0,0,12,24,318720,0x7f1ce60ed980,0x7f1ce58266c0,1371247,1371247,77518,10969984,65536,1075762186,10855352,0,4304789940,17599253449938,17599253373931,17599254525932,17599254595319
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,223519,223519,4194304,256,0,0,12,24,321472,0x7f1ce60ed800,0x7f1ce5826700,1372553,1372553,77477,10980432,65536,1073980519,10850584,0,4297662720,17599254607839,17599254525932,17599255686252,17599255751820
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,223519,223519,4194304,256,0,0,8,24,324224,0x7f1ce60ed680,0x7f1ce5826740,1374673,1374673,77106,10997392,65536,1076734019,10880624,0,4308678552,17599255763570,17599255686252,17599256816973,17599256888421
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,223519,223519,4194304,256,0,0,8,24,326464,0x7f1ce8890500,0x7f1ce5826780,2664917,2664917,143141,21319344,65536,2130988346,21187794,0,8525694980,17599256899991,17599256816973,17599258795214,17599258866681
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,223519,223519,4194304,256,0,0,8,24,329216,0x7f1ce8890380,0x7f1ce58267c0,2666982,2666982,142454,21335864,65536,2131372878,21221592,0,8527232704,17599258887370,17599258795214,17599260740654,17599260807081
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,223519,223519,4194304,256,0,0,12,24,331968,0x7f1ce8890200,0x7f1ce5826800,2671177,2671177,143385,21369424,65536,2133795562,21240229,0,8536923260,17599260818851,17599260740654,17599262739695,17599262809690
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,223519,223519,4194304,256,0,0,12,24,334720,0x7f1ce8890080,0x7f1ce5826840,2667766,2667766,142943,21342136,65536,2126319326,21225480,0,8507017148,17599262822020,17599262739695,17599264745136,17599264813360
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,223519,223519,4194304,256,0,0,8,24,337472,0x7f1ce60edf00,0x7f1ce5826880,2672975,2672975,142959,21383808,65536,2135790377,21263256,0,8544903336,17599264824699,17599264745136,17599266696017,17599266764750
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,223519,223519,4194304,256,0,0,8,24,0,0x7f1ce60edd80,0x7f1ce58268c0,5255554,5255554,272964,42044440,65536,4232756362,41926604,0,16932766864,17599266776960,17599266696017,17599270334258,17599270406228
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid grd Workgroup_Size LDS_Per_Workgroup scr vgpr SGPR fbar sig obj GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 __amd_rocclr_fillBufferAligned.kd 0 0 0 223519 223519 33554432 256 0 0 4 32 4160 0x0 0x7f1ce5804280 387094 387094 8680 3096760 524288 245771477 3011216 0 999328548 17599035568236 17598328816642 17599185813205 17599185923274
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 223519 223519 32768 256 0 0 12 24 13888 0x0 0x7f1ce5823f80 33003 33003 29549 264032 512 1739044 167125 0 6969744 17599191082624 17599185813205 17599191227446 17599191232450
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 5 223519 223519 4194304 256 0 0 12 24 14336 0x7f1ce8890380 0x7f1ce5823fc0 164050 164050 13444 1312408 65536 80869811 1211279 0 325210296 17599191275709 17599191227446 17599191628886 17599191631540
5 3 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 8 223519 223519 4194304 256 0 0 16 24 15040 0x7f1ce8890200 0x7f1ce5824000 311255 311255 23766 2490048 65536 228598662 2391429 0 916123524 17599191677268 17599191628886 17599192061846 17599192064219
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 11 223519 223519 4194304 256 0 0 16 24 15488 0x7f1ce8890080 0x7f1ce5824040 308986 308986 23354 2471896 65536 214366751 2367416 0 859195568 17599192106057 17599192061846 17599192489046 17599192491478
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 14 223519 223519 4194304 256 0 0 12 24 15936 0x7f1ce60edf00 0x7f1ce5824080 164229 164229 13653 1313840 65536 79739799 1213367 0 320688912 17599192533847 17599192489046 17599192819766 17599192822219
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 17 223519 223519 4194304 256 0 0 12 24 16384 0x7f1ce60edd80 0x7f1ce58240c0 164270 164270 13901 1314168 65536 85085195 1213013 0 342069648 17599192862578 17599192819766 17599193152407 17599193154691
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 20 223519 223519 4194304 256 0 0 12 24 17088 0x7f1ce60edc00 0x7f1ce5824100 163629 163629 14731 1309040 65536 101700322 1209658 0 408527388 17599193208009 17599193152407 17599193479927 17599193482142
10 8 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 23 223519 223519 4194304 256 0 0 16 24 17792 0x7f1ce60eda80 0x7f1ce5824140 309902 309902 24313 2479224 65536 231331788 2381450 0 927056496 17599193522181 17599193479927 17599193913527 17599193915851
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 26 223519 223519 4194304 256 0 0 16 24 18496 0x7f1ce60ed900 0x7f1ce5824180 308147 308147 20797 2465184 65536 223234065 2366125 0 894661804 17599193956680 17599193913527 17599194343127 17599194345870
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 29 223519 223519 4194304 256 0 0 16 24 19200 0x7f1ce60ed780 0x7f1ce58241c0 164420 164420 14978 1315368 65536 107801666 1219890 0 432931588 17599194385889 17599194343127 17599194681207 17599194683762
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 32 223519 223519 4194304 256 0 0 16 24 19904 0x7f1ce60ed600 0x7f1ce5824200 163850 163850 14054 1310808 65536 95767506 1210869 0 384799188 17599194725201 17599194681207 17599195007127 17599195008974
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 35 223519 223519 4194304 256 0 0 12 24 20608 0x7f1ce8890480 0x7f1ce5824240 163455 163455 15069 1307648 65536 101466803 1209268 0 407590804 17599195059352 17599195007127 17599195307927 17599195309736
15 13 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 38 223519 223519 4194304 256 0 0 16 24 21312 0x7f1ce8890300 0x7f1ce5824280 311296 311296 24891 2490376 65536 223027785 2383286 0 893843148 17599195357015 17599195307927 17599195716887 17599195718836
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 41 223519 223519 4194304 256 0 0 16 24 22016 0x7f1ce8890180 0x7f1ce58242c0 307413 307413 21313 2459312 65536 220377875 2358693 0 883239532 17599195762984 17599195716887 17599196109847 17599196111616
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 44 223519 223519 4194304 256 0 0 16 24 22720 0x7f1ce8890000 0x7f1ce5824300 163860 163860 14357 1310888 65536 86177672 1212931 0 346446296 17599196153195 17599196109847 17599196415287 17599196417118
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 47 223519 223519 4194304 256 0 0 12 24 23424 0x7f1ce60ede80 0x7f1ce5824340 164511 164511 14669 1316096 65536 101894090 1212423 0 409304048 17599196458717 17599196415287 17599196715448 17599196717250
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 50 223519 223519 4194304 256 0 0 12 24 24128 0x7f1ce60edd00 0x7f1ce5824380 162566 162566 15450 1300536 65536 99198555 1201088 0 398516296 17599196765099 17599196715448 17599197022328 17599197024232
20 18 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 53 223519 223519 4194304 256 0 0 16 24 24832 0x7f1ce60edb80 0x7f1ce58243c0 308486 308486 24663 2467896 65536 229072215 2363677 0 918017676 17599197068781 17599197022328 17599197411768 17599197413713
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 56 223519 223519 4194304 256 0 0 16 24 25536 0x7f1ce60eda00 0x7f1ce5824400 306838 306838 20483 2454712 65536 210761440 2347060 0 844777756 17599197455062 17599197411768 17599197800408 17599197802393
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 59 223519 223519 4194304 256 0 0 12 24 26240 0x7f1ce60ed880 0x7f1ce5824440 162963 162963 14416 1303712 65536 102793107 1207484 0 412900652 17599197843782 17599197800408 17599198102808 17599198104865
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 62 223519 223519 4194304 256 0 0 12 24 26944 0x7f1ce60ed700 0x7f1ce5824480 162934 162934 14706 1303480 65536 96090233 1205611 0 386088624 17599198146734 17599198102808 17599198410648 17599198412477
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 65 223519 223519 4194304 256 0 0 12 24 27648 0x7f1ce8890580 0x7f1ce58244c0 162859 162859 15238 1302880 65536 107652555 1202144 0 432340532 17599198460616 17599198410648 17599198715448 17599198717769
25 23 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 68 223519 223519 4194304 256 0 0 16 24 28608 0x7f1ce8890400 0x7f1ce5824500 308990 308990 23423 2471928 65536 228161252 2373553 0 914374868 17599198760228 17599198715448 17599199109368 17599199111219
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 71 223519 223519 4194304 256 0 0 16 24 29312 0x7f1ce8890280 0x7f1ce5824540 306147 306147 20151 2449184 65536 209050543 2343388 0 837930064 17599199154828 17599199109368 17599199502008 17599199504109
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 74 223519 223519 4194304 256 0 0 12 24 30016 0x7f1ce8890100 0x7f1ce5824580 162202 162202 14765 1297624 65536 103659410 1202611 0 416368760 17599199546568 17599199502008 17599199803928 17599199805552
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 77 223519 223519 4194304 256 0 0 8 24 30976 0x7f1ce60edf80 0x7f1ce58245c0 163079 163079 14477 1304640 65536 92718497 1200483 0 372605996 17599199847341 17599199803928 17599200104729 17599200106534
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 80 223519 223519 4194304 256 0 0 12 24 31680 0x7f1ce60ede00 0x7f1ce5824600 162400 162400 15348 1299208 65536 103841820 1202899 0 417091548 17599200155193 17599200104729 17599200404889 17599200406786
30 28 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 83 223519 223519 4194304 256 0 0 16 24 32640 0x7f1ce60edc80 0x7f1ce5824640 306398 306398 23515 2451192 65536 223314085 2344298 0 894986284 17599200448415 17599200404889 17599200808089 17599200809996
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 86 223519 223519 4194304 256 0 0 12 24 33600 0x7f1ce60edb00 0x7f1ce5824680 307952 307952 21104 2463624 65536 224650082 2360765 0 900327932 17599200852475 17599200808089 17599201203769 17599201205546
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 89 223519 223519 4194304 256 0 0 12 24 34560 0x7f1ce60ed980 0x7f1ce58246c0 164008 164008 14762 1312072 65536 103895188 1212089 0 417308724 17599201248205 17599201203769 17599201510649 17599201512478
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 92 223519 223519 4194304 256 0 0 8 24 35520 0x7f1ce60ed800 0x7f1ce5824700 163010 163010 14494 1304088 65536 91860289 1202289 0 369166104 17599201553217 17599201510649 17599201813689 17599201815460
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 95 223519 223519 4194304 256 0 0 12 24 36224 0x7f1ce60ed680 0x7f1ce5824740 162473 162473 14752 1299792 65536 103696532 1200924 0 416512052 17599201863219 17599201813689 17599202114969 17599202117173
35 33 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 98 223519 223519 4194304 256 0 0 12 24 37184 0x7f1ce8890500 0x7f1ce5824780 305506 305506 23301 2444056 65536 228169266 2345763 0 914408976 17599202157842 17599202114969 17599202506969 17599202508773
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 101 223519 223519 4194304 256 0 0 12 24 38144 0x7f1ce8890380 0x7f1ce58247c0 305717 305717 23005 2445744 65536 218981174 2346926 0 877653892 17599202549452 17599202506969 17599202897049 17599202898983
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 104 223519 223519 4194304 256 0 0 12 24 39104 0x7f1ce8890200 0x7f1ce5824800 162681 162681 14041 1301456 65536 91860945 1201279 0 369175496 17599202940142 17599202897049 17599203203449 17599203205385
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 107 223519 223519 4194304 256 0 0 8 24 40320 0x7f1ce8890080 0x7f1ce5824840 163191 163191 15242 1305536 65536 90365610 1203195 0 363194352 17599203245884 17599203203449 17599203506809 17599203508637
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 110 223519 223519 4194304 256 0 0 12 24 41280 0x7f1ce60edf00 0x7f1ce5824880 161859 161859 13858 1294880 65536 95579670 1195909 0 384043028 17599203556696 17599203506809 17599203817210 17599203819140
40 38 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 113 223519 223519 4194304 256 0 0 12 24 42240 0x7f1ce60edd80 0x7f1ce58248c0 305636 305636 23779 2445096 65536 226682733 2348095 0 908461292 17599203859599 17599203817210 17599204207610 17599204209530
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 116 223519 223519 4194304 256 0 0 12 24 43200 0x7f1ce60edc00 0x7f1ce5824900 305030 305030 22101 2440248 65536 221200829 2340228 0 886532660 17599204255839 17599204207610 17599204600730 17599204602530
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 119 223519 223519 4194304 256 0 0 8 24 44160 0x7f1ce60eda80 0x7f1ce5824940 162587 162587 14434 1300704 65536 99405729 1197980 0 399347716 17599204643099 17599204600730 17599204904250 17599204906362
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 122 223519 223519 4194304 256 0 0 12 24 45376 0x7f1ce60ed900 0x7f1ce5824980 163091 163091 15330 1304736 65536 97276801 1204513 0 390833256 17599204946401 17599204904250 17599205207130 17599205208974
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 125 223519 223519 4194304 256 0 0 12 24 46336 0x7f1ce60ed780 0x7f1ce58249c0 161124 161124 14416 1289000 65536 100075238 1192158 0 402025064 17599205257133 17599205207130 17599205522330 17599205524216
45 43 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 128 223519 223519 4194304 256 0 0 12 24 47552 0x7f1ce60ed600 0x7f1ce5824a00 303879 303879 23298 2431040 65536 219789456 2327008 0 880886488 17599205564615 17599205522330 17599205912090 17599205914126
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 131 223519 223519 4194304 256 0 0 12 24 48512 0x7f1ce8890480 0x7f1ce5824a40 302284 302284 20793 2418280 65536 213011727 2317029 0 853773992 17599205956235 17599205912090 17599206310490 17599206312506
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 134 223519 223519 4194304 256 0 0 8 24 49472 0x7f1ce8890300 0x7f1ce5824a80 161795 161795 14420 1294368 65536 91035453 1195696 0 365874580 17599206353075 17599206310490 17599206621530 17599206623439
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 137 223519 223519 4194304 256 0 0 12 24 50688 0x7f1ce8890180 0x7f1ce5824ac0 162106 162106 16119 1296856 65536 98051476 1192092 0 393944684 17599206664607 17599206621530 17599206925850 17599206927641
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 140 223519 223519 4194304 256 0 0 12 24 51648 0x7f1ce8890000 0x7f1ce5824b00 162005 162005 15343 1296048 65536 93865820 1188512 0 377192988 17599206975550 17599206925850 17599207236091 17599207238053
50 48 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 143 223519 223519 4194304 256 0 0 12 24 52864 0x7f1ce60ede80 0x7f1ce5824b40 301396 301396 22283 2411176 65536 216674007 2310551 0 868426856 17599207279362 17599207236091 17599207626971 17599207628953
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 146 223519 223519 4194304 256 0 0 12 24 54080 0x7f1ce60edd00 0x7f1ce5824b80 299539 299539 19642 2396320 65536 206194038 2294934 0 826505180 17599207675052 17599207626971 17599208024891 17599208026693
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 149 223519 223519 4194304 256 0 0 8 24 55296 0x7f1ce60edb80 0x7f1ce5824bc0 162125 162125 14190 1297008 65536 92278615 1195744 0 370838364 17599208066542 17599208024891 17599208327611 17599208329595
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 152 223519 223519 4194304 256 0 0 12 24 56768 0x7f1ce60eda00 0x7f1ce5824c00 162214 162214 15205 1297720 65536 99118282 1195610 0 398203984 17599208369894 17599208327611 17599208635931 17599208637747
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 155 223519 223519 4194304 256 0 0 12 24 57728 0x7f1ce60ed880 0x7f1ce5824c40 161613 161613 14120 1292912 65536 94041848 1195216 0 377893920 17599208685976 17599208635931 17599208945211 17599208947010
55 53 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 158 223519 223519 4194304 256 0 0 12 24 58944 0x7f1ce60ed700 0x7f1ce5824c80 303465 303465 23759 2427728 65536 222226826 2324855 0 890641624 17599208987999 17599208945211 17599209336891 17599209338770
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 161 223519 223519 4194304 256 0 0 12 24 60160 0x7f1ce8890580 0x7f1ce5824cc0 300746 300746 20912 2405976 65536 213737641 2304791 0 856677840 17599209378479 17599209336891 17599209726171 17599209727870
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 164 223519 223519 4194304 256 0 0 8 24 61376 0x7f1ce8890400 0x7f1ce5824d00 163757 163757 14773 1310064 65536 92688980 1207571 0 372498780 17599209768679 17599209726171 17599210032251 17599210034002
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 167 223519 223519 4194304 256 0 0 12 24 62848 0x7f1ce8890280 0x7f1ce5824d40 168983 168983 15942 1351872 65536 107111514 1248405 0 430178284 17599210073981 17599210032251 17599210352411 17599210354654
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 170 223519 223519 4194304 256 0 0 12 24 63808 0x7f1ce8890100 0x7f1ce5824d80 161745 161745 14451 1293968 65536 91622561 1194499 0 368211260 17599210402933 17599210352411 17599210656892 17599210658776
60 58 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 173 223519 223519 4194304 256 0 0 12 24 65024 0x7f1ce60edf80 0x7f1ce5824dc0 302236 302236 22091 2417896 65536 223073394 2317704 0 894026480 17599210699905 17599210656892 17599211043932 17599211045686
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 176 223519 223519 4194304 256 0 0 12 24 66240 0x7f1ce60ede00 0x7f1ce5824e00 298968 298968 20392 2391752 65536 214210680 2293417 0 858573496 17599211085865 17599211043932 17599211432732 17599211434506
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 179 223519 223519 4194304 256 0 0 8 24 67456 0x7f1ce60edc80 0x7f1ce5824e40 162020 162020 14214 1296168 65536 84657719 1193390 0 340358196 17599211474565 17599211432732 17599211734652 17599211736449
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 182 223519 223519 4194304 256 0 0 12 24 68928 0x7f1ce60edb00 0x7f1ce5824e80 176643 176643 16123 1413152 65536 101640233 1310164 0 408295768 17599211776988 17599211734652 17599212049372 17599212051331
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 185 223519 223519 4194304 256 0 0 12 24 70144 0x7f1ce60ed980 0x7f1ce5824ec0 160200 160200 14521 1281608 65536 91774639 1182297 0 368831804 17599212099949 17599212049372 17599212357212 17599212359093
65 63 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 188 223519 223519 4194304 256 0 0 12 24 71616 0x7f1ce60ed800 0x7f1ce5824f00 300790 300790 22942 2406328 65536 221184750 2307117 0 886468016 17599212400082 17599212357212 17599212751612 17599212753523
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 191 223519 223519 4194304 256 0 0 12 24 72832 0x7f1ce60ed680 0x7f1ce5824f40 303214 303214 22979 2425720 65536 222476360 2321620 0 891634332 17599212794032 17599212751612 17599213140412 17599213142303
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 194 223519 223519 4194304 256 0 0 8 24 74048 0x7f1ce8890500 0x7f1ce5824f80 161576 161576 15002 1292616 65536 93329451 1194379 0 375045880 17599213183432 17599213140412 17599213444252 17599213446165
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 197 223519 223519 4194304 256 0 0 12 24 75776 0x7f1ce8890380 0x7f1ce5824fc0 181529 181529 16342 1452240 65536 114055396 1352505 0 457967400 17599213487164 17599213444252 17599213760092 17599213762087
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 200 223519 223519 4194304 256 0 0 12 24 76992 0x7f1ce8890200 0x7f1ce5825000 160547 160547 14019 1284384 65536 93572627 1185461 0 376026100 17599213822025 17599213760092 17599214066012 17599214067799
70 68 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 203 223519 223519 4194304 256 0 0 12 24 78464 0x7f1ce8890080 0x7f1ce5825040 302277 302277 23450 2418224 65536 217494928 2312009 0 871710180 17599214122088 17599214066012 17599214472573 17599214474469
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 206 223519 223519 4194304 256 0 0 12 24 79936 0x7f1ce60edf00 0x7f1ce5825080 300853 300853 22552 2406832 65536 218269792 2309166 0 874808368 17599214515098 17599214472573 17599214869213 17599214871149
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 209 223519 223519 4194304 256 0 0 8 24 81408 0x7f1ce60edd80 0x7f1ce58250c0 161705 161705 14563 1293648 65536 89960658 1192520 0 361574908 17599214911058 17599214869213 17599215179133 17599215181001
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 212 223519 223519 4194304 256 0 0 12 24 83136 0x7f1ce60edc00 0x7f1ce5825100 189879 189879 17280 1519040 65536 121152417 1416318 0 486350000 17599215221200 17599215179133 17599215500893 17599215502703
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 215 223519 223519 4194304 256 0 0 12 24 84352 0x7f1ce60eda80 0x7f1ce5825140 161595 161595 14563 1292768 65536 90832627 1194715 0 365068304 17599215550182 17599215500893 17599215809853 17599215811795
75 73 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 218 223519 223519 4194304 256 0 0 12 24 85824 0x7f1ce60ed900 0x7f1ce5825180 304373 304373 23948 2434992 65536 223154907 2330830 0 894352844 17599215852234 17599215809853 17599216202173 17599216204095
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 221 223519 223519 4194304 256 0 0 12 24 87296 0x7f1ce60ed780 0x7f1ce58251c0 302025 302025 23949 2416208 65536 217635570 2314395 0 872271164 17599216245874 17599216202173 17599216596253 17599216598185
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 224 223519 223519 4194304 256 0 0 12 24 88768 0x7f1ce60ed600 0x7f1ce5825200 164231 164231 15505 1313856 65536 95391188 1208938 0 383297012 17599216637724 17599216596253 17599216905213 17599216907147
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 227 223519 223519 4194304 256 0 0 12 24 90752 0x7f1ce8890480 0x7f1ce5825240 201157 201157 18060 1609264 65536 132808019 1502674 0 532976100 17599216946956 17599216905213 17599217238173 17599217240109
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 230 223519 223519 4194304 256 0 0 12 24 91968 0x7f1ce8890300 0x7f1ce5825280 161439 161439 15055 1291520 65536 90394810 1183386 0 363313524 17599217287948 17599217238173 17599217542653 17599217544551
80 78 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 233 223519 223519 4194304 256 0 0 12 24 93440 0x7f1ce8890180 0x7f1ce58252c0 301599 301599 23523 2412800 65536 215903820 2308263 0 865345476 17599217591970 17599217542653 17599217943454 17599217945341
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 236 223519 223519 4194304 256 0 0 12 24 94912 0x7f1ce8890000 0x7f1ce5825300 299893 299893 21400 2399152 65536 213209361 2302281 0 854568564 17599217988350 17599217943454 17599218342974 17599218345131
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 239 223519 223519 4194304 256 0 0 12 24 96384 0x7f1ce60ede80 0x7f1ce5825340 161857 161857 15079 1294864 65536 95410546 1195944 0 383376428 17599218384950 17599218342974 17599218651454 17599218653103
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 242 223519 223519 4194304 256 0 0 12 24 98368 0x7f1ce60edd00 0x7f1ce5825380 210961 210961 18726 1687696 65536 122671910 1573016 0 492430000 17599218693772 17599218651454 17599218984894 17599218986714
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 245 223519 223519 4194304 256 0 0 12 24 99584 0x7f1ce60edb80 0x7f1ce58253c0 160722 160722 14786 1285784 65536 94041126 1188643 0 377898620 17599219034443 17599218984894 17599219287454 17599219289297
85 83 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 248 223519 223519 4194304 256 0 0 12 24 101312 0x7f1ce60eda00 0x7f1ce5825400 297215 297215 22381 2377728 65536 217376199 2272933 0 871240176 17599219330136 17599219287454 17599219682174 17599219684177
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 251 223519 223519 4194304 256 0 0 12 24 102784 0x7f1ce60ed880 0x7f1ce5825440 301892 301892 23159 2415144 65536 215777482 2310252 0 864839608 17599219724166 17599219682174 17599220073374 17599220075207
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 254 223519 223519 4194304 256 0 0 12 24 104256 0x7f1ce60ed700 0x7f1ce5825480 160875 160875 15512 1287008 65536 99935082 1186832 0 401477760 17599220115886 17599220073374 17599220377214 17599220378979
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 257 223519 223519 4194304 256 0 0 12 24 106240 0x7f1ce8890580 0x7f1ce58254c0 218300 218300 18735 1746408 65536 142545557 1643475 0 571929752 17599220419158 17599220377214 17599220715934 17599220717570
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 260 223519 223519 4194304 256 0 0 12 24 107712 0x7f1ce8890400 0x7f1ce5825500 160809 160809 14981 1286480 65536 93024188 1185194 0 373830336 17599220765819 17599220715934 17599221020254 17599221022052
90 88 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 263 223519 223519 4194304 256 0 0 16 24 109440 0x7f1ce8890280 0x7f1ce5825540 295522 295522 20151 2364184 65536 200099648 2263590 0 802131380 17599221063171 17599221020254 17599221406975 17599221408643
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 266 223519 223519 4194304 256 0 0 16 24 111168 0x7f1ce8890100 0x7f1ce5825580 299497 299497 21829 2395984 65536 209498979 2296410 0 839727244 17599221450281 17599221406975 17599221798175 17599221800103
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 269 223519 223519 4194304 256 0 0 8 24 112896 0x7f1ce60edf80 0x7f1ce58255c0 162801 162801 15814 1302416 65536 103762745 1199482 0 416787216 17599221840192 17599221798175 17599222108415 17599222110135
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 272 223519 223519 4194304 256 0 0 12 24 115136 0x7f1ce60ede00 0x7f1ce5825600 229107 229107 19573 1832864 65536 144180621 1723384 0 578468672 17599222150574 17599222108415 17599222461055 17599222463096
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 275 223519 223519 4194304 256 0 0 12 24 116608 0x7f1ce60edc80 0x7f1ce5825640 160681 160681 14462 1285456 65536 88587366 1188462 0 356082704 17599222510745 17599222461055 17599222765375 17599222767318
95 93 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 278 223519 223519 4194304 256 0 0 16 24 118336 0x7f1ce60edb00 0x7f1ce5825680 297135 297135 21739 2377088 65536 215165967 2275049 0 862398400 17599222807817 17599222765375 17599223152895 17599223154718
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 281 223519 223519 4194304 256 0 0 16 24 120064 0x7f1ce60ed980 0x7f1ce58256c0 297121 297121 20305 2376976 65536 207446767 2276839 0 831518832 17599223194867 17599223152895 17599223543295 17599223545098
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 284 223519 223519 4194304 256 0 0 12 24 121792 0x7f1ce60ed800 0x7f1ce5825700 163001 163001 15187 1304016 65536 101362097 1204674 0 407182516 17599223585347 17599223543295 17599223848415 17599223850391
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 287 223519 223519 4194304 256 0 0 12 24 124032 0x7f1ce60ed680 0x7f1ce5825740 239925 239925 19579 1919408 65536 146470535 1808793 0 587628928 17599223889670 17599223848415 17599224205695 17599224207662
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 290 223519 223519 4194304 256 0 0 12 24 125504 0x7f1ce8890500 0x7f1ce5825780 161045 161045 14978 1288368 65536 97847558 1190238 0 393119288 17599224255930 17599224205695 17599224515615 17599224517514
100 98 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 293 223519 223519 4194304 256 0 0 12 24 127488 0x7f1ce8890380 0x7f1ce58257c0 295651 295651 19251 2365216 65536 206874185 2267595 0 829232996 17599224559303 17599224515615 17599224902816 17599224904564
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 296 223519 223519 4194304 256 0 0 12 24 129216 0x7f1ce8890200 0x7f1ce5825800 297826 297826 19792 2382616 65536 195167844 2278001 0 782408712 17599224945893 17599224902816 17599225291616 17599225293464
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 299 223519 223519 4194304 256 0 0 12 24 130944 0x7f1ce8890080 0x7f1ce5825840 169599 169599 15760 1356800 65536 105285452 1254879 0 422889800 17599225333593 17599225291616 17599225601376 17599225603426
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 302 223519 223519 4194304 256 0 0 12 24 133440 0x7f1ce60edf00 0x7f1ce5825880 258737 258737 20664 2069904 65536 175156884 1963536 0 702375908 17599225644165 17599225601376 17599225965696 17599225967437
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 305 223519 223519 4194304 256 0 0 12 24 134912 0x7f1ce60edd80 0x7f1ce58258c0 161133 161133 14947 1289072 65536 99668799 1191612 0 400406652 17599226015586 17599225965696 17599226278336 17599226280129
105 103 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 308 223519 223519 4194304 256 0 0 12 24 136896 0x7f1ce60edc00 0x7f1ce5825900 296613 296613 19851 2372912 65536 211958812 2274899 0 849585212 17599226320258 17599226278336 17599226674976 17599226676669
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 311 223519 223519 4194304 256 0 0 12 24 138880 0x7f1ce60eda80 0x7f1ce5825940 296549 296549 20612 2372400 65536 215890509 2271918 0 865297144 17599226716468 17599226674976 17599227064736 17599227066609
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 314 223519 223519 4194304 256 0 0 12 24 140864 0x7f1ce60ed900 0x7f1ce5825980 177585 177585 16300 1420688 65536 111061850 1320744 0 445990508 17599227106748 17599227064736 17599227379776 17599227381681
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 317 223519 223519 4194304 256 0 0 12 24 143616 0x7f1ce60ed780 0x7f1ce58259c0 279463 279463 22603 2235712 65536 197343747 2128046 0 791123128 17599227421940 17599227379776 17599227754656 17599227756442
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 320 223519 223519 4194304 256 0 0 12 24 145344 0x7f1ce60ed600 0x7f1ce5825a00 161081 161081 15306 1288656 65536 99456610 1190651 0 399561276 17599227807350 17599227754656 17599228061216 17599228063134
110 108 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 323 223519 223519 4194304 256 0 0 12 24 147584 0x7f1ce8890480 0x7f1ce5825a40 296477 296477 21328 2371824 65536 210194267 2268497 0 842536848 17599228103923 17599228061216 17599228449377 17599228451204
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 326 223519 223519 4194304 256 0 0 12 24 149568 0x7f1ce8890300 0x7f1ce5825a80 295165 295165 20099 2361328 65536 201808227 2257080 0 808969600 17599228491953 17599228449377 17599228839137 17599228841014
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 329 223519 223519 4194304 256 0 0 12 24 151552 0x7f1ce8890180 0x7f1ce5825ac0 186107 186107 16970 1488864 65536 111191723 1383831 0 446514828 17599228881633 17599228839137 17599229164257 17599229166026
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 332 223519 223519 4194304 256 0 0 12 24 154304 0x7f1ce8890000 0x7f1ce5825b00 298821 298821 22956 2390576 65536 206564441 2285325 0 828009164 17599229206785 17599229164257 17599229559937 17599229561796
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 335 223519 223519 4194304 256 0 0 12 24 156288 0x7f1ce60ede80 0x7f1ce5825b40 170807 170807 16146 1366464 65536 109618243 1269968 0 440209784 17599229610025 17599229559937 17599229873537 17599229875448
115 113 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 338 223519 223519 4194304 256 0 0 12 24 158784 0x7f1ce60edd00 0x7f1ce5825b80 297260 297260 19673 2378088 65536 197640121 2268866 0 792318656 17599229916137 17599229873537 17599230277377 17599230279218
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 341 223519 223519 4194304 256 0 0 12 24 161024 0x7f1ce60edb80 0x7f1ce5825bc0 296572 296572 19642 2372584 65536 194914504 2267424 0 781405500 17599230321996 17599230277377 17599230673697 17599230675577
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 344 223519 223519 4194304 256 0 0 12 24 163264 0x7f1ce60eda00 0x7f1ce5825c00 204886 204886 17647 1639096 65536 129298815 1534522 0 518943612 17599230716236 17599230673697 17599231008737 17599231010679
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 347 223519 223519 4194304 256 0 0 12 24 166528 0x7f1ce60ed880 0x7f1ce5825c40 339686 339686 25283 2717496 65536 242270464 2610005 0 970841356 17599231050558 17599231008737 17599231425377 17599231471227
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 350 223519 223519 4194304 256 0 0 12 24 168512 0x7f1ce60ed700 0x7f1ce5825c80 185664 185664 17222 1485320 65536 99311144 1372031 0 398988988 17599231490727 17599231425377 17599231779778 17599231781749
120 118 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 353 223519 223519 4194304 256 0 0 12 24 171264 0x7f1ce8890580 0x7f1ce5825cc0 297130 297130 19433 2377048 65536 168980440 2248208 0 677690108 17599231823418 17599231779778 17599232174178 17599232175999
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 356 223519 223519 4194304 256 0 0 12 24 173760 0x7f1ce8890400 0x7f1ce5825d00 297218 297218 19703 2377752 65536 185841999 2256938 0 745121804 17599232217538 17599232174178 17599232566018 17599232567829
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 359 223519 223519 4194304 256 0 0 12 24 176256 0x7f1ce8890280 0x7f1ce5825d40 224070 224070 19255 1792568 65536 154540594 1688496 0 619907912 17599232608188 17599232566018 17599232912098 17599232914040
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 362 223519 223519 4194304 256 0 0 12 24 179776 0x7f1ce8890100 0x7f1ce5825d80 379408 379408 27524 3035272 65536 280912538 2929123 0 1125410688 17599232955209 17599232912098 17599233355938 17599233375539
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 365 223519 223519 4194304 256 0 0 12 24 182272 0x7f1ce60edf80 0x7f1ce5825dc0 210274 210274 18456 1682200 65536 134166152 1577796 0 538415380 17599233406918 17599233355938 17599233698658 17599233700550
125 123 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 368 223519 223519 4194304 256 0 0 12 24 185536 0x7f1ce60ede00 0x7f1ce5825e00 305566 305566 22879 2444536 65536 187311519 2330912 0 751005704 17599233741359 17599233698658 17599234099938 17599234122930
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 371 223519 223519 4194304 256 0 0 12 24 188544 0x7f1ce60edc80 0x7f1ce5825e40 311488 311488 20664 2491912 65536 175379827 2359463 0 703290192 17599234141379 17599234099938 17599234521698 17599234542609
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 374 223519 223519 4194304 256 0 0 12 24 191552 0x7f1ce60edb00 0x7f1ce5825e80 265298 265298 21716 2122392 65536 189167497 2016701 0 758434840 17599234564818 17599234521698 17599234894818 17599234896660
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 377 223519 223519 4194304 256 0 0 12 24 195840 0x7f1ce60ed980 0x7f1ce5825ec0 460424 460424 31007 3683400 65536 345057397 3579176 0 1381993856 17599234937179 17599234894818 17599235386979 17599235407387
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 380 223519 223519 4194304 256 0 0 12 24 198592 0x7f1ce60ed800 0x7f1ce5825f00 243092 243092 20413 1944744 65536 159122048 1834807 0 638237984 17599235437666 17599235386979 17599235748579 17599235750578
130 128 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 383 223519 223519 4194304 256 0 0 12 24 202368 0x7f1ce60ed680 0x7f1ce5825f40 335827 335827 22384 2686624 65536 210448050 2567232 0 843565464 17599235791957 17599235748579 17599236170179 17599236187327
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 386 223519 223519 4194304 256 0 0 12 24 205888 0x7f1ce8890500 0x7f1ce5825f80 331346 331346 22209 2650776 65536 198664952 2529289 0 796429876 17599236212287 17599236170179 17599236590339 17599236607707
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 389 223519 223519 4194304 256 0 0 12 24 209408 0x7f1ce8890380 0x7f1ce5825fc0 305461 305461 22903 2443696 65536 221925267 2342350 0 889461912 17599236633026 17599236590339 17599236995139 17599236996897
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 392 223519 223519 4194304 256 0 0 12 24 214464 0x7f1ce8890200 0x7f1ce5826000 541098 541098 35284 4328792 65536 409061131 4223430 0 1638009952 17599237038946 17599236995139 17599237539139 17599237556653
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 395 223519 223519 4194304 256 0 0 12 24 217728 0x7f1ce8890080 0x7f1ce5826040 272959 272959 21652 2183680 65536 178872300 2075612 0 717253708 17599237590162 17599237539139 17599237917699 17599237919603
135 133 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 398 223519 223519 4194304 256 0 0 12 24 222016 0x7f1ce60edf00 0x7f1ce5826080 364250 364250 25231 2914008 65536 239595938 2797370 0 960166628 17599237960842 17599237917699 17599238367779 17599238389651
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 401 223519 223519 4194304 256 0 0 12 24 226048 0x7f1ce60edd80 0x7f1ce58260c0 361051 361051 27014 2888416 65536 250347820 2778101 0 1003159244 17599238410891 17599238367779 17599238811939 17599238830550
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 404 223519 223519 4194304 256 0 0 12 24 230080 0x7f1ce60edc00 0x7f1ce5826100 346530 346530 25136 2772248 65536 244408330 2664140 0 979393744 17599238853770 17599238811939 17599239233540 17599239275419
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 407 223519 223519 4194304 256 0 0 12 24 235904 0x7f1ce60eda80 0x7f1ce5826140 623342 623342 39540 4986744 65536 471218885 4874374 0 1886645808 17599239286438 17599239233540 17599239849060 17599239890713
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 410 223519 223519 4194304 256 0 0 12 24 239424 0x7f1ce60ed900 0x7f1ce5826180 302245 302245 22652 2417968 65536 211097802 2315171 0 846156844 17599239909623 17599239849060 17599240271140 17599240272963
140 138 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 413 223519 223519 4194304 256 0 0 12 24 244224 0x7f1ce60ed780 0x7f1ce58261c0 398016 398016 27369 3184136 65536 275015593 3079684 0 1101844828 17599240314332 17599240271140 17599240730980 17599240773121
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 416 223519 223519 4194304 256 0 0 12 24 248768 0x7f1ce60ed600 0x7f1ce5826200 390013 390013 27492 3120112 65536 291609356 3017706 0 1168212064 17599240783620 17599240730980 17599241209380 17599241250958
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 419 223519 223519 4194304 256 0 0 12 24 253312 0x7f1ce8890480 0x7f1ce5826240 387234 387234 27184 3097880 65536 282987002 2990575 0 1133715156 17599241261508 17599241209380 17599241679140 17599241696477
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 422 223519 223519 4194304 256 0 0 8 24 255552 0x7f1ce8890300 0x7f1ce5826280 717821 717821 44413 5742576 65536 546838363 5632697 0 2189093020 17599241722076 17599241679140 17599242343780 17599242387169
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 425 223519 223519 4194304 256 0 0 12 24 259840 0x7f1ce8890180 0x7f1ce58262c0 364617 364617 26978 2916944 65536 260693479 2797452 0 1044537040 17599242407419 17599242343780 17599242803461 17599242846368
145 143 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 428 223519 223519 4194304 256 0 0 12 24 265664 0x7f1ce8890000 0x7f1ce5826300 469179 469179 31717 3753440 65536 353955504 3646651 0 1417608640 17599242858207 17599242803461 17599243334021 17599243375194
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 431 223519 223519 4194304 256 0 0 12 24 271232 0x7f1ce60ede80 0x7f1ce5826340 471620 471620 31455 3772968 65536 345981677 3668790 0 1385710812 17599243386094 17599243334021 17599243868101 17599243909021
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 434 223519 223519 4194304 256 0 0 8 24 273216 0x7f1ce60edd00 0x7f1ce5826380 482209 482209 32420 3857680 65536 354559889 3749819 0 1419981536 17599243920091 17599243868101 17599244393061 17599244434278
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 437 223519 223519 4194304 256 0 0 8 24 275712 0x7f1ce60edb80 0x7f1ce58263c0 880176 880176 52084 7041416 65536 681498431 6923810 0 2727736368 17599244445347 17599244393061 17599245177381 17599245219388
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 440 223519 223519 4194304 256 0 0 12 24 280768 0x7f1ce60eda00 0x7f1ce5826400 425683 425683 29165 3405472 65536 316443620 3299976 0 1267551264 17599245239757 17599245177381 17599245674661 17599245715875
150 148 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 443 223519 223519 4194304 256 0 0 12 24 287616 0x7f1ce60ed880 0x7f1ce5826440 548412 548412 35509 4387304 65536 413610552 4276643 0 1656223928 17599245726375 17599245674661 17599246252902 17599246298150
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 446 223519 223519 4194304 256 0 0 12 24 294208 0x7f1ce60ed700 0x7f1ce5826480 552445 552445 36131 4419568 65536 417015369 4310800 0 1669847868 17599246309380 17599246252902 17599246841702 17599246885505
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 449 223519 223519 4194304 256 0 0 8 24 296960 0x7f1ce8890580 0x7f1ce58264c0 563006 563006 36733 4504056 65536 424308773 4389098 0 1698977668 17599246896825 17599246841702 17599247423782 17599247465411
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 452 223519 223519 4194304 256 0 0 8 24 299968 0x7f1ce8890400 0x7f1ce5826500 1040093 1040093 60372 8320752 65536 810548879 8216909 0 3243938040 17599247476150 17599247423782 17599248319942 17599248366608
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 455 223519 223519 4194304 256 0 0 8 24 302720 0x7f1ce8890280 0x7f1ce5826540 721316 721316 43820 5770536 65536 547642350 5655562 0 2192311268 17599248385817 17599248320010 17599249006890 17599249054840
155 153 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 458 223519 223519 4194304 256 0 0 12 24 305472 0x7f1ce8890100 0x7f1ce5826580 723963 723963 44643 5791712 65536 552976262 5675103 0 2213647452 17599249066990 17599249006890 17599249730090 17599249773812
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 461 223519 223519 4194304 256 0 0 12 24 308224 0x7f1ce60edf80 0x7f1ce58265c0 722060 722060 44378 5776488 65536 542615241 5659951 0 2172201896 17599249785422 17599249730090 17599250439850 17599250485594
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 464 223519 223519 4194304 256 0 0 8 24 310976 0x7f1ce60ede00 0x7f1ce5826600 726898 726898 45383 5815192 65536 561271847 5695667 0 2246829592 17599250497754 17599250439850 17599251146250 17599251191836
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 467 223519 223519 4194304 256 0 0 8 24 313216 0x7f1ce60edc80 0x7f1ce5826640 1366597 1366597 77082 10932784 65536 1065672643 10816229 0 4264431668 17599251202856 17599251146250 17599252263051 17599252307888
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 470 223519 223519 4194304 256 0 0 8 24 315968 0x7f1ce60edb00 0x7f1ce5826680 1372024 1372024 77782 10976200 65536 1078387006 10851064 0 4315289956 17599252326697 17599252263051 17599253373931 17599253438249
160 158 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 473 223519 223519 4194304 256 0 0 12 24 318720 0x7f1ce60ed980 0x7f1ce58266c0 1371247 1371247 77518 10969984 65536 1075762186 10855352 0 4304789940 17599253449938 17599253373931 17599254525932 17599254595319
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 476 223519 223519 4194304 256 0 0 12 24 321472 0x7f1ce60ed800 0x7f1ce5826700 1372553 1372553 77477 10980432 65536 1073980519 10850584 0 4297662720 17599254607839 17599254525932 17599255686252 17599255751820
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 479 223519 223519 4194304 256 0 0 8 24 324224 0x7f1ce60ed680 0x7f1ce5826740 1374673 1374673 77106 10997392 65536 1076734019 10880624 0 4308678552 17599255763570 17599255686252 17599256816973 17599256888421
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 482 223519 223519 4194304 256 0 0 8 24 326464 0x7f1ce8890500 0x7f1ce5826780 2664917 2664917 143141 21319344 65536 2130988346 21187794 0 8525694980 17599256899991 17599256816973 17599258795214 17599258866681
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 485 223519 223519 4194304 256 0 0 8 24 329216 0x7f1ce8890380 0x7f1ce58267c0 2666982 2666982 142454 21335864 65536 2131372878 21221592 0 8527232704 17599258887370 17599258795214 17599260740654 17599260807081
165 163 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 488 223519 223519 4194304 256 0 0 12 24 331968 0x7f1ce8890200 0x7f1ce5826800 2671177 2671177 143385 21369424 65536 2133795562 21240229 0 8536923260 17599260818851 17599260740654 17599262739695 17599262809690
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 491 223519 223519 4194304 256 0 0 12 24 334720 0x7f1ce8890080 0x7f1ce5826840 2667766 2667766 142943 21342136 65536 2126319326 21225480 0 8507017148 17599262822020 17599262739695 17599264745136 17599264813360
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 494 223519 223519 4194304 256 0 0 8 24 337472 0x7f1ce60edf00 0x7f1ce5826880 2672975 2672975 142959 21383808 65536 2135790377 21263256 0 8544903336 17599264824699 17599264745136 17599266696017 17599266764750
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 497 223519 223519 4194304 256 0 0 8 24 0 0x7f1ce60edd80 0x7f1ce58268c0 5255554 5255554 272964 42044440 65536 4232756362 41926604 0 16932766864 17599266776960 17599266696017 17599270334258 17599270406228
@@ -0,0 +1,5 @@
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,21 @@
pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES SQ_BUSY_CU_CYCLES SQ_WAVE_CYCLES SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ SQC_TC_DATA_WRITE_REQ GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_SH_FIFO_BUSY_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum
pmc: SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES SQC_ICACHE_MISSES_DUPLICATE GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_SH_FIFO_CMD_BUSY_sum TA_SH_FIFO_ADDR_BUSY_sum TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum
pmc: SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE SQC_DCACHE_REQ_READ_1 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_SH_FIFO_DATA_BUSY_sum TA_SH_FIFO_DATA_SFIFO_BUSY_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum
pmc: SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU SQ_INSTS_VSKIPPED TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_SH_FIFO_DATA_TFIFO_BUSY_sum TA_SQ_TA_CMD_CYCLES_sum TD_COALESCABLE_WAVEFRONT_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum
pmc: SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 SQ_INSTS_VALU_MUL_F32 TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_SP_TA_ADDR_CYCLES_sum TA_SP_TA_DATA_CYCLES_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_STALL_sum
pmc: SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 SQ_INSTS_VALU_INT64 TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_SH_FIFO_ADDR_STARVED_WHILE_BUSY_CYCLES_sum TA_SH_FIFO_CMD_STARVED_WHILE_BUSY_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_IO_CREDIT_STALL_sum TCC_EA_WRREQ_GMI_CREDIT_STALL_sum TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum
pmc: SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG SQ_WAIT_ANY TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_SH_FIFO_DATA_STARVED_WHILE_BUSY_CYCLES_sum TA_TA_SH_FIFO_STARVED_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_ATOMIC_sum TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum
pmc: SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_BUFFER_WAVEFRONTS_sum TA_BUFFER_READ_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_EA_RDREQ_IO_CREDIT_STALL_sum TCC_EA_RDREQ_GMI_CREDIT_STALL_sum TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum TCC_TAG_STALL_sum
pmc: SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum
pmc: SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum TA_BUFFER_TOTAL_CYCLES_sum TA_BUFFER_COALESCABLE_WAVEFRONTS_sum TCC_EA_RDREQ_DRAM_sum TCC_EA_WRREQ_DRAM_sum TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum
pmc: SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TCC_EA_ATOMIC_LEVEL_sum
pmc: SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES SQ_INSTS_FLAT_LDS_ONLY SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31]
pmc: SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31]
pmc: TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31]
pmc: TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31]
pmc: TA_FLAT_COALESCEABLE_WAVEFRONTS_sum TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31]
pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31]
gpu:
range:
kernel:
@@ -0,0 +1,168 @@
Dispatch_ID,Kernel_Name,GPU_ID
0,__amd_rocclr_fillBufferAligned.kd,0
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0
1 Dispatch_ID Kernel_Name GPU_ID
2 0 __amd_rocclr_fillBufferAligned.kd 0
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0
5 3 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0
10 8 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0
15 13 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0
20 18 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0
25 23 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0
30 28 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0
35 33 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0
40 38 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0
45 43 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0
50 48 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0
55 53 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0
60 58 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0
65 63 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0
70 68 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0
75 73 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0
80 78 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0
85 83 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0
90 88 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0
95 93 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0
100 98 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0
105 103 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0
110 108 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0
115 113 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0
120 118 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0
125 123 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0
130 128 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0
135 133 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0
140 138 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0
145 143 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0
150 148 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0
155 153 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0
160 158 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0
165 163 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0
File diff suppressed because one or more lines are too long
@@ -0,0 +1,11 @@
Kernel_Name,Count,Sum(ns),Mean(ns),Median(ns),Pct
"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",1,3359203.0,3359203.0,3359203.0,7.843408332395092
"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",1,1724962.0,1724962.0,1724962.0,4.027616468509019
"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",1,1716642.0,1716642.0,1716642.0,4.008190087511643
"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",1,1698242.0,1698242.0,1698242.0,3.965227898767448
"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",1,1673761.0,1673761.0,1673761.0,3.908067173623607
"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",1,1664961.0,1664961.0,1664961.0,3.8875200398763834
"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",1,886081.0,886081.0,886081.0,2.0689119111220653
"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",1,879680.0,879680.0,879680.0,2.053966206222522
"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",1,869921.0,869921.0,869921.0,2.031179901877163
"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",1,860001.0,860001.0,860001.0,2.008017678380292
1 Kernel_Name Count Sum(ns) Mean(ns) Median(ns) Pct
2 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 1 3359203.0 3359203.0 3359203.0 7.843408332395092
3 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 1 1724962.0 1724962.0 1724962.0 4.027616468509019
4 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 1 1716642.0 1716642.0 1716642.0 4.008190087511643
5 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 1 1698242.0 1698242.0 1698242.0 3.965227898767448
6 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 1 1673761.0 1673761.0 1673761.0 3.908067173623607
7 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 1 1664961.0 1664961.0 1664961.0 3.8875200398763834
8 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 1 886081.0 886081.0 886081.0 2.0689119111220653
9 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 1 879680.0 879680.0 879680.0 2.053966206222522
10 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 1 869921.0 869921.0 869921.0 2.031179901877163
11 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 1 860001.0 860001.0 860001.0 2.008017678380292
@@ -0,0 +1,9 @@
Metric,Count,Unit
VALU - Vector,494.8622754491018,Instr per wave
VMEM,7.958083832335329,Instr per wave
LDS_Per_Workgroup,0.0,Instr per wave
VALU - MFMA,0.0,Instr per wave
SALU,24.520958083832337,Instr per wave
SMEM,1.8023952095808384,Instr per wave
Branch,10.179640718562874,Instr per wave
GDS,0.0,Instr per wave
1 Metric Count Unit
2 VALU - Vector 494.8622754491018 Instr per wave
3 VMEM 7.958083832335329 Instr per wave
4 LDS_Per_Workgroup 0.0 Instr per wave
5 VALU - MFMA 0.0 Instr per wave
6 SALU 24.520958083832337 Instr per wave
7 SMEM 1.8023952095808384 Instr per wave
8 Branch 10.179640718562874 Instr per wave
9 GDS 0.0 Instr per wave
@@ -0,0 +1,16 @@
Metric,Count,Unit
INT32,176.1556886227545,Instr per wave
INT64,6.970059880239521,Instr per wave
F16-ADD,0.0,Instr per wave
F16-MUL,0.0,Instr per wave
F16-FMA,76.33532934131736,Instr per wave
F16-Trans,0.0,Instr per wave
F32-ADD,0.0,Instr per wave
F32-MUL,0.0,Instr per wave
F32-FMA,144.51497005988023,Instr per wave
F32-Trans,0.0,Instr per wave
F64-ADD,0.0,Instr per wave
F64-MUL,0.0,Instr per wave
F64-FMA,76.33532934131736,Instr per wave
F64-Trans,0.0,Instr per wave
Conversion,0.0,Instr per wave
1 Metric Count Unit
2 INT32 176.1556886227545 Instr per wave
3 INT64 6.970059880239521 Instr per wave
4 F16-ADD 0.0 Instr per wave
5 F16-MUL 0.0 Instr per wave
6 F16-FMA 76.33532934131736 Instr per wave
7 F16-Trans 0.0 Instr per wave
8 F32-ADD 0.0 Instr per wave
9 F32-MUL 0.0 Instr per wave
10 F32-FMA 144.51497005988023 Instr per wave
11 F32-Trans 0.0 Instr per wave
12 F64-ADD 0.0 Instr per wave
13 F64-MUL 0.0 Instr per wave
14 F64-FMA 76.33532934131736 Instr per wave
15 F64-Trans 0.0 Instr per wave
16 Conversion 0.0 Instr per wave
@@ -0,0 +1,9 @@
type,Count
Buffer Instr,0.0
Buffer Read,0.0
Buffer Write,0.0
Buffer Atomic,0.0
Flat Instr,7.958083832335329
Flat Read,7.952095808383233
Flat Write,0.005988023952095809
Flat Atomic,0.0
1 type Count
2 Buffer Instr 0.0
3 Buffer Read 0.0
4 Buffer Write 0.0
5 Buffer Atomic 0.0
6 Flat Instr 7.958083832335329
7 Flat Read 7.952095808383233
8 Flat Write 0.005988023952095809
9 Flat Atomic 0.0
@@ -0,0 +1,6 @@
type,Count
MFMA-I8,0.0
MFMA-F16,0.0
MFMA-BF16,0.0
MFMA-F32,0.0
MFMA-F64,0.0
1 type Count
2 MFMA-I8 0.0
3 MFMA-F16 0.0
4 MFMA-BF16 0.0
5 MFMA-F32 0.0
6 MFMA-F64 0.0
@@ -0,0 +1,26 @@
Info
dev0
06fa5f860366
AMD EPYC 7282 16-Core Processor
Ubuntu 20.04.5 LTS
5.11.0-27-generic
5.1.3-66
Wed Sep 28 20:46:37 2022 ()
gfx90a
8
104
4
64
32
1024
16
8192
1700
1600
800
1600
32
mi200
56
1638.4
roofline|SQ|LDS_Per_Workgroup|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF
1 Info
2 dev0
3 06fa5f860366
4 AMD EPYC 7282 16-Core Processor
5 Ubuntu 20.04.5 LTS
6 5.11.0-27-generic
7 5.1.3-66
8 Wed Sep 28 20:46:37 2022 ()
9 gfx90a
10 8
11 104
12 4
13 64
14 32
15 1024
16 16
17 8192
18 1700
19 1600
20 800
21 1600
22 32
23 mi200
24 56
25 1638.4
26 roofline|SQ|LDS_Per_Workgroup|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF
@@ -0,0 +1,7 @@
Metric,Value
valu_flops_pop,32.87868139621284
mfma_flops_bf16_pop,0.0
mfma_flops_f16_pop,0.0
mfma_flops_f32_pop,0.0
mfma_flops_f64_pop,0.0
mfma_flops_i8_pop,0.0
1 Metric Value
2 valu_flops_pop 32.87868139621284
3 mfma_flops_bf16_pop 0.0
4 mfma_flops_f16_pop 0.0
5 mfma_flops_f32_pop 0.0
6 mfma_flops_f64_pop 0.0
7 mfma_flops_i8_pop 0.0
@@ -0,0 +1,8 @@
Metric,Avg,Min,Max,Unit
IPC (Avg),0.7030847627757917,0.02512191895962488,1.1584979112383216,Instr/cycle
IPC (Issue),1.0,1.0,1.0,Instr/cycle
SALU Util,2.624359244978694,0.0300105271302199,27.370297176988647,Pct
VALU Util,58.32499961405379,0.7652684418206074,98.96924068419204,Pct
VALU Active Threads,64.0,64.0,64.0,Threads
MFMA Util,0.0,0.0,0.0,Pct
MFMA Instr Cycles,,,,Cycles/instr
1 Metric Avg Min Max Unit
2 IPC (Avg) 0.7030847627757917 0.02512191895962488 1.1584979112383216 Instr/cycle
3 IPC (Issue) 1.0 1.0 1.0 Instr/cycle
4 SALU Util 2.624359244978694 0.0300105271302199 27.370297176988647 Pct
5 VALU Util 58.32499961405379 0.7652684418206074 98.96924068419204 Pct
6 VALU Active Threads 64.0 64.0 64.0 Threads
7 MFMA Util 0.0 0.0 0.0 Pct
8 MFMA Instr Cycles Cycles/instr
@@ -0,0 +1,7 @@
Metric,Avg,Min,Max,Unit
FLOPs (Total),38039.760479041914,0.0,524800.0,Ops per wave
INT8 OPs,0.0,0.0,0.0,Ops per wave
F16 OPs,9770.922155688622,0.0,524800.0,Ops per wave
BF16 OPs,0.0,0.0,0.0,Ops per wave
F32 OPs,18497.91616766467,0.0,524800.0,Ops per wave
F64 OPs,9770.922155688622,0.0,524800.0,Ops per wave
1 Metric Avg Min Max Unit
2 FLOPs (Total) 38039.760479041914 0.0 524800.0 Ops per wave
3 INT8 OPs 0.0 0.0 0.0 Ops per wave
4 F16 OPs 9770.922155688622 0.0 524800.0 Ops per wave
5 BF16 OPs 0.0 0.0 0.0 Ops per wave
6 F32 OPs 18497.91616766467 0.0 524800.0 Ops per wave
7 F64 OPs 9770.922155688622 0.0 524800.0 Ops per wave
@@ -0,0 +1,5 @@
Metric,Value
Utilization,0.0
Access Rate,0.0
Bandwith (Pct-of-Peak),0.0
Bank Conflict Rate,
1 Metric Value
2 Utilization 0.0
3 Access Rate 0.0
4 Bandwith (Pct-of-Peak) 0.0
5 Bank Conflict Rate
@@ -0,0 +1,12 @@
Metric,Avg,Min,Max,Unit
Wave Cycles,18379.615702235056,1876.4345169067383,258464.3599243164,Cycles/wave
LDS_Per_Workgroup Instrs,0.0,0.0,0.0,Instr per wave
Bandwidth,0.0,0.0,0.0,Bytes per wave
Bank Conficts/Access,,,,Conflicts/access
Dispatch_ID Accesses,0.0,0.0,0.0,Cycles per wave
Atomic Cycles,0.0,0.0,0.0,Cycles per wave
Bank Conflict,0.0,0.0,0.0,Cycles per wave
Addr Conflict,0.0,0.0,0.0,Cycles per wave
Unaligned Stall,0.0,0.0,0.0,Cycles per wave
Mem Violations,0.0,0.0,0.0, per wave
LDS_Per_Workgroup Latency,,,,Cycles
1 Metric Avg Min Max Unit
2 Wave Cycles 18379.615702235056 1876.4345169067383 258464.3599243164 Cycles/wave
3 LDS_Per_Workgroup Instrs 0.0 0.0 0.0 Instr per wave
4 Bandwidth 0.0 0.0 0.0 Bytes per wave
5 Bank Conficts/Access Conflicts/access
6 Dispatch_ID Accesses 0.0 0.0 0.0 Cycles per wave
7 Atomic Cycles 0.0 0.0 0.0 Cycles per wave
8 Bank Conflict 0.0 0.0 0.0 Cycles per wave
9 Addr Conflict 0.0 0.0 0.0 Cycles per wave
10 Unaligned Stall 0.0 0.0 0.0 Cycles per wave
11 Mem Violations 0.0 0.0 0.0 per wave
12 LDS_Per_Workgroup Latency Cycles
@@ -0,0 +1,3 @@
Metric,Value
Bandwidth,27.4627002570144
Cache Hit,99.55386551200166
1 Metric Value
2 Bandwidth 27.4627002570144
3 Cache Hit 99.55386551200166
@@ -0,0 +1,6 @@
Metric,Mean,Min,Max,Unit
Req,127.76646706586827,9.0,1835.0,Req per wave
Hits,127.52990574180009,8.993144989013672,1834.900375366211,Hits per wave
Misses - Non Duplicated,0.0017641718516092815,0.0,0.109375,Misses per wave
Misses - Duplicated,0.23479715221656297,0.006641387939453125,3.962890625,Misses per wave
Cache Hit,99.55386551200166,74.54833984375,99.99457086464365,Pct
1 Metric Mean Min Max Unit
2 Req 127.76646706586827 9.0 1835.0 Req per wave
3 Hits 127.52990574180009 8.993144989013672 1834.900375366211 Hits per wave
4 Misses - Non Duplicated 0.0017641718516092815 0.0 0.109375 Misses per wave
5 Misses - Duplicated 0.23479715221656297 0.006641387939453125 3.962890625 Misses per wave
6 Cache Hit 99.55386551200166 74.54833984375 99.99457086464365 Pct
@@ -0,0 +1,3 @@
Metric,Value
Bandwidth,0.9358654354030301
Cache Hit,97.79805084698418
1 Metric Value
2 Bandwidth 0.9358654354030301
3 Cache Hit 97.79805084698418
@@ -0,0 +1,13 @@
Metric,Mean,Min,Max,Unit
Req,1.8023952095808384,1.0,7.0,Req per wave
Hits,1.7701580367402403,0.0,6.987119674682617,Req per wave
Misses - Non Duplicated,0.001501757227732036,0.00042724609375,0.109375,Req per wave
Misses- Duplicated,0.030735415612866065,0.012453079223632812,0.890625,Req per wave
Cache Hit,97.79805084698418,0.0,99.81599535260882,Pct
Read Req (Total),1.8023952095808384,1.0,7.0,Req per wave
Atomic Req,0.0,0.0,0.0,Req per wave
Read Req (1 DWord),0.5868263473053892,0.0,2.0,Req per wave
Read Req (2 DWord),1.0059880239520957,0.0,2.0,Req per wave
Read Req (4 DWord),0.20359281437125748,0.0,2.0,Req per wave
Read Req (8 DWord),0.005988023952095809,0.0,1.0,Req per wave
Read Req (16 DWord),0.0,0.0,0.0,Req per wave
1 Metric Mean Min Max Unit
2 Req 1.8023952095808384 1.0 7.0 Req per wave
3 Hits 1.7701580367402403 0.0 6.987119674682617 Req per wave
4 Misses - Non Duplicated 0.001501757227732036 0.00042724609375 0.109375 Req per wave
5 Misses- Duplicated 0.030735415612866065 0.012453079223632812 0.890625 Req per wave
6 Cache Hit 97.79805084698418 0.0 99.81599535260882 Pct
7 Read Req (Total) 1.8023952095808384 1.0 7.0 Req per wave
8 Atomic Req 0.0 0.0 0.0 Req per wave
9 Read Req (1 DWord) 0.5868263473053892 0.0 2.0 Req per wave
10 Read Req (2 DWord) 1.0059880239520957 0.0 2.0 Req per wave
11 Read Req (4 DWord) 0.20359281437125748 0.0 2.0 Req per wave
12 Read Req (8 DWord) 0.005988023952095809 0.0 1.0 Req per wave
13 Read Req (16 DWord) 0.0 0.0 0.0 Req per wave
@@ -0,0 +1,5 @@
Metric,Mean,Min,Max,Unit
Read Req,0.001501757227732036,0.00042724609375,0.109375,Req per wave
Write Req,0.0,0.0,0.0,Req per wave
Atomic Req,0.0,0.0,0.0,Req per wave
Stall,0.0,0.0,0.0,Cycles per wave
1 Metric Mean Min Max Unit
2 Read Req 0.001501757227732036 0.00042724609375 0.109375 Req per wave
3 Write Req 0.0 0.0 0.0 Req per wave
4 Atomic Req 0.0 0.0 0.0 Req per wave
5 Stall 0.0 0.0 0.0 Cycles per wave
@@ -0,0 +1,17 @@
Metric,Avg,Min,Max,Unit
TA Busy,60.399690205616444,1.0715575229123342,91.38036867456296,Pct
TC2TA Addr Stall,42.20650348979206,0.02892741913162767,74.3471622555892,Pct
TC2TA Data Stall,0.32589882608956333,0.0,54.425103956957074,Pct
TD2TA Addr Stall,0.0,0.0,0.0,Pct
Total Instructions,7.958083832335329,1.0,8.0,Instr per wave
Flat Instr,7.958083832335329,1.0,8.0,Instr per wave
Flat Read Instr,7.952095808383233,0.0,8.0,Instr per wave
Flat Write Instr,0.005988023952095809,0.0,1.0,Instr per wave
Flat Atomic Instr,0.0,0.0,0.0,Instr per wave
Buffer Instr,0.0,0.0,0.0,Instr per wave
Buffer Read Instr,0.0,0.0,0.0,Instr per wave
Buffer Write Instr,0.0,0.0,0.0,Instr per wave
Buffer Atomic Instr,0.0,0.0,0.0,Instr per wave
Buffer Total Cylces,0.0,0.0,0.0,Cycles per wave
Buffer Coalesced Read,0.0,0.0,0.0,Cycles per wave
Buffer Coalesced Write,0.0,0.0,0.0,Cycles per wave
1 Metric Avg Min Max Unit
2 TA Busy 60.399690205616444 1.0715575229123342 91.38036867456296 Pct
3 TC2TA Addr Stall 42.20650348979206 0.02892741913162767 74.3471622555892 Pct
4 TC2TA Data Stall 0.32589882608956333 0.0 54.425103956957074 Pct
5 TD2TA Addr Stall 0.0 0.0 0.0 Pct
6 Total Instructions 7.958083832335329 1.0 8.0 Instr per wave
7 Flat Instr 7.958083832335329 1.0 8.0 Instr per wave
8 Flat Read Instr 7.952095808383233 0.0 8.0 Instr per wave
9 Flat Write Instr 0.005988023952095809 0.0 1.0 Instr per wave
10 Flat Atomic Instr 0.0 0.0 0.0 Instr per wave
11 Buffer Instr 0.0 0.0 0.0 Instr per wave
12 Buffer Read Instr 0.0 0.0 0.0 Instr per wave
13 Buffer Write Instr 0.0 0.0 0.0 Instr per wave
14 Buffer Atomic Instr 0.0 0.0 0.0 Instr per wave
15 Buffer Total Cylces 0.0 0.0 0.0 Cycles per wave
16 Buffer Coalesced Read 0.0 0.0 0.0 Cycles per wave
17 Buffer Coalesced Write 0.0 0.0 0.0 Cycles per wave
@@ -0,0 +1,8 @@
Metric,Avg,Min,Max,Unit
TD Busy,79.23573541285931,5.2054197136339235,95.43880336488618,Pct
TC2TD Stall,63.793725961756735,4.6553830210753615,94.04942750835623,Pct
SPI2TD Stall,0.007767319415803492,0.0,0.019392802672403283,Pct
Coalescable Instr,4.790419161676646,0.0,8.0,Instr per wave
Load Instr,7.952095808383233,0.0,8.0,Instr per wave
Store Instr,0.005988023952095809,0.0,1.0,Instr per wave
Atomic Instr,0.0,0.0,0.0,Instr per wave
1 Metric Avg Min Max Unit
2 TD Busy 79.23573541285931 5.2054197136339235 95.43880336488618 Pct
3 TC2TD Stall 63.793725961756735 4.6553830210753615 94.04942750835623 Pct
4 SPI2TD Stall 0.007767319415803492 0.0 0.019392802672403283 Pct
5 Coalescable Instr 4.790419161676646 0.0 8.0 Instr per wave
6 Load Instr 7.952095808383233 0.0 8.0 Instr per wave
7 Store Instr 0.005988023952095809 0.0 1.0 Instr per wave
8 Atomic Instr 0.0 0.0 0.0 Instr per wave
@@ -0,0 +1,5 @@
Metric,Value
Buffer Coalescing,69.91017964071857
Cache Util,83.85750580258185
Cache BW,3.784409539859472
Cache Hit,20.35928143712575
1 Metric Value
2 Buffer Coalescing 69.91017964071857
3 Cache Util 83.85750580258185
4 Cache BW 3.784409539859472
5 Cache Hit 20.35928143712575
@@ -0,0 +1,6 @@
Metric,Mean,Min,Max,unit
Stalled on L2 Data,68.4022027880778,9.030390438180966,90.86982768886857,Pct
Stalled on L2 Req,1.9697045667081599,0.0,10.857968990334536,Pct
Tag RAM Stall (Read),0.0,0.0,0.0,Pct
Tag RAM Stall (Write),0.0,0.0,0.0,Pct
Tag RAM Stall (Atomic),0.0,0.0,0.0,Pct
1 Metric Mean Min Max unit
2 Stalled on L2 Data 68.4022027880778 9.030390438180966 90.86982768886857 Pct
3 Stalled on L2 Req 1.9697045667081599 0.0 10.857968990334536 Pct
4 Tag RAM Stall (Read) 0.0 0.0 0.0 Pct
5 Tag RAM Stall (Write) 0.0 0.0 0.0 Pct
6 Tag RAM Stall (Atomic) 0.0 0.0 0.0 Pct
@@ -0,0 +1,15 @@
Metric,Avg,Min,Max,Unit
Total Req,279.377245508982,64.0,512.0,Req per wave
Read Req,278.9940119760479,0.0,512.0,Req per wave
Write Req,0.38323353293413176,0.0,64.0,Req per wave
Atomic Req,0.0,0.0,0.0,Req per wave
Cache Accesses,69.8443113772455,16.0,128.0,Req per wave
Cache Hits,25.437125748502993,0.0,64.0,Req per wave
Cache Hit Rate,20.35928143712575,0.0,50.0,Pct
Invalidate,0.0027854142788641466,0.0001983642578125,0.203125,Req per wave
L1-TCR Read,44.35928143712575,0.0,64.0,Req per wave
L1-L2 Write,0.04790419161676647,0.0,8.0,Req per wave
L1-L2 Atomic,0.0,0.0,0.0,Req per wave
L1 Access Latency,1210.918251460184,438.56812477111816,1802.9484405517578,Cycles
L1-L2 Read Latency,784.8365774800978,375.96087551116943,1149.3252959251404,Cycles
L1-L2 Write Latency,352.75868105888367,352.75868105888367,352.75868105888367,Cycles
1 Metric Avg Min Max Unit
2 Total Req 279.377245508982 64.0 512.0 Req per wave
3 Read Req 278.9940119760479 0.0 512.0 Req per wave
4 Write Req 0.38323353293413176 0.0 64.0 Req per wave
5 Atomic Req 0.0 0.0 0.0 Req per wave
6 Cache Accesses 69.8443113772455 16.0 128.0 Req per wave
7 Cache Hits 25.437125748502993 0.0 64.0 Req per wave
8 Cache Hit Rate 20.35928143712575 0.0 50.0 Pct
9 Invalidate 0.0027854142788641466 0.0001983642578125 0.203125 Req per wave
10 L1-TCR Read 44.35928143712575 0.0 64.0 Req per wave
11 L1-L2 Write 0.04790419161676647 0.0 8.0 Req per wave
12 L1-L2 Atomic 0.0 0.0 0.0 Req per wave
13 L1 Access Latency 1210.918251460184 438.56812477111816 1802.9484405517578 Cycles
14 L1-L2 Read Latency 784.8365774800978 375.96087551116943 1149.3252959251404 Cycles
15 L1-L2 Write Latency 352.75868105888367 352.75868105888367 352.75868105888367 Cycles
@@ -0,0 +1,13 @@
Xfer,Mean,Min,Max,Unit
NC - Read,0.0,0.0,0.0,Req per wave
UC - Read,0.0,0.0,0.0,Req per wave
CC - Read,0.0,0.0,0.0,Req per wave
RW - Read,44.35928143712575,0.0,64.0,Req per wave
RW - Write,0.04790419161676647,0.0,8.0,Req per wave
NC - Write,0.0,0.0,0.0,Req per wave
UC - Write,0.0,0.0,0.0,Req per wave
CC - Write,0.0,0.0,0.0,Req per wave
NC - Atomic,0.0,0.0,0.0,Req per wave
UC - Atomic,0.0,0.0,0.0,Req per wave
CC - Atomic,0.0,0.0,0.0,Req per wave
RW - Atomic,0.0,0.0,0.0,Req per wave
1 Xfer Mean Min Max Unit
2 NC - Read 0.0 0.0 0.0 Req per wave
3 UC - Read 0.0 0.0 0.0 Req per wave
4 CC - Read 0.0 0.0 0.0 Req per wave
5 RW - Read 44.35928143712575 0.0 64.0 Req per wave
6 RW - Write 0.04790419161676647 0.0 8.0 Req per wave
7 NC - Write 0.0 0.0 0.0 Req per wave
8 UC - Write 0.0 0.0 0.0 Req per wave
9 CC - Write 0.0 0.0 0.0 Req per wave
10 NC - Atomic 0.0 0.0 0.0 Req per wave
11 UC - Atomic 0.0 0.0 0.0 Req per wave
12 CC - Atomic 0.0 0.0 0.0 Req per wave
13 RW - Atomic 0.0 0.0 0.0 Req per wave
@@ -0,0 +1,6 @@
Metric,Mean,Min,Max,Units
Req,69.8443113772455,16.0,128.0, per wave
Hit Ratio,97.74965561792523,93.017578125,98.5198974609375,Pct
Hits,68.49731481860498,15.720703125,125.99867248535156, per wave
Misses (Translation),0.1389836294208458,0.025390625,0.203125, per wave
Misses (Permission),0.0,0.0,0.0, per wave
1 Metric Mean Min Max Units
2 Req 69.8443113772455 16.0 128.0 per wave
3 Hit Ratio 97.74965561792523 93.017578125 98.5198974609375 Pct
4 Hits 68.49731481860498 15.720703125 125.99867248535156 per wave
5 Misses (Translation) 0.1389836294208458 0.025390625 0.203125 per wave
6 Misses (Permission) 0.0 0.0 0.0 per wave
@@ -0,0 +1,5 @@
Metric,Value,Unit
L2 Util,90.82578501139209,Pct
Cache Hit,3.8646444062429084,Pct
L2-EA Rd BW,1157.9322572223164,Gb/s
L2-EA Wr BW,6.588450813230302,Gb/s
1 Metric Value Unit
2 L2 Util 90.82578501139209 Pct
3 Cache Hit 3.8646444062429084 Pct
4 L2-EA Rd BW 1157.9322572223164 Gb/s
5 L2-EA Wr BW 6.588450813230302 Gb/s
@@ -0,0 +1,16 @@
Metric,Avg,Min,Max,Unit
Read BW,2839.274968861106,0.0379638671875,4096.33984375,Bytes per wave
Write BW,3.0179640718562872,0.0,504.0,Bytes per wave
Read (32B),0.0,0.0,0.0,Req per wave
Read (Uncached 32B),0.007630102648706494,0.001155853271484375,0.2421875,Req per wave
Read (64B),44.36367138845478,0.0005931854248046875,64.00531005859375,Req per wave
HBM Read,44.36216690154846,0.000274658203125,64.00448608398438,Req per wave
Write (32B),0.0,0.0,0.0,Req per wave
Write (Uncached 32B),0.0,0.0,0.0,Req per wave
Write (64B),0.04715568862275449,0.0,7.875,Req per wave
HBM Write,0.04715568862275449,0.0,7.875,Req per wave
Read Latency,532.5202646536594,255.00738578848419,2023.2765273311898,Cycles
Write Latency,408.8238985576327,408.8238985576327,408.8238985576327,Cycles
Atomic Latency,,,,Cycles
Read Stall,5.4338306421939935,0.0,13.589164524396809,Pct
Write Stall,0.09555297262702563,0.0,15.95734642871328,Pct
1 Metric Avg Min Max Unit
2 Read BW 2839.274968861106 0.0379638671875 4096.33984375 Bytes per wave
3 Write BW 3.0179640718562872 0.0 504.0 Bytes per wave
4 Read (32B) 0.0 0.0 0.0 Req per wave
5 Read (Uncached 32B) 0.007630102648706494 0.001155853271484375 0.2421875 Req per wave
6 Read (64B) 44.36367138845478 0.0005931854248046875 64.00531005859375 Req per wave
7 HBM Read 44.36216690154846 0.000274658203125 64.00448608398438 Req per wave
8 Write (32B) 0.0 0.0 0.0 Req per wave
9 Write (Uncached 32B) 0.0 0.0 0.0 Req per wave
10 Write (64B) 0.04715568862275449 0.0 7.875 Req per wave
11 HBM Write 0.04715568862275449 0.0 7.875 Req per wave
12 Read Latency 532.5202646536594 255.00738578848419 2023.2765273311898 Cycles
13 Write Latency 408.8238985576327 408.8238985576327 408.8238985576327 Cycles
14 Atomic Latency Cycles
15 Read Stall 5.4338306421939935 0.0 13.589164524396809 Pct
16 Write Stall 0.09555297262702563 0.0 15.95734642871328 Pct
@@ -0,0 +1,19 @@
Metric,Avg,Min,Max,Unit
Req,23.469673545060758,8.00143051147461,36.424224853515625,Req per wave
Streaming Req,0.0,0.0,0.0,Req per wave
Read Req,23.40472572006865,0.00142669677734375,36.12065124511719,Req per wave
Write Req,0.04790419161676647,0.0,8.0,Req per wave
Atomic Req,0.0,0.0,0.0,Req per wave
Probe Req,0.0,0.0,0.0,Req per wave
Hits,1.2620279689035017,0.00592041015625,4.4204864501953125,Hits per wave
Misses,22.207645576157255,4.000587463378906,32.00492858886719,Misses per wave
Cache Hit,3.8646444062429084,0.036982424769836826,50.00159711889287,Pct
Writeback,0.024407792234135244,0.0004730224609375,3.9375057220458984, per wave
NC Req,6.395899607035928e-07,0.0,0.0001068115234375,Req per wave
UC Req,0.0037058527598124065,0.000576019287109375,0.115234375,Req per wave
CC Req,0.0,0.0,0.0,Req per wave
RW Req,23.478994129660602,8.000747680664062,36.23834228515625,Req per wave
Writeback (Normal),0.023577844311377244,0.0,3.9375, per wave
Writeback (TC Req),0.0,0.0,0.0, per wave
Evict (Normal),21.16720250980583,0.0,31.0008544921875, per wave
Evict (TC Req),0.0,0.0,0.0, per wave
1 Metric Avg Min Max Unit
2 Req 23.469673545060758 8.00143051147461 36.424224853515625 Req per wave
3 Streaming Req 0.0 0.0 0.0 Req per wave
4 Read Req 23.40472572006865 0.00142669677734375 36.12065124511719 Req per wave
5 Write Req 0.04790419161676647 0.0 8.0 Req per wave
6 Atomic Req 0.0 0.0 0.0 Req per wave
7 Probe Req 0.0 0.0 0.0 Req per wave
8 Hits 1.2620279689035017 0.00592041015625 4.4204864501953125 Hits per wave
9 Misses 22.207645576157255 4.000587463378906 32.00492858886719 Misses per wave
10 Cache Hit 3.8646444062429084 0.036982424769836826 50.00159711889287 Pct
11 Writeback 0.024407792234135244 0.0004730224609375 3.9375057220458984 per wave
12 NC Req 6.395899607035928e-07 0.0 0.0001068115234375 Req per wave
13 UC Req 0.0037058527598124065 0.000576019287109375 0.115234375 Req per wave
14 CC Req 0.0 0.0 0.0 Req per wave
15 RW Req 23.478994129660602 8.000747680664062 36.23834228515625 Req per wave
16 Writeback (Normal) 0.023577844311377244 0.0 3.9375 per wave
17 Writeback (TC Req) 0.0 0.0 0.0 per wave
18 Evict (Normal) 21.16720250980583 0.0 31.0008544921875 per wave
19 Evict (TC Req) 0.0 0.0 0.0 per wave
@@ -0,0 +1,8 @@
Metric,Avg,Min,Max,Unit
Read - Remote Socket Stall,0.0,0.0,0.0,Req per wave
Read - Peer GCD Stall,0.0,0.0,0.0,Req per wave
Read - HBM Stall,5.470586171407185,0.0,13.750839233398438,Req per wave
Write - Remote Socket Stall,0.0,0.0,0.0,Req per wave
Write - Peer GCD Stall,0.0,0.0,0.0,Req per wave
Write - HBM Stall,0.017345085829317927,0.0,2.8966293334960938,Req per wave
Write - Credit Starvation,0.0,0.0,0.0,Req per wave
1 Metric Avg Min Max Unit
2 Read - Remote Socket Stall 0.0 0.0 0.0 Req per wave
3 Read - Peer GCD Stall 0.0 0.0 0.0 Req per wave
4 Read - HBM Stall 5.470586171407185 0.0 13.750839233398438 Req per wave
5 Write - Remote Socket Stall 0.0 0.0 0.0 Req per wave
6 Write - Peer GCD Stall 0.0 0.0 0.0 Req per wave
7 Write - HBM Stall 0.017345085829317927 0.0 2.8966293334960938 Req per wave
8 Write - Credit Starvation 0.0 0.0 0.0 Req per wave
@@ -0,0 +1,17 @@
Channel,Hit Rate,Req,Read Req,Write Req,AtomicReq,EA Read Req,EA Write Req,EA AtomicReq,EA Read Lat - cycles,EA Write Lat - cycles,EA Atomic Lat - cycles,EA Read Stall - IO,EA Read Stall - GMI,EA Read Stall - DRAM,EA Write Stall - IO,EA Write Stall - GMI,EA Write Stall - DRAM,EA Write Stall - Starve
0,3.754107069495128,0.7326293876785004,0.7311323816904765,0.0014970059880239522,0.0,1.3865442333107223,0.0014736152694610778,0.0,510.0813652566453,391.02186414930554,,0.0,0.0,0.17742892510876684,0.0,0.0,0.0005136592659407747,0.0
1,3.7301767284930105,0.7324463621584955,0.7309493561704715,0.0014970059880239522,0.0,1.3862423468492702,0.0014736152694610778,0.0,506.7038280870002,390.59734623015873,,0.0,0.0,0.14513456607293226,0.0,0.0,0.0005163889445230633,0.0
2,3.7590174013861404,0.7334210401523613,0.7319240341643374,0.0014970059880239522,0.0,1.3877424594171033,0.0014736152694610778,0.0,499.2515528808397,387.5887199280754,,0.0,0.0,0.15166231258186752,0.0,0.0,0.0005098902536723428,0.0
3,3.7602686307356885,0.7325616710914109,0.731064665103387,0.0014970059880239522,0.0,1.3862688669901408,0.0014736152694610778,0.0,671.0148511912901,400.6867404513889,,0.0,0.0,0.17130631315494013,0.0,0.0,0.0005350284233778537,0.0
4,3.771444663150135,0.7326580664354884,0.7311610604474644,0.0014970059880239522,0.0,1.3862425524317576,0.0014736152694610778,0.0,528.5223755264707,397.68035404265873,,0.0,0.0,0.19972402606895584,0.0,0.0,0.00051740543571061,0.0
5,4.140366813619267,0.7352681416951253,0.7337711357071014,0.0014970059880239522,0.0,1.3863159225372497,0.0014736152694610778,0.0,538.7202338578606,396.2301044766865,,0.0,0.0,0.15394747614146706,0.0,0.0,0.0005239612328078218,0.0
6,3.7675371239539013,0.7327470608100206,0.7312500548219967,0.0014970059880239522,0.0,1.3862421641092815,0.0014736152694610778,0.0,532.3160955415417,392.6710999503968,,0.0,0.0,0.1731010025846744,0.0,0.0,0.0005134536834534057,0.0
7,3.7477731337834497,0.7325510721720622,0.7310540661840381,0.0014970059880239522,0.0,1.386242072739287,0.0014736152694610778,0.0,564.0307970152255,411.79856460813494,,0.0,0.0,0.2545371598112369,0.0,0.0,0.0005561234708317739,0.0
8,3.7629309659316106,0.7326391528466505,0.7311421468586266,0.0014970059880239522,0.0,1.386242255479276,0.0014736152694610778,0.0,507.97677537642045,391.88161117311506,,0.0,0.0,0.14353321555131923,0.0,0.0,0.0005085996525016373,0.0
9,3.7575408114508546,0.7326003205990363,0.7311033146110123,0.0014970059880239522,0.0,1.3865574933811575,0.0014736152694610778,0.0,497.16612321445524,393.7639586433532,,0.0,0.0,0.12181785720551086,0.0,0.0,0.0005294091687231007,0.0
10,3.726852178423305,0.7323970223615269,0.730900016373503,0.0014970059880239522,0.0,1.386242255479276,0.0014736152694610778,0.0,498.90197363177896,388.83580574156747,,0.0,0.0,0.1292610396882017,0.0,0.0,0.0005159206733018338,0.0
11,3.754955466426272,0.7333893918705557,0.7318923858825318,0.0014970059880239522,0.0,1.3862417986293039,0.0014736152694610778,0.0,523.2367198919861,407.1199544270833,,0.0,0.0,0.15274733126520396,0.0,0.0,0.0005579508707194985,0.0
12,3.7591571325768944,0.7325624934213604,0.7310654874333364,0.0014970059880239522,0.0,1.386242255479276,0.0014736152694610778,0.0,521.8157094361352,398.43614366319446,,0.0,0.0,0.15330523645092628,0.0,0.0,0.0005298089124485404,0.0
13,3.7576054099297367,0.7340993367269367,0.7326023307389128,0.0014970059880239522,0.0,1.386242255479276,0.0014736152694610778,0.0,514.3841949084031,399.42599051339283,,0.0,0.0,0.1628006803775262,0.0,0.0,0.0005350626871257485,0.0
14,4.140579696897814,0.735247948926366,0.7337509429383421,0.0014970059880239522,0.0,1.386288854176413,0.0014736152694610778,0.0,507.3541977665633,394.47763981894843,,0.0,0.0,0.1612470249929828,0.0,0.0,0.0005199637955534244,0.0
15,3.7720056060337694,0.7327599439792291,0.7312629379912051,0.0014970059880239522,0.0,1.386242449640514,0.0014736152694610778,0.0,536.8516158117187,408.61793154761904,,0.0,0.0,0.2033304911173746,0.0,0.0,0.0005554153533752807,0.0
1 Channel Hit Rate Req Read Req Write Req AtomicReq EA Read Req EA Write Req EA AtomicReq EA Read Lat - cycles EA Write Lat - cycles EA Atomic Lat - cycles EA Read Stall - IO EA Read Stall - GMI EA Read Stall - DRAM EA Write Stall - IO EA Write Stall - GMI EA Write Stall - DRAM EA Write Stall - Starve
2 0 3.754107069495128 0.7326293876785004 0.7311323816904765 0.0014970059880239522 0.0 1.3865442333107223 0.0014736152694610778 0.0 510.0813652566453 391.02186414930554 0.0 0.0 0.17742892510876684 0.0 0.0 0.0005136592659407747 0.0
3 1 3.7301767284930105 0.7324463621584955 0.7309493561704715 0.0014970059880239522 0.0 1.3862423468492702 0.0014736152694610778 0.0 506.7038280870002 390.59734623015873 0.0 0.0 0.14513456607293226 0.0 0.0 0.0005163889445230633 0.0
4 2 3.7590174013861404 0.7334210401523613 0.7319240341643374 0.0014970059880239522 0.0 1.3877424594171033 0.0014736152694610778 0.0 499.2515528808397 387.5887199280754 0.0 0.0 0.15166231258186752 0.0 0.0 0.0005098902536723428 0.0
5 3 3.7602686307356885 0.7325616710914109 0.731064665103387 0.0014970059880239522 0.0 1.3862688669901408 0.0014736152694610778 0.0 671.0148511912901 400.6867404513889 0.0 0.0 0.17130631315494013 0.0 0.0 0.0005350284233778537 0.0
6 4 3.771444663150135 0.7326580664354884 0.7311610604474644 0.0014970059880239522 0.0 1.3862425524317576 0.0014736152694610778 0.0 528.5223755264707 397.68035404265873 0.0 0.0 0.19972402606895584 0.0 0.0 0.00051740543571061 0.0
7 5 4.140366813619267 0.7352681416951253 0.7337711357071014 0.0014970059880239522 0.0 1.3863159225372497 0.0014736152694610778 0.0 538.7202338578606 396.2301044766865 0.0 0.0 0.15394747614146706 0.0 0.0 0.0005239612328078218 0.0
8 6 3.7675371239539013 0.7327470608100206 0.7312500548219967 0.0014970059880239522 0.0 1.3862421641092815 0.0014736152694610778 0.0 532.3160955415417 392.6710999503968 0.0 0.0 0.1731010025846744 0.0 0.0 0.0005134536834534057 0.0
9 7 3.7477731337834497 0.7325510721720622 0.7310540661840381 0.0014970059880239522 0.0 1.386242072739287 0.0014736152694610778 0.0 564.0307970152255 411.79856460813494 0.0 0.0 0.2545371598112369 0.0 0.0 0.0005561234708317739 0.0
10 8 3.7629309659316106 0.7326391528466505 0.7311421468586266 0.0014970059880239522 0.0 1.386242255479276 0.0014736152694610778 0.0 507.97677537642045 391.88161117311506 0.0 0.0 0.14353321555131923 0.0 0.0 0.0005085996525016373 0.0
11 9 3.7575408114508546 0.7326003205990363 0.7311033146110123 0.0014970059880239522 0.0 1.3865574933811575 0.0014736152694610778 0.0 497.16612321445524 393.7639586433532 0.0 0.0 0.12181785720551086 0.0 0.0 0.0005294091687231007 0.0
12 10 3.726852178423305 0.7323970223615269 0.730900016373503 0.0014970059880239522 0.0 1.386242255479276 0.0014736152694610778 0.0 498.90197363177896 388.83580574156747 0.0 0.0 0.1292610396882017 0.0 0.0 0.0005159206733018338 0.0
13 11 3.754955466426272 0.7333893918705557 0.7318923858825318 0.0014970059880239522 0.0 1.3862417986293039 0.0014736152694610778 0.0 523.2367198919861 407.1199544270833 0.0 0.0 0.15274733126520396 0.0 0.0 0.0005579508707194985 0.0
14 12 3.7591571325768944 0.7325624934213604 0.7310654874333364 0.0014970059880239522 0.0 1.386242255479276 0.0014736152694610778 0.0 521.8157094361352 398.43614366319446 0.0 0.0 0.15330523645092628 0.0 0.0 0.0005298089124485404 0.0
15 13 3.7576054099297367 0.7340993367269367 0.7326023307389128 0.0014970059880239522 0.0 1.386242255479276 0.0014736152694610778 0.0 514.3841949084031 399.42599051339283 0.0 0.0 0.1628006803775262 0.0 0.0 0.0005350626871257485 0.0
16 14 4.140579696897814 0.735247948926366 0.7337509429383421 0.0014970059880239522 0.0 1.386288854176413 0.0014736152694610778 0.0 507.3541977665633 394.47763981894843 0.0 0.0 0.1612470249929828 0.0 0.0 0.0005199637955534244 0.0
17 15 3.7720056060337694 0.7327599439792291 0.7312629379912051 0.0014970059880239522 0.0 1.386242449640514 0.0014736152694610778 0.0 536.8516158117187 408.61793154761904 0.0 0.0 0.2033304911173746 0.0 0.0 0.0005554153533752807 0.0
@@ -0,0 +1,17 @@
Channel,Hit Rate,Req,Read Req,Write Req,AtomicReq,EA Read Req,EA Write Req,EA AtomicReq,EA Read Lat - cycles,EA Write Lat - cycles,EA Atomic Lat - cycles,EA Read Stall - IO,EA Read Stall - GMI,EA Read Stall - DRAM,EA Write Stall - IO,EA Write Stall - GMI,EA Write Stall - DRAM,EA Write Stall - Starve
16,3.746882616699952,0.7325092247146332,0.7310122187266093,0.0014970059880239522,0.0,1.386242255479276,0.0014736152694610778,0.0,537.5290860061721,389.6076388888889,,0.0,0.0,0.21745090141981663,0.0,0.0,0.0005116034410670846,0.0
17,3.754880263427981,0.7325616710914109,0.731064665103387,0.0014970059880239522,0.0,1.3862421641092815,0.0014736152694610778,0.0,522.3758857677735,391.84861731150795,,0.0,0.0,0.1959920186482504,0.0,0.0,0.0005262454826674775,0.0
18,3.7447116564244998,0.7324915903057166,0.7309945843176927,0.0014970059880239522,0.0,1.387022121223861,0.0014736152694610778,0.0,518.1120903597763,384.6289992559524,,0.0,0.0,0.1293527751625655,0.0,0.0,0.00048967464241439,0.0
19,3.73891146458907,0.732473875948055,0.7309768699600311,0.0014970059880239522,0.0,1.3862421641092815,0.0014736152694610778,0.0,536.4406848956414,401.8602818080357,,0.0,0.0,0.20439083990222678,0.0,0.0,0.0005381235819376871,0.0
20,3.774157690893384,0.7330538812511695,0.7315568752631456,0.0014970059880239522,0.0,1.3862576056383327,0.0014736152694610778,0.0,544.6680873024022,393.83607700892856,,0.0,0.0,0.204071044921875,0.0,0.0,0.000504773533986714,0.0
21,3.762456038197521,0.732598584569143,0.731101578581119,0.0014970059880239522,0.0,1.386242529589259,0.0014736152694610778,0.0,520.6098579261452,396.7990451388889,,0.0,0.0,0.21825998272010666,0.0,0.0,0.0005211516054804454,0.0
22,3.783860086411397,0.7328417201242047,0.7313447141361807,0.0014970059880239522,0.0,1.386269449473855,0.0014736152694610778,0.0,526.2488188497113,392.6523204985119,,0.0,0.0,0.1488468375748503,0.0,0.0,0.000511660547313576,0.0
23,3.9431443570476152,0.7333279912343282,0.7318309852463043,0.0014970059880239522,0.0,1.3862543163185348,0.0014736152694610778,0.0,560.0257129920067,409.01890345982144,,0.0,0.0,0.26034180418459957,0.0,0.0,0.0005554153533752807,0.0
24,3.7727987350145957,0.7327277817412051,0.7312307757531812,0.0014970059880239522,0.0,1.3862428036992422,0.0014736152694610778,0.0,505.95352548174526,391.57591610863096,,0.0,0.0,0.17619954183430014,0.0,0.0,0.0005119574997953313,0.0
25,3.7516695260297874,0.7325662395911302,0.7310692336031063,0.0014970059880239522,0.0,1.386242072739287,0.0014736152694610778,0.0,511.47053786835556,389.3184756324405,,0.0,0.0,0.1545044676272455,0.0,0.0,0.0005102557336498877,0.0
26,3.74728390328537,0.7325036511449756,0.7310066451569517,0.0014970059880239522,0.0,1.3862419813692928,0.0014736152694610778,0.0,509.11703314039187,391.73260013640873,,0.0,0.0,0.15643548108860403,0.0,0.0,0.0005313964661010012,0.0
27,3.744347035365334,0.732515266555512,0.7310182605674881,0.0014970059880239522,0.0,1.387014697411817,0.0014736152694610778,0.0,509.8409042428115,403.22064887152777,,0.0,0.0,0.16160391619105538,0.0,0.0,0.000542794872900683,0.0
28,3.7378256939046732,0.7324492859983158,0.7309522800102919,0.0014970059880239522,0.0,1.386242072739287,0.0014736152694610778,0.0,515.6845663304465,399.324955047123,,0.0,0.0,0.14986999877198728,0.0,0.0,0.0005325500122801272,0.0
29,3.768823915219057,0.7330112114637911,0.7315142054757672,0.0014970059880239522,0.0,1.3862424382192646,0.0014736152694610778,0.0,508.6636606657089,398.6381448412698,,0.0,0.0,0.17484160097773205,0.0,0.0,0.0005368215595176834,0.0
30,3.755447685140178,0.7325416610626403,0.7310446550746164,0.0014970059880239522,0.0,1.3862419813692928,0.0014736152694610778,0.0,511.73747978702727,394.16917782738096,,0.0,0.0,0.1702224822815307,0.0,0.0,0.0005174282782092065,0.0
31,3.7749462903838324,0.732737923810582,0.731240917822558,0.0014970059880239522,0.0,1.3862425410105084,0.0014736152694610778,0.0,536.0630834314311,410.0417751736111,,0.0,0.0,0.2012089712177208,0.0,0.0,0.0005557008846077377,0.0
1 Channel Hit Rate Req Read Req Write Req AtomicReq EA Read Req EA Write Req EA AtomicReq EA Read Lat - cycles EA Write Lat - cycles EA Atomic Lat - cycles EA Read Stall - IO EA Read Stall - GMI EA Read Stall - DRAM EA Write Stall - IO EA Write Stall - GMI EA Write Stall - DRAM EA Write Stall - Starve
2 16 3.746882616699952 0.7325092247146332 0.7310122187266093 0.0014970059880239522 0.0 1.386242255479276 0.0014736152694610778 0.0 537.5290860061721 389.6076388888889 0.0 0.0 0.21745090141981663 0.0 0.0 0.0005116034410670846 0.0
3 17 3.754880263427981 0.7325616710914109 0.731064665103387 0.0014970059880239522 0.0 1.3862421641092815 0.0014736152694610778 0.0 522.3758857677735 391.84861731150795 0.0 0.0 0.1959920186482504 0.0 0.0 0.0005262454826674775 0.0
4 18 3.7447116564244998 0.7324915903057166 0.7309945843176927 0.0014970059880239522 0.0 1.387022121223861 0.0014736152694610778 0.0 518.1120903597763 384.6289992559524 0.0 0.0 0.1293527751625655 0.0 0.0 0.00048967464241439 0.0
5 19 3.73891146458907 0.732473875948055 0.7309768699600311 0.0014970059880239522 0.0 1.3862421641092815 0.0014736152694610778 0.0 536.4406848956414 401.8602818080357 0.0 0.0 0.20439083990222678 0.0 0.0 0.0005381235819376871 0.0
6 20 3.774157690893384 0.7330538812511695 0.7315568752631456 0.0014970059880239522 0.0 1.3862576056383327 0.0014736152694610778 0.0 544.6680873024022 393.83607700892856 0.0 0.0 0.204071044921875 0.0 0.0 0.000504773533986714 0.0
7 21 3.762456038197521 0.732598584569143 0.731101578581119 0.0014970059880239522 0.0 1.386242529589259 0.0014736152694610778 0.0 520.6098579261452 396.7990451388889 0.0 0.0 0.21825998272010666 0.0 0.0 0.0005211516054804454 0.0
8 22 3.783860086411397 0.7328417201242047 0.7313447141361807 0.0014970059880239522 0.0 1.386269449473855 0.0014736152694610778 0.0 526.2488188497113 392.6523204985119 0.0 0.0 0.1488468375748503 0.0 0.0 0.000511660547313576 0.0
9 23 3.9431443570476152 0.7333279912343282 0.7318309852463043 0.0014970059880239522 0.0 1.3862543163185348 0.0014736152694610778 0.0 560.0257129920067 409.01890345982144 0.0 0.0 0.26034180418459957 0.0 0.0 0.0005554153533752807 0.0
10 24 3.7727987350145957 0.7327277817412051 0.7312307757531812 0.0014970059880239522 0.0 1.3862428036992422 0.0014736152694610778 0.0 505.95352548174526 391.57591610863096 0.0 0.0 0.17619954183430014 0.0 0.0 0.0005119574997953313 0.0
11 25 3.7516695260297874 0.7325662395911302 0.7310692336031063 0.0014970059880239522 0.0 1.386242072739287 0.0014736152694610778 0.0 511.47053786835556 389.3184756324405 0.0 0.0 0.1545044676272455 0.0 0.0 0.0005102557336498877 0.0
12 26 3.74728390328537 0.7325036511449756 0.7310066451569517 0.0014970059880239522 0.0 1.3862419813692928 0.0014736152694610778 0.0 509.11703314039187 391.73260013640873 0.0 0.0 0.15643548108860403 0.0 0.0 0.0005313964661010012 0.0
13 27 3.744347035365334 0.732515266555512 0.7310182605674881 0.0014970059880239522 0.0 1.387014697411817 0.0014736152694610778 0.0 509.8409042428115 403.22064887152777 0.0 0.0 0.16160391619105538 0.0 0.0 0.000542794872900683 0.0
14 28 3.7378256939046732 0.7324492859983158 0.7309522800102919 0.0014970059880239522 0.0 1.386242072739287 0.0014736152694610778 0.0 515.6845663304465 399.324955047123 0.0 0.0 0.14986999877198728 0.0 0.0 0.0005325500122801272 0.0
15 29 3.768823915219057 0.7330112114637911 0.7315142054757672 0.0014970059880239522 0.0 1.3862424382192646 0.0014736152694610778 0.0 508.6636606657089 398.6381448412698 0.0 0.0 0.17484160097773205 0.0 0.0 0.0005368215595176834 0.0
16 30 3.755447685140178 0.7325416610626403 0.7310446550746164 0.0014970059880239522 0.0 1.3862419813692928 0.0014736152694610778 0.0 511.73747978702727 394.16917782738096 0.0 0.0 0.1702224822815307 0.0 0.0 0.0005174282782092065 0.0
17 31 3.7749462903838324 0.732737923810582 0.731240917822558 0.0014970059880239522 0.0 1.3862425410105084 0.0014736152694610778 0.0 536.0630834314311 410.0417751736111 0.0 0.0 0.2012089712177208 0.0 0.0 0.0005557008846077377 0.0
@@ -0,0 +1,55 @@
Metric,Value,Alias
Wave Life,18380.0,wave_life_
Active CUs,103/104,active_cu_
SALU,25.0,salu_
SMEM,2.0,smem_
VALU,495.0,valu_
MFMA,0.0,mfma_
VMEM,8.0,vmem_
LDS_Per_Workgroup,0.0,lds_
GWS,0.0,gws_
BR,10.0,br_
VGPR,12.0,vgpr_
SGPR,24.0,sgpr_
LDS_Per_Workgroup Allocation,0.0,lds_alloc_
Scratch Allocation,0.0,scratch_alloc_
Wavefronts,67894.0,wavefronts_
Workgroups,16973.0,workgroups_
LDS_Per_Workgroup Req,0.0,lds_req_
IL1 Fetch,128.0,il1_fetch_
IL1 Hit,100.0,il1_hit_
IL1_L2 Rd,0.0,il1_l2_req_
vL1D Rd,2.0,sl1_rd_
vL1D Hit,98.0,sl1_hit_
vL1D_L2 Rd,0.0,sl1_l2_rd_
vL1D_L2 Wr,0.0,sl1_l2_wr_
vL1D_L2 Atomic,0.0,sl1_l2_atom_
VL1 Rd,279.0,vl1_rd_
VL1 Wr,0.0,vl1_wr_
VL1 Atomic,0.0,vl1_atom_
VL1 Hit,20.0,vl1_hit_
VL1 Lat,1211.0,vl1_lat_
VL1_L2 Rd,44.0,vl1_l2_rd_
VL1_L2 Wr,0.0,vl1_l2_wr_
vL1_L2 Atomic,0.0,vl1_l2_atom_
L2 Rd,23.0,l2_rd_
L2 Wr,0.0,l2_wr_
L2 Atomic,0.0,l2_atom_
L2 Hit,4.0,l2_hit_
L2 Rd Lat,785.0,l2_rd_lat_
L2 Wr Lat,353.0,l2_wr_lat_
Fabric Rd Lat,533.0,fabric_rd_lat_
Fabric Wr Lat,409.0,fabric_wr_lat_
Fabric Atomic Lat,,fabric_atom_lat_
Fabric_L2 Rd,44.0,l2_fabric_rd_
Fabric_L2 Wr,0.0,l2_fabric_wr_
Fabric_l2 Atomic,0.0,l2_fabric_atom_
HBM Rd,44.0,hbm_rd_
HBM Wr,0.0,hbm_wr_
LDS_Per_Workgroup Util,0.0,lds_util_
VL1 Coalesce,70.0,vl1_coales_
VL1 Stall,2.0,vl1_stall_
LDS_Per_Workgroup Lat,,lds_lat_
vL1D Lat,,sl1_lat_
IL1 Lat,,il1_lat_
Wave Occupancy,26.0,wave_occ_
1 Metric Value Alias
2 Wave Life 18380.0 wave_life_
3 Active CUs 103/104 active_cu_
4 SALU 25.0 salu_
5 SMEM 2.0 smem_
6 VALU 495.0 valu_
7 MFMA 0.0 mfma_
8 VMEM 8.0 vmem_
9 LDS_Per_Workgroup 0.0 lds_
10 GWS 0.0 gws_
11 BR 10.0 br_
12 VGPR 12.0 vgpr_
13 SGPR 24.0 sgpr_
14 LDS_Per_Workgroup Allocation 0.0 lds_alloc_
15 Scratch Allocation 0.0 scratch_alloc_
16 Wavefronts 67894.0 wavefronts_
17 Workgroups 16973.0 workgroups_
18 LDS_Per_Workgroup Req 0.0 lds_req_
19 IL1 Fetch 128.0 il1_fetch_
20 IL1 Hit 100.0 il1_hit_
21 IL1_L2 Rd 0.0 il1_l2_req_
22 vL1D Rd 2.0 sl1_rd_
23 vL1D Hit 98.0 sl1_hit_
24 vL1D_L2 Rd 0.0 sl1_l2_rd_
25 vL1D_L2 Wr 0.0 sl1_l2_wr_
26 vL1D_L2 Atomic 0.0 sl1_l2_atom_
27 VL1 Rd 279.0 vl1_rd_
28 VL1 Wr 0.0 vl1_wr_
29 VL1 Atomic 0.0 vl1_atom_
30 VL1 Hit 20.0 vl1_hit_
31 VL1 Lat 1211.0 vl1_lat_
32 VL1_L2 Rd 44.0 vl1_l2_rd_
33 VL1_L2 Wr 0.0 vl1_l2_wr_
34 vL1_L2 Atomic 0.0 vl1_l2_atom_
35 L2 Rd 23.0 l2_rd_
36 L2 Wr 0.0 l2_wr_
37 L2 Atomic 0.0 l2_atom_
38 L2 Hit 4.0 l2_hit_
39 L2 Rd Lat 785.0 l2_rd_lat_
40 L2 Wr Lat 353.0 l2_wr_lat_
41 Fabric Rd Lat 533.0 fabric_rd_lat_
42 Fabric Wr Lat 409.0 fabric_wr_lat_
43 Fabric Atomic Lat fabric_atom_lat_
44 Fabric_L2 Rd 44.0 l2_fabric_rd_
45 Fabric_L2 Wr 0.0 l2_fabric_wr_
46 Fabric_l2 Atomic 0.0 l2_fabric_atom_
47 HBM Rd 44.0 hbm_rd_
48 HBM Wr 0.0 hbm_wr_
49 LDS_Per_Workgroup Util 0.0 lds_util_
50 VL1 Coalesce 70.0 vl1_coales_
51 VL1 Stall 2.0 vl1_stall_
52 LDS_Per_Workgroup Lat lds_lat_
53 vL1D Lat sl1_lat_
54 IL1 Lat il1_lat_
55 Wave Occupancy 26.0 wave_occ_
@@ -0,0 +1,168 @@
Dispatch_ID,Kernel_Name,GPU_ID
0,__amd_rocclr_fillBufferAligned.kd,0
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0
1 Dispatch_ID Kernel_Name GPU_ID
2 0 __amd_rocclr_fillBufferAligned.kd 0
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0
5 3 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0
10 8 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0
15 13 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0
20 18 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0
25 23 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0
30 28 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0
35 33 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0
40 38 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0
45 43 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0
50 48 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0
55 53 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0
60 58 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0
65 63 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0
70 68 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0
75 73 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0
80 78 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0
85 83 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0
90 88 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0
95 93 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0
100 98 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0
105 103 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0
110 108 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0
115 113 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0
120 118 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0
125 123 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0
130 128 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0
135 133 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0
140 138 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0
145 143 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0
150 148 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0
155 153 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0
160 158 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0
165 163 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0
@@ -0,0 +1,30 @@
Metric,Value,Unit,Peak,PoP
VALU FLOPs,7440.577114688551,Gflop,22630.4,32.87868139621284
VALU IOPs,2300.074166182063,Giop,22630.4,10.163647863855976
MFMA FLOPs (BF16),0.0,Gflop,90521.6,0.0
MFMA FLOPs (F16),0.0,Gflop,181043.2,0.0
MFMA FLOPs (F32),0.0,Gflop,45260.8,0.0
MFMA FLOPs (F64),0.0,Gflop,45260.8,0.0
MFMA IOPs (Int8),0.0,Giop,181043.2,0.0
Active CUs,103,Cus,104,99.03846153846153
SALU Util,2.624359244978694,Pct,100,2.624359244978694
VALU Util,58.32499961405379,Pct,100,58.32499961405379
MFMA Util,0.0,Pct,100,0.0
VALU Active Threads/Wave,64.0,Threads,64,100.0
IPC - Issue,1.0,Instr/cycle,5,20.0
LDS_Per_Workgroup BW,0.0,Gb/sec,22630.4,0.0
LDS_Per_Workgroup Bank Conflict,,Conflicts/access,32,
Instr Cache Hit Rate,99.99250938551732,Pct,100,99.99250938551732
Instr Cache BW,1673.2474012593727,Gb/s,6092.8,27.46270025701439
Scalar L1D Cache Hit Rate,99.34855886013408,Pct,100,99.34855886013408
Scalar L1D Cache BW,57.02040924823583,Gb/s,6092.8,0.9358654354030302
Vector L1D Cache Hit Rate,20.35928143712575,Pct,100,20.35928143712575
Vector L1D Cache BW,1689.9750228454398,Gb/s,11315.199999999999,14.935441024864252
L2 Cache Hit Rate,3.8646444062429084,Pct,100,3.8646444062429084
L2-Fabric Read BW,1157.9322572223164,Gb/s,1638.4,70.67457624647926
L2-Fabric Write BW,6.588450813230302,Gb/s,1638.4,0.40212712483095103
L2-Fabric Read Latency,532.5202646536594,Cycles,,
L2-Fabric Write Latency,408.8238985576327,Cycles,,
Wave Occupancy,2671.4435683321913,Wavefronts,3328,80.2717418369048
Instr Fetch BW,403.13152263901986,Gb/s,3046.4,13.233046305114886
Instr Fetch Latency,17.229752576806337,Cycles,,
1 Metric Value Unit Peak PoP
2 VALU FLOPs 7440.577114688551 Gflop 22630.4 32.87868139621284
3 VALU IOPs 2300.074166182063 Giop 22630.4 10.163647863855976
4 MFMA FLOPs (BF16) 0.0 Gflop 90521.6 0.0
5 MFMA FLOPs (F16) 0.0 Gflop 181043.2 0.0
6 MFMA FLOPs (F32) 0.0 Gflop 45260.8 0.0
7 MFMA FLOPs (F64) 0.0 Gflop 45260.8 0.0
8 MFMA IOPs (Int8) 0.0 Giop 181043.2 0.0
9 Active CUs 103 Cus 104 99.03846153846153
10 SALU Util 2.624359244978694 Pct 100 2.624359244978694
11 VALU Util 58.32499961405379 Pct 100 58.32499961405379
12 MFMA Util 0.0 Pct 100 0.0
13 VALU Active Threads/Wave 64.0 Threads 64 100.0
14 IPC - Issue 1.0 Instr/cycle 5 20.0
15 LDS_Per_Workgroup BW 0.0 Gb/sec 22630.4 0.0
16 LDS_Per_Workgroup Bank Conflict Conflicts/access 32
17 Instr Cache Hit Rate 99.99250938551732 Pct 100 99.99250938551732
18 Instr Cache BW 1673.2474012593727 Gb/s 6092.8 27.46270025701439
19 Scalar L1D Cache Hit Rate 99.34855886013408 Pct 100 99.34855886013408
20 Scalar L1D Cache BW 57.02040924823583 Gb/s 6092.8 0.9358654354030302
21 Vector L1D Cache Hit Rate 20.35928143712575 Pct 100 20.35928143712575
22 Vector L1D Cache BW 1689.9750228454398 Gb/s 11315.199999999999 14.935441024864252
23 L2 Cache Hit Rate 3.8646444062429084 Pct 100 3.8646444062429084
24 L2-Fabric Read BW 1157.9322572223164 Gb/s 1638.4 70.67457624647926
25 L2-Fabric Write BW 6.588450813230302 Gb/s 1638.4 0.40212712483095103
26 L2-Fabric Read Latency 532.5202646536594 Cycles
27 L2-Fabric Write Latency 408.8238985576327 Cycles
28 Wave Occupancy 2671.4435683321913 Wavefronts 3328 80.2717418369048
29 Instr Fetch BW 403.13152263901986 Gb/s 3046.4 13.233046305114886
30 Instr Fetch Latency 17.229752576806337 Cycles
@@ -0,0 +1,9 @@
Metric,Avg,Min,Max,Unit
GPU Busy Cycles,416751.1377245509,32809,5255461,Cycles/kernel
CPF Busy,416751.1377245509,32809,5255461,Cycles/kernel
CPF Util,100.0,100.0,100.0,Pct
CPF Stall,0.0,0.0,0.0,Cycles/kernel
L2Cache Intf Busy,2418.814371257485,2252,2726,Cycles/kernel
L2Cache Intf Util,1.0181470775822945,0.05126623605312804,9.017030873318298,Pct
L2Cache Intf Stall,0.0,0.0,0.0,Pct
UTCL1 Stall,0.0,0,0,Cycles/kernel
1 Metric Avg Min Max Unit
2 GPU Busy Cycles 416751.1377245509 32809 5255461 Cycles/kernel
3 CPF Busy 416751.1377245509 32809 5255461 Cycles/kernel
4 CPF Util 100.0 100.0 100.0 Pct
5 CPF Stall 0.0 0.0 0.0 Cycles/kernel
6 L2Cache Intf Busy 2418.814371257485 2252 2726 Cycles/kernel
7 L2Cache Intf Util 1.0181470775822945 0.05126623605312804 9.017030873318298 Pct
8 L2Cache Intf Stall 0.0 0.0 0.0 Pct
9 UTCL1 Stall 0.0 0 0 Cycles/kernel
@@ -0,0 +1,13 @@
Metric,Avg,Min,Max,Unit
GPU Busy Cycles,416751.1377245509,32809,5255461,Cycles
CPC Busy Cycles,416751.1377245509,32809,5255461,Cycles
CPC Util,100.0,100.0,100.0,Pct
CPC Stall Cycles,12266.491017964072,8946,45189,Cycles
CPC Stall Rate,4.608435375516067,0.8598484509731877,32.213721844615804,Pct
CPC Packet Decoding,28914.017964071856,8813,273959,Cycles
SPI Intf Busy Cycles,386991.2035928144,498,4973937,Cycles
SPI Intf Util,91.41354263667465,1.5178761925081532,96.28895191459988,Pct
L2Cache Intf Util,0.12498736917431186,0.0057437161463088065,0.8998003754134016,Pct
UTCL1 Stall Cycles,2450.497005988024,896,3342,Cycles
UTCL2 Intf Busy Cycles,2972.634730538922,1214,3677,Cycles
UTCL2 Intf Util,1.1935740135939938,0.059211547489698924,5.082885474226024,Pct
1 Metric Avg Min Max Unit
2 GPU Busy Cycles 416751.1377245509 32809 5255461 Cycles
3 CPC Busy Cycles 416751.1377245509 32809 5255461 Cycles
4 CPC Util 100.0 100.0 100.0 Pct
5 CPC Stall Cycles 12266.491017964072 8946 45189 Cycles
6 CPC Stall Rate 4.608435375516067 0.8598484509731877 32.213721844615804 Pct
7 CPC Packet Decoding 28914.017964071856 8813 273959 Cycles
8 SPI Intf Busy Cycles 386991.2035928144 498 4973937 Cycles
9 SPI Intf Util 91.41354263667465 1.5178761925081532 96.28895191459988 Pct
10 L2Cache Intf Util 0.12498736917431186 0.0057437161463088065 0.8998003754134016 Pct
11 UTCL1 Stall Cycles 2450.497005988024 896 3342 Cycles
12 UTCL2 Intf Busy Cycles 2972.634730538922 1214 3677 Cycles
13 UTCL2 Intf Util 1.1935740135939938 0.059211547489698924 5.082885474226024 Pct

Some files were not shown because too many files have changed in this diff Show More