Moving workloads to old

Signed-off-by: Jose Santos <josantos@login1.hpcfund>
This commit is contained in:
Jose Santos
2024-02-20 11:01:23 -06:00
committad av Karl W. Schulz
förälder 76873dd0c4
incheckning 989e29cf81
9701 ändrade filer med 4016 tillägg och 0 borttagningar
@@ -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",0,0,0,935069,935074,33554432,256,0,0,8,32,6464,0x0,0x7fb1e8e04180,504417,504417,524288,6291456,791548,101536232,12076606776836515,12076607020949616,12076607021273775,12076607021386317
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,935069,935074,32768,256,0,0,24,24,12480,0x0,0x7fb1e8e35100,27457,27457,512,8192,8659,1112808,12076607036018836,12076607036328752,12076607036334672,12076607036343359
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,935069,935074,4194304,256,0,0,24,24,12928,0x7fb2f49b3900,0x7fb1e8e35140,221451,221451,65536,917504,137700,17627108,12076607036410164,12076607036634350,12076607036769870,12076607036773860
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,935069,935074,4194304,256,0,0,36,24,13632,0x7fb2f49b3800,0x7fb1e8e35180,398529,398529,65536,1245184,176363,22595116,12076607036850743,12076607037034989,12076607037288428,12076607037361443
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,935069,935074,4194304,256,0,0,28,24,14080,0x7fb2f49b3700,0x7fb1e8e351c0,410715,410715,65536,983040,136833,17475532,12076607037393453,12076607037585546,12076607037846505,12076607037914191
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,935069,935074,4194304,256,0,0,24,24,14528,0x7fb2f49b3600,0x7fb1e8e35200,226705,226705,65536,1048576,153290,19537144,12076607037942794,12076607038138984,12076607038278504,12076607038282236
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,935069,935074,4194304,256,0,0,24,24,14976,0x7fb2f49b3500,0x7fb1e8e35240,228547,228547,65536,983040,147995,18962320,12076607038336266,12076607038515783,12076607038656262,12076607038659818
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,935069,935074,4194304,256,0,0,24,24,15424,0x7fb2f49b3400,0x7fb1e8e35280,216161,216161,65536,1048576,146752,18784452,12076607038742652,12076607038911941,12076607039044420,12076607039048191
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,935069,935074,4194304,256,0,0,28,24,16128,0x7fb2f49b3300,0x7fb1e8e352c0,407219,407219,65536,1572864,245751,31439136,12076607039102291,12076607039289699,12076607039549378,12076607039593976
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,935069,935074,4194304,256,0,0,28,24,16832,0x7fb2f49b3a00,0x7fb1e8e35300,402961,402961,65536,1179648,166989,21330680,12076607039617790,12076607039813377,12076607040069536,12076607040112089
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,935069,935074,4194304,256,0,0,24,24,17536,0x7fb2f49b3900,0x7fb1e8e35340,211699,211699,65536,1114112,161801,20744520,12076607040145602,12076607040328415,12076607040457535,12076607040461169
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,935069,935074,4194304,256,0,0,24,24,18240,0x7fb2f49b3800,0x7fb1e8e35380,228737,228737,65536,1114112,157285,20107324,12076607040513937,12076607040691774,12076607040832413,12076607040835916
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,935069,935074,4194304,256,0,0,24,24,18944,0x7fb2f49b3700,0x7fb1e8e353c0,217083,217083,65536,1179648,164032,20966992,12076607040903351,12076607041083932,12076607041216731,12076607041220842
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,935069,935074,4194304,256,0,0,28,24,19904,0x7fb2f49b3600,0x7fb1e8e35400,406313,406313,65536,1835008,252183,32259532,12076607041274622,12076607041448410,12076607041705849,12076607041774261
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,935069,935074,4194304,256,0,0,28,24,20608,0x7fb2f49b3500,0x7fb1e8e35440,404715,404715,65536,1310720,179910,23054132,12076607041801262,12076607041986328,12076607042243607,12076607042312442
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,935069,935074,4194304,256,0,0,24,24,21312,0x7fb2f49b3400,0x7fb1e8e35480,216817,216817,65536,1245184,174001,22306216,12076607042340044,12076607042526486,12076607042659445,12076607042663235
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,935069,935074,4194304,256,0,0,24,24,22016,0x7fb2f49b3300,0x7fb1e8e354c0,219347,219347,65536,1310720,181451,23167172,12076607042717035,12076607042886484,12076607043020084,12076607043024036
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,935069,935074,4194304,256,0,0,24,24,22720,0x7fb2f49b3a00,0x7fb1e8e35500,216545,216545,65536,1310720,180617,23118392,12076607043091932,12076607043261843,12076607043394642,12076607043398342
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,935069,935074,4194304,256,0,0,28,24,23680,0x7fb2f49b3900,0x7fb1e8e35540,410411,410411,65536,2097152,298957,38165200,12076607043453104,12076607043629521,12076607043891600,12076607043936203
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,935069,935074,4194304,256,0,0,28,24,24384,0x7fb2f49b3800,0x7fb1e8e35580,405265,405265,65536,1441792,197254,25187912,12076607043960438,12076607044156879,12076607044415758,12076607044457943
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,935069,935074,4194304,256,0,0,24,24,25088,0x7fb2f49b3700,0x7fb1e8e355c0,211955,211955,65536,1376256,190093,24361152,12076607044494992,12076607044662797,12076607044791757,12076607044795531
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,935069,935074,4194304,256,0,0,24,24,25792,0x7fb2f49b3600,0x7fb1e8e35600,224401,224401,65536,1507328,211513,27052060,12076607044848650,12076607045029676,12076607045167755,12076607045172192
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,935069,935074,4194304,256,0,0,24,24,26496,0x7fb2f49b3500,0x7fb1e8e35640,213291,213291,65536,1441792,206408,26511396,12076607045238255,12076607045408394,12076607045538153,12076607045541819
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,935069,935074,4194304,256,0,0,28,24,27712,0x7fb2f49b3400,0x7fb1e8e35680,406521,406521,65536,2359296,322321,41245052,12076607045594057,12076607045769673,12076607046029831,12076607046098796
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,935069,935074,4194304,256,0,0,28,24,28416,0x7fb2f49b3300,0x7fb1e8e356c0,402387,402387,65536,1572864,210221,26926876,12076607046130294,12076607046318790,12076607046576069,12076607046643980
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,935069,935074,4194304,256,0,0,24,24,29120,0x7fb2f49b3a00,0x7fb1e8e35700,213697,213697,65536,1507328,217132,27733596,12076607046675619,12076607046861028,12076607046992387,12076607046996125
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,935069,935074,4194304,256,0,0,24,24,30080,0x7fb2f49b3900,0x7fb1e8e35740,229571,229571,65536,1703936,233010,29842576,12076607047049554,12076607047231586,12076607047372866,12076607047376693
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,935069,935074,4194304,256,0,0,24,24,30784,0x7fb2f49b3800,0x7fb1e8e35780,221441,221441,65536,1572864,215600,27520968,12076607047442275,12076607047610785,12076607047746944,12076607047750738
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,935069,935074,4194304,256,0,0,28,24,32000,0x7fb2f49b3700,0x7fb1e8e357c0,397083,397083,65536,2621440,359612,46041044,12076607047804589,12076607047973503,12076607048228062,12076607048272499
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,935069,935074,4194304,256,0,0,28,24,32960,0x7fb2f49b3600,0x7fb1e8e35800,401329,401329,65536,1703936,230733,29537124,12076607048299870,12076607048484861,12076607048741500,12076607048782758
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,935069,935074,4194304,256,0,0,24,24,33920,0x7fb2f49b3500,0x7fb1e8e35840,220467,220467,65536,1638400,229834,29380464,12076607048815619,12076607048987739,12076607049123099,12076607049127129
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,935069,935074,4194304,256,0,0,24,24,34880,0x7fb2f49b3400,0x7fb1e8e35880,229225,229225,65536,1900544,266452,34181504,12076607049180618,12076607049356698,12076607049498297,12076607049502086
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,935069,935074,4194304,256,0,0,24,24,35840,0x7fb2f49b3300,0x7fb1e8e358c0,213827,213827,65536,1703936,240960,30802172,12076607049568109,12076607049740696,12076607049871896,12076607049875561
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,935069,935074,4194304,256,0,0,28,24,37312,0x7fb2f49b3a00,0x7fb1e8e35900,406265,406265,65536,2883584,391865,50146776,12076607049928539,12076607050118295,12076607050379573,12076607050448426
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,935069,935074,4194304,256,0,0,28,24,38272,0x7fb2f49b3900,0x7fb1e8e35940,399859,399859,65536,1835008,244685,31280692,12076607050474846,12076607050659252,12076607050915251,12076607050982089
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,935069,935074,4194304,256,0,0,24,24,39232,0x7fb2f49b3800,0x7fb1e8e35980,221417,221417,65536,1769472,277053,35437688,12076607051013768,12076607051199890,12076607051336209,12076607051339925
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,935069,935074,4194304,256,0,0,24,24,40192,0x7fb2f49b3700,0x7fb1e8e359c0,222395,222395,65536,2097152,309591,39541216,12076607051393314,12076607051562449,12076607051699568,12076607051703210
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,935069,935074,4194304,256,0,0,24,24,41152,0x7fb2f49b3600,0x7fb1e8e35a00,211073,211073,65536,1835008,253693,32484200,12076607051769283,12076607051935407,12076607052065166,12076607052068881
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,935069,935074,4194304,256,0,0,28,24,42624,0x7fb2f49b3500,0x7fb1e8e35a40,400595,400595,65536,3145728,419612,53657848,12076607052120667,12076607052299565,12076607052557164,12076607052598215
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,935069,935074,4194304,256,0,0,28,24,43584,0x7fb2f49b3400,0x7fb1e8e35a80,396953,396953,65536,1966080,272534,34812732,12076607052631397,12076607052799243,12076607053054122,12076607053123302
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,935069,935074,4194304,256,0,0,24,24,44544,0x7fb2f49b3300,0x7fb1e8e35ac0,221611,221611,65536,1900544,278506,35717872,12076607053150412,12076607053348841,12076607053484521,12076607053488431
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,935069,935074,4194304,256,0,0,24,24,45760,0x7fb2f49b3a00,0x7fb1e8e35b00,227921,227921,65536,2293760,307076,39319028,12076607053540548,12076607053727240,12076607053868839,12076607053872195
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,935069,935074,4194304,256,0,0,24,24,46720,0x7fb2f49b3900,0x7fb1e8e35b40,217787,217787,65536,1966080,267715,34185840,12076607053937567,12076607054107718,12076607054241317,12076607054244868
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,935069,935074,4194304,256,0,0,28,24,48448,0x7fb2f49b3800,0x7fb1e8e35b80,419897,419897,65536,3407872,482823,61784604,12076607054297807,12076607054473156,12076607054744035,12076607054810621
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,935069,935074,4194304,256,0,0,28,24,49408,0x7fb2f49b3700,0x7fb1e8e35bc0,402603,402603,65536,2097152,276300,35440948,12076607054837240,12076607055024194,12076607055282113,12076607055349473
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,935069,935074,4194304,256,0,0,24,24,50368,0x7fb2f49b3600,0x7fb1e8e35c00,228313,228313,65536,2031616,277326,35474084,12076607055376002,12076607055561152,12076607055702271,12076607055705706
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,935069,935074,4194304,256,0,0,24,24,51584,0x7fb2f49b3500,0x7fb1e8e35c40,235331,235331,65536,2490368,344616,44111616,12076607055758384,12076607055925150,12076607056071550,12076607056075353
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,935069,935074,4194304,256,0,0,24,24,52544,0x7fb2f49b3400,0x7fb1e8e35c80,215553,215553,65536,2097152,285404,36484628,12076607056141606,12076607056310589,12076607056441308,12076607056444911
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,935069,935074,4194304,256,0,0,28,24,54272,0x7fb2f49b3300,0x7fb1e8e35cc0,421987,421987,65536,3670016,495514,63310996,12076607056499983,12076607056676827,12076607056948986,12076607057018127
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,935069,935074,4194304,256,0,0,28,24,55488,0x7fb2f49b3a00,0x7fb1e8e35d00,397225,397225,65536,2228224,300078,38488544,12076607057044556,12076607057231865,12076607057487384,12076607057554595
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,935069,935074,4194304,256,0,0,24,24,56704,0x7fb2f49b3900,0x7fb1e8e35d40,214459,214459,65536,2162688,314738,40158468,12076607057578339,12076607057760663,12076607057892022,12076607057895589
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,935069,935074,4194304,256,0,0,24,24,58176,0x7fb2f49b3800,0x7fb1e8e35d80,232217,232217,65536,2686976,375703,48088720,12076607057950000,12076607058125141,12076607058269461,12076607058273332
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,935069,935074,4194304,256,0,0,24,24,59392,0x7fb2f49b3700,0x7fb1e8e35dc0,219619,219619,65536,2228224,313771,40142644,12076607058340476,12076607058507540,12076607058642899,12076607058646576
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,935069,935074,4194304,256,0,0,28,24,61376,0x7fb2f49b3600,0x7fb1e8e35e00,417929,417929,65536,3932160,534532,68482416,12076607058700897,12076607058872018,12076607059141937,12076607059210385
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,935069,935074,4194304,256,0,0,28,24,62592,0x7fb2f49b3500,0x7fb1e8e35e40,400307,400307,65536,2359296,309817,39559812,12076607059235020,12076607059420336,12076607059677935,12076607059745179
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,935069,935074,4194304,256,0,0,24,24,63808,0x7fb2f49b3400,0x7fb1e8e35e80,217825,217825,65536,2293760,319640,40936172,12076607059769354,12076607059950734,12076607060083373,12076607060087326
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,935069,935074,4194304,256,0,0,24,24,65280,0x7fb2f49b3300,0x7fb1e8e35ec0,230483,230483,65536,2883584,406531,51929100,12076607060141447,12076607060321932,12076607060465132,12076607060468775
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,935069,935074,4194304,256,0,0,24,24,66496,0x7fb2f49b3a00,0x7fb1e8e35f00,220913,220913,65536,2359296,326631,41693704,12076607060535089,12076607060698571,12076607060834890,12076607060838583
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,935069,935074,4194304,256,0,0,28,24,68480,0x7fb2f49b3900,0x7fb1e8e35f40,416051,416051,65536,4194304,617087,78847628,12076607060890480,12076607061063209,12076607061332008,12076607061400869
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,935069,935074,4194304,256,0,0,28,24,69696,0x7fb2f49b3800,0x7fb1e8e35f80,400145,400145,65536,2490368,327972,41982188,12076607061425675,12076607061609287,12076607061866726,12076607061933781
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,935069,935074,4194304,256,0,0,24,24,70912,0x7fb2f49b3700,0x7fb1e8e35fc0,224731,224731,65536,2424832,379311,48552392,12076607061957685,12076607062146725,12076607062284964,12076607062288951
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,935069,935074,4194304,256,0,0,24,24,72384,0x7fb2f49b3600,0x7fb1e8e36000,226561,226561,65536,3080192,442921,56866692,12076607062341028,12076607062513123,12076607062654403,12076607062658108
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,935069,935074,4194304,256,0,0,24,24,73600,0x7fb2f49b3500,0x7fb1e8e36040,217851,217851,65536,2490368,335219,42934564,12076607062724642,12076607062889602,12076607063023841,12076607063027876
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,935069,935074,4194304,256,0,0,28,24,75840,0x7fb2f49b3400,0x7fb1e8e36080,417505,417505,65536,4456448,603706,77498408,12076607063081515,12076607063256960,12076607063527199,12076607063594460
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,935069,935074,4194304,256,0,0,28,24,77056,0x7fb2f49b3300,0x7fb1e8e360c0,399331,399331,65536,2621440,344644,44144628,12076607063618685,12076607063806878,12076607064063517,12076607064106312
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,935069,935074,4194304,256,0,0,24,24,78272,0x7fb2f49b3a00,0x7fb1e8e36100,212497,212497,65536,2555904,364875,46724548,12076607064137640,12076607064315356,12076607064446235,12076607064450041
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,935069,935074,4194304,256,0,0,24,24,80000,0x7fb2f49b3900,0x7fb1e8e36140,230755,230755,65536,3276800,462248,59455836,12076607064507318,12076607064669914,12076607064813274,12076607064817124
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,935069,935074,4194304,256,0,0,24,24,81216,0x7fb2f49b3800,0x7fb1e8e36180,211697,211697,65536,2621440,363062,46410020,12076607064882636,12076607065053113,12076607065183512,12076607065187603
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,935069,935074,4194304,256,0,0,28,24,83456,0x7fb2f49b3700,0x7fb1e8e361c0,415971,415971,65536,4718592,619363,79527584,12076607065239670,12076607065414071,12076607065682390,12076607065730924
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,935069,935074,4194304,256,0,0,28,24,84928,0x7fb2f49b3600,0x7fb1e8e36200,399409,399409,65536,2752512,365471,46914260,12076607065754918,12076607065937429,12076607066194868,12076607066246503
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,935069,935074,4194304,256,0,0,24,24,86400,0x7fb2f49b3500,0x7fb1e8e36240,215395,215395,65536,2686976,384627,49205924,12076607066271589,12076607066456627,12076607066589106,12076607066592897
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,935069,935074,4194304,256,0,0,24,24,88128,0x7fb2f49b3400,0x7fb1e8e36280,241657,241657,65536,3473408,542279,69310404,12076607066646276,12076607066816785,12076607066967985,12076607066971792
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,935069,935074,4194304,256,0,0,24,24,89600,0x7fb2f49b3300,0x7fb1e8e362c0,224123,224123,65536,2752512,397755,50902000,12076607067062130,12076607067227984,12076607067366383,12076607067370233
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,935069,935074,4194304,256,0,0,28,24,92096,0x7fb2f49b3a00,0x7fb1e8e36300,416721,416721,65536,4980736,670509,85731704,12076607067423181,12076607067598862,12076607067868461,12076607067890330
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,935069,935074,4194304,256,0,0,28,24,93568,0x7fb2f49b3900,0x7fb1e8e36340,398979,398979,65536,2883584,380981,48708128,12076607067940624,12076607068110540,12076607068367339,12076607068417040
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,935069,935074,4194304,256,0,0,24,24,95040,0x7fb2f49b3800,0x7fb1e8e36380,222009,222009,65536,2818048,405701,51831776,12076607068441786,12076607068626218,12076607068763657,12076607068767502
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,935069,935074,4194304,256,0,0,24,24,96768,0x7fb2f49b3700,0x7fb1e8e363c0,250283,250283,65536,3670016,503137,64681772,12076607068819809,12076607068991496,12076607069147816,12076607069151877
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,935069,935074,4194304,256,0,0,24,24,98240,0x7fb2f49b3600,0x7fb1e8e36400,217937,217937,65536,2883584,391651,50102172,12076607069219864,12076607069389735,12076607069524134,12076607069528077
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,935069,935074,4194304,256,0,0,28,24,100736,0x7fb2f49b3500,0x7fb1e8e36440,412995,412995,65536,5177344,681882,87255116,12076607069580394,12076607069755013,12076607070021892,12076607070071918
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,935069,935074,4194304,256,0,0,28,24,102208,0x7fb2f49b3400,0x7fb1e8e36480,451409,451409,65536,3014656,403380,51732012,12076607070097476,12076607070281571,12076607070573730,12076607070622873
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,935069,935074,4194304,256,0,0,24,24,103680,0x7fb2f49b3300,0x7fb1e8e364c0,217907,217907,65536,2949120,423873,54142876,12076607070646778,12076607070838369,12076607070971968,12076607070975980
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,935069,935074,4194304,256,0,0,24,24,105664,0x7fb2f49b3a00,0x7fb1e8e36500,264337,264337,65536,3866624,533438,67881272,12076607071032014,12076607071208607,12076607071374846,12076607071379180
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,935069,935074,4194304,256,0,0,24,24,107136,0x7fb2f49b3900,0x7fb1e8e36540,213235,213235,65536,3014656,396179,50686140,12076607071444261,12076607071610526,12076607071741885,12076607071745912
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,935069,935074,4194304,256,0,0,28,24,109888,0x7fb2f49b3800,0x7fb1e8e36580,414657,414657,65536,5439488,704212,90138824,12076607071797729,12076607071969884,12076607072238683,12076607072288441
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,935069,935074,4194304,256,0,0,28,24,111360,0x7fb2f49b3700,0x7fb1e8e365c0,455699,455699,65536,3145728,416870,53478980,12076607072312977,12076607072499482,12076607072793721,12076607072842212
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,935069,935074,4194304,256,0,0,24,24,112832,0x7fb2f49b3600,0x7fb1e8e36600,219369,219369,65536,3080192,507763,64933636,12076607072865866,12076607073053560,12076607073188599,12076607073192814
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,935069,935074,4194304,256,0,0,24,24,114816,0x7fb2f49b3500,0x7fb1e8e36640,277547,277547,65536,4063232,553684,70680060,12076607073246313,12076607073417878,12076607073592757,12076607073596585
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,935069,935074,4194304,256,0,0,24,24,116288,0x7fb2f49b3400,0x7fb1e8e36680,223001,223001,65536,3145728,456216,58399568,12076607073663760,12076607073828436,12076607073966516,12076607073970330
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,935069,935074,4194304,256,0,0,28,24,119040,0x7fb2f49b3300,0x7fb1e8e366c0,413939,413939,65536,5701632,829430,106122232,12076607074030302,12076607074209235,12076607074477234,12076607074526254
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,935069,935074,4194304,256,0,0,28,24,120768,0x7fb2f49b3a00,0x7fb1e8e36700,403385,403385,65536,3276800,429855,54875156,12076607074550008,12076607074734033,12076607074994511,12076607075021405
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,935069,935074,4194304,256,0,0,24,24,122496,0x7fb2f49b3900,0x7fb1e8e36740,225675,225675,65536,3211264,488349,62521156,12076607075064275,12076607075231791,12076607075371630,12076607075375804
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,935069,935074,4194304,256,0,0,24,24,124736,0x7fb2f49b3800,0x7fb1e8e36780,291617,291617,65536,4259840,586782,74985140,12076607075427470,12076607075601229,12076607075784428,12076607075788272
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,935069,935074,4194304,256,0,0,24,24,126464,0x7fb2f49b3700,0x7fb1e8e367c0,225755,225755,65536,3276800,499862,63952216,12076607075856068,12076607076026827,12076607076166827,12076607076170813
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,935069,935074,4194304,256,0,0,20,24,127936,0x7fb2f49b3600,0x7fb1e8e36800,412089,412089,65536,7733248,977658,125097504,12076607076223321,12076607076399626,12076607076667145,12076607076719043
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,935069,935074,4194304,256,0,0,28,24,129664,0x7fb2f49b3500,0x7fb1e8e36840,407651,407651,65536,3407872,444297,56593724,12076607076745262,12076607076932583,12076607077195462,12076607077244190
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,935069,935074,4194304,256,0,0,24,24,131392,0x7fb2f49b3400,0x7fb1e8e36880,226969,226969,65536,3342336,458648,58735012,12076607077268305,12076607077456421,12076607077597221,12076607077601154
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,935069,935074,4194304,256,0,0,24,24,133632,0x7fb2f49b3300,0x7fb1e8e368c0,301475,301475,65536,4456448,635716,81143032,12076607077658561,12076607077822020,12076607078013859,12076607078060408
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,935069,935074,4194304,256,0,0,24,24,135360,0x7fb2f49b3a00,0x7fb1e8e36900,229737,229737,65536,3538944,531910,68167600,12076607078098489,12076607078264578,12076607078405377,12076607078409077
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,935069,935074,4194304,256,0,0,20,24,136832,0x7fb2f49b3900,0x7fb1e8e36940,435539,435539,65536,8978432,1128815,144500616,12076607078466043,12076607078630496,12076607078914335,12076607078935496
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,935069,935074,4194304,256,0,0,28,24,138560,0x7fb2f49b3800,0x7fb1e8e36980,394617,394617,65536,3670016,514021,66048348,12076607078982634,12076607079152734,12076607079408413,12076607079457617
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,935069,935074,4194304,256,0,0,24,24,140288,0x7fb2f49b3700,0x7fb1e8e369c0,227075,227075,65536,3604480,524153,67172096,12076607079483415,12076607079665852,12076607079806652,12076607079810473
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,935069,935074,4194304,256,0,0,24,24,142784,0x7fb2f49b3600,0x7fb1e8e36a00,329097,329097,65536,4849664,692690,87980460,12076607079864043,12076607080040891,12076607080251610,12076607080300435
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,935069,935074,4194304,256,0,0,24,24,144768,0x7fb2f49b3500,0x7fb1e8e36a40,226403,226403,65536,3801088,581253,74372408,12076607080338455,12076607080503929,12076607080644408,12076607080648081
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,935069,935074,4194304,256,0,0,20,24,145728,0x7fb2f49b3400,0x7fb1e8e36a80,470537,470537,65536,14548992,1828637,234034324,12076607080700419,12076607080878167,12076607081185526,12076607081234983
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,935069,935074,4194304,256,0,0,28,24,147712,0x7fb2f49b3300,0x7fb1e8e36ac0,404651,404651,65536,3932160,518104,66211720,12076607081261102,12076607081443605,12076607081705684,12076607081752906
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,935069,935074,4194304,256,0,0,24,24,149696,0x7fb2f49b3a00,0x7fb1e8e36b00,218833,218833,65536,3866624,618650,79262516,12076607081776971,12076607081958803,12076607082095282,12076607082099411
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,935069,935074,4194304,256,0,0,24,24,152192,0x7fb2f49b3900,0x7fb1e8e36b40,356915,356915,65536,5242880,719398,92075292,12076607082150867,12076607082327281,12076607082556080,12076607082603138
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,935069,935074,4194304,256,0,0,24,24,154176,0x7fb2f49b3800,0x7fb1e8e36b80,222913,222913,65536,4063232,627426,80319960,12076607082639516,12076607082803919,12076607082942479,12076607082946397
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,935069,935074,4194304,256,0,0,20,24,155648,0x7fb2f49b3700,0x7fb1e8e36bc0,503139,503139,65536,10027008,1262411,161220076,12076607082998554,12076607083181038,12076607083510156,12076607083559106
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,935069,935074,4194304,256,0,0,28,24,157632,0x7fb2f49b3600,0x7fb1e8e36c00,406481,406481,65536,4194304,545664,69736164,12076607083581979,12076607083767479,12076607084031479,12076607084082600
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,935069,935074,4194304,256,0,0,24,24,159616,0x7fb2f49b3500,0x7fb1e8e36c40,221899,221899,65536,4128768,622734,79652544,12076607084104861,12076607084305877,12076607084443476,12076607084446487
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,935069,935074,4194304,256,0,0,24,24,162368,0x7fb2f49b3400,0x7fb1e8e36c80,381041,381041,65536,5636096,770775,98247000,12076607084501569,12076607084677556,12076607084922995,12076607084969299
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,935069,935074,4194304,256,0,0,24,24,164608,0x7fb2f49b3300,0x7fb1e8e36cc0,226619,226619,65536,4587520,655899,83961808,12076607085013682,12076607085180914,12076607085321394,12076607085324680
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,935069,935074,4194304,256,0,0,20,24,166336,0x7fb2f49b3a00,0x7fb1e8e36d00,575985,575985,65536,11075584,1394189,178374672,12076607085378210,12076607085546673,12076607085925232,12076607085971684
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,935069,935074,4194304,256,0,0,28,24,168576,0x7fb2f49b3900,0x7fb1e8e36d40,401963,401963,65536,4718592,669814,85825632,12076607085995318,12076607086186031,12076607086446350,12076607086466625
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,935069,935074,4194304,256,0,0,24,24,170816,0x7fb2f49b3800,0x7fb1e8e36d80,223681,223681,65536,4653056,667946,85594900,12076607086512831,12076607086678350,12076607086817389,12076607086820583
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,935069,935074,4194304,256,0,0,24,24,174080,0x7fb2f49b3700,0x7fb1e8e36dc0,434675,434675,65536,6422528,894480,114787936,12076607086873562,12076607087072588,12076607087352747,12076607087401173
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,935069,935074,4194304,256,0,0,24,24,176576,0x7fb2f49b3600,0x7fb1e8e36e00,222969,222969,65536,5111808,791119,101342588,12076607087445996,12076607087616747,12076607087755786,12076607087758949
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,935069,935074,4194304,256,0,0,20,24,177792,0x7fb2f49b3500,0x7fb1e8e36e40,647523,647523,65536,15007744,1881597,241002168,12076607087810795,12076607087984265,12076607088411144,12076607088458590
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,935069,935074,4194304,256,0,0,28,24,180288,0x7fb2f49b3400,0x7fb1e8e36e80,409081,409081,65536,5242880,687313,88316524,12076607088483737,12076607088676423,12076607088941863,12076607088988656
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,935069,935074,4194304,256,0,0,24,24,182784,0x7fb2f49b3300,0x7fb1e8e36ec0,219755,219755,65536,5177344,789959,101051380,12076607089016728,12076607089211302,12076607089347781,12076607089351190
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,935069,935074,4194304,256,0,0,24,24,186304,0x7fb2f49b3a00,0x7fb1e8e36f00,488401,488401,65536,7208960,979036,126381744,12076607089404860,12076607089575941,12076607089891620,12076607089939795
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,935069,935074,4194304,256,0,0,24,24,189312,0x7fb2f49b3900,0x7fb1e8e36f40,244835,244835,65536,6160384,944851,120972172,12076607089986332,12076607090161059,12076607090314658,12076607090317918
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,935069,935074,4194304,256,0,0,20,24,190784,0x7fb2f49b3800,0x7fb1e8e36f80,784929,784929,65536,17104896,2148466,275140452,12076607090370406,12076607090554978,12076607091073216,12076607091095254
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,935069,935074,4194304,256,0,0,28,24,193792,0x7fb2f49b3700,0x7fb1e8e36fc0,456899,456899,65536,6291456,835568,107190536,12076607091150217,12076607091319295,12076607091617534,12076607091664734
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,935069,935074,4194304,256,0,0,24,24,196800,0x7fb2f49b3600,0x7fb1e8e37000,245729,245729,65536,6225920,915795,117326864,12076607091693597,12076607091877534,12076607092032253,12076607092035654
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,935069,935074,4194304,256,0,0,24,24,201088,0x7fb2f49b3500,0x7fb1e8e37040,593875,593875,65536,8781824,1249565,160133432,12076607092090175,12076607092276092,12076607092662171,12076607092708766
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,935069,935074,4194304,256,0,0,24,24,204608,0x7fb2f49b3400,0x7fb1e8e37080,276121,276121,65536,7208960,1008435,128927104,12076607092748720,12076607092914170,12076607093089530,12076607093092900
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,935069,935074,4194304,256,0,0,20,24,206080,0x7fb2f49b3300,0x7fb1e8e370c0,942539,942539,65536,19202048,2414294,308160104,12076607093146069,12076607093323929,12076607093946647,12076607093994998
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,935069,935074,4194304,256,0,0,28,24,209600,0x7fb2f49b3a00,0x7fb1e8e37100,505193,505193,65536,7340032,959851,122951072,12076607094019965,12076607094212086,12076607094542965,12076607094590246
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,935069,935074,4194304,256,0,0,24,24,213120,0x7fb2f49b3900,0x7fb1e8e37140,280955,280955,65536,7274496,1035974,132703404,12076607094614210,12076607094796245,12076607094974324,12076607094977506
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,935069,935074,4194304,256,0,0,24,24,218176,0x7fb2f49b3800,0x7fb1e8e37180,700225,700225,65536,10354688,1451513,185974588,12076607095031627,12076607095211123,12076607095668562,12076607095716130
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,935069,935074,4194304,256,0,0,24,24,222208,0x7fb2f49b3700,0x7fb1e8e371c0,370371,370371,65536,8257536,1151861,147391804,12076607095756805,12076607095923761,12076607096161360,12076607096209638
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,935069,935074,4194304,256,0,0,20,24,223936,0x7fb2f49b3600,0x7fb1e8e37200,1065625,1065625,65536,21299200,2669811,341662804,12076607096234704,12076607096420240,12076607097124077,12076607097171597
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,935069,935074,4194304,256,0,0,28,24,227968,0x7fb2f49b3500,0x7fb1e8e37240,567019,567019,65536,8388608,1192134,152811500,12076607097204899,12076607097392717,12076607097765835,12076607097812710
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,935069,935074,4194304,256,0,0,24,24,232000,0x7fb2f49b3400,0x7fb1e8e37280,374217,374217,65536,8323072,1289301,164974828,12076607097836945,12076607098034635,12076607098275114,12076607098329020
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,935069,935074,4194304,256,0,0,24,24,237824,0x7fb2f49b3300,0x7fb1e8e372c0,806699,806699,65536,11927552,1610806,206248708,12076607098355369,12076607098555593,12076607099083911,12076607099132585
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,935069,935074,4194304,256,0,0,24,24,242368,0x7fb2f49b3a00,0x7fb1e8e37300,349865,349865,65536,9306112,1445438,185100516,12076607099174683,12076607099343591,12076607099568710,12076607099616745
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,935069,935074,4194304,256,0,0,20,24,243584,0x7fb2f49b3900,0x7fb1e8e37340,1208963,1208963,65536,29163520,3652378,467598068,12076607099646741,12076607099823589,12076607100625027,12076607100675295
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,935069,935074,4194304,256,0,0,28,24,248128,0x7fb2f49b3800,0x7fb1e8e37380,642609,642609,65536,9437184,1259387,161220340,12076607100700642,12076607100885986,12076607101308065,12076607101377501
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,935069,935074,4194304,256,0,0,24,24,252672,0x7fb2f49b3700,0x7fb1e8e373c0,352675,352675,65536,9371648,1362401,174437700,12076607101401405,12076607101586944,12076607101812863,12076607101853486
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,935069,935074,4194304,256,0,0,24,24,259264,0x7fb2f49b3600,0x7fb1e8e37400,909297,909297,65536,13500416,1939392,249470212,12076607101889804,12076607102070942,12076607102668540,12076607102736529
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,935069,935074,4194304,256,0,0,24,24,264832,0x7fb2f49b3500,0x7fb1e8e37440,419643,419643,65536,11403264,1810727,231780600,12076607102773227,12076607102951099,12076607103221499,12076607103288866
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,935069,935074,4194304,256,0,0,20,24,266304,0x7fb2f49b3400,0x7fb1e8e37480,1486913,1486913,65536,33357824,4176847,534462840,12076607103313472,12076607103498618,12076607104484535,12076607104551705
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,935069,935074,4194304,256,0,0,28,24,271872,0x7fb2f49b3300,0x7fb1e8e374c0,776779,776779,65536,11534336,1559715,199237440,12076607104575750,12076607104769654,12076607105284692,12076607105351593
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,935069,935074,4194304,256,0,0,24,24,277440,0x7fb2f49b3a00,0x7fb1e8e37500,426753,426753,65536,11534336,1851403,236927948,12076607105381649,12076607105566611,12076607105840691,12076607105906605
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,935069,935074,4194304,256,0,0,12,24,279936,0x7fb2f49b3900,0x7fb1e8e37540,1125395,1125395,65536,19267584,2430276,311028800,12076607105932844,12076607106126290,12076607106865007,12076607106933055
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,935069,935074,4194304,256,0,0,24,24,286528,0x7fb2f49b3800,0x7fb1e8e37580,486113,486113,65536,13500416,1989643,254748480,12076607106973300,12076607107145487,12076607107461486,12076607107527841
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,935069,935074,4194304,256,0,0,20,24,288000,0x7fb2f49b3700,0x7fb1e8e375c0,1768347,1768347,65536,37552128,4698100,601656016,12076607107554941,12076607107742125,12076607108914921,12076607108982587
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,935069,935074,4194304,256,0,0,32,24,294592,0x7fb2f49b3600,0x7fb1e8e37600,916145,916145,65536,13631488,1837594,235009216,12076607109018424,12076607109204200,12076607109814118,12076607109881229
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,935069,935074,4194304,256,0,0,24,24,301184,0x7fb2f49b3500,0x7fb1e8e37640,492811,492811,65536,13631488,2078014,266048836,12076607109909411,12076607110110597,12076607110430276,12076607110499398
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,935069,935074,4194304,256,0,0,12,24,304960,0x7fb2f49b3400,0x7fb1e8e37680,1336065,1336065,65536,21692416,2740602,350269840,12076607110534754,12076607110704516,12076607111582753,12076607111651411
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,935069,935074,4194304,256,0,0,24,24,313600,0x7fb2f49b3300,0x7fb1e8e376c0,632747,632747,65536,17694720,2788850,356809268,12076607111700342,12076607111867392,12076607112280991,12076607112347516
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,935069,935074,4194304,256,0,0,20,24,314816,0x7fb2f49b3a00,0x7fb1e8e37700,2332393,2332393,65536,57475072,7193674,920847108,12076607112378243,12076607112564030,12076607114112985,12076607114179414
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,935069,935074,4194304,256,0,0,20,24,317568,0x7fb2f49b3900,0x7fb1e8e37740,1200323,1200323,65536,19660800,2471365,316217244,12076607114210191,12076607114395704,12076607115190902,12076607115257670
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,935069,935074,4194304,256,0,0,12,24,320320,0x7fb2f49b3800,0x7fb1e8e37780,640169,640169,65536,20381696,2574270,329482260,12076607115287555,12076607115473301,12076607115888660,12076607115954926
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,935069,935074,4194304,256,0,0,12,24,324096,0x7fb2f49b3700,0x7fb1e8e377c0,1757027,1757027,65536,28704768,3613734,462492340,12076607115982508,12076607116170899,12076607117329615,12076607117396298
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,935069,935074,4194304,256,0,0,12,24,328896,0x7fb2f49b3600,0x7fb1e8e37800,1200825,1200825,65536,36634624,4627052,592393124,12076607117434739,12076607117604014,12076607118390892,12076607118457622
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,935069,935074,4194304,256,0,0,20,24,330112,0x7fb2f49b3500,0x7fb1e8e37840,4583811,4583811,65536,105840640,13238877,1694936080,12076607118490763,12076607118680971,12076607121732962,12076607121800290
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,935069,935074,4194304,256,0,0,20,24,332864,0x7fb2f49b3400,0x7fb1e8e37880,2324345,2324345,65536,38535168,4833306,618039328,12076607121831808,12076607122027681,12076607123570556,12076607123639781
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,935069,935074,4194304,256,0,0,12,24,335616,0x7fb2f49b3300,0x7fb1e8e378c0,1202627,1202627,65536,39124992,4909655,628517764,12076607123663065,12076607123857915,12076607124647353,12076607124713499
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,935069,935074,4194304,256,0,0,12,24,339392,0x7fb2f49b3a00,0x7fb1e8e37900,3442929,3442929,65536,55771136,7010935,897488352,12076607124738455,12076607124929752,12076607127212465,12076607127280584
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,935069,935074,4194304,256,0,0,12,24,344192,0x7fb2f49b3900,0x7fb1e8e37940,2322507,2322507,65536,72548352,9109453,1166161620,12076607127325978,12076607127497744,12076607129033259,12076607129100299
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,935069,935074,4194304,256,0,0,20,24,345408,0x7fb2f49b3800,0x7fb1e8e37980,9086257,9086257,65536,210698240,26342168,3372581544,12076607129130234,12076607129314698,12076607135372600,12076607135440141
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,935069,935074,4194304,256,0,0,20,24,348160,0x7fb2f49b3700,0x7fb1e8e379c0,4572891,4572891,65536,76283904,9533686,1221835664,12076607135472702,12076607135649719,12076607138693070,12076607138760458
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,935069,935074,4194304,256,0,0,12,24,350912,0x7fb2f49b3600,0x7fb1e8e37a00,2328209,2328209,65536,77398016,9689987,1240750856,12076607138789231,12076607138985709,12076607140524904,12076607140593778
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,935069,935074,4194304,256,0,0,12,24,0,0x7fb2f49b3500,0x7fb1e8e37a40,6811723,6811723,65536,110821376,13888539,1777979164,12076607140622982,12076607140811943,12076607145340089,12076607145411670
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 935069 935074 33554432 256 0 0 8 32 6464 0x0 0x7fb1e8e04180 504417 504417 524288 6291456 791548 101536232 12076606776836515 12076607020949616 12076607021273775 12076607021386317
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 935069 935074 32768 256 0 0 24 24 12480 0x0 0x7fb1e8e35100 27457 27457 512 8192 8659 1112808 12076607036018836 12076607036328752 12076607036334672 12076607036343359
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 4 935069 935074 4194304 256 0 0 24 24 12928 0x7fb2f49b3900 0x7fb1e8e35140 221451 221451 65536 917504 137700 17627108 12076607036410164 12076607036634350 12076607036769870 12076607036773860
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 935069 935074 4194304 256 0 0 36 24 13632 0x7fb2f49b3800 0x7fb1e8e35180 398529 398529 65536 1245184 176363 22595116 12076607036850743 12076607037034989 12076607037288428 12076607037361443
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 8 935069 935074 4194304 256 0 0 28 24 14080 0x7fb2f49b3700 0x7fb1e8e351c0 410715 410715 65536 983040 136833 17475532 12076607037393453 12076607037585546 12076607037846505 12076607037914191
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 10 935069 935074 4194304 256 0 0 24 24 14528 0x7fb2f49b3600 0x7fb1e8e35200 226705 226705 65536 1048576 153290 19537144 12076607037942794 12076607038138984 12076607038278504 12076607038282236
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 12 935069 935074 4194304 256 0 0 24 24 14976 0x7fb2f49b3500 0x7fb1e8e35240 228547 228547 65536 983040 147995 18962320 12076607038336266 12076607038515783 12076607038656262 12076607038659818
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 14 935069 935074 4194304 256 0 0 24 24 15424 0x7fb2f49b3400 0x7fb1e8e35280 216161 216161 65536 1048576 146752 18784452 12076607038742652 12076607038911941 12076607039044420 12076607039048191
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 935069 935074 4194304 256 0 0 28 24 16128 0x7fb2f49b3300 0x7fb1e8e352c0 407219 407219 65536 1572864 245751 31439136 12076607039102291 12076607039289699 12076607039549378 12076607039593976
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 18 935069 935074 4194304 256 0 0 28 24 16832 0x7fb2f49b3a00 0x7fb1e8e35300 402961 402961 65536 1179648 166989 21330680 12076607039617790 12076607039813377 12076607040069536 12076607040112089
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 20 935069 935074 4194304 256 0 0 24 24 17536 0x7fb2f49b3900 0x7fb1e8e35340 211699 211699 65536 1114112 161801 20744520 12076607040145602 12076607040328415 12076607040457535 12076607040461169
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 22 935069 935074 4194304 256 0 0 24 24 18240 0x7fb2f49b3800 0x7fb1e8e35380 228737 228737 65536 1114112 157285 20107324 12076607040513937 12076607040691774 12076607040832413 12076607040835916
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 24 935069 935074 4194304 256 0 0 24 24 18944 0x7fb2f49b3700 0x7fb1e8e353c0 217083 217083 65536 1179648 164032 20966992 12076607040903351 12076607041083932 12076607041216731 12076607041220842
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 935069 935074 4194304 256 0 0 28 24 19904 0x7fb2f49b3600 0x7fb1e8e35400 406313 406313 65536 1835008 252183 32259532 12076607041274622 12076607041448410 12076607041705849 12076607041774261
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 28 935069 935074 4194304 256 0 0 28 24 20608 0x7fb2f49b3500 0x7fb1e8e35440 404715 404715 65536 1310720 179910 23054132 12076607041801262 12076607041986328 12076607042243607 12076607042312442
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 30 935069 935074 4194304 256 0 0 24 24 21312 0x7fb2f49b3400 0x7fb1e8e35480 216817 216817 65536 1245184 174001 22306216 12076607042340044 12076607042526486 12076607042659445 12076607042663235
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 32 935069 935074 4194304 256 0 0 24 24 22016 0x7fb2f49b3300 0x7fb1e8e354c0 219347 219347 65536 1310720 181451 23167172 12076607042717035 12076607042886484 12076607043020084 12076607043024036
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 34 935069 935074 4194304 256 0 0 24 24 22720 0x7fb2f49b3a00 0x7fb1e8e35500 216545 216545 65536 1310720 180617 23118392 12076607043091932 12076607043261843 12076607043394642 12076607043398342
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 935069 935074 4194304 256 0 0 28 24 23680 0x7fb2f49b3900 0x7fb1e8e35540 410411 410411 65536 2097152 298957 38165200 12076607043453104 12076607043629521 12076607043891600 12076607043936203
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 38 935069 935074 4194304 256 0 0 28 24 24384 0x7fb2f49b3800 0x7fb1e8e35580 405265 405265 65536 1441792 197254 25187912 12076607043960438 12076607044156879 12076607044415758 12076607044457943
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 40 935069 935074 4194304 256 0 0 24 24 25088 0x7fb2f49b3700 0x7fb1e8e355c0 211955 211955 65536 1376256 190093 24361152 12076607044494992 12076607044662797 12076607044791757 12076607044795531
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 42 935069 935074 4194304 256 0 0 24 24 25792 0x7fb2f49b3600 0x7fb1e8e35600 224401 224401 65536 1507328 211513 27052060 12076607044848650 12076607045029676 12076607045167755 12076607045172192
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 44 935069 935074 4194304 256 0 0 24 24 26496 0x7fb2f49b3500 0x7fb1e8e35640 213291 213291 65536 1441792 206408 26511396 12076607045238255 12076607045408394 12076607045538153 12076607045541819
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 935069 935074 4194304 256 0 0 28 24 27712 0x7fb2f49b3400 0x7fb1e8e35680 406521 406521 65536 2359296 322321 41245052 12076607045594057 12076607045769673 12076607046029831 12076607046098796
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 48 935069 935074 4194304 256 0 0 28 24 28416 0x7fb2f49b3300 0x7fb1e8e356c0 402387 402387 65536 1572864 210221 26926876 12076607046130294 12076607046318790 12076607046576069 12076607046643980
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 50 935069 935074 4194304 256 0 0 24 24 29120 0x7fb2f49b3a00 0x7fb1e8e35700 213697 213697 65536 1507328 217132 27733596 12076607046675619 12076607046861028 12076607046992387 12076607046996125
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 52 935069 935074 4194304 256 0 0 24 24 30080 0x7fb2f49b3900 0x7fb1e8e35740 229571 229571 65536 1703936 233010 29842576 12076607047049554 12076607047231586 12076607047372866 12076607047376693
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 54 935069 935074 4194304 256 0 0 24 24 30784 0x7fb2f49b3800 0x7fb1e8e35780 221441 221441 65536 1572864 215600 27520968 12076607047442275 12076607047610785 12076607047746944 12076607047750738
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 935069 935074 4194304 256 0 0 28 24 32000 0x7fb2f49b3700 0x7fb1e8e357c0 397083 397083 65536 2621440 359612 46041044 12076607047804589 12076607047973503 12076607048228062 12076607048272499
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 58 935069 935074 4194304 256 0 0 28 24 32960 0x7fb2f49b3600 0x7fb1e8e35800 401329 401329 65536 1703936 230733 29537124 12076607048299870 12076607048484861 12076607048741500 12076607048782758
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 60 935069 935074 4194304 256 0 0 24 24 33920 0x7fb2f49b3500 0x7fb1e8e35840 220467 220467 65536 1638400 229834 29380464 12076607048815619 12076607048987739 12076607049123099 12076607049127129
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 62 935069 935074 4194304 256 0 0 24 24 34880 0x7fb2f49b3400 0x7fb1e8e35880 229225 229225 65536 1900544 266452 34181504 12076607049180618 12076607049356698 12076607049498297 12076607049502086
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 64 935069 935074 4194304 256 0 0 24 24 35840 0x7fb2f49b3300 0x7fb1e8e358c0 213827 213827 65536 1703936 240960 30802172 12076607049568109 12076607049740696 12076607049871896 12076607049875561
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 935069 935074 4194304 256 0 0 28 24 37312 0x7fb2f49b3a00 0x7fb1e8e35900 406265 406265 65536 2883584 391865 50146776 12076607049928539 12076607050118295 12076607050379573 12076607050448426
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 68 935069 935074 4194304 256 0 0 28 24 38272 0x7fb2f49b3900 0x7fb1e8e35940 399859 399859 65536 1835008 244685 31280692 12076607050474846 12076607050659252 12076607050915251 12076607050982089
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 70 935069 935074 4194304 256 0 0 24 24 39232 0x7fb2f49b3800 0x7fb1e8e35980 221417 221417 65536 1769472 277053 35437688 12076607051013768 12076607051199890 12076607051336209 12076607051339925
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 72 935069 935074 4194304 256 0 0 24 24 40192 0x7fb2f49b3700 0x7fb1e8e359c0 222395 222395 65536 2097152 309591 39541216 12076607051393314 12076607051562449 12076607051699568 12076607051703210
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 74 935069 935074 4194304 256 0 0 24 24 41152 0x7fb2f49b3600 0x7fb1e8e35a00 211073 211073 65536 1835008 253693 32484200 12076607051769283 12076607051935407 12076607052065166 12076607052068881
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 935069 935074 4194304 256 0 0 28 24 42624 0x7fb2f49b3500 0x7fb1e8e35a40 400595 400595 65536 3145728 419612 53657848 12076607052120667 12076607052299565 12076607052557164 12076607052598215
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 78 935069 935074 4194304 256 0 0 28 24 43584 0x7fb2f49b3400 0x7fb1e8e35a80 396953 396953 65536 1966080 272534 34812732 12076607052631397 12076607052799243 12076607053054122 12076607053123302
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 80 935069 935074 4194304 256 0 0 24 24 44544 0x7fb2f49b3300 0x7fb1e8e35ac0 221611 221611 65536 1900544 278506 35717872 12076607053150412 12076607053348841 12076607053484521 12076607053488431
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 82 935069 935074 4194304 256 0 0 24 24 45760 0x7fb2f49b3a00 0x7fb1e8e35b00 227921 227921 65536 2293760 307076 39319028 12076607053540548 12076607053727240 12076607053868839 12076607053872195
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 84 935069 935074 4194304 256 0 0 24 24 46720 0x7fb2f49b3900 0x7fb1e8e35b40 217787 217787 65536 1966080 267715 34185840 12076607053937567 12076607054107718 12076607054241317 12076607054244868
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 935069 935074 4194304 256 0 0 28 24 48448 0x7fb2f49b3800 0x7fb1e8e35b80 419897 419897 65536 3407872 482823 61784604 12076607054297807 12076607054473156 12076607054744035 12076607054810621
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 88 935069 935074 4194304 256 0 0 28 24 49408 0x7fb2f49b3700 0x7fb1e8e35bc0 402603 402603 65536 2097152 276300 35440948 12076607054837240 12076607055024194 12076607055282113 12076607055349473
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 90 935069 935074 4194304 256 0 0 24 24 50368 0x7fb2f49b3600 0x7fb1e8e35c00 228313 228313 65536 2031616 277326 35474084 12076607055376002 12076607055561152 12076607055702271 12076607055705706
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 92 935069 935074 4194304 256 0 0 24 24 51584 0x7fb2f49b3500 0x7fb1e8e35c40 235331 235331 65536 2490368 344616 44111616 12076607055758384 12076607055925150 12076607056071550 12076607056075353
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 94 935069 935074 4194304 256 0 0 24 24 52544 0x7fb2f49b3400 0x7fb1e8e35c80 215553 215553 65536 2097152 285404 36484628 12076607056141606 12076607056310589 12076607056441308 12076607056444911
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 935069 935074 4194304 256 0 0 28 24 54272 0x7fb2f49b3300 0x7fb1e8e35cc0 421987 421987 65536 3670016 495514 63310996 12076607056499983 12076607056676827 12076607056948986 12076607057018127
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 98 935069 935074 4194304 256 0 0 28 24 55488 0x7fb2f49b3a00 0x7fb1e8e35d00 397225 397225 65536 2228224 300078 38488544 12076607057044556 12076607057231865 12076607057487384 12076607057554595
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 100 935069 935074 4194304 256 0 0 24 24 56704 0x7fb2f49b3900 0x7fb1e8e35d40 214459 214459 65536 2162688 314738 40158468 12076607057578339 12076607057760663 12076607057892022 12076607057895589
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 102 935069 935074 4194304 256 0 0 24 24 58176 0x7fb2f49b3800 0x7fb1e8e35d80 232217 232217 65536 2686976 375703 48088720 12076607057950000 12076607058125141 12076607058269461 12076607058273332
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 104 935069 935074 4194304 256 0 0 24 24 59392 0x7fb2f49b3700 0x7fb1e8e35dc0 219619 219619 65536 2228224 313771 40142644 12076607058340476 12076607058507540 12076607058642899 12076607058646576
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 935069 935074 4194304 256 0 0 28 24 61376 0x7fb2f49b3600 0x7fb1e8e35e00 417929 417929 65536 3932160 534532 68482416 12076607058700897 12076607058872018 12076607059141937 12076607059210385
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 108 935069 935074 4194304 256 0 0 28 24 62592 0x7fb2f49b3500 0x7fb1e8e35e40 400307 400307 65536 2359296 309817 39559812 12076607059235020 12076607059420336 12076607059677935 12076607059745179
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 110 935069 935074 4194304 256 0 0 24 24 63808 0x7fb2f49b3400 0x7fb1e8e35e80 217825 217825 65536 2293760 319640 40936172 12076607059769354 12076607059950734 12076607060083373 12076607060087326
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 112 935069 935074 4194304 256 0 0 24 24 65280 0x7fb2f49b3300 0x7fb1e8e35ec0 230483 230483 65536 2883584 406531 51929100 12076607060141447 12076607060321932 12076607060465132 12076607060468775
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 114 935069 935074 4194304 256 0 0 24 24 66496 0x7fb2f49b3a00 0x7fb1e8e35f00 220913 220913 65536 2359296 326631 41693704 12076607060535089 12076607060698571 12076607060834890 12076607060838583
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 935069 935074 4194304 256 0 0 28 24 68480 0x7fb2f49b3900 0x7fb1e8e35f40 416051 416051 65536 4194304 617087 78847628 12076607060890480 12076607061063209 12076607061332008 12076607061400869
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 118 935069 935074 4194304 256 0 0 28 24 69696 0x7fb2f49b3800 0x7fb1e8e35f80 400145 400145 65536 2490368 327972 41982188 12076607061425675 12076607061609287 12076607061866726 12076607061933781
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 120 935069 935074 4194304 256 0 0 24 24 70912 0x7fb2f49b3700 0x7fb1e8e35fc0 224731 224731 65536 2424832 379311 48552392 12076607061957685 12076607062146725 12076607062284964 12076607062288951
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 122 935069 935074 4194304 256 0 0 24 24 72384 0x7fb2f49b3600 0x7fb1e8e36000 226561 226561 65536 3080192 442921 56866692 12076607062341028 12076607062513123 12076607062654403 12076607062658108
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 124 935069 935074 4194304 256 0 0 24 24 73600 0x7fb2f49b3500 0x7fb1e8e36040 217851 217851 65536 2490368 335219 42934564 12076607062724642 12076607062889602 12076607063023841 12076607063027876
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 935069 935074 4194304 256 0 0 28 24 75840 0x7fb2f49b3400 0x7fb1e8e36080 417505 417505 65536 4456448 603706 77498408 12076607063081515 12076607063256960 12076607063527199 12076607063594460
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 128 935069 935074 4194304 256 0 0 28 24 77056 0x7fb2f49b3300 0x7fb1e8e360c0 399331 399331 65536 2621440 344644 44144628 12076607063618685 12076607063806878 12076607064063517 12076607064106312
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 130 935069 935074 4194304 256 0 0 24 24 78272 0x7fb2f49b3a00 0x7fb1e8e36100 212497 212497 65536 2555904 364875 46724548 12076607064137640 12076607064315356 12076607064446235 12076607064450041
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 132 935069 935074 4194304 256 0 0 24 24 80000 0x7fb2f49b3900 0x7fb1e8e36140 230755 230755 65536 3276800 462248 59455836 12076607064507318 12076607064669914 12076607064813274 12076607064817124
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 134 935069 935074 4194304 256 0 0 24 24 81216 0x7fb2f49b3800 0x7fb1e8e36180 211697 211697 65536 2621440 363062 46410020 12076607064882636 12076607065053113 12076607065183512 12076607065187603
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 935069 935074 4194304 256 0 0 28 24 83456 0x7fb2f49b3700 0x7fb1e8e361c0 415971 415971 65536 4718592 619363 79527584 12076607065239670 12076607065414071 12076607065682390 12076607065730924
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 138 935069 935074 4194304 256 0 0 28 24 84928 0x7fb2f49b3600 0x7fb1e8e36200 399409 399409 65536 2752512 365471 46914260 12076607065754918 12076607065937429 12076607066194868 12076607066246503
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 140 935069 935074 4194304 256 0 0 24 24 86400 0x7fb2f49b3500 0x7fb1e8e36240 215395 215395 65536 2686976 384627 49205924 12076607066271589 12076607066456627 12076607066589106 12076607066592897
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 142 935069 935074 4194304 256 0 0 24 24 88128 0x7fb2f49b3400 0x7fb1e8e36280 241657 241657 65536 3473408 542279 69310404 12076607066646276 12076607066816785 12076607066967985 12076607066971792
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 144 935069 935074 4194304 256 0 0 24 24 89600 0x7fb2f49b3300 0x7fb1e8e362c0 224123 224123 65536 2752512 397755 50902000 12076607067062130 12076607067227984 12076607067366383 12076607067370233
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 935069 935074 4194304 256 0 0 28 24 92096 0x7fb2f49b3a00 0x7fb1e8e36300 416721 416721 65536 4980736 670509 85731704 12076607067423181 12076607067598862 12076607067868461 12076607067890330
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 148 935069 935074 4194304 256 0 0 28 24 93568 0x7fb2f49b3900 0x7fb1e8e36340 398979 398979 65536 2883584 380981 48708128 12076607067940624 12076607068110540 12076607068367339 12076607068417040
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 150 935069 935074 4194304 256 0 0 24 24 95040 0x7fb2f49b3800 0x7fb1e8e36380 222009 222009 65536 2818048 405701 51831776 12076607068441786 12076607068626218 12076607068763657 12076607068767502
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 152 935069 935074 4194304 256 0 0 24 24 96768 0x7fb2f49b3700 0x7fb1e8e363c0 250283 250283 65536 3670016 503137 64681772 12076607068819809 12076607068991496 12076607069147816 12076607069151877
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 154 935069 935074 4194304 256 0 0 24 24 98240 0x7fb2f49b3600 0x7fb1e8e36400 217937 217937 65536 2883584 391651 50102172 12076607069219864 12076607069389735 12076607069524134 12076607069528077
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 935069 935074 4194304 256 0 0 28 24 100736 0x7fb2f49b3500 0x7fb1e8e36440 412995 412995 65536 5177344 681882 87255116 12076607069580394 12076607069755013 12076607070021892 12076607070071918
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 158 935069 935074 4194304 256 0 0 28 24 102208 0x7fb2f49b3400 0x7fb1e8e36480 451409 451409 65536 3014656 403380 51732012 12076607070097476 12076607070281571 12076607070573730 12076607070622873
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 160 935069 935074 4194304 256 0 0 24 24 103680 0x7fb2f49b3300 0x7fb1e8e364c0 217907 217907 65536 2949120 423873 54142876 12076607070646778 12076607070838369 12076607070971968 12076607070975980
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 162 935069 935074 4194304 256 0 0 24 24 105664 0x7fb2f49b3a00 0x7fb1e8e36500 264337 264337 65536 3866624 533438 67881272 12076607071032014 12076607071208607 12076607071374846 12076607071379180
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 164 935069 935074 4194304 256 0 0 24 24 107136 0x7fb2f49b3900 0x7fb1e8e36540 213235 213235 65536 3014656 396179 50686140 12076607071444261 12076607071610526 12076607071741885 12076607071745912
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 935069 935074 4194304 256 0 0 28 24 109888 0x7fb2f49b3800 0x7fb1e8e36580 414657 414657 65536 5439488 704212 90138824 12076607071797729 12076607071969884 12076607072238683 12076607072288441
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 168 935069 935074 4194304 256 0 0 28 24 111360 0x7fb2f49b3700 0x7fb1e8e365c0 455699 455699 65536 3145728 416870 53478980 12076607072312977 12076607072499482 12076607072793721 12076607072842212
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 170 935069 935074 4194304 256 0 0 24 24 112832 0x7fb2f49b3600 0x7fb1e8e36600 219369 219369 65536 3080192 507763 64933636 12076607072865866 12076607073053560 12076607073188599 12076607073192814
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 172 935069 935074 4194304 256 0 0 24 24 114816 0x7fb2f49b3500 0x7fb1e8e36640 277547 277547 65536 4063232 553684 70680060 12076607073246313 12076607073417878 12076607073592757 12076607073596585
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 174 935069 935074 4194304 256 0 0 24 24 116288 0x7fb2f49b3400 0x7fb1e8e36680 223001 223001 65536 3145728 456216 58399568 12076607073663760 12076607073828436 12076607073966516 12076607073970330
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 935069 935074 4194304 256 0 0 28 24 119040 0x7fb2f49b3300 0x7fb1e8e366c0 413939 413939 65536 5701632 829430 106122232 12076607074030302 12076607074209235 12076607074477234 12076607074526254
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 178 935069 935074 4194304 256 0 0 28 24 120768 0x7fb2f49b3a00 0x7fb1e8e36700 403385 403385 65536 3276800 429855 54875156 12076607074550008 12076607074734033 12076607074994511 12076607075021405
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 180 935069 935074 4194304 256 0 0 24 24 122496 0x7fb2f49b3900 0x7fb1e8e36740 225675 225675 65536 3211264 488349 62521156 12076607075064275 12076607075231791 12076607075371630 12076607075375804
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 182 935069 935074 4194304 256 0 0 24 24 124736 0x7fb2f49b3800 0x7fb1e8e36780 291617 291617 65536 4259840 586782 74985140 12076607075427470 12076607075601229 12076607075784428 12076607075788272
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 184 935069 935074 4194304 256 0 0 24 24 126464 0x7fb2f49b3700 0x7fb1e8e367c0 225755 225755 65536 3276800 499862 63952216 12076607075856068 12076607076026827 12076607076166827 12076607076170813
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 935069 935074 4194304 256 0 0 20 24 127936 0x7fb2f49b3600 0x7fb1e8e36800 412089 412089 65536 7733248 977658 125097504 12076607076223321 12076607076399626 12076607076667145 12076607076719043
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 188 935069 935074 4194304 256 0 0 28 24 129664 0x7fb2f49b3500 0x7fb1e8e36840 407651 407651 65536 3407872 444297 56593724 12076607076745262 12076607076932583 12076607077195462 12076607077244190
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 190 935069 935074 4194304 256 0 0 24 24 131392 0x7fb2f49b3400 0x7fb1e8e36880 226969 226969 65536 3342336 458648 58735012 12076607077268305 12076607077456421 12076607077597221 12076607077601154
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 192 935069 935074 4194304 256 0 0 24 24 133632 0x7fb2f49b3300 0x7fb1e8e368c0 301475 301475 65536 4456448 635716 81143032 12076607077658561 12076607077822020 12076607078013859 12076607078060408
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 194 935069 935074 4194304 256 0 0 24 24 135360 0x7fb2f49b3a00 0x7fb1e8e36900 229737 229737 65536 3538944 531910 68167600 12076607078098489 12076607078264578 12076607078405377 12076607078409077
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 935069 935074 4194304 256 0 0 20 24 136832 0x7fb2f49b3900 0x7fb1e8e36940 435539 435539 65536 8978432 1128815 144500616 12076607078466043 12076607078630496 12076607078914335 12076607078935496
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 198 935069 935074 4194304 256 0 0 28 24 138560 0x7fb2f49b3800 0x7fb1e8e36980 394617 394617 65536 3670016 514021 66048348 12076607078982634 12076607079152734 12076607079408413 12076607079457617
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 200 935069 935074 4194304 256 0 0 24 24 140288 0x7fb2f49b3700 0x7fb1e8e369c0 227075 227075 65536 3604480 524153 67172096 12076607079483415 12076607079665852 12076607079806652 12076607079810473
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 202 935069 935074 4194304 256 0 0 24 24 142784 0x7fb2f49b3600 0x7fb1e8e36a00 329097 329097 65536 4849664 692690 87980460 12076607079864043 12076607080040891 12076607080251610 12076607080300435
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 204 935069 935074 4194304 256 0 0 24 24 144768 0x7fb2f49b3500 0x7fb1e8e36a40 226403 226403 65536 3801088 581253 74372408 12076607080338455 12076607080503929 12076607080644408 12076607080648081
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 935069 935074 4194304 256 0 0 20 24 145728 0x7fb2f49b3400 0x7fb1e8e36a80 470537 470537 65536 14548992 1828637 234034324 12076607080700419 12076607080878167 12076607081185526 12076607081234983
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 208 935069 935074 4194304 256 0 0 28 24 147712 0x7fb2f49b3300 0x7fb1e8e36ac0 404651 404651 65536 3932160 518104 66211720 12076607081261102 12076607081443605 12076607081705684 12076607081752906
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 210 935069 935074 4194304 256 0 0 24 24 149696 0x7fb2f49b3a00 0x7fb1e8e36b00 218833 218833 65536 3866624 618650 79262516 12076607081776971 12076607081958803 12076607082095282 12076607082099411
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 212 935069 935074 4194304 256 0 0 24 24 152192 0x7fb2f49b3900 0x7fb1e8e36b40 356915 356915 65536 5242880 719398 92075292 12076607082150867 12076607082327281 12076607082556080 12076607082603138
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 214 935069 935074 4194304 256 0 0 24 24 154176 0x7fb2f49b3800 0x7fb1e8e36b80 222913 222913 65536 4063232 627426 80319960 12076607082639516 12076607082803919 12076607082942479 12076607082946397
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 935069 935074 4194304 256 0 0 20 24 155648 0x7fb2f49b3700 0x7fb1e8e36bc0 503139 503139 65536 10027008 1262411 161220076 12076607082998554 12076607083181038 12076607083510156 12076607083559106
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 218 935069 935074 4194304 256 0 0 28 24 157632 0x7fb2f49b3600 0x7fb1e8e36c00 406481 406481 65536 4194304 545664 69736164 12076607083581979 12076607083767479 12076607084031479 12076607084082600
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 220 935069 935074 4194304 256 0 0 24 24 159616 0x7fb2f49b3500 0x7fb1e8e36c40 221899 221899 65536 4128768 622734 79652544 12076607084104861 12076607084305877 12076607084443476 12076607084446487
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 222 935069 935074 4194304 256 0 0 24 24 162368 0x7fb2f49b3400 0x7fb1e8e36c80 381041 381041 65536 5636096 770775 98247000 12076607084501569 12076607084677556 12076607084922995 12076607084969299
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 224 935069 935074 4194304 256 0 0 24 24 164608 0x7fb2f49b3300 0x7fb1e8e36cc0 226619 226619 65536 4587520 655899 83961808 12076607085013682 12076607085180914 12076607085321394 12076607085324680
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 935069 935074 4194304 256 0 0 20 24 166336 0x7fb2f49b3a00 0x7fb1e8e36d00 575985 575985 65536 11075584 1394189 178374672 12076607085378210 12076607085546673 12076607085925232 12076607085971684
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 228 935069 935074 4194304 256 0 0 28 24 168576 0x7fb2f49b3900 0x7fb1e8e36d40 401963 401963 65536 4718592 669814 85825632 12076607085995318 12076607086186031 12076607086446350 12076607086466625
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 230 935069 935074 4194304 256 0 0 24 24 170816 0x7fb2f49b3800 0x7fb1e8e36d80 223681 223681 65536 4653056 667946 85594900 12076607086512831 12076607086678350 12076607086817389 12076607086820583
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 232 935069 935074 4194304 256 0 0 24 24 174080 0x7fb2f49b3700 0x7fb1e8e36dc0 434675 434675 65536 6422528 894480 114787936 12076607086873562 12076607087072588 12076607087352747 12076607087401173
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 234 935069 935074 4194304 256 0 0 24 24 176576 0x7fb2f49b3600 0x7fb1e8e36e00 222969 222969 65536 5111808 791119 101342588 12076607087445996 12076607087616747 12076607087755786 12076607087758949
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 935069 935074 4194304 256 0 0 20 24 177792 0x7fb2f49b3500 0x7fb1e8e36e40 647523 647523 65536 15007744 1881597 241002168 12076607087810795 12076607087984265 12076607088411144 12076607088458590
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 238 935069 935074 4194304 256 0 0 28 24 180288 0x7fb2f49b3400 0x7fb1e8e36e80 409081 409081 65536 5242880 687313 88316524 12076607088483737 12076607088676423 12076607088941863 12076607088988656
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 240 935069 935074 4194304 256 0 0 24 24 182784 0x7fb2f49b3300 0x7fb1e8e36ec0 219755 219755 65536 5177344 789959 101051380 12076607089016728 12076607089211302 12076607089347781 12076607089351190
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 242 935069 935074 4194304 256 0 0 24 24 186304 0x7fb2f49b3a00 0x7fb1e8e36f00 488401 488401 65536 7208960 979036 126381744 12076607089404860 12076607089575941 12076607089891620 12076607089939795
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 244 935069 935074 4194304 256 0 0 24 24 189312 0x7fb2f49b3900 0x7fb1e8e36f40 244835 244835 65536 6160384 944851 120972172 12076607089986332 12076607090161059 12076607090314658 12076607090317918
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 935069 935074 4194304 256 0 0 20 24 190784 0x7fb2f49b3800 0x7fb1e8e36f80 784929 784929 65536 17104896 2148466 275140452 12076607090370406 12076607090554978 12076607091073216 12076607091095254
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 248 935069 935074 4194304 256 0 0 28 24 193792 0x7fb2f49b3700 0x7fb1e8e36fc0 456899 456899 65536 6291456 835568 107190536 12076607091150217 12076607091319295 12076607091617534 12076607091664734
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 250 935069 935074 4194304 256 0 0 24 24 196800 0x7fb2f49b3600 0x7fb1e8e37000 245729 245729 65536 6225920 915795 117326864 12076607091693597 12076607091877534 12076607092032253 12076607092035654
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 252 935069 935074 4194304 256 0 0 24 24 201088 0x7fb2f49b3500 0x7fb1e8e37040 593875 593875 65536 8781824 1249565 160133432 12076607092090175 12076607092276092 12076607092662171 12076607092708766
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 254 935069 935074 4194304 256 0 0 24 24 204608 0x7fb2f49b3400 0x7fb1e8e37080 276121 276121 65536 7208960 1008435 128927104 12076607092748720 12076607092914170 12076607093089530 12076607093092900
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 935069 935074 4194304 256 0 0 20 24 206080 0x7fb2f49b3300 0x7fb1e8e370c0 942539 942539 65536 19202048 2414294 308160104 12076607093146069 12076607093323929 12076607093946647 12076607093994998
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 258 935069 935074 4194304 256 0 0 28 24 209600 0x7fb2f49b3a00 0x7fb1e8e37100 505193 505193 65536 7340032 959851 122951072 12076607094019965 12076607094212086 12076607094542965 12076607094590246
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 260 935069 935074 4194304 256 0 0 24 24 213120 0x7fb2f49b3900 0x7fb1e8e37140 280955 280955 65536 7274496 1035974 132703404 12076607094614210 12076607094796245 12076607094974324 12076607094977506
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 262 935069 935074 4194304 256 0 0 24 24 218176 0x7fb2f49b3800 0x7fb1e8e37180 700225 700225 65536 10354688 1451513 185974588 12076607095031627 12076607095211123 12076607095668562 12076607095716130
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 264 935069 935074 4194304 256 0 0 24 24 222208 0x7fb2f49b3700 0x7fb1e8e371c0 370371 370371 65536 8257536 1151861 147391804 12076607095756805 12076607095923761 12076607096161360 12076607096209638
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 935069 935074 4194304 256 0 0 20 24 223936 0x7fb2f49b3600 0x7fb1e8e37200 1065625 1065625 65536 21299200 2669811 341662804 12076607096234704 12076607096420240 12076607097124077 12076607097171597
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 268 935069 935074 4194304 256 0 0 28 24 227968 0x7fb2f49b3500 0x7fb1e8e37240 567019 567019 65536 8388608 1192134 152811500 12076607097204899 12076607097392717 12076607097765835 12076607097812710
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 270 935069 935074 4194304 256 0 0 24 24 232000 0x7fb2f49b3400 0x7fb1e8e37280 374217 374217 65536 8323072 1289301 164974828 12076607097836945 12076607098034635 12076607098275114 12076607098329020
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 272 935069 935074 4194304 256 0 0 24 24 237824 0x7fb2f49b3300 0x7fb1e8e372c0 806699 806699 65536 11927552 1610806 206248708 12076607098355369 12076607098555593 12076607099083911 12076607099132585
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 274 935069 935074 4194304 256 0 0 24 24 242368 0x7fb2f49b3a00 0x7fb1e8e37300 349865 349865 65536 9306112 1445438 185100516 12076607099174683 12076607099343591 12076607099568710 12076607099616745
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 935069 935074 4194304 256 0 0 20 24 243584 0x7fb2f49b3900 0x7fb1e8e37340 1208963 1208963 65536 29163520 3652378 467598068 12076607099646741 12076607099823589 12076607100625027 12076607100675295
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 278 935069 935074 4194304 256 0 0 28 24 248128 0x7fb2f49b3800 0x7fb1e8e37380 642609 642609 65536 9437184 1259387 161220340 12076607100700642 12076607100885986 12076607101308065 12076607101377501
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 280 935069 935074 4194304 256 0 0 24 24 252672 0x7fb2f49b3700 0x7fb1e8e373c0 352675 352675 65536 9371648 1362401 174437700 12076607101401405 12076607101586944 12076607101812863 12076607101853486
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 282 935069 935074 4194304 256 0 0 24 24 259264 0x7fb2f49b3600 0x7fb1e8e37400 909297 909297 65536 13500416 1939392 249470212 12076607101889804 12076607102070942 12076607102668540 12076607102736529
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 284 935069 935074 4194304 256 0 0 24 24 264832 0x7fb2f49b3500 0x7fb1e8e37440 419643 419643 65536 11403264 1810727 231780600 12076607102773227 12076607102951099 12076607103221499 12076607103288866
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 935069 935074 4194304 256 0 0 20 24 266304 0x7fb2f49b3400 0x7fb1e8e37480 1486913 1486913 65536 33357824 4176847 534462840 12076607103313472 12076607103498618 12076607104484535 12076607104551705
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 288 935069 935074 4194304 256 0 0 28 24 271872 0x7fb2f49b3300 0x7fb1e8e374c0 776779 776779 65536 11534336 1559715 199237440 12076607104575750 12076607104769654 12076607105284692 12076607105351593
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 290 935069 935074 4194304 256 0 0 24 24 277440 0x7fb2f49b3a00 0x7fb1e8e37500 426753 426753 65536 11534336 1851403 236927948 12076607105381649 12076607105566611 12076607105840691 12076607105906605
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 292 935069 935074 4194304 256 0 0 12 24 279936 0x7fb2f49b3900 0x7fb1e8e37540 1125395 1125395 65536 19267584 2430276 311028800 12076607105932844 12076607106126290 12076607106865007 12076607106933055
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 294 935069 935074 4194304 256 0 0 24 24 286528 0x7fb2f49b3800 0x7fb1e8e37580 486113 486113 65536 13500416 1989643 254748480 12076607106973300 12076607107145487 12076607107461486 12076607107527841
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 935069 935074 4194304 256 0 0 20 24 288000 0x7fb2f49b3700 0x7fb1e8e375c0 1768347 1768347 65536 37552128 4698100 601656016 12076607107554941 12076607107742125 12076607108914921 12076607108982587
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 298 935069 935074 4194304 256 0 0 32 24 294592 0x7fb2f49b3600 0x7fb1e8e37600 916145 916145 65536 13631488 1837594 235009216 12076607109018424 12076607109204200 12076607109814118 12076607109881229
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 300 935069 935074 4194304 256 0 0 24 24 301184 0x7fb2f49b3500 0x7fb1e8e37640 492811 492811 65536 13631488 2078014 266048836 12076607109909411 12076607110110597 12076607110430276 12076607110499398
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 302 935069 935074 4194304 256 0 0 12 24 304960 0x7fb2f49b3400 0x7fb1e8e37680 1336065 1336065 65536 21692416 2740602 350269840 12076607110534754 12076607110704516 12076607111582753 12076607111651411
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 304 935069 935074 4194304 256 0 0 24 24 313600 0x7fb2f49b3300 0x7fb1e8e376c0 632747 632747 65536 17694720 2788850 356809268 12076607111700342 12076607111867392 12076607112280991 12076607112347516
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 935069 935074 4194304 256 0 0 20 24 314816 0x7fb2f49b3a00 0x7fb1e8e37700 2332393 2332393 65536 57475072 7193674 920847108 12076607112378243 12076607112564030 12076607114112985 12076607114179414
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 308 935069 935074 4194304 256 0 0 20 24 317568 0x7fb2f49b3900 0x7fb1e8e37740 1200323 1200323 65536 19660800 2471365 316217244 12076607114210191 12076607114395704 12076607115190902 12076607115257670
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 310 935069 935074 4194304 256 0 0 12 24 320320 0x7fb2f49b3800 0x7fb1e8e37780 640169 640169 65536 20381696 2574270 329482260 12076607115287555 12076607115473301 12076607115888660 12076607115954926
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 312 935069 935074 4194304 256 0 0 12 24 324096 0x7fb2f49b3700 0x7fb1e8e377c0 1757027 1757027 65536 28704768 3613734 462492340 12076607115982508 12076607116170899 12076607117329615 12076607117396298
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 314 935069 935074 4194304 256 0 0 12 24 328896 0x7fb2f49b3600 0x7fb1e8e37800 1200825 1200825 65536 36634624 4627052 592393124 12076607117434739 12076607117604014 12076607118390892 12076607118457622
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 935069 935074 4194304 256 0 0 20 24 330112 0x7fb2f49b3500 0x7fb1e8e37840 4583811 4583811 65536 105840640 13238877 1694936080 12076607118490763 12076607118680971 12076607121732962 12076607121800290
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 318 935069 935074 4194304 256 0 0 20 24 332864 0x7fb2f49b3400 0x7fb1e8e37880 2324345 2324345 65536 38535168 4833306 618039328 12076607121831808 12076607122027681 12076607123570556 12076607123639781
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 320 935069 935074 4194304 256 0 0 12 24 335616 0x7fb2f49b3300 0x7fb1e8e378c0 1202627 1202627 65536 39124992 4909655 628517764 12076607123663065 12076607123857915 12076607124647353 12076607124713499
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 322 935069 935074 4194304 256 0 0 12 24 339392 0x7fb2f49b3a00 0x7fb1e8e37900 3442929 3442929 65536 55771136 7010935 897488352 12076607124738455 12076607124929752 12076607127212465 12076607127280584
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 324 935069 935074 4194304 256 0 0 12 24 344192 0x7fb2f49b3900 0x7fb1e8e37940 2322507 2322507 65536 72548352 9109453 1166161620 12076607127325978 12076607127497744 12076607129033259 12076607129100299
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 935069 935074 4194304 256 0 0 20 24 345408 0x7fb2f49b3800 0x7fb1e8e37980 9086257 9086257 65536 210698240 26342168 3372581544 12076607129130234 12076607129314698 12076607135372600 12076607135440141
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 328 935069 935074 4194304 256 0 0 20 24 348160 0x7fb2f49b3700 0x7fb1e8e379c0 4572891 4572891 65536 76283904 9533686 1221835664 12076607135472702 12076607135649719 12076607138693070 12076607138760458
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 330 935069 935074 4194304 256 0 0 12 24 350912 0x7fb2f49b3600 0x7fb1e8e37a00 2328209 2328209 65536 77398016 9689987 1240750856 12076607138789231 12076607138985709 12076607140524904 12076607140593778
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 332 935069 935074 4194304 256 0 0 12 24 0 0x7fb2f49b3500 0x7fb1e8e37a40 6811723 6811723 65536 110821376 13888539 1777979164 12076607140622982 12076607140811943 12076607145340089 12076607145411670
@@ -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",0,0,0,936874,936879,33554432,256,0,0,8,32,6464,0x0,0x7f608a404180,0,0,0,12076632988700397,12076633233142956,12076633233467755,12076633233577518
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,936874,936879,32768,256,0,0,24,24,12480,0x0,0x7f608a435100,0,0,0,12076633248282761,12076633248580944,12076633248587504,12076633248592868
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,936874,936879,4194304,256,0,0,24,24,12928,0x7f61960b3900,0x7f608a435140,0,0,0,12076633248655084,12076633248875663,12076633249007503,12076633249011156
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,936874,936879,4194304,256,0,0,36,24,13632,0x7f61960b3800,0x7f608a435180,0,0,0,12076633249083771,12076633249259982,12076633249507821,12076633249576949
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,936874,936879,4194304,256,0,0,28,24,14080,0x7f61960b3700,0x7f608a4351c0,0,0,0,12076633249608708,12076633249789420,12076633250035179,12076633250105001
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,936874,936879,4194304,256,0,0,24,24,14528,0x7f61960b3600,0x7f608a435200,0,0,0,12076633250132733,12076633250316619,12076633250448138,12076633250451676
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,936874,936879,4194304,256,0,0,24,24,14976,0x7f61960b3500,0x7f608a435240,0,0,0,12076633250496409,12076633250679817,12076633250812617,12076633250816044
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,936874,936879,4194304,256,0,0,24,24,15424,0x7f61960b3400,0x7f608a435280,0,0,0,12076633250895321,12076633251060296,12076633251191976,12076633251195409
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,936874,936879,4194304,256,0,0,28,24,16128,0x7f61960b3300,0x7f608a4352c0,0,0,0,12076633251246094,12076633251413895,12076633251661094,12076633251701931
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,936874,936879,4194304,256,0,0,28,24,16832,0x7f61960b3a00,0x7f608a435300,0,0,0,12076633251729673,12076633251907493,12076633252160773,12076633252201130
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,936874,936879,4194304,256,0,0,24,24,17536,0x7f61960b3900,0x7f608a435340,0,0,0,12076633252226157,12076633252419172,12076633252550691,12076633252553866
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,936874,936879,4194304,256,0,0,24,24,18240,0x7f61960b3800,0x7f608a435380,0,0,0,12076633252603118,12076633252768771,12076633252906050,12076633252909488
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,936874,936879,4194304,256,0,0,24,24,18944,0x7f61960b3700,0x7f608a4353c0,0,0,0,12076633252972405,12076633253146529,12076633253279009,12076633253282592
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,936874,936879,4194304,256,0,0,28,24,19904,0x7f61960b3600,0x7f608a435400,0,0,0,12076633253333196,12076633253509248,12076633253764447,12076633253830080
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,936874,936879,4194304,256,0,0,28,24,20608,0x7f61960b3500,0x7f608a435440,0,0,0,12076633253855728,12076633254038846,12076633254284126,12076633254350308
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,936874,936879,4194304,256,0,0,24,24,21312,0x7f61960b3400,0x7f608a435480,0,0,0,12076633254374643,12076633254569085,12076633254696444,12076633254699788
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,936874,936879,4194304,256,0,0,24,24,22016,0x7f61960b3300,0x7f608a4354c0,0,0,0,12076633254755151,12076633254917723,12076633255047163,12076633255050440
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,936874,936879,4194304,256,0,0,24,24,22720,0x7f61960b3a00,0x7f608a435500,0,0,0,12076633255116212,12076633255282362,12076633255415482,12076633255419256
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,936874,936879,4194304,256,0,0,28,24,23680,0x7f61960b3900,0x7f608a435540,0,0,0,12076633255468568,12076633255632441,12076633255880920,12076633255946547
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,936874,936879,4194304,256,0,0,28,24,24384,0x7f61960b3800,0x7f608a435580,0,0,0,12076633255971814,12076633256167319,12076633256415479,12076633256482744
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,936874,936879,4194304,256,0,0,24,24,25088,0x7f61960b3700,0x7f608a4355c0,0,0,0,12076633256513532,12076633256694198,12076633256824277,12076633256827666
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,936874,936879,4194304,256,0,0,24,24,25792,0x7f61960b3600,0x7f608a435600,0,0,0,12076633256875695,12076633257046196,12076633257177396,12076633257180993
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,936874,936879,4194304,256,0,0,24,24,26496,0x7f61960b3500,0x7f608a435640,0,0,0,12076633257242778,12076633257409555,12076633257538995,12076633257542646
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,936874,936879,4194304,256,0,0,28,24,27712,0x7f61960b3400,0x7f608a435680,0,0,0,12076633257590625,12076633257760274,12076633258010673,12076633258077330
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,936874,936879,4194304,256,0,0,28,24,28416,0x7f61960b3300,0x7f608a4356c0,0,0,0,12076633258106565,12076633258284592,12076633258536752,12076633258601906
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,936874,936879,4194304,256,0,0,24,24,29120,0x7f61960b3a00,0x7f608a435700,0,0,0,12076633258628776,12076633258812431,12076633258942990,12076633258946537
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,936874,936879,4194304,256,0,0,24,24,30080,0x7f61960b3900,0x7f608a435740,0,0,0,12076633258996160,12076633259162990,12076633259293709,12076633259297250
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,936874,936879,4194304,256,0,0,24,24,30784,0x7f61960b3800,0x7f608a435780,0,0,0,12076633259359465,12076633259524268,12076633259654668,12076633259658061
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,936874,936879,4194304,256,0,0,28,24,32000,0x7f61960b3700,0x7f608a4357c0,0,0,0,12076633259706872,12076633259876267,12076633260129866,12076633260195971
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,936874,936879,4194304,256,0,0,28,24,32960,0x7f61960b3600,0x7f608a435800,0,0,0,12076633260219806,12076633260405705,12076633260656105,12076633260721960
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,936874,936879,4194304,256,0,0,24,24,33920,0x7f61960b3500,0x7f608a435840,0,0,0,12076633260748980,12076633260926024,12076633261062503,12076633261066380
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,936874,936879,4194304,256,0,0,24,24,34880,0x7f61960b3400,0x7f608a435880,0,0,0,12076633261118247,12076633261280263,12076633261410822,12076633261414207
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,936874,936879,4194304,256,0,0,24,24,35840,0x7f61960b3300,0x7f608a4358c0,0,0,0,12076633261475622,12076633261637701,12076633261767301,12076633261771041
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,936874,936879,4194304,256,0,0,28,24,37312,0x7f61960b3a00,0x7f608a435900,0,0,0,12076633261822056,12076633261987140,12076633262240579,12076633262309383
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,936874,936879,4194304,256,0,0,28,24,38272,0x7f61960b3900,0x7f608a435940,0,0,0,12076633262335331,12076633262518499,12076633262770338,12076633262836934
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,936874,936879,4194304,256,0,0,24,24,39232,0x7f61960b3800,0x7f608a435980,0,0,0,12076633262862812,12076633263045537,12076633263174976,12076633263179050
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,936874,936879,4194304,256,0,0,24,24,40192,0x7f61960b3700,0x7f608a4359c0,0,0,0,12076633263228392,12076633263397856,12076633263532415,12076633263536104
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,936874,936879,4194304,256,0,0,24,24,41152,0x7f61960b3600,0x7f608a435a00,0,0,0,12076633263597128,12076633263758014,12076633263886494,12076633263890213
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,936874,936879,4194304,256,0,0,28,24,42624,0x7f61960b3500,0x7f608a435a40,0,0,0,12076633263939264,12076633264116733,12076633264370012,12076633264436299
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,936874,936879,4194304,256,0,0,28,24,43584,0x7f61960b3400,0x7f608a435a80,0,0,0,12076633264461406,12076633264642332,12076633264895611,12076633264936519
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,936874,936879,4194304,256,0,0,24,24,44544,0x7f61960b3300,0x7f608a435ac0,0,0,0,12076633264961666,12076633265147450,12076633265280569,12076633265284477
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,936874,936879,4194304,256,0,0,24,24,45760,0x7f61960b3a00,0x7f608a435b00,0,0,0,12076633265328649,12076633265503449,12076633265636568,12076633265640128
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,936874,936879,4194304,256,0,0,24,24,46720,0x7f61960b3900,0x7f608a435b40,0,0,0,12076633265701512,12076633265864248,12076633265994967,12076633265998645
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,936874,936879,4194304,256,0,0,28,24,48448,0x7f61960b3800,0x7f608a435b80,0,0,0,12076633266047025,12076633266217846,12076633266486326,12076633266554890
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,936874,936879,4194304,256,0,0,28,24,49408,0x7f61960b3700,0x7f608a435bc0,0,0,0,12076633266577662,12076633266756405,12076633267008404,12076633267075178
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,936874,936879,4194304,256,0,0,24,24,50368,0x7f61960b3600,0x7f608a435c00,0,0,0,12076633267102458,12076633267288243,12076633267415762,12076633267419418
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,936874,936879,4194304,256,0,0,24,24,51584,0x7f61960b3500,0x7f608a435c40,0,0,0,12076633267469291,12076633267632402,12076633267763441,12076633267767095
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,936874,936879,4194304,256,0,0,24,24,52544,0x7f61960b3400,0x7f608a435c80,0,0,0,12076633267827266,12076633267990641,12076633268119760,12076633268123598
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,936874,936879,4194304,256,0,0,28,24,54272,0x7f61960b3300,0x7f608a435cc0,0,0,0,12076633268173450,12076633268353839,12076633268615119,12076633268657311
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,936874,936879,4194304,256,0,0,28,24,55488,0x7f61960b3a00,0x7f608a435d00,0,0,0,12076633268680654,12076633268861358,12076633269151117,12076633269218785
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,936874,936879,4194304,256,0,0,24,24,56704,0x7f61960b3900,0x7f608a435d40,0,0,0,12076633269246707,12076633269422316,12076633269592075,12076633269595656
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,936874,936879,4194304,256,0,0,24,24,58176,0x7f61960b3800,0x7f608a435d80,0,0,0,12076633269648084,12076633269809515,12076633269949354,12076633269953011
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,936874,936879,4194304,256,0,0,24,24,59392,0x7f61960b3700,0x7f608a435dc0,0,0,0,12076633270019164,12076633270181353,12076633270313833,12076633270317358
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,936874,936879,4194304,256,0,0,28,24,61376,0x7f61960b3600,0x7f608a435e00,0,0,0,12076633270370327,12076633270532552,12076633270796231,12076633270862883
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,936874,936879,4194304,256,0,0,28,24,62592,0x7f61960b3500,0x7f608a435e40,0,0,0,12076633270898730,12076633271061991,12076633271308390,12076633271374665
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,936874,936879,4194304,256,0,0,24,24,63808,0x7f61960b3400,0x7f608a435e80,0,0,0,12076633271405943,12076633271589509,12076633271718628,12076633271722212
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,936874,936879,4194304,256,0,0,24,24,65280,0x7f61960b3300,0x7f608a435ec0,0,0,0,12076633271770912,12076633271932868,12076633272075747,12076633272079266
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,936874,936879,4194304,256,0,0,24,24,66496,0x7f61960b3a00,0x7f608a435f00,0,0,0,12076633272141782,12076633272304866,12076633272433666,12076633272437141
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,936874,936879,4194304,256,0,0,28,24,68480,0x7f61960b3900,0x7f608a435f40,0,0,0,12076633272485612,12076633272647905,12076633272911264,12076633272933585
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,936874,936879,4194304,256,0,0,28,24,69696,0x7f61960b3800,0x7f608a435f80,0,0,0,12076633272975523,12076633273140864,12076633273395743,12076633273445096
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,936874,936879,4194304,256,0,0,24,24,70912,0x7f61960b3700,0x7f608a435fc0,0,0,0,12076633273473159,12076633273648382,12076633273782142,12076633273785700
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,936874,936879,4194304,256,0,0,24,24,72384,0x7f61960b3600,0x7f608a436000,0,0,0,12076633273834611,12076633274003741,12076633274144860,12076633274148886
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,936874,936879,4194304,256,0,0,24,24,73600,0x7f61960b3500,0x7f608a436040,0,0,0,12076633274210490,12076633274371260,12076633274502299,12076633274505970
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,936874,936879,4194304,256,0,0,28,24,75840,0x7f61960b3400,0x7f608a436080,0,0,0,12076633274555151,12076633274717499,12076633274978138,12076633275025376
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,936874,936879,4194304,256,0,0,28,24,77056,0x7f61960b3300,0x7f608a4360c0,0,0,0,12076633275051615,12076633275229657,12076633275477816,12076633275524695
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,936874,936879,4194304,256,0,0,24,24,78272,0x7f61960b3a00,0x7f608a436100,0,0,0,12076633275550663,12076633275726775,12076633275857175,12076633275860810
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,936874,936879,4194304,256,0,0,24,24,80000,0x7f61960b3900,0x7f608a436140,0,0,0,12076633275909751,12076633276086454,12076633276231414,12076633276235206
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,936874,936879,4194304,256,0,0,24,24,81216,0x7f61960b3800,0x7f608a436180,0,0,0,12076633276298985,12076633276459573,12076633276595412,12076633276599324
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,936874,936879,4194304,256,0,0,28,24,83456,0x7f61960b3700,0x7f608a4361c0,0,0,0,12076633276647052,12076633276813492,12076633277074771,12076633277125593
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,936874,936879,4194304,256,0,0,28,24,84928,0x7f61960b3600,0x7f608a436200,0,0,0,12076633277149186,12076633277331890,12076633277590129,12076633277638687
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,936874,936879,4194304,256,0,0,24,24,86400,0x7f61960b3500,0x7f608a436240,0,0,0,12076633277665527,12076633277840208,12076633277972688,12076633277976395
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,936874,936879,4194304,256,0,0,24,24,88128,0x7f61960b3400,0x7f608a436280,0,0,0,12076633278029724,12076633278204047,12076633278354127,12076633278357765
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,936874,936879,4194304,256,0,0,24,24,89600,0x7f61960b3300,0x7f608a4362c0,0,0,0,12076633278438284,12076633278598446,12076633278732685,12076633278736299
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,936874,936879,4194304,256,0,0,28,24,92096,0x7f61960b3a00,0x7f608a436300,0,0,0,12076633278786382,12076633278948525,12076633279214764,12076633279262998
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,936874,936879,4194304,256,0,0,28,24,93568,0x7f61960b3900,0x7f608a436340,0,0,0,12076633279293315,12076633279473163,12076633279726922,12076633279778217
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,936874,936879,4194304,256,0,0,24,24,95040,0x7f61960b3800,0x7f608a436380,0,0,0,12076633279813532,12076633279990601,12076633280127081,12076633280130863
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,936874,936879,4194304,256,0,0,24,24,96768,0x7f61960b3700,0x7f608a4363c0,0,0,0,12076633280180215,12076633280349320,12076633280506760,12076633280510399
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,936874,936879,4194304,256,0,0,24,24,98240,0x7f61960b3600,0x7f608a436400,0,0,0,12076633280571983,12076633280734279,12076633280864358,12076633280867904
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,936874,936879,4194304,256,0,0,28,24,100736,0x7f61960b3500,0x7f608a436440,0,0,0,12076633280916294,12076633281085478,12076633281345317,12076633281395826
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,936874,936879,4194304,256,0,0,28,24,102208,0x7f61960b3400,0x7f608a436480,0,0,0,12076633281422776,12076633281599716,12076633281849155,12076633281895325
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,936874,936879,4194304,256,0,0,24,24,103680,0x7f61960b3300,0x7f608a4364c0,0,0,0,12076633281921594,12076633282100194,12076633282236994,12076633282240898
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,936874,936879,4194304,256,0,0,24,24,105664,0x7f61960b3a00,0x7f608a436500,0,0,0,12076633282284318,12076633282460353,12076633282625953,12076633282629581
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,936874,936879,4194304,256,0,0,24,24,107136,0x7f61960b3900,0x7f608a436540,0,0,0,12076633282690083,12076633282847872,12076633282979391,12076633282983018
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,936874,936879,4194304,256,0,0,28,24,109888,0x7f61960b3800,0x7f608a436580,0,0,0,12076633283031619,12076633283211711,12076633283472510,12076633283519316
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,936874,936879,4194304,256,0,0,28,24,111360,0x7f61960b3700,0x7f608a4365c0,0,0,0,12076633283545524,12076633283720349,12076633283975868,12076633284022852
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,936874,936879,4194304,256,0,0,24,24,112832,0x7f61960b3600,0x7f608a436600,0,0,0,12076633284047989,12076633284232827,12076633284366107,12076633284370068
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,936874,936879,4194304,256,0,0,24,24,114816,0x7f61960b3500,0x7f608a436640,0,0,0,12076633284418819,12076633284585946,12076633284759866,12076633284763480
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,936874,936879,4194304,256,0,0,24,24,116288,0x7f61960b3400,0x7f608a436680,0,0,0,12076633284826527,12076633284988985,12076633285125464,12076633285129290
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,936874,936879,4194304,256,0,0,28,24,119040,0x7f61960b3300,0x7f608a4366c0,0,0,0,12076633285181057,12076633285342744,12076633285599383,12076633285625774
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,936874,936879,4194304,256,0,0,28,24,120768,0x7f61960b3a00,0x7f608a436700,0,0,0,12076633285668022,12076633285828182,12076633286081141,12076633286108352
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,936874,936879,4194304,256,0,0,24,24,122496,0x7f61960b3900,0x7f608a436740,0,0,0,12076633286153105,12076633286312180,12076633286445300,12076633286449176
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,936874,936879,4194304,256,0,0,24,24,124736,0x7f61960b3800,0x7f608a436780,0,0,0,12076633286498036,12076633286660659,12076633286843539,12076633286847456
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,936874,936879,4194304,256,0,0,24,24,126464,0x7f61960b3700,0x7f608a4367c0,0,0,0,12076633286908300,12076633287070098,12076633287208498,12076633287212586
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,936874,936879,4194304,256,0,0,20,24,127936,0x7f61960b3600,0x7f608a436800,0,0,0,12076633287261647,12076633287430097,12076633287696336,12076633287716503
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,936874,936879,4194304,256,0,0,28,24,129664,0x7f61960b3500,0x7f608a436840,0,0,0,12076633287761988,12076633287923695,12076633288174094,12076633288199181
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,936874,936879,4194304,256,0,0,24,24,131392,0x7f61960b3400,0x7f608a436880,0,0,0,12076633288243794,12076633288403374,12076633288532813,12076633288536689
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,936874,936879,4194304,256,0,0,24,24,133632,0x7f61960b3300,0x7f608a4368c0,0,0,0,12076633288584948,12076633288745772,12076633288938412,12076633288961709
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,936874,936879,4194304,256,0,0,24,24,135360,0x7f61960b3a00,0x7f608a436900,0,0,0,12076633289024366,12076633289187371,12076633289317931,12076633289321859
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,936874,936879,4194304,256,0,0,20,24,136832,0x7f61960b3900,0x7f608a436940,0,0,0,12076633289363366,12076633289545130,12076633289831369,12076633289855281
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,936874,936879,4194304,256,0,0,28,24,138560,0x7f61960b3800,0x7f608a436980,0,0,0,12076633289899614,12076633290070728,12076633290354727,12076633290382903
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,936874,936879,4194304,256,0,0,24,24,140288,0x7f61960b3700,0x7f608a4369c0,0,0,0,12076633290424430,12076633290584806,12076633290719366,12076633290723366
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,936874,936879,4194304,256,0,0,24,24,142784,0x7f61960b3600,0x7f608a436a00,0,0,0,12076633290771716,12076633290941765,12076633291152165,12076633291176639
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,936874,936879,4194304,256,0,0,24,24,144768,0x7f61960b3500,0x7f608a436a40,0,0,0,12076633291242452,12076633291407204,12076633291545443,12076633291549302
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,936874,936879,4194304,256,0,0,20,24,145728,0x7f61960b3400,0x7f608a436a80,0,0,0,12076633291597883,12076633291776163,12076633292083522,12076633292109204
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,936874,936879,4194304,256,0,0,28,24,147712,0x7f61960b3300,0x7f608a436ac0,0,0,0,12076633292158676,12076633292322561,12076633292578880,12076633292602492
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,936874,936879,4194304,256,0,0,24,24,149696,0x7f61960b3a00,0x7f608a436b00,0,0,0,12076633292649299,12076633292807839,12076633292943679,12076633292947423
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,936874,936879,4194304,256,0,0,24,24,152192,0x7f61960b3900,0x7f608a436b40,0,0,0,12076633292996174,12076633293161598,12076633293389917,12076633293417397
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,936874,936879,4194304,256,0,0,24,24,154176,0x7f61960b3800,0x7f608a436b80,0,0,0,12076633293470767,12076633293631836,12076633293769116,12076633293772798
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,936874,936879,4194304,256,0,0,20,24,155648,0x7f61960b3700,0x7f608a436bc0,0,0,0,12076633293822220,12076633293993115,12076633294324954,12076633294353188
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,936874,936879,4194304,256,0,0,28,24,157632,0x7f61960b3600,0x7f608a436c00,0,0,0,12076633294398242,12076633294560153,12076633294822233,12076633294847177
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,936874,936879,4194304,256,0,0,24,24,159616,0x7f61960b3500,0x7f608a436c40,0,0,0,12076633294890838,12076633295059352,12076633295197271,12076633295201356
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,936874,936879,4194304,256,0,0,24,24,162368,0x7f61960b3400,0x7f608a436c80,0,0,0,12076633295249225,12076633295419031,12076633295665110,12076633295685576
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,936874,936879,4194304,256,0,0,24,24,164608,0x7f61960b3300,0x7f608a436cc0,0,0,0,12076633295742252,12076633295904949,12076633296045589,12076633296049513
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,936874,936879,4194304,256,0,0,20,24,166336,0x7f61960b3a00,0x7f608a436d00,0,0,0,12076633296097262,12076633296280966,12076633296657766,12076633296685867
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,936874,936879,4194304,256,0,0,28,24,168576,0x7f61960b3900,0x7f608a436d40,0,0,0,12076633296723918,12076633296886884,12076633297151364,12076633297178453
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,936874,936879,4194304,256,0,0,24,24,170816,0x7f61960b3800,0x7f608a436d80,0,0,0,12076633297220161,12076633297383523,12076633297525603,12076633297528014
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,936874,936879,4194304,256,0,0,24,24,174080,0x7f61960b3700,0x7f608a436dc0,0,0,0,12076633297580221,12076633297741283,12076633298020962,12076633298044374
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,936874,936879,4194304,256,0,0,24,24,176576,0x7f61960b3600,0x7f608a436e00,0,0,0,12076633298107161,12076633298273282,12076633298413602,12076633298416346
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,936874,936879,4194304,256,0,0,20,24,177792,0x7f61960b3500,0x7f608a436e40,0,0,0,12076633298466800,12076633298647681,12076633299071201,12076633299095800
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,936874,936879,4194304,256,0,0,28,24,180288,0x7f61960b3400,0x7f608a436e80,0,0,0,12076633299139231,12076633299308160,12076633299567360,12076633299590430
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,936874,936879,4194304,256,0,0,24,24,182784,0x7f61960b3300,0x7f608a436ec0,0,0,0,12076633299637748,12076633299804639,12076633299945439,12076633299948135
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,936874,936879,4194304,256,0,0,24,24,186304,0x7f61960b3a00,0x7f608a436f00,0,0,0,12076633299990254,12076633300171999,12076633300487678,12076633300511293
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,936874,936879,4194304,256,0,0,24,24,189312,0x7f61960b3900,0x7f608a436f40,0,0,0,12076633300570533,12076633300734398,12076633300887038,12076633300889767
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,936874,936879,4194304,256,0,0,20,24,190784,0x7f61960b3800,0x7f608a436f80,0,0,0,12076633300937165,12076633301115037,12076633301631676,12076633301659378
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,936874,936879,4194304,256,0,0,28,24,193792,0x7f61960b3700,0x7f608a436fc0,0,0,0,12076633301703430,12076633301865276,12076633302163515,12076633302190136
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,936874,936879,4194304,256,0,0,24,24,196800,0x7f61960b3600,0x7f608a437000,0,0,0,12076633302234328,12076633302396315,12076633302551995,12076633302554644
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,936874,936879,4194304,256,0,0,24,24,201088,0x7f61960b3500,0x7f608a437040,0,0,0,12076633302603625,12076633302771354,12076633303156474,12076633303180137
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,936874,936879,4194304,256,0,0,24,24,204608,0x7f61960b3400,0x7f608a437080,0,0,0,12076633303242233,12076633303404793,12076633303582393,12076633303584940
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,936874,936879,4194304,256,0,0,20,24,206080,0x7f61960b3300,0x7f608a4370c0,0,0,0,12076633303633100,12076633303803993,12076633304414232,12076633304437426
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,936874,936879,4194304,256,0,0,28,24,209600,0x7f61960b3a00,0x7f608a437100,0,0,0,12076633304476499,12076633304637111,12076633304965591,12076633304984393
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,936874,936879,4194304,256,0,0,24,24,213120,0x7f61960b3900,0x7f608a437140,0,0,0,12076633305038173,12076633305203350,12076633305382550,12076633305385199
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,936874,936879,4194304,256,0,0,24,24,218176,0x7f61960b3800,0x7f608a437180,0,0,0,12076633305433739,12076633305614070,12076633306070229,12076633306094148
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,936874,936879,4194304,256,0,0,24,24,222208,0x7f61960b3700,0x7f608a4371c0,0,0,0,12076633306154109,12076633306318389,12076633306519028,12076633306564092
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,936874,936879,4194304,256,0,0,20,24,223936,0x7f61960b3600,0x7f608a437200,0,0,0,12076633306592905,12076633306767028,12076633307477107,12076633307523847
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,936874,936879,4194304,256,0,0,28,24,227968,0x7f61960b3500,0x7f608a437240,0,0,0,12076633307547892,12076633307737106,12076633308109426,12076633308157085
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,936874,936879,4194304,256,0,0,24,24,232000,0x7f61960b3400,0x7f608a437280,0,0,0,12076633308188143,12076633308370385,12076633308573425,12076633308619024
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,936874,936879,4194304,256,0,0,24,24,237824,0x7f61960b3300,0x7f608a4372c0,0,0,0,12076633308647447,12076633308822065,12076633309347504,12076633309396020
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,936874,936879,4194304,256,0,0,24,24,242368,0x7f61960b3a00,0x7f608a437300,0,0,0,12076633309437276,12076633309601423,12076633309825103,12076633309874319
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,936874,936879,4194304,256,0,0,20,24,243584,0x7f61960b3900,0x7f608a437340,0,0,0,12076633309899737,12076633310079822,12076633310878861,12076633310926136
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,936874,936879,4194304,256,0,0,28,24,248128,0x7f61960b3800,0x7f608a437380,0,0,0,12076633310953026,12076633311138381,12076633311557900,12076633311605259
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,936874,936879,4194304,256,0,0,24,24,252672,0x7f61960b3700,0x7f608a4373c0,0,0,0,12076633311631217,12076633311813740,12076633312041419,12076633312087807
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,936874,936879,4194304,256,0,0,24,24,259264,0x7f61960b3600,0x7f608a437400,0,0,0,12076633312112462,12076633312292139,12076633312889738,12076633312935874
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,936874,936879,4194304,256,0,0,24,24,264832,0x7f61960b3500,0x7f608a437440,0,0,0,12076633312975969,12076633313151337,12076633313419977,12076633313467934
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,936874,936879,4194304,256,0,0,20,24,266304,0x7f61960b3400,0x7f608a437480,0,0,0,12076633313493632,12076633313672937,12076633314658695,12076633314725303
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,936874,936879,4194304,256,0,0,28,24,271872,0x7f61960b3300,0x7f608a4374c0,0,0,0,12076633314756260,12076633314936934,12076633315454214,12076633315523988
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,936874,936879,4194304,256,0,0,24,24,277440,0x7f61960b3a00,0x7f608a437500,0,0,0,12076633315542292,12076633315737733,12076633316011173,12076633316058723
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,936874,936879,4194304,256,0,0,12,24,279936,0x7f61960b3900,0x7f608a437540,0,0,0,12076633316081686,12076633316265252,12076633317003331,12076633317069343
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,936874,936879,4194304,256,0,0,24,24,286528,0x7f61960b3800,0x7f608a437580,0,0,0,12076633317108786,12076633317274851,12076633317590690,12076633317656675
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,936874,936879,4194304,256,0,0,20,24,288000,0x7f61960b3700,0x7f608a4375c0,0,0,0,12076633317677955,12076633317864450,12076633319034368,12076633319102575
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,936874,936879,4194304,256,0,0,32,24,294592,0x7f61960b3600,0x7f608a437600,0,0,0,12076633319135887,12076633319321247,12076633319932606,12076633319998361
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,936874,936879,4194304,256,0,0,24,24,301184,0x7f61960b3500,0x7f608a437640,0,0,0,12076633320030581,12076633320206366,12076633320523965,12076633320592386
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,936874,936879,4194304,256,0,0,12,24,304960,0x7f61960b3400,0x7f608a437680,0,0,0,12076633320617833,12076633320794685,12076633321674043,12076633321740522
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,936874,936879,4194304,256,0,0,24,24,313600,0x7f61960b3300,0x7f608a4376c0,0,0,0,12076633321778643,12076633321945723,12076633322379322,12076633322446986
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,936874,936879,4194304,256,0,0,20,24,314816,0x7f61960b3a00,0x7f608a437700,0,0,0,12076633322473746,12076633322659802,12076633324208919,12076633324276459
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,936874,936879,4194304,256,0,0,20,24,317568,0x7f61960b3900,0x7f608a437740,0,0,0,12076633324306204,12076633324488439,12076633325283157,12076633325350296
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,936874,936879,4194304,256,0,0,12,24,320320,0x7f61960b3800,0x7f608a437780,0,0,0,12076633325379391,12076633325562997,12076633325977236,12076633326043927
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,936874,936879,4194304,256,0,0,12,24,324096,0x7f61960b3700,0x7f608a4377c0,0,0,0,12076633326068562,12076633326254996,12076633327413714,12076633327480288
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,936874,936879,4194304,256,0,0,12,24,328896,0x7f61960b3600,0x7f608a437800,0,0,0,12076633327521235,12076633327688753,12076633328474832,12076633328542544
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,936874,936879,4194304,256,0,0,20,24,330112,0x7f61960b3500,0x7f608a437840,0,0,0,12076633328574043,12076633328754672,12076633331806507,12076633331873751
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,936874,936879,4194304,256,0,0,20,24,332864,0x7f61960b3400,0x7f608a437880,0,0,0,12076633331903486,12076633332089866,12076633333631304,12076633333699707
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,936874,936879,4194304,256,0,0,12,24,335616,0x7f61960b3300,0x7f608a4378c0,0,0,0,12076633333718633,12076633333917383,12076633334706502,12076633334775609
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,936874,936879,4194304,256,0,0,12,24,339392,0x7f61960b3a00,0x7f608a437900,0,0,0,12076633334805665,12076633334990981,12076633337274018,12076633337341361
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,936874,936879,4194304,256,0,0,12,24,344192,0x7f61960b3900,0x7f608a437940,0,0,0,12076633337386325,12076633337554977,12076633339089695,12076633339156187
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,936874,936879,4194304,256,0,0,20,24,345408,0x7f61960b3800,0x7f608a437980,0,0,0,12076633339186183,12076633339368574,12076633345424244,12076633345491572
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,936874,936879,4194304,256,0,0,20,24,348160,0x7f61960b3700,0x7f608a4379c0,0,0,0,12076633345522229,12076633345703764,12076633348746799,12076633348812990
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,936874,936879,4194304,256,0,0,12,24,350912,0x7f61960b3600,0x7f608a437a00,0,0,0,12076633348844318,12076633349024238,12076633350563916,12076633350634588
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,936874,936879,4194304,256,0,0,12,24,0,0x7f61960b3500,0x7f608a437a40,0,0,0,12076633350663292,12076633350846795,12076633355372868,12076633355441740
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 936874 936879 33554432 256 0 0 8 32 6464 0x0 0x7f608a404180 0 0 0 12076632988700397 12076633233142956 12076633233467755 12076633233577518
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 936874 936879 32768 256 0 0 24 24 12480 0x0 0x7f608a435100 0 0 0 12076633248282761 12076633248580944 12076633248587504 12076633248592868
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 4 936874 936879 4194304 256 0 0 24 24 12928 0x7f61960b3900 0x7f608a435140 0 0 0 12076633248655084 12076633248875663 12076633249007503 12076633249011156
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 936874 936879 4194304 256 0 0 36 24 13632 0x7f61960b3800 0x7f608a435180 0 0 0 12076633249083771 12076633249259982 12076633249507821 12076633249576949
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 8 936874 936879 4194304 256 0 0 28 24 14080 0x7f61960b3700 0x7f608a4351c0 0 0 0 12076633249608708 12076633249789420 12076633250035179 12076633250105001
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 10 936874 936879 4194304 256 0 0 24 24 14528 0x7f61960b3600 0x7f608a435200 0 0 0 12076633250132733 12076633250316619 12076633250448138 12076633250451676
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 12 936874 936879 4194304 256 0 0 24 24 14976 0x7f61960b3500 0x7f608a435240 0 0 0 12076633250496409 12076633250679817 12076633250812617 12076633250816044
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 14 936874 936879 4194304 256 0 0 24 24 15424 0x7f61960b3400 0x7f608a435280 0 0 0 12076633250895321 12076633251060296 12076633251191976 12076633251195409
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 936874 936879 4194304 256 0 0 28 24 16128 0x7f61960b3300 0x7f608a4352c0 0 0 0 12076633251246094 12076633251413895 12076633251661094 12076633251701931
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 18 936874 936879 4194304 256 0 0 28 24 16832 0x7f61960b3a00 0x7f608a435300 0 0 0 12076633251729673 12076633251907493 12076633252160773 12076633252201130
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 20 936874 936879 4194304 256 0 0 24 24 17536 0x7f61960b3900 0x7f608a435340 0 0 0 12076633252226157 12076633252419172 12076633252550691 12076633252553866
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 22 936874 936879 4194304 256 0 0 24 24 18240 0x7f61960b3800 0x7f608a435380 0 0 0 12076633252603118 12076633252768771 12076633252906050 12076633252909488
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 24 936874 936879 4194304 256 0 0 24 24 18944 0x7f61960b3700 0x7f608a4353c0 0 0 0 12076633252972405 12076633253146529 12076633253279009 12076633253282592
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 936874 936879 4194304 256 0 0 28 24 19904 0x7f61960b3600 0x7f608a435400 0 0 0 12076633253333196 12076633253509248 12076633253764447 12076633253830080
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 28 936874 936879 4194304 256 0 0 28 24 20608 0x7f61960b3500 0x7f608a435440 0 0 0 12076633253855728 12076633254038846 12076633254284126 12076633254350308
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 30 936874 936879 4194304 256 0 0 24 24 21312 0x7f61960b3400 0x7f608a435480 0 0 0 12076633254374643 12076633254569085 12076633254696444 12076633254699788
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 32 936874 936879 4194304 256 0 0 24 24 22016 0x7f61960b3300 0x7f608a4354c0 0 0 0 12076633254755151 12076633254917723 12076633255047163 12076633255050440
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 34 936874 936879 4194304 256 0 0 24 24 22720 0x7f61960b3a00 0x7f608a435500 0 0 0 12076633255116212 12076633255282362 12076633255415482 12076633255419256
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 936874 936879 4194304 256 0 0 28 24 23680 0x7f61960b3900 0x7f608a435540 0 0 0 12076633255468568 12076633255632441 12076633255880920 12076633255946547
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 38 936874 936879 4194304 256 0 0 28 24 24384 0x7f61960b3800 0x7f608a435580 0 0 0 12076633255971814 12076633256167319 12076633256415479 12076633256482744
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 40 936874 936879 4194304 256 0 0 24 24 25088 0x7f61960b3700 0x7f608a4355c0 0 0 0 12076633256513532 12076633256694198 12076633256824277 12076633256827666
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 42 936874 936879 4194304 256 0 0 24 24 25792 0x7f61960b3600 0x7f608a435600 0 0 0 12076633256875695 12076633257046196 12076633257177396 12076633257180993
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 44 936874 936879 4194304 256 0 0 24 24 26496 0x7f61960b3500 0x7f608a435640 0 0 0 12076633257242778 12076633257409555 12076633257538995 12076633257542646
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 936874 936879 4194304 256 0 0 28 24 27712 0x7f61960b3400 0x7f608a435680 0 0 0 12076633257590625 12076633257760274 12076633258010673 12076633258077330
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 48 936874 936879 4194304 256 0 0 28 24 28416 0x7f61960b3300 0x7f608a4356c0 0 0 0 12076633258106565 12076633258284592 12076633258536752 12076633258601906
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 50 936874 936879 4194304 256 0 0 24 24 29120 0x7f61960b3a00 0x7f608a435700 0 0 0 12076633258628776 12076633258812431 12076633258942990 12076633258946537
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 52 936874 936879 4194304 256 0 0 24 24 30080 0x7f61960b3900 0x7f608a435740 0 0 0 12076633258996160 12076633259162990 12076633259293709 12076633259297250
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 54 936874 936879 4194304 256 0 0 24 24 30784 0x7f61960b3800 0x7f608a435780 0 0 0 12076633259359465 12076633259524268 12076633259654668 12076633259658061
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 936874 936879 4194304 256 0 0 28 24 32000 0x7f61960b3700 0x7f608a4357c0 0 0 0 12076633259706872 12076633259876267 12076633260129866 12076633260195971
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 58 936874 936879 4194304 256 0 0 28 24 32960 0x7f61960b3600 0x7f608a435800 0 0 0 12076633260219806 12076633260405705 12076633260656105 12076633260721960
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 60 936874 936879 4194304 256 0 0 24 24 33920 0x7f61960b3500 0x7f608a435840 0 0 0 12076633260748980 12076633260926024 12076633261062503 12076633261066380
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 62 936874 936879 4194304 256 0 0 24 24 34880 0x7f61960b3400 0x7f608a435880 0 0 0 12076633261118247 12076633261280263 12076633261410822 12076633261414207
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 64 936874 936879 4194304 256 0 0 24 24 35840 0x7f61960b3300 0x7f608a4358c0 0 0 0 12076633261475622 12076633261637701 12076633261767301 12076633261771041
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 936874 936879 4194304 256 0 0 28 24 37312 0x7f61960b3a00 0x7f608a435900 0 0 0 12076633261822056 12076633261987140 12076633262240579 12076633262309383
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 68 936874 936879 4194304 256 0 0 28 24 38272 0x7f61960b3900 0x7f608a435940 0 0 0 12076633262335331 12076633262518499 12076633262770338 12076633262836934
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 70 936874 936879 4194304 256 0 0 24 24 39232 0x7f61960b3800 0x7f608a435980 0 0 0 12076633262862812 12076633263045537 12076633263174976 12076633263179050
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 72 936874 936879 4194304 256 0 0 24 24 40192 0x7f61960b3700 0x7f608a4359c0 0 0 0 12076633263228392 12076633263397856 12076633263532415 12076633263536104
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 74 936874 936879 4194304 256 0 0 24 24 41152 0x7f61960b3600 0x7f608a435a00 0 0 0 12076633263597128 12076633263758014 12076633263886494 12076633263890213
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 936874 936879 4194304 256 0 0 28 24 42624 0x7f61960b3500 0x7f608a435a40 0 0 0 12076633263939264 12076633264116733 12076633264370012 12076633264436299
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 78 936874 936879 4194304 256 0 0 28 24 43584 0x7f61960b3400 0x7f608a435a80 0 0 0 12076633264461406 12076633264642332 12076633264895611 12076633264936519
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 80 936874 936879 4194304 256 0 0 24 24 44544 0x7f61960b3300 0x7f608a435ac0 0 0 0 12076633264961666 12076633265147450 12076633265280569 12076633265284477
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 82 936874 936879 4194304 256 0 0 24 24 45760 0x7f61960b3a00 0x7f608a435b00 0 0 0 12076633265328649 12076633265503449 12076633265636568 12076633265640128
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 84 936874 936879 4194304 256 0 0 24 24 46720 0x7f61960b3900 0x7f608a435b40 0 0 0 12076633265701512 12076633265864248 12076633265994967 12076633265998645
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 936874 936879 4194304 256 0 0 28 24 48448 0x7f61960b3800 0x7f608a435b80 0 0 0 12076633266047025 12076633266217846 12076633266486326 12076633266554890
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 88 936874 936879 4194304 256 0 0 28 24 49408 0x7f61960b3700 0x7f608a435bc0 0 0 0 12076633266577662 12076633266756405 12076633267008404 12076633267075178
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 90 936874 936879 4194304 256 0 0 24 24 50368 0x7f61960b3600 0x7f608a435c00 0 0 0 12076633267102458 12076633267288243 12076633267415762 12076633267419418
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 92 936874 936879 4194304 256 0 0 24 24 51584 0x7f61960b3500 0x7f608a435c40 0 0 0 12076633267469291 12076633267632402 12076633267763441 12076633267767095
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 94 936874 936879 4194304 256 0 0 24 24 52544 0x7f61960b3400 0x7f608a435c80 0 0 0 12076633267827266 12076633267990641 12076633268119760 12076633268123598
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 936874 936879 4194304 256 0 0 28 24 54272 0x7f61960b3300 0x7f608a435cc0 0 0 0 12076633268173450 12076633268353839 12076633268615119 12076633268657311
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 98 936874 936879 4194304 256 0 0 28 24 55488 0x7f61960b3a00 0x7f608a435d00 0 0 0 12076633268680654 12076633268861358 12076633269151117 12076633269218785
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 100 936874 936879 4194304 256 0 0 24 24 56704 0x7f61960b3900 0x7f608a435d40 0 0 0 12076633269246707 12076633269422316 12076633269592075 12076633269595656
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 102 936874 936879 4194304 256 0 0 24 24 58176 0x7f61960b3800 0x7f608a435d80 0 0 0 12076633269648084 12076633269809515 12076633269949354 12076633269953011
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 104 936874 936879 4194304 256 0 0 24 24 59392 0x7f61960b3700 0x7f608a435dc0 0 0 0 12076633270019164 12076633270181353 12076633270313833 12076633270317358
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 936874 936879 4194304 256 0 0 28 24 61376 0x7f61960b3600 0x7f608a435e00 0 0 0 12076633270370327 12076633270532552 12076633270796231 12076633270862883
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 108 936874 936879 4194304 256 0 0 28 24 62592 0x7f61960b3500 0x7f608a435e40 0 0 0 12076633270898730 12076633271061991 12076633271308390 12076633271374665
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 110 936874 936879 4194304 256 0 0 24 24 63808 0x7f61960b3400 0x7f608a435e80 0 0 0 12076633271405943 12076633271589509 12076633271718628 12076633271722212
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 112 936874 936879 4194304 256 0 0 24 24 65280 0x7f61960b3300 0x7f608a435ec0 0 0 0 12076633271770912 12076633271932868 12076633272075747 12076633272079266
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 114 936874 936879 4194304 256 0 0 24 24 66496 0x7f61960b3a00 0x7f608a435f00 0 0 0 12076633272141782 12076633272304866 12076633272433666 12076633272437141
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 936874 936879 4194304 256 0 0 28 24 68480 0x7f61960b3900 0x7f608a435f40 0 0 0 12076633272485612 12076633272647905 12076633272911264 12076633272933585
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 118 936874 936879 4194304 256 0 0 28 24 69696 0x7f61960b3800 0x7f608a435f80 0 0 0 12076633272975523 12076633273140864 12076633273395743 12076633273445096
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 120 936874 936879 4194304 256 0 0 24 24 70912 0x7f61960b3700 0x7f608a435fc0 0 0 0 12076633273473159 12076633273648382 12076633273782142 12076633273785700
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 122 936874 936879 4194304 256 0 0 24 24 72384 0x7f61960b3600 0x7f608a436000 0 0 0 12076633273834611 12076633274003741 12076633274144860 12076633274148886
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 124 936874 936879 4194304 256 0 0 24 24 73600 0x7f61960b3500 0x7f608a436040 0 0 0 12076633274210490 12076633274371260 12076633274502299 12076633274505970
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 936874 936879 4194304 256 0 0 28 24 75840 0x7f61960b3400 0x7f608a436080 0 0 0 12076633274555151 12076633274717499 12076633274978138 12076633275025376
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 128 936874 936879 4194304 256 0 0 28 24 77056 0x7f61960b3300 0x7f608a4360c0 0 0 0 12076633275051615 12076633275229657 12076633275477816 12076633275524695
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 130 936874 936879 4194304 256 0 0 24 24 78272 0x7f61960b3a00 0x7f608a436100 0 0 0 12076633275550663 12076633275726775 12076633275857175 12076633275860810
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 132 936874 936879 4194304 256 0 0 24 24 80000 0x7f61960b3900 0x7f608a436140 0 0 0 12076633275909751 12076633276086454 12076633276231414 12076633276235206
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 134 936874 936879 4194304 256 0 0 24 24 81216 0x7f61960b3800 0x7f608a436180 0 0 0 12076633276298985 12076633276459573 12076633276595412 12076633276599324
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 936874 936879 4194304 256 0 0 28 24 83456 0x7f61960b3700 0x7f608a4361c0 0 0 0 12076633276647052 12076633276813492 12076633277074771 12076633277125593
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 138 936874 936879 4194304 256 0 0 28 24 84928 0x7f61960b3600 0x7f608a436200 0 0 0 12076633277149186 12076633277331890 12076633277590129 12076633277638687
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 140 936874 936879 4194304 256 0 0 24 24 86400 0x7f61960b3500 0x7f608a436240 0 0 0 12076633277665527 12076633277840208 12076633277972688 12076633277976395
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 142 936874 936879 4194304 256 0 0 24 24 88128 0x7f61960b3400 0x7f608a436280 0 0 0 12076633278029724 12076633278204047 12076633278354127 12076633278357765
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 144 936874 936879 4194304 256 0 0 24 24 89600 0x7f61960b3300 0x7f608a4362c0 0 0 0 12076633278438284 12076633278598446 12076633278732685 12076633278736299
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 936874 936879 4194304 256 0 0 28 24 92096 0x7f61960b3a00 0x7f608a436300 0 0 0 12076633278786382 12076633278948525 12076633279214764 12076633279262998
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 148 936874 936879 4194304 256 0 0 28 24 93568 0x7f61960b3900 0x7f608a436340 0 0 0 12076633279293315 12076633279473163 12076633279726922 12076633279778217
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 150 936874 936879 4194304 256 0 0 24 24 95040 0x7f61960b3800 0x7f608a436380 0 0 0 12076633279813532 12076633279990601 12076633280127081 12076633280130863
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 152 936874 936879 4194304 256 0 0 24 24 96768 0x7f61960b3700 0x7f608a4363c0 0 0 0 12076633280180215 12076633280349320 12076633280506760 12076633280510399
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 154 936874 936879 4194304 256 0 0 24 24 98240 0x7f61960b3600 0x7f608a436400 0 0 0 12076633280571983 12076633280734279 12076633280864358 12076633280867904
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 936874 936879 4194304 256 0 0 28 24 100736 0x7f61960b3500 0x7f608a436440 0 0 0 12076633280916294 12076633281085478 12076633281345317 12076633281395826
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 158 936874 936879 4194304 256 0 0 28 24 102208 0x7f61960b3400 0x7f608a436480 0 0 0 12076633281422776 12076633281599716 12076633281849155 12076633281895325
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 160 936874 936879 4194304 256 0 0 24 24 103680 0x7f61960b3300 0x7f608a4364c0 0 0 0 12076633281921594 12076633282100194 12076633282236994 12076633282240898
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 162 936874 936879 4194304 256 0 0 24 24 105664 0x7f61960b3a00 0x7f608a436500 0 0 0 12076633282284318 12076633282460353 12076633282625953 12076633282629581
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 164 936874 936879 4194304 256 0 0 24 24 107136 0x7f61960b3900 0x7f608a436540 0 0 0 12076633282690083 12076633282847872 12076633282979391 12076633282983018
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 936874 936879 4194304 256 0 0 28 24 109888 0x7f61960b3800 0x7f608a436580 0 0 0 12076633283031619 12076633283211711 12076633283472510 12076633283519316
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 168 936874 936879 4194304 256 0 0 28 24 111360 0x7f61960b3700 0x7f608a4365c0 0 0 0 12076633283545524 12076633283720349 12076633283975868 12076633284022852
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 170 936874 936879 4194304 256 0 0 24 24 112832 0x7f61960b3600 0x7f608a436600 0 0 0 12076633284047989 12076633284232827 12076633284366107 12076633284370068
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 172 936874 936879 4194304 256 0 0 24 24 114816 0x7f61960b3500 0x7f608a436640 0 0 0 12076633284418819 12076633284585946 12076633284759866 12076633284763480
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 174 936874 936879 4194304 256 0 0 24 24 116288 0x7f61960b3400 0x7f608a436680 0 0 0 12076633284826527 12076633284988985 12076633285125464 12076633285129290
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 936874 936879 4194304 256 0 0 28 24 119040 0x7f61960b3300 0x7f608a4366c0 0 0 0 12076633285181057 12076633285342744 12076633285599383 12076633285625774
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 178 936874 936879 4194304 256 0 0 28 24 120768 0x7f61960b3a00 0x7f608a436700 0 0 0 12076633285668022 12076633285828182 12076633286081141 12076633286108352
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 180 936874 936879 4194304 256 0 0 24 24 122496 0x7f61960b3900 0x7f608a436740 0 0 0 12076633286153105 12076633286312180 12076633286445300 12076633286449176
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 182 936874 936879 4194304 256 0 0 24 24 124736 0x7f61960b3800 0x7f608a436780 0 0 0 12076633286498036 12076633286660659 12076633286843539 12076633286847456
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 184 936874 936879 4194304 256 0 0 24 24 126464 0x7f61960b3700 0x7f608a4367c0 0 0 0 12076633286908300 12076633287070098 12076633287208498 12076633287212586
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 936874 936879 4194304 256 0 0 20 24 127936 0x7f61960b3600 0x7f608a436800 0 0 0 12076633287261647 12076633287430097 12076633287696336 12076633287716503
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 188 936874 936879 4194304 256 0 0 28 24 129664 0x7f61960b3500 0x7f608a436840 0 0 0 12076633287761988 12076633287923695 12076633288174094 12076633288199181
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 190 936874 936879 4194304 256 0 0 24 24 131392 0x7f61960b3400 0x7f608a436880 0 0 0 12076633288243794 12076633288403374 12076633288532813 12076633288536689
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 192 936874 936879 4194304 256 0 0 24 24 133632 0x7f61960b3300 0x7f608a4368c0 0 0 0 12076633288584948 12076633288745772 12076633288938412 12076633288961709
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 194 936874 936879 4194304 256 0 0 24 24 135360 0x7f61960b3a00 0x7f608a436900 0 0 0 12076633289024366 12076633289187371 12076633289317931 12076633289321859
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 936874 936879 4194304 256 0 0 20 24 136832 0x7f61960b3900 0x7f608a436940 0 0 0 12076633289363366 12076633289545130 12076633289831369 12076633289855281
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 198 936874 936879 4194304 256 0 0 28 24 138560 0x7f61960b3800 0x7f608a436980 0 0 0 12076633289899614 12076633290070728 12076633290354727 12076633290382903
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 200 936874 936879 4194304 256 0 0 24 24 140288 0x7f61960b3700 0x7f608a4369c0 0 0 0 12076633290424430 12076633290584806 12076633290719366 12076633290723366
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 202 936874 936879 4194304 256 0 0 24 24 142784 0x7f61960b3600 0x7f608a436a00 0 0 0 12076633290771716 12076633290941765 12076633291152165 12076633291176639
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 204 936874 936879 4194304 256 0 0 24 24 144768 0x7f61960b3500 0x7f608a436a40 0 0 0 12076633291242452 12076633291407204 12076633291545443 12076633291549302
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 936874 936879 4194304 256 0 0 20 24 145728 0x7f61960b3400 0x7f608a436a80 0 0 0 12076633291597883 12076633291776163 12076633292083522 12076633292109204
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 208 936874 936879 4194304 256 0 0 28 24 147712 0x7f61960b3300 0x7f608a436ac0 0 0 0 12076633292158676 12076633292322561 12076633292578880 12076633292602492
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 210 936874 936879 4194304 256 0 0 24 24 149696 0x7f61960b3a00 0x7f608a436b00 0 0 0 12076633292649299 12076633292807839 12076633292943679 12076633292947423
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 212 936874 936879 4194304 256 0 0 24 24 152192 0x7f61960b3900 0x7f608a436b40 0 0 0 12076633292996174 12076633293161598 12076633293389917 12076633293417397
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 214 936874 936879 4194304 256 0 0 24 24 154176 0x7f61960b3800 0x7f608a436b80 0 0 0 12076633293470767 12076633293631836 12076633293769116 12076633293772798
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 936874 936879 4194304 256 0 0 20 24 155648 0x7f61960b3700 0x7f608a436bc0 0 0 0 12076633293822220 12076633293993115 12076633294324954 12076633294353188
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 218 936874 936879 4194304 256 0 0 28 24 157632 0x7f61960b3600 0x7f608a436c00 0 0 0 12076633294398242 12076633294560153 12076633294822233 12076633294847177
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 220 936874 936879 4194304 256 0 0 24 24 159616 0x7f61960b3500 0x7f608a436c40 0 0 0 12076633294890838 12076633295059352 12076633295197271 12076633295201356
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 222 936874 936879 4194304 256 0 0 24 24 162368 0x7f61960b3400 0x7f608a436c80 0 0 0 12076633295249225 12076633295419031 12076633295665110 12076633295685576
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 224 936874 936879 4194304 256 0 0 24 24 164608 0x7f61960b3300 0x7f608a436cc0 0 0 0 12076633295742252 12076633295904949 12076633296045589 12076633296049513
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 936874 936879 4194304 256 0 0 20 24 166336 0x7f61960b3a00 0x7f608a436d00 0 0 0 12076633296097262 12076633296280966 12076633296657766 12076633296685867
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 228 936874 936879 4194304 256 0 0 28 24 168576 0x7f61960b3900 0x7f608a436d40 0 0 0 12076633296723918 12076633296886884 12076633297151364 12076633297178453
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 230 936874 936879 4194304 256 0 0 24 24 170816 0x7f61960b3800 0x7f608a436d80 0 0 0 12076633297220161 12076633297383523 12076633297525603 12076633297528014
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 232 936874 936879 4194304 256 0 0 24 24 174080 0x7f61960b3700 0x7f608a436dc0 0 0 0 12076633297580221 12076633297741283 12076633298020962 12076633298044374
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 234 936874 936879 4194304 256 0 0 24 24 176576 0x7f61960b3600 0x7f608a436e00 0 0 0 12076633298107161 12076633298273282 12076633298413602 12076633298416346
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 936874 936879 4194304 256 0 0 20 24 177792 0x7f61960b3500 0x7f608a436e40 0 0 0 12076633298466800 12076633298647681 12076633299071201 12076633299095800
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 238 936874 936879 4194304 256 0 0 28 24 180288 0x7f61960b3400 0x7f608a436e80 0 0 0 12076633299139231 12076633299308160 12076633299567360 12076633299590430
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 240 936874 936879 4194304 256 0 0 24 24 182784 0x7f61960b3300 0x7f608a436ec0 0 0 0 12076633299637748 12076633299804639 12076633299945439 12076633299948135
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 242 936874 936879 4194304 256 0 0 24 24 186304 0x7f61960b3a00 0x7f608a436f00 0 0 0 12076633299990254 12076633300171999 12076633300487678 12076633300511293
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 244 936874 936879 4194304 256 0 0 24 24 189312 0x7f61960b3900 0x7f608a436f40 0 0 0 12076633300570533 12076633300734398 12076633300887038 12076633300889767
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 936874 936879 4194304 256 0 0 20 24 190784 0x7f61960b3800 0x7f608a436f80 0 0 0 12076633300937165 12076633301115037 12076633301631676 12076633301659378
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 248 936874 936879 4194304 256 0 0 28 24 193792 0x7f61960b3700 0x7f608a436fc0 0 0 0 12076633301703430 12076633301865276 12076633302163515 12076633302190136
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 250 936874 936879 4194304 256 0 0 24 24 196800 0x7f61960b3600 0x7f608a437000 0 0 0 12076633302234328 12076633302396315 12076633302551995 12076633302554644
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 252 936874 936879 4194304 256 0 0 24 24 201088 0x7f61960b3500 0x7f608a437040 0 0 0 12076633302603625 12076633302771354 12076633303156474 12076633303180137
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 254 936874 936879 4194304 256 0 0 24 24 204608 0x7f61960b3400 0x7f608a437080 0 0 0 12076633303242233 12076633303404793 12076633303582393 12076633303584940
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 936874 936879 4194304 256 0 0 20 24 206080 0x7f61960b3300 0x7f608a4370c0 0 0 0 12076633303633100 12076633303803993 12076633304414232 12076633304437426
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 258 936874 936879 4194304 256 0 0 28 24 209600 0x7f61960b3a00 0x7f608a437100 0 0 0 12076633304476499 12076633304637111 12076633304965591 12076633304984393
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 260 936874 936879 4194304 256 0 0 24 24 213120 0x7f61960b3900 0x7f608a437140 0 0 0 12076633305038173 12076633305203350 12076633305382550 12076633305385199
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 262 936874 936879 4194304 256 0 0 24 24 218176 0x7f61960b3800 0x7f608a437180 0 0 0 12076633305433739 12076633305614070 12076633306070229 12076633306094148
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 264 936874 936879 4194304 256 0 0 24 24 222208 0x7f61960b3700 0x7f608a4371c0 0 0 0 12076633306154109 12076633306318389 12076633306519028 12076633306564092
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 936874 936879 4194304 256 0 0 20 24 223936 0x7f61960b3600 0x7f608a437200 0 0 0 12076633306592905 12076633306767028 12076633307477107 12076633307523847
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 268 936874 936879 4194304 256 0 0 28 24 227968 0x7f61960b3500 0x7f608a437240 0 0 0 12076633307547892 12076633307737106 12076633308109426 12076633308157085
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 270 936874 936879 4194304 256 0 0 24 24 232000 0x7f61960b3400 0x7f608a437280 0 0 0 12076633308188143 12076633308370385 12076633308573425 12076633308619024
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 272 936874 936879 4194304 256 0 0 24 24 237824 0x7f61960b3300 0x7f608a4372c0 0 0 0 12076633308647447 12076633308822065 12076633309347504 12076633309396020
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 274 936874 936879 4194304 256 0 0 24 24 242368 0x7f61960b3a00 0x7f608a437300 0 0 0 12076633309437276 12076633309601423 12076633309825103 12076633309874319
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 936874 936879 4194304 256 0 0 20 24 243584 0x7f61960b3900 0x7f608a437340 0 0 0 12076633309899737 12076633310079822 12076633310878861 12076633310926136
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 278 936874 936879 4194304 256 0 0 28 24 248128 0x7f61960b3800 0x7f608a437380 0 0 0 12076633310953026 12076633311138381 12076633311557900 12076633311605259
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 280 936874 936879 4194304 256 0 0 24 24 252672 0x7f61960b3700 0x7f608a4373c0 0 0 0 12076633311631217 12076633311813740 12076633312041419 12076633312087807
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 282 936874 936879 4194304 256 0 0 24 24 259264 0x7f61960b3600 0x7f608a437400 0 0 0 12076633312112462 12076633312292139 12076633312889738 12076633312935874
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 284 936874 936879 4194304 256 0 0 24 24 264832 0x7f61960b3500 0x7f608a437440 0 0 0 12076633312975969 12076633313151337 12076633313419977 12076633313467934
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 936874 936879 4194304 256 0 0 20 24 266304 0x7f61960b3400 0x7f608a437480 0 0 0 12076633313493632 12076633313672937 12076633314658695 12076633314725303
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 288 936874 936879 4194304 256 0 0 28 24 271872 0x7f61960b3300 0x7f608a4374c0 0 0 0 12076633314756260 12076633314936934 12076633315454214 12076633315523988
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 290 936874 936879 4194304 256 0 0 24 24 277440 0x7f61960b3a00 0x7f608a437500 0 0 0 12076633315542292 12076633315737733 12076633316011173 12076633316058723
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 292 936874 936879 4194304 256 0 0 12 24 279936 0x7f61960b3900 0x7f608a437540 0 0 0 12076633316081686 12076633316265252 12076633317003331 12076633317069343
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 294 936874 936879 4194304 256 0 0 24 24 286528 0x7f61960b3800 0x7f608a437580 0 0 0 12076633317108786 12076633317274851 12076633317590690 12076633317656675
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 936874 936879 4194304 256 0 0 20 24 288000 0x7f61960b3700 0x7f608a4375c0 0 0 0 12076633317677955 12076633317864450 12076633319034368 12076633319102575
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 298 936874 936879 4194304 256 0 0 32 24 294592 0x7f61960b3600 0x7f608a437600 0 0 0 12076633319135887 12076633319321247 12076633319932606 12076633319998361
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 300 936874 936879 4194304 256 0 0 24 24 301184 0x7f61960b3500 0x7f608a437640 0 0 0 12076633320030581 12076633320206366 12076633320523965 12076633320592386
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 302 936874 936879 4194304 256 0 0 12 24 304960 0x7f61960b3400 0x7f608a437680 0 0 0 12076633320617833 12076633320794685 12076633321674043 12076633321740522
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 304 936874 936879 4194304 256 0 0 24 24 313600 0x7f61960b3300 0x7f608a4376c0 0 0 0 12076633321778643 12076633321945723 12076633322379322 12076633322446986
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 936874 936879 4194304 256 0 0 20 24 314816 0x7f61960b3a00 0x7f608a437700 0 0 0 12076633322473746 12076633322659802 12076633324208919 12076633324276459
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 308 936874 936879 4194304 256 0 0 20 24 317568 0x7f61960b3900 0x7f608a437740 0 0 0 12076633324306204 12076633324488439 12076633325283157 12076633325350296
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 310 936874 936879 4194304 256 0 0 12 24 320320 0x7f61960b3800 0x7f608a437780 0 0 0 12076633325379391 12076633325562997 12076633325977236 12076633326043927
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 312 936874 936879 4194304 256 0 0 12 24 324096 0x7f61960b3700 0x7f608a4377c0 0 0 0 12076633326068562 12076633326254996 12076633327413714 12076633327480288
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 314 936874 936879 4194304 256 0 0 12 24 328896 0x7f61960b3600 0x7f608a437800 0 0 0 12076633327521235 12076633327688753 12076633328474832 12076633328542544
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 936874 936879 4194304 256 0 0 20 24 330112 0x7f61960b3500 0x7f608a437840 0 0 0 12076633328574043 12076633328754672 12076633331806507 12076633331873751
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 318 936874 936879 4194304 256 0 0 20 24 332864 0x7f61960b3400 0x7f608a437880 0 0 0 12076633331903486 12076633332089866 12076633333631304 12076633333699707
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 320 936874 936879 4194304 256 0 0 12 24 335616 0x7f61960b3300 0x7f608a4378c0 0 0 0 12076633333718633 12076633333917383 12076633334706502 12076633334775609
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 322 936874 936879 4194304 256 0 0 12 24 339392 0x7f61960b3a00 0x7f608a437900 0 0 0 12076633334805665 12076633334990981 12076633337274018 12076633337341361
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 324 936874 936879 4194304 256 0 0 12 24 344192 0x7f61960b3900 0x7f608a437940 0 0 0 12076633337386325 12076633337554977 12076633339089695 12076633339156187
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 936874 936879 4194304 256 0 0 20 24 345408 0x7f61960b3800 0x7f608a437980 0 0 0 12076633339186183 12076633339368574 12076633345424244 12076633345491572
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 328 936874 936879 4194304 256 0 0 20 24 348160 0x7f61960b3700 0x7f608a4379c0 0 0 0 12076633345522229 12076633345703764 12076633348746799 12076633348812990
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 330 936874 936879 4194304 256 0 0 12 24 350912 0x7f61960b3600 0x7f608a437a00 0 0 0 12076633348844318 12076633349024238 12076633350563916 12076633350634588
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 332 936874 936879 4194304 256 0 0 12 24 0 0x7f61960b3500 0x7f608a437a40 0 0 0 12076633350663292 12076633350846795 12076633355372868 12076633355441740
@@ -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",0,0,0,936496,936501,33554432,256,0,0,8,32,6464,0x0,0x7f17e8404180,4194304,3122666,398904176,12076630480743351,12076630718390515,12076630718714354,12076630718822006
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,936496,936501,32768,256,0,0,24,24,12480,0x0,0x7f17e8435100,512,21524,2754256,12076630733442442,12076630733749898,12076630733756458,12076630733761836
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,936496,936501,4194304,256,0,0,24,24,12928,0x7f18f4030900,0x7f17e8435140,65536,146806,18775720,12076630733826656,12076630734045577,12076630734179017,12076630734183330
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,936496,936501,4194304,256,0,0,36,24,13632,0x7f18f4030800,0x7f17e8435180,65536,166800,21363552,12076630734250836,12076630734424456,12076630734676455,12076630734744404
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,936496,936501,4194304,256,0,0,28,24,14080,0x7f18f4030700,0x7f17e84351c0,65536,145312,18687568,12076630734769059,12076630734956294,12076630735209893,12076630735278627
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,936496,936501,4194304,256,0,0,24,24,14528,0x7f18f4030600,0x7f17e8435200,65536,150966,19402760,12076630735302752,12076630735488292,12076630735621092,12076630735624911
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,936496,936501,4194304,256,0,0,24,24,14976,0x7f18f4030500,0x7f17e8435240,65536,143290,18432448,12076630735674393,12076630735852771,12076630735986530,12076630735990331
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,936496,936501,4194304,256,0,0,24,24,15424,0x7f18f4030400,0x7f17e8435280,131072,227390,29160816,12076630736069599,12076630736239969,12076630736372449,12076630736376349
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,936496,936501,4194304,256,0,0,28,24,16128,0x7f18f4030300,0x7f17e84352c0,131072,189048,24236312,12076630736425691,12076630736594848,12076630736859327,12076630736901155
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,936496,936501,4194304,256,0,0,28,24,16832,0x7f18f4030a00,0x7f17e8435300,65536,148268,19040936,12076630736924379,12076630737129406,12076630737382525,12076630737423557
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,936496,936501,4194304,256,0,0,24,24,17536,0x7f18f4030900,0x7f17e8435340,131072,225494,28835256,12076630737447872,12076630737636284,12076630737769244,12076630737772967
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,936496,936501,4194304,256,0,0,24,24,18240,0x7f18f4030800,0x7f17e8435380,131072,224970,28826816,12076630737822008,12076630737987003,12076630738122203,12076630738126284
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,936496,936501,4194304,256,0,0,24,24,18944,0x7f18f4030700,0x7f17e84353c0,131072,226920,29124800,12076630738189021,12076630738358362,12076630738491961,12076630738495431
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,936496,936501,4194304,256,0,0,28,24,19904,0x7f18f4030600,0x7f17e8435400,131072,188884,24133824,12076630738544602,12076630738707800,12076630738967000,12076630739033422
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,936496,936501,4194304,256,0,0,28,24,20608,0x7f18f4030500,0x7f17e8435440,65536,145354,18673600,12076630739060312,12076630739245559,12076630739502998,12076630739569298
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,936496,936501,4194304,256,0,0,24,24,21312,0x7f18f4030400,0x7f17e8435480,131072,225206,28872752,12076630739595898,12076630739772117,12076630739904916,12076630739908349
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,936496,936501,4194304,256,0,0,24,24,22016,0x7f18f4030300,0x7f17e84354c0,131072,219560,28258888,12076630739957340,12076630740132275,12076630740260595,12076630740264552
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,936496,936501,4194304,256,0,0,24,24,22720,0x7f18f4030a00,0x7f17e8435500,131072,264056,33825168,12076630740326287,12076630740491314,12076630740667473,12076630740671338
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,936496,936501,4194304,256,0,0,28,24,23680,0x7f18f4030900,0x7f17e8435540,131072,180248,23012800,12076630740719638,12076630740889393,12076630741144752,12076630741211082
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,936496,936501,4194304,256,0,0,28,24,24384,0x7f18f4030800,0x7f17e8435580,65536,152108,19358000,12076630741236900,12076630741422351,12076630741680270,12076630741747320
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,936496,936501,4194304,256,0,0,24,24,25088,0x7f18f4030700,0x7f17e84355c0,131072,240572,30745160,12076630741770152,12076630741952429,12076630742085388,12076630742089256
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,936496,936501,4194304,256,0,0,24,24,25792,0x7f18f4030600,0x7f17e8435600,131072,227926,29102264,12076630742137025,12076630742315147,12076630742445387,12076630742449195
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,936496,936501,4194304,256,0,0,24,24,26496,0x7f18f4030500,0x7f17e8435640,131072,238044,30586152,12076630742511051,12076630742675146,12076630742808906,12076630742812662
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,936496,936501,4194304,256,0,0,28,24,27712,0x7f18f4030400,0x7f17e8435680,131072,214086,27454552,12076630742860410,12076630743039145,12076630743299624,12076630743365810
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,936496,936501,4194304,256,0,0,28,24,28416,0x7f18f4030300,0x7f17e84356c0,65536,151892,19296600,12076630743392941,12076630743572743,12076630743826662,12076630743893562
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,936496,936501,4194304,256,0,0,24,24,29120,0x7f18f4030a00,0x7f17e8435700,131072,227084,29063024,12076630743916916,12076630744096741,12076630744229700,12076630744233504
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,936496,936501,4194304,256,0,0,24,24,30080,0x7f18f4030900,0x7f17e8435740,131072,229102,29379856,12076630744284449,12076630744448740,12076630744578819,12076630744582634
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,936496,936501,4194304,256,0,0,24,24,30784,0x7f18f4030800,0x7f17e8435780,131072,223660,28589792,12076630744643166,12076630744804258,12076630744933858,12076630744937734
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,936496,936501,4194304,256,0,0,28,24,32000,0x7f18f4030700,0x7f17e84357c0,131072,188756,24135584,12076630744985393,12076630745172737,12076630745435136,12076630745501092
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,936496,936501,4194304,256,0,0,28,24,32960,0x7f18f4030600,0x7f17e8435800,65536,149072,19052288,12076630745525418,12076630745703935,12076630745960734,12076630746027231
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,936496,936501,4194304,256,0,0,24,24,33920,0x7f18f4030500,0x7f17e8435840,131072,221292,28294208,12076630746054892,12076630746232413,12076630746368733,12076630746372603
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,936496,936501,4194304,256,0,0,24,24,34880,0x7f18f4030400,0x7f17e8435880,131072,224710,28664736,12076630746420783,12076630746583132,12076630746718331,12076630746721993
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,936496,936501,4194304,256,0,0,24,24,35840,0x7f18f4030300,0x7f17e84358c0,131072,221994,28400584,12076630746783147,12076630746946171,12076630747076730,12076630747081081
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,936496,936501,4194304,256,0,0,28,24,37312,0x7f18f4030a00,0x7f17e8435900,131072,217500,27821104,12076630747129852,12076630747303289,12076630747563928,12076630747631135
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,936496,936501,4194304,256,0,0,28,24,38272,0x7f18f4030900,0x7f17e8435940,65536,145802,18533032,12076630747657163,12076630747834007,12076630748087127,12076630748154638
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,936496,936501,4194304,256,0,0,24,24,39232,0x7f18f4030800,0x7f17e8435980,131072,227466,29112696,12076630748178493,12076630748364246,12076630748501205,12076630748504940
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,936496,936501,4194304,256,0,0,24,24,40192,0x7f18f4030700,0x7f17e84359c0,131072,228766,29163784,12076630748553921,12076630748717684,12076630748854324,12076630748858297
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,936496,936501,4194304,256,0,0,24,24,41152,0x7f18f4030600,0x7f17e8435a00,131072,217996,27926896,12076630748919220,12076630749086643,12076630749218962,12076630749222755
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,936496,936501,4194304,256,0,0,28,24,42624,0x7f18f4030500,0x7f17e8435a40,131072,183100,23413936,12076630749271796,12076630749443922,12076630749703761,12076630749770233
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,936496,936501,4194304,256,0,0,28,24,43584,0x7f18f4030400,0x7f17e8435a80,65536,152676,19429816,12076630749794378,12076630749972560,12076630750232559,12076630750330926
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,936496,936501,4194304,256,0,0,24,24,44544,0x7f18f4030300,0x7f17e8435ac0,131072,223680,28697848,12076630750354861,12076630750548078,12076630750684717,12076630750688662
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,936496,936501,4194304,256,0,0,24,24,45760,0x7f18f4030a00,0x7f17e8435b00,131072,226080,29158928,12076630750736942,12076630750906636,12076630751043756,12076630751048231
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,936496,936501,4194304,256,0,0,24,24,46720,0x7f18f4030900,0x7f17e8435b40,131072,225830,28997752,12076630751108353,12076630751277195,12076630751411114,12076630751415093
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,936496,936501,4194304,256,0,0,28,24,48448,0x7f18f4030800,0x7f17e8435b80,131072,180756,23135336,12076630751465056,12076630751622794,12076630751892553,12076630751963002
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,936496,936501,4194304,256,0,0,28,24,49408,0x7f18f4030700,0x7f17e8435bc0,65536,149440,19114736,12076630751989592,12076630752170152,12076630752426471,12076630752493219
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,936496,936501,4194304,256,0,0,24,24,50368,0x7f18f4030600,0x7f17e8435c00,131072,262266,33623728,12076630752519848,12076630752699110,12076630752828069,12076630752832029
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,936496,936501,4194304,256,0,0,24,24,51584,0x7f18f4030500,0x7f17e8435c40,131072,227186,29060408,12076630752881821,12076630753052069,12076630753188388,12076630753191978
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,936496,936501,4194304,256,0,0,24,24,52544,0x7f18f4030400,0x7f17e8435c80,131072,230542,29470864,12076630753253212,12076630753416867,12076630753551107,12076630753554743
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,936496,936501,4194304,256,0,0,28,24,54272,0x7f18f4030300,0x7f17e8435cc0,131072,177778,22873048,12076630753602021,12076630753773186,12076630754037505,12076630754103965
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,936496,936501,4194304,256,0,0,28,24,55488,0x7f18f4030a00,0x7f17e8435d00,65536,173192,22154512,12076630754130945,12076630754309184,12076630754565183,12076630754631786
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,936496,936501,4194304,256,0,0,24,24,56704,0x7f18f4030900,0x7f17e8435d40,131072,227532,29252136,12076630754654709,12076630754831742,12076630754965662,12076630754969194
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,936496,936501,4194304,256,0,0,24,24,58176,0x7f18f4030800,0x7f17e8435d80,131072,229234,29409264,12076630755019708,12076630755193341,12076630755334460,12076630755338551
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,936496,936501,4194304,256,0,0,24,24,59392,0x7f18f4030700,0x7f17e8435dc0,131072,228260,29183648,12076630755399925,12076630755561499,12076630755699419,12076630755703179
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,936496,936501,4194304,256,0,0,28,24,61376,0x7f18f4030600,0x7f17e8435e00,131072,225254,28764944,12076630755751660,12076630755919578,12076630756178297,12076630756245338
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,936496,936501,4194304,256,0,0,28,24,62592,0x7f18f4030500,0x7f17e8435e40,65536,149242,19063064,12076630756272358,12076630756448696,12076630756708375,12076630756774753
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,936496,936501,4194304,256,0,0,24,24,63808,0x7f18f4030400,0x7f17e8435e80,131072,227156,29014288,12076630756799128,12076630756979894,12076630757113814,12076630757118462
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,936496,936501,4194304,256,0,0,24,24,65280,0x7f18f4030300,0x7f17e8435ec0,131072,227782,28907472,12076630757168094,12076630757331253,12076630757470293,12076630757474214
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,936496,936501,4194304,256,0,0,24,24,66496,0x7f18f4030a00,0x7f17e8435f00,131072,227102,29022864,12076630757534035,12076630757693812,12076630757829171,12076630757832911
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,936496,936501,4194304,256,0,0,28,24,68480,0x7f18f4030900,0x7f17e8435f40,131072,227088,29089344,12076630757880630,12076630758053810,12076630758311250,12076630758378676
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,936496,936501,4194304,256,0,0,28,24,69696,0x7f18f4030800,0x7f17e8435f80,65536,147704,18861032,12076630758405416,12076630758579409,12076630758833328,12076630758899234
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,936496,936501,4194304,256,0,0,24,24,70912,0x7f18f4030700,0x7f17e8435fc0,131072,225116,28894504,12076630758925974,12076630759114927,12076630759247406,12076630759251199
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,936496,936501,4194304,256,0,0,24,24,72384,0x7f18f4030600,0x7f17e8436000,131072,226356,28938968,12076630759300401,12076630759463085,12076630759602125,12076630759606019
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,936496,936501,4194304,256,0,0,24,24,73600,0x7f18f4030500,0x7f17e8436040,131072,225464,28891992,12076630759666862,12076630759827084,12076630759958124,12076630759961801
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,936496,936501,4194304,256,0,0,28,24,75840,0x7f18f4030400,0x7f17e8436080,131072,176088,22573592,12076630760013808,12076630760177483,12076630760446122,12076630760512545
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,936496,936501,4194304,256,0,0,28,24,77056,0x7f18f4030300,0x7f17e84360c0,65536,146200,18638136,12076630760536089,12076630760720041,12076630760976040,12076630761018497
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,936496,936501,4194304,256,0,0,24,24,78272,0x7f18f4030a00,0x7f17e8436100,131072,264440,33553728,12076630761040888,12076630761222279,12076630761352679,12076630761356676
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,936496,936501,4194304,256,0,0,24,24,80000,0x7f18f4030900,0x7f17e8436140,131072,197214,25313256,12076630761405857,12076630761574598,12076630761721477,12076630761725392
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,936496,936501,4194304,256,0,0,24,24,81216,0x7f18f4030800,0x7f17e8436180,131072,225482,28825616,12076630761785584,12076630761943076,12076630762078116,12076630762082105
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,936496,936501,4194304,256,0,0,28,24,83456,0x7f18f4030700,0x7f17e84361c0,131072,180478,23151528,12076630762129794,12076630762300995,12076630762570114,12076630762591432
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,936496,936501,4194304,256,0,0,28,24,84928,0x7f18f4030600,0x7f17e8436200,65536,180078,23066240,12076630762634322,12076630762792833,12076630763090272,12076630763113874
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,936496,936501,4194304,256,0,0,24,24,86400,0x7f18f4030500,0x7f17e8436240,131072,233184,29574320,12076630763158197,12076630763319871,12076630763454111,12076630763458125
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,936496,936501,4194304,256,0,0,24,24,88128,0x7f18f4030400,0x7f17e8436280,131072,199190,25603288,12076630763506124,12076630763673150,12076630763825150,12076630763829095
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,936496,936501,4194304,256,0,0,24,24,89600,0x7f18f4030300,0x7f17e84362c0,131072,230656,29615904,12076630763911097,12076630764071869,12076630764206108,12076630764210123
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,936496,936501,4194304,256,0,0,28,24,92096,0x7f18f4030a00,0x7f17e8436300,131072,183604,23426328,12076630764258634,12076630764426907,12076630764697786,12076630764722096
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,936496,936501,4194304,256,0,0,28,24,93568,0x7f18f4030900,0x7f17e8436340,65536,144156,18434176,12076630764763383,12076630764925306,12076630765180345,12076630765204984
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,936496,936501,4194304,256,0,0,24,24,95040,0x7f18f4030800,0x7f17e8436380,131072,218512,27909952,12076630765247433,12076630765408344,12076630765542263,12076630765545828
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,936496,936501,4194304,256,0,0,24,24,96768,0x7f18f4030700,0x7f17e84363c0,131072,230722,29479352,12076630765596031,12076630765765623,12076630765923542,12076630765927498
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,936496,936501,4194304,256,0,0,24,24,98240,0x7f18f4030600,0x7f17e8436400,131072,223186,28522608,12076630765987219,12076630766158581,12076630766292341,12076630766296665
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,936496,936501,4194304,256,0,0,28,24,100736,0x7f18f4030500,0x7f17e8436440,131072,182648,23339480,12076630766345836,12076630766516660,12076630766781619,12076630766829576
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,936496,936501,4194304,256,0,0,28,24,102208,0x7f18f4030400,0x7f17e8436480,65536,186902,23869552,12076630766854182,12076630767035538,12076630767288177,12076630767338382
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,936496,936501,4194304,256,0,0,24,24,103680,0x7f18f4030300,0x7f17e84364c0,131072,228500,29147816,12076630767365653,12076630767540816,12076630767675696,12076630767679337
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,936496,936501,4194304,256,0,0,24,24,105664,0x7f18f4030a00,0x7f17e8436500,131072,218106,27972760,12076630767728779,12076630767895695,12076630768061934,12076630768065795
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,936496,936501,4194304,256,0,0,24,24,107136,0x7f18f4030900,0x7f17e8436540,131072,225908,28729320,12076630768128412,12076630768290893,12076630768421293,12076630768425354
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,936496,936501,4194304,256,0,0,28,24,109888,0x7f18f4030800,0x7f17e8436580,131072,180044,23043184,12076630768473734,12076630768640652,12076630768907051,12076630768931195
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,936496,936501,4194304,256,0,0,28,24,111360,0x7f18f4030700,0x7f17e84365c0,65536,151132,19419864,12076630768976980,12076630769161450,12076630769421129,12076630769468905
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,936496,936501,4194304,256,0,0,24,24,112832,0x7f18f4030600,0x7f17e8436600,131072,265290,33842312,12076630769492760,12076630769670568,12076630769807848,12076630769811863
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,936496,936501,4194304,256,0,0,24,24,114816,0x7f18f4030500,0x7f17e8436640,131072,223124,28752200,12076630769861646,12076630770031207,12076630770204486,12076630770208471
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,936496,936501,4194304,256,0,0,24,24,116288,0x7f18f4030400,0x7f17e8436680,131072,225756,29003960,12076630770269695,12076630770430726,12076630770562085,12076630770566086
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,936496,936501,4194304,256,0,0,28,24,119040,0x7f18f4030300,0x7f17e84366c0,131072,178990,22852184,12076630770615679,12076630770777604,12076630771042723,12076630771091424
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,936496,936501,4194304,256,0,0,28,24,120768,0x7f18f4030a00,0x7f17e8436700,65536,144814,18524880,12076630771118253,12076630771294723,12076630771554082,12076630771600681
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,936496,936501,4194304,256,0,0,24,24,122496,0x7f18f4030900,0x7f17e8436740,131072,227744,29192792,12076630771625737,12076630771805761,12076630771941440,12076630771945592
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,936496,936501,4194304,256,0,0,24,24,124736,0x7f18f4030800,0x7f17e8436780,131072,227082,28994272,12076630771994333,12076630772168479,12076630772350719,12076630772354974
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,936496,936501,4194304,256,0,0,24,24,126464,0x7f18f4030700,0x7f17e84367c0,131072,226390,29055120,12076630772416588,12076630772579518,12076630772720317,12076630772723990
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,936496,936501,4194304,256,0,0,20,24,127936,0x7f18f4030600,0x7f17e8436800,131072,223916,28593808,12076630772770507,12076630772936157,12076630773203356,12076630773250399
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,936496,936501,4194304,256,0,0,28,24,129664,0x7f18f4030500,0x7f17e8436840,65536,151472,19400720,12076630773273172,12076630773451355,12076630773710074,12076630773756300
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,936496,936501,4194304,256,0,0,24,24,131392,0x7f18f4030400,0x7f17e8436880,131072,257456,32738176,12076630773781838,12076630773955353,12076630774097592,12076630774101833
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,936496,936501,4194304,256,0,0,24,24,133632,0x7f18f4030300,0x7f17e84368c0,131072,235504,29915176,12076630774150303,12076630774322232,12076630774513271,12076630774561378
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,936496,936501,4194304,256,0,0,24,24,135360,0x7f18f4030a00,0x7f17e8436900,131072,256744,32770632,12076630774598196,12076630774758870,12076630774899349,12076630774903304
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,936496,936501,4194304,256,0,0,20,24,136832,0x7f18f4030900,0x7f17e8436940,131072,221814,28524864,12076630774952726,12076630775123669,12076630775406548,12076630775455772
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,936496,936501,4194304,256,0,0,28,24,138560,0x7f18f4030800,0x7f17e8436980,65536,153198,19621168,12076630775479025,12076630775659987,12076630775917906,12076630775964748
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,936496,936501,4194304,256,0,0,24,24,140288,0x7f18f4030700,0x7f17e84369c0,131072,246534,31503272,12076630775991037,12076630776179345,12076630776313584,12076630776317915
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,936496,936501,4194304,256,0,0,24,24,142784,0x7f18f4030600,0x7f17e8436a00,131072,219418,28232720,12076630776366896,12076630776538224,12076630776749583,12076630776771990
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,936496,936501,4194304,256,0,0,24,24,144768,0x7f18f4030500,0x7f17e8436a40,131072,220666,28206928,12076630776825820,12076630776987982,12076630777126861,12076630777130848
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,936496,936501,4194304,256,0,0,20,24,145728,0x7f18f4030400,0x7f17e8436a80,131072,220914,28364160,12076630777180931,12076630777346221,12076630777653419,12076630777700587
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,936496,936501,4194304,256,0,0,28,24,147712,0x7f18f4030300,0x7f17e8436ac0,65536,144544,18398472,12076630777724111,12076630777900779,12076630778160938,12076630778209855
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,936496,936501,4194304,256,0,0,24,24,149696,0x7f18f4030a00,0x7f17e8436b00,131072,215842,27686136,12076630778236775,12076630778412617,12076630778548296,12076630778552051
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,936496,936501,4194304,256,0,0,24,24,152192,0x7f18f4030900,0x7f17e8436b40,131072,225646,29102320,12076630778600181,12076630778766375,12076630778994215,12076630779043365
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,936496,936501,4194304,256,0,0,24,24,154176,0x7f18f4030800,0x7f17e8436b80,131072,228722,29085824,12076630779077990,12076630779247174,12076630779383173,12076630779387625
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,936496,936501,4194304,256,0,0,20,24,155648,0x7f18f4030700,0x7f17e8436bc0,131072,225666,28944104,12076630779437468,12076630779610212,12076630779939331,12076630779987521
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,936496,936501,4194304,256,0,0,28,24,157632,0x7f18f4030600,0x7f17e8436c00,65536,143190,18288432,12076630780015714,12076630780195010,12076630780457889,12076630780506937
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,936496,936501,4194304,256,0,0,24,24,159616,0x7f18f4030500,0x7f17e8436c40,131072,228308,29263736,12076630780533056,12076630780712928,12076630780848608,12076630780852781
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,936496,936501,4194304,256,0,0,24,24,162368,0x7f18f4030400,0x7f17e8436c80,131072,229866,29433672,12076630780901071,12076630781073567,12076630781318366,12076630781368059
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,936496,936501,4194304,256,0,0,24,24,164608,0x7f18f4030300,0x7f17e8436cc0,131072,223206,28804256,12076630781410769,12076630781575563,12076630781712523,12076630781719633
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,936496,936501,4194304,256,0,0,20,24,166336,0x7f18f4030a00,0x7f17e8436d00,131072,228840,29255776,12076630781762894,12076630781931561,12076630782308040,12076630782355576
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,936496,936501,4194304,256,0,0,28,24,168576,0x7f18f4030900,0x7f17e8436d40,65536,149238,18983736,12076630782381955,12076630782559879,12076630782825799,12076630782872948
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,936496,936501,4194304,256,0,0,24,24,170816,0x7f18f4030800,0x7f17e8436d80,131072,230536,29506024,12076630782898456,12076630783077478,12076630783220037,12076630783223300
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,936496,936501,4194304,256,0,0,24,24,174080,0x7f18f4030700,0x7f17e8436dc0,131072,229452,29219960,12076630783272983,12076630783446917,12076630783756196,12076630783801987
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,936496,936501,4194304,256,0,0,24,24,176576,0x7f18f4030600,0x7f17e8436e00,131072,230522,29545328,12076630783837322,12076630784001795,12076630784141955,12076630784145506
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,936496,936501,4194304,256,0,0,20,24,177792,0x7f18f4030500,0x7f17e8436e40,131072,209118,26916032,12076630784193916,12076630784367074,12076630784792513,12076630784840148
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,936496,936501,4194304,256,0,0,28,24,180288,0x7f18f4030400,0x7f17e8436e80,65536,154162,19781176,12076630784863591,12076630785052512,12076630785316192,12076630785364583
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,936496,936501,4194304,256,0,0,24,24,182784,0x7f18f4030300,0x7f17e8436ec0,131072,225288,28626392,12076630785392425,12076630785568191,12076630785707071,12076630785710817
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,936496,936501,4194304,256,0,0,24,24,186304,0x7f18f4030a00,0x7f17e8436f00,131072,225312,28824128,12076630785759147,12076630785925150,12076630786240509,12076630786288993
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,936496,936501,4194304,256,0,0,24,24,189312,0x7f18f4030900,0x7f17e8436f40,131072,227616,28908840,12076630786330530,12076630786491709,12076630786644188,12076630786647249
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,936496,936501,4194304,256,0,0,20,24,190784,0x7f18f4030800,0x7f17e8436f80,131072,225682,28777744,12076630786695389,12076630786863228,12076630787380186,12076630787429053
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,936496,936501,4194304,256,0,0,28,24,193792,0x7f18f4030700,0x7f17e8436fc0,65536,152368,19589216,12076630787462896,12076630787632665,12076630787931705,12076630787978586
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,936496,936501,4194304,256,0,0,24,24,196800,0x7f18f4030600,0x7f17e8437000,131072,223520,28545808,12076630788015083,12076630788183704,12076630788338744,12076630788342282
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,936496,936501,4194304,256,0,0,24,24,201088,0x7f18f4030500,0x7f17e8437040,131072,225832,29001952,12076630788397264,12076630788558423,12076630788944342,12076630788965792
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,936496,936501,4194304,256,0,0,24,24,204608,0x7f18f4030400,0x7f17e8437080,131072,224964,28784144,12076630789036884,12076630789204501,12076630789380341,12076630789383810
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,936496,936501,4194304,256,0,0,20,24,206080,0x7f18f4030300,0x7f17e84370c0,131072,228980,29111080,12076630789433773,12076630789606100,12076630790217298,12076630790265530
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,936496,936501,4194304,256,0,0,28,24,209600,0x7f18f4030a00,0x7f17e8437100,65536,145750,18715544,12076630790299653,12076630790473458,12076630790800497,12076630790847332
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,936496,936501,4194304,256,0,0,24,24,213120,0x7f18f4030900,0x7f17e8437140,131072,244068,31342136,12076630790884271,12076630791056656,12076630791234896,12076630791238570
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,936496,936501,4194304,256,0,0,24,24,218176,0x7f18f4030800,0x7f17e8437180,131072,246312,31211640,12076630791291749,12076630791455535,12076630791912014,12076630791958108
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,936496,936501,4194304,256,0,0,24,24,222208,0x7f18f4030700,0x7f17e84371c0,131072,228350,29181552,12076630791998343,12076630792167213,12076630792367053,12076630792414186
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,936496,936501,4194304,256,0,0,20,24,223936,0x7f18f4030600,0x7f17e8437200,131072,221566,28882232,12076630792444613,12076630792615212,12076630793319530,12076630793367139
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,936496,936501,4194304,256,0,0,28,24,227968,0x7f18f4030500,0x7f17e8437240,65536,147556,18861440,12076630793390973,12076630793577609,12076630793977288,12076630794025494
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,936496,936501,4194304,256,0,0,24,24,232000,0x7f18f4030400,0x7f17e8437280,131072,226096,28999416,12076630794057984,12076630794237608,12076630794440007,12076630794487543
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,936496,936501,4194304,256,0,0,24,24,237824,0x7f18f4030300,0x7f17e84372c0,131072,243370,30875000,12076630794513702,12076630794688486,12076630795215365,12076630795261944
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,936496,936501,4194304,256,0,0,24,24,242368,0x7f18f4030a00,0x7f17e8437300,131072,232722,29537392,12076630795298512,12076630795460804,12076630795684804,12076630795732198
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,936496,936501,4194304,256,0,0,20,24,243584,0x7f18f4030900,0x7f17e8437340,131072,226182,29068344,12076630795757796,12076630795931043,12076630796730401,12076630796781650
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,936496,936501,4194304,256,0,0,28,24,248128,0x7f18f4030800,0x7f17e8437380,65536,152344,19488520,12076630796807899,12076630796985920,12076630797407199,12076630797455855
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,936496,936501,4194304,256,0,0,24,24,252672,0x7f18f4030700,0x7f17e84373c0,131072,228182,29192104,12076630797479599,12076630797659678,12076630797888158,12076630797935176
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,936496,936501,4194304,256,0,0,24,24,259264,0x7f18f4030600,0x7f17e8437400,131072,225926,28971024,12076630797961756,12076630798140477,12076630798737755,12076630798785869
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,936496,936501,4194304,256,0,0,24,24,264832,0x7f18f4030500,0x7f17e8437440,131072,224962,28784784,12076630798826785,12076630798988955,12076630799258554,12076630799308010
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,936496,936501,4194304,256,0,0,20,24,266304,0x7f18f4030400,0x7f17e8437480,131072,230724,29303736,12076630799331574,12076630799516793,12076630800502071,12076630800568915
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,936496,936501,4194304,256,0,0,28,24,271872,0x7f18f4030300,0x7f17e84374c0,65536,147582,18854272,12076630800600514,12076630800779030,12076630801311988,12076630801378822
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,936496,936501,4194304,256,0,0,24,24,277440,0x7f18f4030a00,0x7f17e8437500,131072,226488,29189608,12076630801406563,12076630801587508,12076630801858547,12076630801924547
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,936496,936501,4194304,256,0,0,12,24,279936,0x7f18f4030900,0x7f17e8437540,131072,218074,27634208,12076630801950315,12076630802135506,12076630802874544,12076630802942130
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,936496,936501,4194304,256,0,0,24,24,286528,0x7f18f4030800,0x7f17e8437580,131072,219106,28138184,12076630802981232,12076630803157743,12076630803474063,12076630803541054
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,936496,936501,4194304,256,0,0,20,24,288000,0x7f18f4030700,0x7f17e84375c0,131072,224538,28854304,12076630803564638,12076630803745902,12076630804917579,12076630804987584
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,936496,936501,4194304,256,0,0,32,24,294592,0x7f18f4030600,0x7f17e8437600,65536,147524,18774424,12076630805023241,12076630805205738,12076630805815336,12076630805883811
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,936496,936501,4194304,256,0,0,24,24,301184,0x7f18f4030500,0x7f17e8437640,131072,226012,28842272,12076630805911944,12076630806097255,12076630806416295,12076630806484218
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,936496,936501,4194304,256,0,0,12,24,304960,0x7f18f4030400,0x7f17e8437680,131072,225610,29069248,12076630806512471,12076630806686534,12076630807565251,12076630807631983
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,936496,936501,4194304,256,0,0,24,24,313600,0x7f18f4030300,0x7f17e84376c0,131072,254558,32850600,12076630807668531,12076630807834691,12076630808246850,12076630808315845
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,936496,936501,4194304,256,0,0,20,24,314816,0x7f18f4030a00,0x7f17e8437700,131072,226646,29183472,12076630808347384,12076630808528769,12076630810076445,12076630810144407
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,936496,936501,4194304,256,0,0,20,24,317568,0x7f18f4030900,0x7f17e8437740,65536,146264,18739032,12076630810174753,12076630810354844,12076630811149882,12076630811216802
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,936496,936501,4194304,256,0,0,12,24,320320,0x7f18f4030800,0x7f17e8437780,131072,262206,33522600,12076630811243782,12076630811427481,12076630811842520,12076630811908639
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,936496,936501,4194304,256,0,0,12,24,324096,0x7f18f4030700,0x7f17e84377c0,131072,225932,28775136,12076630811933695,12076630812121879,12076630813280116,12076630813348357
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,936496,936501,4194304,256,0,0,12,24,328896,0x7f18f4030600,0x7f17e8437800,131072,212086,27305448,12076630813389683,12076630813549235,12076630814334513,12076630814401756
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,936496,936501,4194304,256,0,0,20,24,330112,0x7f18f4030500,0x7f17e8437840,131072,278198,35698600,12076630814433465,12076630814610672,12076630817661224,12076630817728875
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,936496,936501,4194304,256,0,0,20,24,332864,0x7f18f4030400,0x7f17e8437880,65536,147728,18993832,12076630817759983,12076630817929703,12076630819470179,12076630819538611
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,936496,936501,4194304,256,0,0,12,24,335616,0x7f18f4030300,0x7f17e84378c0,131072,230624,29452312,12076630819562395,12076630819751778,12076630820541376,12076630820609142
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,936496,936501,4194304,256,0,0,12,24,339392,0x7f18f4030a00,0x7f17e8437900,131072,225176,29231608,12076630820639719,12076630820825856,12076630823106489,12076630823175005
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,936496,936501,4194304,256,0,0,12,24,344192,0x7f18f4030900,0x7f17e8437940,131072,226042,28801544,12076630823218656,12076630823383449,12076630824918164,12076630824984611
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,936496,936501,4194304,256,0,0,20,24,345408,0x7f18f4030800,0x7f17e8437980,131072,229440,29399096,12076630825019356,12076630825203444,12076630831257027,12076630831327209
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,936496,936501,4194304,256,0,0,20,24,348160,0x7f18f4030700,0x7f17e84379c0,65536,153238,19696104,12076630831358758,12076630831539747,12076630834579258,12076630834649489
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,936496,936501,4194304,256,0,0,12,24,350912,0x7f18f4030600,0x7f17e8437a00,131072,223628,28401128,12076630834684204,12076630834850618,12076630836389973,12076630836458544
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,936496,936501,4194304,256,0,0,12,24,0,0x7f18f4030500,0x7f17e8437a40,131072,225772,28788384,12076630836488380,12076630836670613,12076630841197640,12076630841270295
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 936496 936501 33554432 256 0 0 8 32 6464 0x0 0x7f17e8404180 4194304 3122666 398904176 12076630480743351 12076630718390515 12076630718714354 12076630718822006
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 936496 936501 32768 256 0 0 24 24 12480 0x0 0x7f17e8435100 512 21524 2754256 12076630733442442 12076630733749898 12076630733756458 12076630733761836
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 4 936496 936501 4194304 256 0 0 24 24 12928 0x7f18f4030900 0x7f17e8435140 65536 146806 18775720 12076630733826656 12076630734045577 12076630734179017 12076630734183330
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 936496 936501 4194304 256 0 0 36 24 13632 0x7f18f4030800 0x7f17e8435180 65536 166800 21363552 12076630734250836 12076630734424456 12076630734676455 12076630734744404
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 8 936496 936501 4194304 256 0 0 28 24 14080 0x7f18f4030700 0x7f17e84351c0 65536 145312 18687568 12076630734769059 12076630734956294 12076630735209893 12076630735278627
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 10 936496 936501 4194304 256 0 0 24 24 14528 0x7f18f4030600 0x7f17e8435200 65536 150966 19402760 12076630735302752 12076630735488292 12076630735621092 12076630735624911
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 12 936496 936501 4194304 256 0 0 24 24 14976 0x7f18f4030500 0x7f17e8435240 65536 143290 18432448 12076630735674393 12076630735852771 12076630735986530 12076630735990331
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 14 936496 936501 4194304 256 0 0 24 24 15424 0x7f18f4030400 0x7f17e8435280 131072 227390 29160816 12076630736069599 12076630736239969 12076630736372449 12076630736376349
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 936496 936501 4194304 256 0 0 28 24 16128 0x7f18f4030300 0x7f17e84352c0 131072 189048 24236312 12076630736425691 12076630736594848 12076630736859327 12076630736901155
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 18 936496 936501 4194304 256 0 0 28 24 16832 0x7f18f4030a00 0x7f17e8435300 65536 148268 19040936 12076630736924379 12076630737129406 12076630737382525 12076630737423557
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 20 936496 936501 4194304 256 0 0 24 24 17536 0x7f18f4030900 0x7f17e8435340 131072 225494 28835256 12076630737447872 12076630737636284 12076630737769244 12076630737772967
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 22 936496 936501 4194304 256 0 0 24 24 18240 0x7f18f4030800 0x7f17e8435380 131072 224970 28826816 12076630737822008 12076630737987003 12076630738122203 12076630738126284
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 24 936496 936501 4194304 256 0 0 24 24 18944 0x7f18f4030700 0x7f17e84353c0 131072 226920 29124800 12076630738189021 12076630738358362 12076630738491961 12076630738495431
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 936496 936501 4194304 256 0 0 28 24 19904 0x7f18f4030600 0x7f17e8435400 131072 188884 24133824 12076630738544602 12076630738707800 12076630738967000 12076630739033422
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 28 936496 936501 4194304 256 0 0 28 24 20608 0x7f18f4030500 0x7f17e8435440 65536 145354 18673600 12076630739060312 12076630739245559 12076630739502998 12076630739569298
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 30 936496 936501 4194304 256 0 0 24 24 21312 0x7f18f4030400 0x7f17e8435480 131072 225206 28872752 12076630739595898 12076630739772117 12076630739904916 12076630739908349
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 32 936496 936501 4194304 256 0 0 24 24 22016 0x7f18f4030300 0x7f17e84354c0 131072 219560 28258888 12076630739957340 12076630740132275 12076630740260595 12076630740264552
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 34 936496 936501 4194304 256 0 0 24 24 22720 0x7f18f4030a00 0x7f17e8435500 131072 264056 33825168 12076630740326287 12076630740491314 12076630740667473 12076630740671338
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 936496 936501 4194304 256 0 0 28 24 23680 0x7f18f4030900 0x7f17e8435540 131072 180248 23012800 12076630740719638 12076630740889393 12076630741144752 12076630741211082
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 38 936496 936501 4194304 256 0 0 28 24 24384 0x7f18f4030800 0x7f17e8435580 65536 152108 19358000 12076630741236900 12076630741422351 12076630741680270 12076630741747320
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 40 936496 936501 4194304 256 0 0 24 24 25088 0x7f18f4030700 0x7f17e84355c0 131072 240572 30745160 12076630741770152 12076630741952429 12076630742085388 12076630742089256
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 42 936496 936501 4194304 256 0 0 24 24 25792 0x7f18f4030600 0x7f17e8435600 131072 227926 29102264 12076630742137025 12076630742315147 12076630742445387 12076630742449195
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 44 936496 936501 4194304 256 0 0 24 24 26496 0x7f18f4030500 0x7f17e8435640 131072 238044 30586152 12076630742511051 12076630742675146 12076630742808906 12076630742812662
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 936496 936501 4194304 256 0 0 28 24 27712 0x7f18f4030400 0x7f17e8435680 131072 214086 27454552 12076630742860410 12076630743039145 12076630743299624 12076630743365810
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 48 936496 936501 4194304 256 0 0 28 24 28416 0x7f18f4030300 0x7f17e84356c0 65536 151892 19296600 12076630743392941 12076630743572743 12076630743826662 12076630743893562
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 50 936496 936501 4194304 256 0 0 24 24 29120 0x7f18f4030a00 0x7f17e8435700 131072 227084 29063024 12076630743916916 12076630744096741 12076630744229700 12076630744233504
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 52 936496 936501 4194304 256 0 0 24 24 30080 0x7f18f4030900 0x7f17e8435740 131072 229102 29379856 12076630744284449 12076630744448740 12076630744578819 12076630744582634
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 54 936496 936501 4194304 256 0 0 24 24 30784 0x7f18f4030800 0x7f17e8435780 131072 223660 28589792 12076630744643166 12076630744804258 12076630744933858 12076630744937734
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 936496 936501 4194304 256 0 0 28 24 32000 0x7f18f4030700 0x7f17e84357c0 131072 188756 24135584 12076630744985393 12076630745172737 12076630745435136 12076630745501092
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 58 936496 936501 4194304 256 0 0 28 24 32960 0x7f18f4030600 0x7f17e8435800 65536 149072 19052288 12076630745525418 12076630745703935 12076630745960734 12076630746027231
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 60 936496 936501 4194304 256 0 0 24 24 33920 0x7f18f4030500 0x7f17e8435840 131072 221292 28294208 12076630746054892 12076630746232413 12076630746368733 12076630746372603
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 62 936496 936501 4194304 256 0 0 24 24 34880 0x7f18f4030400 0x7f17e8435880 131072 224710 28664736 12076630746420783 12076630746583132 12076630746718331 12076630746721993
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 64 936496 936501 4194304 256 0 0 24 24 35840 0x7f18f4030300 0x7f17e84358c0 131072 221994 28400584 12076630746783147 12076630746946171 12076630747076730 12076630747081081
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 936496 936501 4194304 256 0 0 28 24 37312 0x7f18f4030a00 0x7f17e8435900 131072 217500 27821104 12076630747129852 12076630747303289 12076630747563928 12076630747631135
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 68 936496 936501 4194304 256 0 0 28 24 38272 0x7f18f4030900 0x7f17e8435940 65536 145802 18533032 12076630747657163 12076630747834007 12076630748087127 12076630748154638
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 70 936496 936501 4194304 256 0 0 24 24 39232 0x7f18f4030800 0x7f17e8435980 131072 227466 29112696 12076630748178493 12076630748364246 12076630748501205 12076630748504940
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 72 936496 936501 4194304 256 0 0 24 24 40192 0x7f18f4030700 0x7f17e84359c0 131072 228766 29163784 12076630748553921 12076630748717684 12076630748854324 12076630748858297
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 74 936496 936501 4194304 256 0 0 24 24 41152 0x7f18f4030600 0x7f17e8435a00 131072 217996 27926896 12076630748919220 12076630749086643 12076630749218962 12076630749222755
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 936496 936501 4194304 256 0 0 28 24 42624 0x7f18f4030500 0x7f17e8435a40 131072 183100 23413936 12076630749271796 12076630749443922 12076630749703761 12076630749770233
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 78 936496 936501 4194304 256 0 0 28 24 43584 0x7f18f4030400 0x7f17e8435a80 65536 152676 19429816 12076630749794378 12076630749972560 12076630750232559 12076630750330926
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 80 936496 936501 4194304 256 0 0 24 24 44544 0x7f18f4030300 0x7f17e8435ac0 131072 223680 28697848 12076630750354861 12076630750548078 12076630750684717 12076630750688662
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 82 936496 936501 4194304 256 0 0 24 24 45760 0x7f18f4030a00 0x7f17e8435b00 131072 226080 29158928 12076630750736942 12076630750906636 12076630751043756 12076630751048231
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 84 936496 936501 4194304 256 0 0 24 24 46720 0x7f18f4030900 0x7f17e8435b40 131072 225830 28997752 12076630751108353 12076630751277195 12076630751411114 12076630751415093
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 936496 936501 4194304 256 0 0 28 24 48448 0x7f18f4030800 0x7f17e8435b80 131072 180756 23135336 12076630751465056 12076630751622794 12076630751892553 12076630751963002
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 88 936496 936501 4194304 256 0 0 28 24 49408 0x7f18f4030700 0x7f17e8435bc0 65536 149440 19114736 12076630751989592 12076630752170152 12076630752426471 12076630752493219
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 90 936496 936501 4194304 256 0 0 24 24 50368 0x7f18f4030600 0x7f17e8435c00 131072 262266 33623728 12076630752519848 12076630752699110 12076630752828069 12076630752832029
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 92 936496 936501 4194304 256 0 0 24 24 51584 0x7f18f4030500 0x7f17e8435c40 131072 227186 29060408 12076630752881821 12076630753052069 12076630753188388 12076630753191978
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 94 936496 936501 4194304 256 0 0 24 24 52544 0x7f18f4030400 0x7f17e8435c80 131072 230542 29470864 12076630753253212 12076630753416867 12076630753551107 12076630753554743
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 936496 936501 4194304 256 0 0 28 24 54272 0x7f18f4030300 0x7f17e8435cc0 131072 177778 22873048 12076630753602021 12076630753773186 12076630754037505 12076630754103965
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 98 936496 936501 4194304 256 0 0 28 24 55488 0x7f18f4030a00 0x7f17e8435d00 65536 173192 22154512 12076630754130945 12076630754309184 12076630754565183 12076630754631786
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 100 936496 936501 4194304 256 0 0 24 24 56704 0x7f18f4030900 0x7f17e8435d40 131072 227532 29252136 12076630754654709 12076630754831742 12076630754965662 12076630754969194
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 102 936496 936501 4194304 256 0 0 24 24 58176 0x7f18f4030800 0x7f17e8435d80 131072 229234 29409264 12076630755019708 12076630755193341 12076630755334460 12076630755338551
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 104 936496 936501 4194304 256 0 0 24 24 59392 0x7f18f4030700 0x7f17e8435dc0 131072 228260 29183648 12076630755399925 12076630755561499 12076630755699419 12076630755703179
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 936496 936501 4194304 256 0 0 28 24 61376 0x7f18f4030600 0x7f17e8435e00 131072 225254 28764944 12076630755751660 12076630755919578 12076630756178297 12076630756245338
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 108 936496 936501 4194304 256 0 0 28 24 62592 0x7f18f4030500 0x7f17e8435e40 65536 149242 19063064 12076630756272358 12076630756448696 12076630756708375 12076630756774753
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 110 936496 936501 4194304 256 0 0 24 24 63808 0x7f18f4030400 0x7f17e8435e80 131072 227156 29014288 12076630756799128 12076630756979894 12076630757113814 12076630757118462
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 112 936496 936501 4194304 256 0 0 24 24 65280 0x7f18f4030300 0x7f17e8435ec0 131072 227782 28907472 12076630757168094 12076630757331253 12076630757470293 12076630757474214
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 114 936496 936501 4194304 256 0 0 24 24 66496 0x7f18f4030a00 0x7f17e8435f00 131072 227102 29022864 12076630757534035 12076630757693812 12076630757829171 12076630757832911
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 936496 936501 4194304 256 0 0 28 24 68480 0x7f18f4030900 0x7f17e8435f40 131072 227088 29089344 12076630757880630 12076630758053810 12076630758311250 12076630758378676
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 118 936496 936501 4194304 256 0 0 28 24 69696 0x7f18f4030800 0x7f17e8435f80 65536 147704 18861032 12076630758405416 12076630758579409 12076630758833328 12076630758899234
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 120 936496 936501 4194304 256 0 0 24 24 70912 0x7f18f4030700 0x7f17e8435fc0 131072 225116 28894504 12076630758925974 12076630759114927 12076630759247406 12076630759251199
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 122 936496 936501 4194304 256 0 0 24 24 72384 0x7f18f4030600 0x7f17e8436000 131072 226356 28938968 12076630759300401 12076630759463085 12076630759602125 12076630759606019
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 124 936496 936501 4194304 256 0 0 24 24 73600 0x7f18f4030500 0x7f17e8436040 131072 225464 28891992 12076630759666862 12076630759827084 12076630759958124 12076630759961801
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 936496 936501 4194304 256 0 0 28 24 75840 0x7f18f4030400 0x7f17e8436080 131072 176088 22573592 12076630760013808 12076630760177483 12076630760446122 12076630760512545
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 128 936496 936501 4194304 256 0 0 28 24 77056 0x7f18f4030300 0x7f17e84360c0 65536 146200 18638136 12076630760536089 12076630760720041 12076630760976040 12076630761018497
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 130 936496 936501 4194304 256 0 0 24 24 78272 0x7f18f4030a00 0x7f17e8436100 131072 264440 33553728 12076630761040888 12076630761222279 12076630761352679 12076630761356676
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 132 936496 936501 4194304 256 0 0 24 24 80000 0x7f18f4030900 0x7f17e8436140 131072 197214 25313256 12076630761405857 12076630761574598 12076630761721477 12076630761725392
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 134 936496 936501 4194304 256 0 0 24 24 81216 0x7f18f4030800 0x7f17e8436180 131072 225482 28825616 12076630761785584 12076630761943076 12076630762078116 12076630762082105
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 936496 936501 4194304 256 0 0 28 24 83456 0x7f18f4030700 0x7f17e84361c0 131072 180478 23151528 12076630762129794 12076630762300995 12076630762570114 12076630762591432
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 138 936496 936501 4194304 256 0 0 28 24 84928 0x7f18f4030600 0x7f17e8436200 65536 180078 23066240 12076630762634322 12076630762792833 12076630763090272 12076630763113874
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 140 936496 936501 4194304 256 0 0 24 24 86400 0x7f18f4030500 0x7f17e8436240 131072 233184 29574320 12076630763158197 12076630763319871 12076630763454111 12076630763458125
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 142 936496 936501 4194304 256 0 0 24 24 88128 0x7f18f4030400 0x7f17e8436280 131072 199190 25603288 12076630763506124 12076630763673150 12076630763825150 12076630763829095
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 144 936496 936501 4194304 256 0 0 24 24 89600 0x7f18f4030300 0x7f17e84362c0 131072 230656 29615904 12076630763911097 12076630764071869 12076630764206108 12076630764210123
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 936496 936501 4194304 256 0 0 28 24 92096 0x7f18f4030a00 0x7f17e8436300 131072 183604 23426328 12076630764258634 12076630764426907 12076630764697786 12076630764722096
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 148 936496 936501 4194304 256 0 0 28 24 93568 0x7f18f4030900 0x7f17e8436340 65536 144156 18434176 12076630764763383 12076630764925306 12076630765180345 12076630765204984
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 150 936496 936501 4194304 256 0 0 24 24 95040 0x7f18f4030800 0x7f17e8436380 131072 218512 27909952 12076630765247433 12076630765408344 12076630765542263 12076630765545828
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 152 936496 936501 4194304 256 0 0 24 24 96768 0x7f18f4030700 0x7f17e84363c0 131072 230722 29479352 12076630765596031 12076630765765623 12076630765923542 12076630765927498
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 154 936496 936501 4194304 256 0 0 24 24 98240 0x7f18f4030600 0x7f17e8436400 131072 223186 28522608 12076630765987219 12076630766158581 12076630766292341 12076630766296665
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 936496 936501 4194304 256 0 0 28 24 100736 0x7f18f4030500 0x7f17e8436440 131072 182648 23339480 12076630766345836 12076630766516660 12076630766781619 12076630766829576
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 158 936496 936501 4194304 256 0 0 28 24 102208 0x7f18f4030400 0x7f17e8436480 65536 186902 23869552 12076630766854182 12076630767035538 12076630767288177 12076630767338382
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 160 936496 936501 4194304 256 0 0 24 24 103680 0x7f18f4030300 0x7f17e84364c0 131072 228500 29147816 12076630767365653 12076630767540816 12076630767675696 12076630767679337
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 162 936496 936501 4194304 256 0 0 24 24 105664 0x7f18f4030a00 0x7f17e8436500 131072 218106 27972760 12076630767728779 12076630767895695 12076630768061934 12076630768065795
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 164 936496 936501 4194304 256 0 0 24 24 107136 0x7f18f4030900 0x7f17e8436540 131072 225908 28729320 12076630768128412 12076630768290893 12076630768421293 12076630768425354
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 936496 936501 4194304 256 0 0 28 24 109888 0x7f18f4030800 0x7f17e8436580 131072 180044 23043184 12076630768473734 12076630768640652 12076630768907051 12076630768931195
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 168 936496 936501 4194304 256 0 0 28 24 111360 0x7f18f4030700 0x7f17e84365c0 65536 151132 19419864 12076630768976980 12076630769161450 12076630769421129 12076630769468905
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 170 936496 936501 4194304 256 0 0 24 24 112832 0x7f18f4030600 0x7f17e8436600 131072 265290 33842312 12076630769492760 12076630769670568 12076630769807848 12076630769811863
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 172 936496 936501 4194304 256 0 0 24 24 114816 0x7f18f4030500 0x7f17e8436640 131072 223124 28752200 12076630769861646 12076630770031207 12076630770204486 12076630770208471
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 174 936496 936501 4194304 256 0 0 24 24 116288 0x7f18f4030400 0x7f17e8436680 131072 225756 29003960 12076630770269695 12076630770430726 12076630770562085 12076630770566086
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 936496 936501 4194304 256 0 0 28 24 119040 0x7f18f4030300 0x7f17e84366c0 131072 178990 22852184 12076630770615679 12076630770777604 12076630771042723 12076630771091424
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 178 936496 936501 4194304 256 0 0 28 24 120768 0x7f18f4030a00 0x7f17e8436700 65536 144814 18524880 12076630771118253 12076630771294723 12076630771554082 12076630771600681
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 180 936496 936501 4194304 256 0 0 24 24 122496 0x7f18f4030900 0x7f17e8436740 131072 227744 29192792 12076630771625737 12076630771805761 12076630771941440 12076630771945592
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 182 936496 936501 4194304 256 0 0 24 24 124736 0x7f18f4030800 0x7f17e8436780 131072 227082 28994272 12076630771994333 12076630772168479 12076630772350719 12076630772354974
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 184 936496 936501 4194304 256 0 0 24 24 126464 0x7f18f4030700 0x7f17e84367c0 131072 226390 29055120 12076630772416588 12076630772579518 12076630772720317 12076630772723990
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 936496 936501 4194304 256 0 0 20 24 127936 0x7f18f4030600 0x7f17e8436800 131072 223916 28593808 12076630772770507 12076630772936157 12076630773203356 12076630773250399
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 188 936496 936501 4194304 256 0 0 28 24 129664 0x7f18f4030500 0x7f17e8436840 65536 151472 19400720 12076630773273172 12076630773451355 12076630773710074 12076630773756300
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 190 936496 936501 4194304 256 0 0 24 24 131392 0x7f18f4030400 0x7f17e8436880 131072 257456 32738176 12076630773781838 12076630773955353 12076630774097592 12076630774101833
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 192 936496 936501 4194304 256 0 0 24 24 133632 0x7f18f4030300 0x7f17e84368c0 131072 235504 29915176 12076630774150303 12076630774322232 12076630774513271 12076630774561378
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 194 936496 936501 4194304 256 0 0 24 24 135360 0x7f18f4030a00 0x7f17e8436900 131072 256744 32770632 12076630774598196 12076630774758870 12076630774899349 12076630774903304
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 936496 936501 4194304 256 0 0 20 24 136832 0x7f18f4030900 0x7f17e8436940 131072 221814 28524864 12076630774952726 12076630775123669 12076630775406548 12076630775455772
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 198 936496 936501 4194304 256 0 0 28 24 138560 0x7f18f4030800 0x7f17e8436980 65536 153198 19621168 12076630775479025 12076630775659987 12076630775917906 12076630775964748
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 200 936496 936501 4194304 256 0 0 24 24 140288 0x7f18f4030700 0x7f17e84369c0 131072 246534 31503272 12076630775991037 12076630776179345 12076630776313584 12076630776317915
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 202 936496 936501 4194304 256 0 0 24 24 142784 0x7f18f4030600 0x7f17e8436a00 131072 219418 28232720 12076630776366896 12076630776538224 12076630776749583 12076630776771990
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 204 936496 936501 4194304 256 0 0 24 24 144768 0x7f18f4030500 0x7f17e8436a40 131072 220666 28206928 12076630776825820 12076630776987982 12076630777126861 12076630777130848
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 936496 936501 4194304 256 0 0 20 24 145728 0x7f18f4030400 0x7f17e8436a80 131072 220914 28364160 12076630777180931 12076630777346221 12076630777653419 12076630777700587
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 208 936496 936501 4194304 256 0 0 28 24 147712 0x7f18f4030300 0x7f17e8436ac0 65536 144544 18398472 12076630777724111 12076630777900779 12076630778160938 12076630778209855
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 210 936496 936501 4194304 256 0 0 24 24 149696 0x7f18f4030a00 0x7f17e8436b00 131072 215842 27686136 12076630778236775 12076630778412617 12076630778548296 12076630778552051
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 212 936496 936501 4194304 256 0 0 24 24 152192 0x7f18f4030900 0x7f17e8436b40 131072 225646 29102320 12076630778600181 12076630778766375 12076630778994215 12076630779043365
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 214 936496 936501 4194304 256 0 0 24 24 154176 0x7f18f4030800 0x7f17e8436b80 131072 228722 29085824 12076630779077990 12076630779247174 12076630779383173 12076630779387625
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 936496 936501 4194304 256 0 0 20 24 155648 0x7f18f4030700 0x7f17e8436bc0 131072 225666 28944104 12076630779437468 12076630779610212 12076630779939331 12076630779987521
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 218 936496 936501 4194304 256 0 0 28 24 157632 0x7f18f4030600 0x7f17e8436c00 65536 143190 18288432 12076630780015714 12076630780195010 12076630780457889 12076630780506937
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 220 936496 936501 4194304 256 0 0 24 24 159616 0x7f18f4030500 0x7f17e8436c40 131072 228308 29263736 12076630780533056 12076630780712928 12076630780848608 12076630780852781
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 222 936496 936501 4194304 256 0 0 24 24 162368 0x7f18f4030400 0x7f17e8436c80 131072 229866 29433672 12076630780901071 12076630781073567 12076630781318366 12076630781368059
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 224 936496 936501 4194304 256 0 0 24 24 164608 0x7f18f4030300 0x7f17e8436cc0 131072 223206 28804256 12076630781410769 12076630781575563 12076630781712523 12076630781719633
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 936496 936501 4194304 256 0 0 20 24 166336 0x7f18f4030a00 0x7f17e8436d00 131072 228840 29255776 12076630781762894 12076630781931561 12076630782308040 12076630782355576
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 228 936496 936501 4194304 256 0 0 28 24 168576 0x7f18f4030900 0x7f17e8436d40 65536 149238 18983736 12076630782381955 12076630782559879 12076630782825799 12076630782872948
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 230 936496 936501 4194304 256 0 0 24 24 170816 0x7f18f4030800 0x7f17e8436d80 131072 230536 29506024 12076630782898456 12076630783077478 12076630783220037 12076630783223300
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 232 936496 936501 4194304 256 0 0 24 24 174080 0x7f18f4030700 0x7f17e8436dc0 131072 229452 29219960 12076630783272983 12076630783446917 12076630783756196 12076630783801987
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 234 936496 936501 4194304 256 0 0 24 24 176576 0x7f18f4030600 0x7f17e8436e00 131072 230522 29545328 12076630783837322 12076630784001795 12076630784141955 12076630784145506
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 936496 936501 4194304 256 0 0 20 24 177792 0x7f18f4030500 0x7f17e8436e40 131072 209118 26916032 12076630784193916 12076630784367074 12076630784792513 12076630784840148
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 238 936496 936501 4194304 256 0 0 28 24 180288 0x7f18f4030400 0x7f17e8436e80 65536 154162 19781176 12076630784863591 12076630785052512 12076630785316192 12076630785364583
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 240 936496 936501 4194304 256 0 0 24 24 182784 0x7f18f4030300 0x7f17e8436ec0 131072 225288 28626392 12076630785392425 12076630785568191 12076630785707071 12076630785710817
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 242 936496 936501 4194304 256 0 0 24 24 186304 0x7f18f4030a00 0x7f17e8436f00 131072 225312 28824128 12076630785759147 12076630785925150 12076630786240509 12076630786288993
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 244 936496 936501 4194304 256 0 0 24 24 189312 0x7f18f4030900 0x7f17e8436f40 131072 227616 28908840 12076630786330530 12076630786491709 12076630786644188 12076630786647249
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 936496 936501 4194304 256 0 0 20 24 190784 0x7f18f4030800 0x7f17e8436f80 131072 225682 28777744 12076630786695389 12076630786863228 12076630787380186 12076630787429053
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 248 936496 936501 4194304 256 0 0 28 24 193792 0x7f18f4030700 0x7f17e8436fc0 65536 152368 19589216 12076630787462896 12076630787632665 12076630787931705 12076630787978586
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 250 936496 936501 4194304 256 0 0 24 24 196800 0x7f18f4030600 0x7f17e8437000 131072 223520 28545808 12076630788015083 12076630788183704 12076630788338744 12076630788342282
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 252 936496 936501 4194304 256 0 0 24 24 201088 0x7f18f4030500 0x7f17e8437040 131072 225832 29001952 12076630788397264 12076630788558423 12076630788944342 12076630788965792
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 254 936496 936501 4194304 256 0 0 24 24 204608 0x7f18f4030400 0x7f17e8437080 131072 224964 28784144 12076630789036884 12076630789204501 12076630789380341 12076630789383810
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 936496 936501 4194304 256 0 0 20 24 206080 0x7f18f4030300 0x7f17e84370c0 131072 228980 29111080 12076630789433773 12076630789606100 12076630790217298 12076630790265530
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 258 936496 936501 4194304 256 0 0 28 24 209600 0x7f18f4030a00 0x7f17e8437100 65536 145750 18715544 12076630790299653 12076630790473458 12076630790800497 12076630790847332
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 260 936496 936501 4194304 256 0 0 24 24 213120 0x7f18f4030900 0x7f17e8437140 131072 244068 31342136 12076630790884271 12076630791056656 12076630791234896 12076630791238570
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 262 936496 936501 4194304 256 0 0 24 24 218176 0x7f18f4030800 0x7f17e8437180 131072 246312 31211640 12076630791291749 12076630791455535 12076630791912014 12076630791958108
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 264 936496 936501 4194304 256 0 0 24 24 222208 0x7f18f4030700 0x7f17e84371c0 131072 228350 29181552 12076630791998343 12076630792167213 12076630792367053 12076630792414186
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 936496 936501 4194304 256 0 0 20 24 223936 0x7f18f4030600 0x7f17e8437200 131072 221566 28882232 12076630792444613 12076630792615212 12076630793319530 12076630793367139
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 268 936496 936501 4194304 256 0 0 28 24 227968 0x7f18f4030500 0x7f17e8437240 65536 147556 18861440 12076630793390973 12076630793577609 12076630793977288 12076630794025494
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 270 936496 936501 4194304 256 0 0 24 24 232000 0x7f18f4030400 0x7f17e8437280 131072 226096 28999416 12076630794057984 12076630794237608 12076630794440007 12076630794487543
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 272 936496 936501 4194304 256 0 0 24 24 237824 0x7f18f4030300 0x7f17e84372c0 131072 243370 30875000 12076630794513702 12076630794688486 12076630795215365 12076630795261944
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 274 936496 936501 4194304 256 0 0 24 24 242368 0x7f18f4030a00 0x7f17e8437300 131072 232722 29537392 12076630795298512 12076630795460804 12076630795684804 12076630795732198
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 936496 936501 4194304 256 0 0 20 24 243584 0x7f18f4030900 0x7f17e8437340 131072 226182 29068344 12076630795757796 12076630795931043 12076630796730401 12076630796781650
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 278 936496 936501 4194304 256 0 0 28 24 248128 0x7f18f4030800 0x7f17e8437380 65536 152344 19488520 12076630796807899 12076630796985920 12076630797407199 12076630797455855
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 280 936496 936501 4194304 256 0 0 24 24 252672 0x7f18f4030700 0x7f17e84373c0 131072 228182 29192104 12076630797479599 12076630797659678 12076630797888158 12076630797935176
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 282 936496 936501 4194304 256 0 0 24 24 259264 0x7f18f4030600 0x7f17e8437400 131072 225926 28971024 12076630797961756 12076630798140477 12076630798737755 12076630798785869
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 284 936496 936501 4194304 256 0 0 24 24 264832 0x7f18f4030500 0x7f17e8437440 131072 224962 28784784 12076630798826785 12076630798988955 12076630799258554 12076630799308010
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 936496 936501 4194304 256 0 0 20 24 266304 0x7f18f4030400 0x7f17e8437480 131072 230724 29303736 12076630799331574 12076630799516793 12076630800502071 12076630800568915
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 288 936496 936501 4194304 256 0 0 28 24 271872 0x7f18f4030300 0x7f17e84374c0 65536 147582 18854272 12076630800600514 12076630800779030 12076630801311988 12076630801378822
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 290 936496 936501 4194304 256 0 0 24 24 277440 0x7f18f4030a00 0x7f17e8437500 131072 226488 29189608 12076630801406563 12076630801587508 12076630801858547 12076630801924547
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 292 936496 936501 4194304 256 0 0 12 24 279936 0x7f18f4030900 0x7f17e8437540 131072 218074 27634208 12076630801950315 12076630802135506 12076630802874544 12076630802942130
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 294 936496 936501 4194304 256 0 0 24 24 286528 0x7f18f4030800 0x7f17e8437580 131072 219106 28138184 12076630802981232 12076630803157743 12076630803474063 12076630803541054
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 936496 936501 4194304 256 0 0 20 24 288000 0x7f18f4030700 0x7f17e84375c0 131072 224538 28854304 12076630803564638 12076630803745902 12076630804917579 12076630804987584
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 298 936496 936501 4194304 256 0 0 32 24 294592 0x7f18f4030600 0x7f17e8437600 65536 147524 18774424 12076630805023241 12076630805205738 12076630805815336 12076630805883811
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 300 936496 936501 4194304 256 0 0 24 24 301184 0x7f18f4030500 0x7f17e8437640 131072 226012 28842272 12076630805911944 12076630806097255 12076630806416295 12076630806484218
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 302 936496 936501 4194304 256 0 0 12 24 304960 0x7f18f4030400 0x7f17e8437680 131072 225610 29069248 12076630806512471 12076630806686534 12076630807565251 12076630807631983
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 304 936496 936501 4194304 256 0 0 24 24 313600 0x7f18f4030300 0x7f17e84376c0 131072 254558 32850600 12076630807668531 12076630807834691 12076630808246850 12076630808315845
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 936496 936501 4194304 256 0 0 20 24 314816 0x7f18f4030a00 0x7f17e8437700 131072 226646 29183472 12076630808347384 12076630808528769 12076630810076445 12076630810144407
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 308 936496 936501 4194304 256 0 0 20 24 317568 0x7f18f4030900 0x7f17e8437740 65536 146264 18739032 12076630810174753 12076630810354844 12076630811149882 12076630811216802
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 310 936496 936501 4194304 256 0 0 12 24 320320 0x7f18f4030800 0x7f17e8437780 131072 262206 33522600 12076630811243782 12076630811427481 12076630811842520 12076630811908639
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 312 936496 936501 4194304 256 0 0 12 24 324096 0x7f18f4030700 0x7f17e84377c0 131072 225932 28775136 12076630811933695 12076630812121879 12076630813280116 12076630813348357
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 314 936496 936501 4194304 256 0 0 12 24 328896 0x7f18f4030600 0x7f17e8437800 131072 212086 27305448 12076630813389683 12076630813549235 12076630814334513 12076630814401756
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 936496 936501 4194304 256 0 0 20 24 330112 0x7f18f4030500 0x7f17e8437840 131072 278198 35698600 12076630814433465 12076630814610672 12076630817661224 12076630817728875
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 318 936496 936501 4194304 256 0 0 20 24 332864 0x7f18f4030400 0x7f17e8437880 65536 147728 18993832 12076630817759983 12076630817929703 12076630819470179 12076630819538611
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 320 936496 936501 4194304 256 0 0 12 24 335616 0x7f18f4030300 0x7f17e84378c0 131072 230624 29452312 12076630819562395 12076630819751778 12076630820541376 12076630820609142
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 322 936496 936501 4194304 256 0 0 12 24 339392 0x7f18f4030a00 0x7f17e8437900 131072 225176 29231608 12076630820639719 12076630820825856 12076630823106489 12076630823175005
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 324 936496 936501 4194304 256 0 0 12 24 344192 0x7f18f4030900 0x7f17e8437940 131072 226042 28801544 12076630823218656 12076630823383449 12076630824918164 12076630824984611
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 936496 936501 4194304 256 0 0 20 24 345408 0x7f18f4030800 0x7f17e8437980 131072 229440 29399096 12076630825019356 12076630825203444 12076630831257027 12076630831327209
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 328 936496 936501 4194304 256 0 0 20 24 348160 0x7f18f4030700 0x7f17e84379c0 65536 153238 19696104 12076630831358758 12076630831539747 12076630834579258 12076630834649489
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 330 936496 936501 4194304 256 0 0 12 24 350912 0x7f18f4030600 0x7f17e8437a00 131072 223628 28401128 12076630834684204 12076630834850618 12076630836389973 12076630836458544
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 332 936496 936501 4194304 256 0 0 12 24 0 0x7f18f4030500 0x7f17e8437a40 131072 225772 28788384 12076630836488380 12076630836670613 12076630841197640 12076630841270295
@@ -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",0,0,0,936686,936691,33554432,256,0,0,8,32,6464,0x0,0x7fa3b8c04180,1048576,11096456,1419911252,12076631726864889,12076631974434106,12076631974755065,12076631974864438
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,936686,936691,32768,256,0,0,24,24,12480,0x0,0x7fa3b8c35100,4096,107784,13788356,12076631989518086,12076631989806097,12076631989812497,12076631989817693
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,936686,936691,4194304,256,0,0,24,24,12928,0x7fa4c491a900,0x7fa3b8c35140,524288,10667896,1365491840,12076631989877063,12076631990100976,12076631990238896,12076631990242964
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,936686,936691,4194304,256,0,0,36,24,13632,0x7fa4c491a800,0x7fa3b8c35180,524288,13037531,1668759720,12076631990314367,12076631990488335,12076631990742414,12076631990810750
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,936686,936691,4194304,256,0,0,28,24,14080,0x7fa4c491a700,0x7fa3b8c351c0,524288,13959441,1786798668,12076631990847188,12076631991030093,12076631991286732,12076631991355774
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,936686,936691,4194304,256,0,0,24,24,14528,0x7fa4c491a600,0x7fa3b8c35200,524288,10689784,1368193348,12076631991381402,12076631991568812,12076631991707211,12076631991710684
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,936686,936691,4194304,256,0,0,24,24,14976,0x7fa4c491a500,0x7fa3b8c35240,524288,10655940,1363974456,12076631991762390,12076631991925130,12076631992064170,12076631992067828
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,936686,936691,4194304,256,0,0,24,24,15424,0x7fa4c491a400,0x7fa3b8c35280,524288,11186260,1431745012,12076631992148108,12076631992322569,12076631992459369,12076631992462773
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,936686,936691,4194304,256,0,0,28,24,16128,0x7fa4c491a300,0x7fa3b8c352c0,524288,13594400,1740078036,12076631992511934,12076631992691208,12076631992944807,12076631992987780
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,936686,936691,4194304,256,0,0,28,24,16832,0x7fa4c491aa00,0x7fa3b8c35300,524288,14091881,1803759428,12076631993018276,12076631993203366,12076631993497925,12076631993540698
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,936686,936691,4194304,256,0,0,24,24,17536,0x7fa4c491a900,0x7fa3b8c35340,524288,12434664,1591612184,12076631993566897,12076631993763365,12076631993894724,12076631993898233
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,936686,936691,4194304,256,0,0,24,24,18240,0x7fa4c491a800,0x7fa3b8c35380,524288,13287858,1700833736,12076631993952885,12076631994123684,12076631994252003,12076631994255778
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,936686,936691,4194304,256,0,0,24,24,18944,0x7fa4c491a700,0x7fa3b8c353c0,524288,12675209,1622335436,12076631994322272,12076631994486722,12076631994617762,12076631994621148
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,936686,936691,4194304,256,0,0,28,24,19904,0x7fa4c491a600,0x7fa3b8c35400,524288,13780254,1763880268,12076631994671482,12076631994836801,12076631995091841,12076631995161984
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,936686,936691,4194304,256,0,0,28,24,20608,0x7fa4c491a500,0x7fa3b8c35440,524288,14284271,1828348304,12076631995189024,12076631995374080,12076631995622399,12076631995689605
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,936686,936691,4194304,256,0,0,24,24,21312,0x7fa4c491a400,0x7fa3b8c35480,524288,12727172,1629027216,12076631995716886,12076631995897598,12076631996026878,12076631996030650
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,936686,936691,4194304,256,0,0,24,24,22016,0x7fa4c491a300,0x7fa3b8c354c0,524288,11350987,1452996020,12076631996079160,12076631996249757,12076631996385277,12076631996388806
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,936686,936691,4194304,256,0,0,24,24,22720,0x7fa4c491aa00,0x7fa3b8c35500,524288,12579972,1610252068,12076631996452134,12076631996616476,12076631996747355,12076631996750779
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,936686,936691,4194304,256,0,0,28,24,23680,0x7fa4c491a900,0x7fa3b8c35540,524288,12812013,1639861484,12076631996800953,12076631996964635,12076631997225914,12076631997294401
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,936686,936691,4194304,256,0,0,28,24,24384,0x7fa4c491a800,0x7fa3b8c35580,524288,13955090,1786187824,12076631997317964,12076631997507513,12076631997761112,12076631997828504
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,936686,936691,4194304,256,0,0,24,24,25088,0x7fa4c491a700,0x7fa3b8c355c0,524288,12648248,1618952704,12076631997855043,12076631998038071,12076631998168471,12076631998172133
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,936686,936691,4194304,256,0,0,24,24,25792,0x7fa4c491a600,0x7fa3b8c35600,524288,11189762,1432283564,12076631998221645,12076631998396150,12076631998532150,12076631998535780
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,936686,936691,4194304,256,0,0,24,24,26496,0x7fa4c491a500,0x7fa3b8c35640,524288,13050016,1670295384,12076631998597074,12076631998758549,12076631998887829,12076631998891311
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,936686,936691,4194304,256,0,0,28,24,27712,0x7fa4c491a400,0x7fa3b8c35680,524288,13693562,1752750104,12076631998942657,12076631999114228,12076631999373427,12076631999443258
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,936686,936691,4194304,256,0,0,28,24,28416,0x7fa4c491a300,0x7fa3b8c356c0,524288,13879294,1776540664,12076631999467823,12076631999648466,12076631999905266,12076631999972562
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,936686,936691,4194304,256,0,0,24,24,29120,0x7fa4c491aa00,0x7fa3b8c35700,524288,12094408,1547985556,12076631999999783,12076632000180625,12076632000313424,12076632000317183
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,936686,936691,4194304,256,0,0,24,24,30080,0x7fa4c491a900,0x7fa3b8c35740,524288,12382294,1584924164,12076632000369150,12076632000527984,12076632000660783,12076632000664299
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,936686,936691,4194304,256,0,0,24,24,30784,0x7fa4c491a800,0x7fa3b8c35780,524288,12566523,1608501928,12076632000726465,12076632000889582,12076632001020462,12076632001024289
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,936686,936691,4194304,256,0,0,28,24,32000,0x7fa4c491a700,0x7fa3b8c357c0,524288,13388619,1713662940,12076632001073971,12076632001253581,12076632001515181,12076632001582848
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,936686,936691,4194304,256,0,0,28,24,32960,0x7fa4c491a600,0x7fa3b8c35800,524288,13637840,1745632680,12076632001609788,12076632001788940,12076632002041419,12076632002112032
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,936686,936691,4194304,256,0,0,24,24,33920,0x7fa4c491a500,0x7fa3b8c35840,524288,12761042,1633355396,12076632002136287,12076632002318218,12076632002449418,12076632002452956
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,936686,936691,4194304,256,0,0,24,24,34880,0x7fa4c491a400,0x7fa3b8c35880,524288,11217114,1435872640,12076632002504522,12076632002667817,12076632002804457,12076632002807966
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,936686,936691,4194304,256,0,0,24,24,35840,0x7fa4c491a300,0x7fa3b8c358c0,524288,12495035,1599387404,12076632002871154,12076632003039816,12076632003171175,12076632003175119
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,936686,936691,4194304,256,0,0,28,24,37312,0x7fa4c491aa00,0x7fa3b8c35900,524288,13371610,1711527468,12076632003225263,12076632003396935,12076632003654534,12076632003722938
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,936686,936691,4194304,256,0,0,28,24,38272,0x7fa4c491a900,0x7fa3b8c35940,524288,13837964,1771234508,12076632003750319,12076632003928293,12076632004184292,12076632004253135
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,936686,936691,4194304,256,0,0,24,24,39232,0x7fa4c491a800,0x7fa3b8c35980,524288,11566995,1480559520,12076632004281047,12076632004459811,12076632004595651,12076632004599128
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,936686,936691,4194304,256,0,0,24,24,40192,0x7fa4c491a700,0x7fa3b8c359c0,524288,12757724,1633023048,12076632004649241,12076632004829410,12076632004961250,12076632004964899
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,936686,936691,4194304,256,0,0,24,24,41152,0x7fa4c491a600,0x7fa3b8c35a00,524288,12429876,1590980968,12076632005032524,12076632005197249,12076632005327329,12076632005331040
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,936686,936691,4194304,256,0,0,28,24,42624,0x7fa4c491a500,0x7fa3b8c35a40,524288,13457016,1722474288,12076632005381123,12076632005545568,12076632005801887,12076632005870243
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,936686,936691,4194304,256,0,0,28,24,43584,0x7fa4c491a400,0x7fa3b8c35a80,524288,13657110,1748062052,12076632005893145,12076632006076446,12076632006336766,12076632006406029
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,936686,936691,4194304,256,0,0,24,24,44544,0x7fa4c491a300,0x7fa3b8c35ac0,524288,12748746,1631856924,12076632006432769,12076632006608285,12076632006739324,12076632006742946
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,936686,936691,4194304,256,0,0,24,24,45760,0x7fa4c491aa00,0x7fa3b8c35b00,524288,10426734,1334713616,12076632006792678,12076632006956444,12076632007096923,12076632007100561
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,936686,936691,4194304,256,0,0,24,24,46720,0x7fa4c491a900,0x7fa3b8c35b40,524288,12588625,1611260212,12076632007163057,12076632007324762,12076632007455162,12076632007458918
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,936686,936691,4194304,256,0,0,28,24,48448,0x7fa4c491a800,0x7fa3b8c35b80,524288,13875290,1776031308,12076632007510233,12076632007673401,12076632007938201,12076632008013810
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,936686,936691,4194304,256,0,0,28,24,49408,0x7fa4c491a700,0x7fa3b8c35bc0,524288,14085119,1802903820,12076632008038195,12076632008219640,12076632008474999,12076632008545379
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,936686,936691,4194304,256,0,0,24,24,50368,0x7fa4c491a600,0x7fa3b8c35c00,524288,13172884,1686138416,12076632008567961,12076632008750518,12076632008878358,12076632008881915
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,936686,936691,4194304,256,0,0,24,24,51584,0x7fa4c491a500,0x7fa3b8c35c40,524288,10440186,1336242800,12076632008932238,12076632009099157,12076632009238677,12076632009242375
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,936686,936691,4194304,256,0,0,24,24,52544,0x7fa4c491a400,0x7fa3b8c35c80,524288,12648685,1619016092,12076632009305503,12076632009466676,12076632009597075,12076632009600642
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,936686,936691,4194304,256,0,0,28,24,54272,0x7fa4c491a300,0x7fa3b8c35cc0,524288,13896022,1778697304,12076632009650184,12076632009812115,12076632010083474,12076632010152879
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,936686,936691,4194304,256,0,0,28,24,55488,0x7fa4c491aa00,0x7fa3b8c35d00,524288,13695447,1753024176,12076632010178286,12076632010361073,12076632010657072,12076632010724733
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,936686,936691,4194304,256,0,0,24,24,56704,0x7fa4c491a900,0x7fa3b8c35d40,524288,11033413,1412272048,12076632010749959,12076632010926031,12076632011063791,12076632011067530
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,936686,936691,4194304,256,0,0,24,24,58176,0x7fa4c491a800,0x7fa3b8c35d80,524288,9420400,1205790712,12076632011118144,12076632011282030,12076632011424750,12076632011428281
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,936686,936691,4194304,256,0,0,24,24,59392,0x7fa4c491a700,0x7fa3b8c35dc0,524288,12316996,1576606928,12076632011489926,12076632011651469,12076632011784749,12076632011788612
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,936686,936691,4194304,256,0,0,28,24,61376,0x7fa4c491a600,0x7fa3b8c35e00,524288,13748793,1759803552,12076632011838214,12076632012000748,12076632012271627,12076632012314850
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,936686,936691,4194304,256,0,0,28,24,62592,0x7fa4c491a500,0x7fa3b8c35e40,524288,13590756,1739682560,12076632012338805,12076632012523946,12076632012781865,12076632012847862
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,936686,936691,4194304,256,0,0,24,24,63808,0x7fa4c491a400,0x7fa3b8c35e80,524288,11638260,1489764796,12076632012876605,12076632013057385,12076632013191624,12076632013195368
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,936686,936691,4194304,256,0,0,24,24,65280,0x7fa4c491a300,0x7fa3b8c35ec0,524288,8879909,1136630552,12076632013244410,12076632013414664,12076632013553863,12076632013557342
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,936686,936691,4194304,256,0,0,24,24,66496,0x7fa4c491aa00,0x7fa3b8c35f00,524288,12450878,1593642436,12076632013619327,12076632013782502,12076632013914022,12076632013917592
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,936686,936691,4194304,256,0,0,28,24,68480,0x7fa4c491a900,0x7fa3b8c35f40,524288,13561968,1735908564,12076632013966843,12076632014138341,12076632014398660,12076632014467595
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,936686,936691,4194304,256,0,0,28,24,69696,0x7fa4c491a800,0x7fa3b8c35f80,524288,13479846,1725387392,12076632014493673,12076632014671140,12076632014928259,12076632014995086
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,936686,936691,4194304,256,0,0,24,24,70912,0x7fa4c491a700,0x7fa3b8c35fc0,524288,11674039,1494197704,12076632015027055,12076632015203458,12076632015338978,12076632015342612
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,936686,936691,4194304,256,0,0,24,24,72384,0x7fa4c491a600,0x7fa3b8c36000,524288,7078457,906093676,12076632015391303,12076632015556257,12076632015695616,12076632015699256
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,936686,936691,4194304,256,0,0,24,24,73600,0x7fa4c491a500,0x7fa3b8c36040,524288,12426427,1590556356,12076632015761031,12076632015922496,12076632016054335,12076632016058193
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,936686,936691,4194304,256,0,0,28,24,75840,0x7fa4c491a400,0x7fa3b8c36080,524288,12975973,1660968428,12076632016108226,12076632016285695,12076632016554494,12076632016603939
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,936686,936691,4194304,256,0,0,28,24,77056,0x7fa4c491a300,0x7fa3b8c360c0,524288,13050721,1670492132,12076632016628494,12076632016805693,12076632017062332,12076632017113046
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,936686,936691,4194304,256,0,0,24,24,78272,0x7fa4c491aa00,0x7fa3b8c36100,524288,12464778,1595380240,12076632017137361,12076632017318171,12076632017450171,12076632017453789
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,936686,936691,4194304,256,0,0,24,24,80000,0x7fa4c491a900,0x7fa3b8c36140,524288,7302888,934678224,12076632017502510,12076632017665210,12076632017809850,12076632017813499
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,936686,936691,4194304,256,0,0,24,24,81216,0x7fa4c491a800,0x7fa3b8c36180,524288,11572968,1481327076,12076632017875514,12076632018041049,12076632018175609,12076632018179459
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,936686,936691,4194304,256,0,0,28,24,83456,0x7fa4c491a700,0x7fa3b8c361c0,524288,12964342,1659505604,12076632018229482,12076632018400248,12076632018662807,12076632018712851
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,936686,936691,4194304,256,0,0,28,24,84928,0x7fa4c491a600,0x7fa3b8c36200,524288,13652339,1747483944,12076632018736005,12076632018914966,12076632019171606,12076632019222810
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,936686,936691,4194304,256,0,0,24,24,86400,0x7fa4c491a500,0x7fa3b8c36240,524288,11193312,1432687492,12076632019250552,12076632019427445,12076632019563604,12076632019567371
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,936686,936691,4194304,256,0,0,24,24,88128,0x7fa4c491a400,0x7fa3b8c36280,524288,5695137,728931472,12076632019618155,12076632019777844,12076632019928883,12076632019932670
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,936686,936691,4194304,256,0,0,24,24,89600,0x7fa4c491a300,0x7fa3b8c362c0,524288,10959406,1402768040,12076632020023449,12076632020184722,12076632020322482,12076632020326072
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,936686,936691,4194304,256,0,0,28,24,92096,0x7fa4c491aa00,0x7fa3b8c36300,524288,12813072,1640044404,12076632020376556,12076632020546321,12076632020815280,12076632020865185
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,936686,936691,4194304,256,0,0,28,24,93568,0x7fa4c491a900,0x7fa3b8c36340,524288,13523973,1730967548,12076632020890813,12076632021071920,12076632021327119,12076632021377628
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,936686,936691,4194304,256,0,0,24,24,95040,0x7fa4c491a800,0x7fa3b8c36380,524288,11713883,1499301460,12076632021405300,12076632021581678,12076632021716558,12076632021720466
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,936686,936691,4194304,256,0,0,24,24,96768,0x7fa4c491a700,0x7fa3b8c363c0,524288,4941367,632540184,12076632021771761,12076632021934157,12076632022093836,12076632022097567
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,936686,936691,4194304,256,0,0,24,24,98240,0x7fa4c491a600,0x7fa3b8c36400,524288,10799652,1382412612,12076632022161166,12076632022331916,12076632022469195,12076632022472986
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,936686,936691,4194304,256,0,0,28,24,100736,0x7fa4c491a500,0x7fa3b8c36440,524288,11637447,1489586852,12076632022522528,12076632022686955,12076632022955594,12076632022979057
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,936686,936691,4194304,256,0,0,28,24,102208,0x7fa4c491a400,0x7fa3b8c36480,524288,12905568,1651914172,12076632023026165,12076632023186793,12076632023443592,12076632023494265
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,936686,936691,4194304,256,0,0,24,24,103680,0x7fa4c491a300,0x7fa3b8c364c0,524288,11704822,1498183668,12076632023519052,12076632023693352,12076632023827911,12076632023831653
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,936686,936691,4194304,256,0,0,24,24,105664,0x7fa4c491aa00,0x7fa3b8c36500,524288,3762652,481574592,12076632023882107,12076632024057190,12076632024222470,12076632024226297
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,936686,936691,4194304,256,0,0,24,24,107136,0x7fa4c491a900,0x7fa3b8c36540,524288,12605205,1613459792,12076632024292961,12076632024473029,12076632024604069,12076632024607827
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,936686,936691,4194304,256,0,0,28,24,109888,0x7fa4c491a800,0x7fa3b8c36580,524288,10444034,1336771500,12076632024656838,12076632024826308,12076632025090787,12076632025141429
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,936686,936691,4194304,256,0,0,28,24,111360,0x7fa4c491a700,0x7fa3b8c365c0,524288,13406164,1715990536,12076632025164843,12076632025347266,12076632025605986,12076632025653522
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,936686,936691,4194304,256,0,0,24,24,112832,0x7fa4c491a600,0x7fa3b8c36600,524288,11540052,1477134588,12076632025682526,12076632025854945,12076632025989344,12076632025993064
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,936686,936691,4194304,256,0,0,24,24,114816,0x7fa4c491a500,0x7fa3b8c36640,524288,3620430,463424412,12076632026044579,12076632026209184,12076632026383263,12076632026387066
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,936686,936691,4194304,256,0,0,24,24,116288,0x7fa4c491a400,0x7fa3b8c36680,524288,11668692,1493571988,12076632026449573,12076632026609982,12076632026745982,12076632026749681
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,936686,936691,4194304,256,0,0,28,24,119040,0x7fa4c491a300,0x7fa3b8c366c0,524288,8056353,1031230972,12076632026798572,12076632026965501,12076632027230941,12076632027282121
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,936686,936691,4194304,256,0,0,28,24,120768,0x7fa4c491aa00,0x7fa3b8c36700,524288,13749320,1759956576,12076632027305415,12076632027492220,12076632027752699,12076632027799995
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,936686,936691,4194304,256,0,0,24,24,122496,0x7fa4c491a900,0x7fa3b8c36740,524288,10784351,1380429000,12076632027826113,12076632028002458,12076632028141818,12076632028145487
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,936686,936691,4194304,256,0,0,24,24,124736,0x7fa4c491a800,0x7fa3b8c36780,524288,3311186,423791844,12076632028195270,12076632028364217,12076632028547096,12076632028550881
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,936686,936691,4194304,256,0,0,24,24,126464,0x7fa4c491a700,0x7fa3b8c367c0,524288,11121544,1423671032,12076632028615211,12076632028774776,12076632028912055,12076632028915730
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,936686,936691,4194304,256,0,0,20,24,127936,0x7fa4c491a600,0x7fa3b8c36800,524288,4286397,548630380,12076632028964851,12076632029138615,12076632029404534,12076632029428644
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,936686,936691,4194304,256,0,0,28,24,129664,0x7fa4c491a500,0x7fa3b8c36840,524288,13462371,1723138352,12076632029470582,12076632029629973,12076632029893652,12076632029940606
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,936686,936691,4194304,256,0,0,24,24,131392,0x7fa4c491a400,0x7fa3b8c36880,524288,12055338,1543171640,12076632029965813,12076632030148691,12076632030281971,12076632030285869
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,936686,936691,4194304,256,0,0,24,24,133632,0x7fa4c491a300,0x7fa3b8c368c0,524288,3580745,458347708,12076632030335832,12076632030500690,12076632030693010,12076632030740785
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,936686,936691,4194304,256,0,0,24,24,135360,0x7fa4c491aa00,0x7fa3b8c36900,524288,10762855,1377632076,12076632030778806,12076632030936049,12076632031074929,12076632031078844
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,936686,936691,4194304,256,0,0,20,24,136832,0x7fa4c491a900,0x7fa3b8c36940,524288,2965668,379544784,12076632031129438,12076632031301968,12076632031587567,12076632031637383
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,936686,936691,4194304,256,0,0,28,24,138560,0x7fa4c491a800,0x7fa3b8c36980,524288,13724870,1756829964,12076632031664984,12076632031841006,12076632032101005,12076632032149555
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,936686,936691,4194304,256,0,0,24,24,140288,0x7fa4c491a700,0x7fa3b8c369c0,524288,12556783,1607226172,12076632032177487,12076632032353645,12076632032486924,12076632032490890
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,936686,936691,4194304,256,0,0,24,24,142784,0x7fa4c491a600,0x7fa3b8c36a00,524288,3509537,449168532,12076632032541094,12076632032703083,12076632032913163,12076632032960313
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,936686,936691,4194304,256,0,0,24,24,144768,0x7fa4c491a500,0x7fa3b8c36a40,524288,9577535,1225947856,12076632032998785,12076632033167082,12076632033310442,12076632033314402
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,936686,936691,4194304,256,0,0,20,24,145728,0x7fa4c491a400,0x7fa3b8c36a80,524288,2549341,326373608,12076632033365447,12076632033528041,12076632033835560,12076632033882228
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,936686,936691,4194304,256,0,0,28,24,147712,0x7fa4c491a300,0x7fa3b8c36ac0,524288,13938329,1784048764,12076632033904650,12076632034089479,12076632034352038,12076632034402696
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,936686,936691,4194304,256,0,0,24,24,149696,0x7fa4c491aa00,0x7fa3b8c36b00,524288,9647066,1234926464,12076632034426060,12076632034604838,12076632034744357,12076632034748249
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,936686,936691,4194304,256,0,0,24,24,152192,0x7fa4c491a900,0x7fa3b8c36b40,524288,3497597,447756936,12076632034796669,12076632034959076,12076632035187236,12076632035237569
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,936686,936691,4194304,256,0,0,24,24,154176,0x7fa4c491a800,0x7fa3b8c36b80,524288,10935167,1399592344,12076632035275720,12076632035441315,12076632035577155,12076632035581098
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,936686,936691,4194304,256,0,0,20,24,155648,0x7fa4c491a700,0x7fa3b8c36bc0,524288,2487821,318415480,12076632035630039,12076632035796354,12076632036126913,12076632036176236
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,936686,936691,4194304,256,0,0,28,24,157632,0x7fa4c491a600,0x7fa3b8c36c00,524288,13487975,1726388348,12076632036200771,12076632036381632,12076632036638911,12076632036686435
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,936686,936691,4194304,256,0,0,24,24,159616,0x7fa4c491a500,0x7fa3b8c36c40,524288,10837100,1387119932,12076632036712363,12076632036887390,12076632037028510,12076632037032228
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,936686,936691,4194304,256,0,0,24,24,162368,0x7fa4c491a400,0x7fa3b8c36c80,524288,3418032,437393740,12076632037082782,12076632037247576,12076632037493816,12076632037520967
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,936686,936691,4194304,256,0,0,24,24,164608,0x7fa4c491a300,0x7fa3b8c36cc0,524288,9739267,1246664408,12076632037571831,12076632037734934,12076632037875574,12076632037878542
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,936686,936691,4194304,256,0,0,20,24,166336,0x7fa4c491aa00,0x7fa3b8c36d00,524288,2392954,306166508,12076632037926591,12076632038102133,12076632038479893,12076632038529072
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,936686,936691,4194304,256,0,0,28,24,168576,0x7fa4c491a900,0x7fa3b8c36d40,524288,11973629,1532529168,12076632038558877,12076632038733492,12076632038999891,12076632039047356
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,936686,936691,4194304,256,0,0,24,24,170816,0x7fa4c491a800,0x7fa3b8c36d80,524288,9364067,1198516552,12076632039084305,12076632039248691,12076632039388531,12076632039391546
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,936686,936691,4194304,256,0,0,24,24,174080,0x7fa4c491a700,0x7fa3b8c36dc0,524288,3430122,439102892,12076632039440808,12076632039615090,12076632039895090,12076632039917334
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,936686,936691,4194304,256,0,0,24,24,176576,0x7fa4c491a600,0x7fa3b8c36e00,524288,8700235,1113566308,12076632039971595,12076632040143409,12076632040283249,12076632040286551
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,936686,936691,4194304,256,0,0,20,24,177792,0x7fa4c491a500,0x7fa3b8c36e40,524288,2361529,302112880,12076632040336604,12076632040499408,12076632040947727,12076632040994448
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,936686,936691,4194304,256,0,0,28,24,180288,0x7fa4c491a400,0x7fa3b8c36e80,524288,10828654,1386005372,12076632041026187,12076632041206767,12076632041475406,12076632041522701
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,936686,936691,4194304,256,0,0,24,24,182784,0x7fa4c491a300,0x7fa3b8c36ec0,524288,7486533,958334076,12076632041549200,12076632041729006,12076632041869006,12076632041871770
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,936686,936691,4194304,256,0,0,24,24,186304,0x7fa4c491aa00,0x7fa3b8c36f00,524288,3449786,441526416,12076632041920781,12076632042089965,12076632042405644,12076632042455185
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,936686,936691,4194304,256,0,0,24,24,189312,0x7fa4c491a900,0x7fa3b8c36f40,524288,4153049,531489656,12076632042496352,12076632042660524,12076632042814124,12076632042817058
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,936686,936691,4194304,256,0,0,20,24,190784,0x7fa4c491a800,0x7fa3b8c36f80,524288,2386279,305359020,12076632042866139,12076632043043563,12076632043563402,12076632043613570
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,936686,936691,4194304,256,0,0,28,24,193792,0x7fa4c491a700,0x7fa3b8c36fc0,524288,7969875,1020139468,12076632043638085,12076632043818442,12076632044118121,12076632044167029
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,936686,936691,4194304,256,0,0,24,24,196800,0x7fa4c491a600,0x7fa3b8c37000,524288,3407015,435995508,12076632044190914,12076632044376840,12076632044532040,12076632044535024
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,936686,936691,4194304,256,0,0,24,24,201088,0x7fa4c491a500,0x7fa3b8c37040,524288,3473919,444763716,12076632044584306,12076632044752360,12076632045163879,12076632045187578
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,936686,936691,4194304,256,0,0,24,24,204608,0x7fa4c491a400,0x7fa3b8c37080,524288,3272315,418740372,12076632045246337,12076632045413478,12076632045590598,12076632045594014
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,936686,936691,4194304,256,0,0,20,24,206080,0x7fa4c491a300,0x7fa3b8c370c0,524288,2294983,293732696,12076632045643756,12076632045807557,12076632046418916,12076632046469482
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,936686,936691,4194304,256,0,0,28,24,209600,0x7fa4c491aa00,0x7fa3b8c37100,524288,4396336,562643820,12076632046492745,12076632046680036,12076632047007875,12076632047056684
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,936686,936691,4194304,256,0,0,24,24,213120,0x7fa4c491a900,0x7fa3b8c37140,524288,3356672,429650728,12076632047089546,12076632047260994,12076632047440194,12076632047443404
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,936686,936691,4194304,256,0,0,24,24,218176,0x7fa4c491a800,0x7fa3b8c37180,524288,3698088,473353416,12076632047493357,12076632047655714,12076632048111233,12076632048160708
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,936686,936691,4194304,256,0,0,24,24,222208,0x7fa4c491a700,0x7fa3b8c371c0,524288,3115363,398663524,12076632048197096,12076632048360512,12076632048560352,12076632048608731
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,936686,936691,4194304,256,0,0,20,24,223936,0x7fa4c491a600,0x7fa3b8c37200,524288,2353399,301326212,12076632048638747,12076632048819391,12076632049524030,12076632049574578
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,936686,936691,4194304,256,0,0,28,24,227968,0x7fa4c491a500,0x7fa3b8c37240,524288,3759297,481240984,12076632049597982,12076632049780989,12076632050154908,12076632050204870
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,936686,936691,4194304,256,0,0,24,24,232000,0x7fa4c491a400,0x7fa3b8c37280,524288,3337562,427130436,12076632050230498,12076632050409788,12076632050614107,12076632050661219
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,936686,936691,4194304,256,0,0,24,24,237824,0x7fa4c491a300,0x7fa3b8c372c0,524288,4483183,573876308,12076632050687679,12076632050863067,12076632051389626,12076632051440479
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,936686,936691,4194304,256,0,0,24,24,242368,0x7fa4c491aa00,0x7fa3b8c37300,524288,3191474,408441500,12076632051481154,12076632051645305,12076632051870265,12076632051916845
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,936686,936691,4194304,256,0,0,20,24,243584,0x7fa4c491a900,0x7fa3b8c37340,524288,2314303,296064368,12076632051943294,12076632052123864,12076632052925143,12076632052974532
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,936686,936691,4194304,256,0,0,28,24,248128,0x7fa4c491a800,0x7fa3b8c37380,524288,3330637,426356880,12076632052998307,12076632053183222,12076632053605461,12076632053655018
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,936686,936691,4194304,256,0,0,24,24,252672,0x7fa4c491a700,0x7fa3b8c373c0,524288,3178098,406760076,12076632053678402,12076632053858101,12076632054084020,12076632054134019
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,936686,936691,4194304,256,0,0,24,24,259264,0x7fa4c491a600,0x7fa3b8c37400,524288,4681601,599231332,12076632054161791,12076632054342900,12076632054940659,12076632054989581
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,936686,936691,4194304,256,0,0,24,24,264832,0x7fa4c491a500,0x7fa3b8c37440,524288,3300771,422651168,12076632055030657,12076632055198738,12076632055468177,12076632055518154
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,936686,936691,4194304,256,0,0,20,24,266304,0x7fa4c491a400,0x7fa3b8c37480,524288,2318734,296756940,12076632055546176,12076632055725617,12076632056713135,12076632056783137
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,936686,936691,4194304,256,0,0,28,24,271872,0x7fa4c491a300,0x7fa3b8c374c0,524288,3537473,452802788,12076632056818092,12076632056985934,12076632057502733,12076632057571854
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,936686,936691,4194304,256,0,0,24,24,277440,0x7fa4c491aa00,0x7fa3b8c37500,524288,3306185,423158436,12076632057603863,12076632057780493,12076632058053772,12076632058122468
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,936686,936691,4194304,256,0,0,12,24,279936,0x7fa4c491a900,0x7fa3b8c37540,524288,2211182,283065684,12076632058155329,12076632058324332,12076632059063530,12076632059131936
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,936686,936691,4194304,256,0,0,24,24,286528,0x7fa4c491a800,0x7fa3b8c37580,524288,3343527,427946244,12076632059175547,12076632059338729,12076632059655529,12076632059722444
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,936686,936691,4194304,256,0,0,20,24,288000,0x7fa4c491a700,0x7fa3b8c375c0,524288,2272972,290999932,12076632059747401,12076632059928968,12076632061102246,12076632061171640
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,936686,936691,4194304,256,0,0,32,24,294592,0x7fa4c491a600,0x7fa3b8c37600,524288,3455071,442240716,12076632061201365,12076632061387525,12076632061996164,12076632062064481
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,936686,936691,4194304,256,0,0,24,24,301184,0x7fa4c491a500,0x7fa3b8c37640,524288,3344160,428037120,12076632062093996,12076632062276483,12076632062596643,12076632062663014
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,936686,936691,4194304,256,0,0,12,24,304960,0x7fa4c491a400,0x7fa3b8c37680,524288,2215325,283556952,12076632062686568,12076632062871682,12076632063751680,12076632063820357
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,936686,936691,4194304,256,0,0,24,24,313600,0x7fa4c491a300,0x7fa3b8c376c0,524288,3332364,426460868,12076632063861203,12076632064032160,12076632064444959,12076632064513807
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,936686,936691,4194304,256,0,0,20,24,314816,0x7fa4c491aa00,0x7fa3b8c37700,524288,2296507,293956708,12076632064536629,12076632064719038,12076632066269595,12076632066338411
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,936686,936691,4194304,256,0,0,20,24,317568,0x7fa4c491a900,0x7fa3b8c37740,524288,2267842,290215000,12076632066369378,12076632066552955,12076632067348313,12076632067416947
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,936686,936691,4194304,256,0,0,12,24,320320,0x7fa4c491a800,0x7fa3b8c37780,524288,2156090,275898460,12076632067446322,12076632067628632,12076632068067031,12076632068135273
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,936686,936691,4194304,256,0,0,12,24,324096,0x7fa4c491a700,0x7fa3b8c377c0,524288,2232883,285813132,12076632068165610,12076632068346391,12076632069505588,12076632069574180
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,936686,936691,4194304,256,0,0,12,24,328896,0x7fa4c491a600,0x7fa3b8c37800,524288,2225959,285007468,12076632069618492,12076632069786388,12076632070573266,12076632070643479
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,936686,936691,4194304,256,0,0,20,24,330112,0x7fa4c491a500,0x7fa3b8c37840,524288,2662622,340672136,12076632070676410,12076632070851826,12076632073906059,12076632073976108
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,936686,936691,4194304,256,0,0,20,24,332864,0x7fa4c491a400,0x7fa3b8c37880,524288,2315165,296215488,12076632074010582,12076632074194539,12076632075739016,12076632075809107
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,936686,936691,4194304,256,0,0,12,24,335616,0x7fa4c491a300,0x7fa3b8c378c0,524288,2180249,278951920,12076632075842059,12076632076032295,12076632076822053,12076632076890990
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,936686,936691,4194304,256,0,0,12,24,339392,0x7fa4c491aa00,0x7fa3b8c37900,524288,2566313,328514036,12076632076915155,12076632077120613,12076632079403168,12076632079473193
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,936686,936691,4194304,256,0,0,12,24,344192,0x7fa4c491a900,0x7fa3b8c37940,524288,2340991,299613432,12076632079518137,12076632079686847,12076632081222524,12076632081291946
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,936686,936691,4194304,256,0,0,20,24,345408,0x7fa4c491a800,0x7fa3b8c37980,524288,2837649,363088816,12076632081322042,12076632081503164,12076632087560911,12076632087632931
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,936686,936691,4194304,256,0,0,20,24,348160,0x7fa4c491a700,0x7fa3b8c379c0,524288,3308509,423416964,12076632087658479,12076632087838991,12076632090885384,12076632090958577
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,936686,936691,4194304,256,0,0,12,24,350912,0x7fa4c491a600,0x7fa3b8c37a00,524288,2303191,294805748,12076632090985548,12076632091177224,12076632092716581,12076632092788411
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,936686,936691,4194304,256,0,0,12,24,0,0x7fa4c491a500,0x7fa3b8c37a40,524288,2535117,324431768,12076632092814990,12076632093004740,12076632097533531,12076632097603959
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 936686 936691 33554432 256 0 0 8 32 6464 0x0 0x7fa3b8c04180 1048576 11096456 1419911252 12076631726864889 12076631974434106 12076631974755065 12076631974864438
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 936686 936691 32768 256 0 0 24 24 12480 0x0 0x7fa3b8c35100 4096 107784 13788356 12076631989518086 12076631989806097 12076631989812497 12076631989817693
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 4 936686 936691 4194304 256 0 0 24 24 12928 0x7fa4c491a900 0x7fa3b8c35140 524288 10667896 1365491840 12076631989877063 12076631990100976 12076631990238896 12076631990242964
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 936686 936691 4194304 256 0 0 36 24 13632 0x7fa4c491a800 0x7fa3b8c35180 524288 13037531 1668759720 12076631990314367 12076631990488335 12076631990742414 12076631990810750
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 8 936686 936691 4194304 256 0 0 28 24 14080 0x7fa4c491a700 0x7fa3b8c351c0 524288 13959441 1786798668 12076631990847188 12076631991030093 12076631991286732 12076631991355774
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 10 936686 936691 4194304 256 0 0 24 24 14528 0x7fa4c491a600 0x7fa3b8c35200 524288 10689784 1368193348 12076631991381402 12076631991568812 12076631991707211 12076631991710684
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 12 936686 936691 4194304 256 0 0 24 24 14976 0x7fa4c491a500 0x7fa3b8c35240 524288 10655940 1363974456 12076631991762390 12076631991925130 12076631992064170 12076631992067828
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 14 936686 936691 4194304 256 0 0 24 24 15424 0x7fa4c491a400 0x7fa3b8c35280 524288 11186260 1431745012 12076631992148108 12076631992322569 12076631992459369 12076631992462773
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 936686 936691 4194304 256 0 0 28 24 16128 0x7fa4c491a300 0x7fa3b8c352c0 524288 13594400 1740078036 12076631992511934 12076631992691208 12076631992944807 12076631992987780
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 18 936686 936691 4194304 256 0 0 28 24 16832 0x7fa4c491aa00 0x7fa3b8c35300 524288 14091881 1803759428 12076631993018276 12076631993203366 12076631993497925 12076631993540698
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 20 936686 936691 4194304 256 0 0 24 24 17536 0x7fa4c491a900 0x7fa3b8c35340 524288 12434664 1591612184 12076631993566897 12076631993763365 12076631993894724 12076631993898233
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 22 936686 936691 4194304 256 0 0 24 24 18240 0x7fa4c491a800 0x7fa3b8c35380 524288 13287858 1700833736 12076631993952885 12076631994123684 12076631994252003 12076631994255778
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 24 936686 936691 4194304 256 0 0 24 24 18944 0x7fa4c491a700 0x7fa3b8c353c0 524288 12675209 1622335436 12076631994322272 12076631994486722 12076631994617762 12076631994621148
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 936686 936691 4194304 256 0 0 28 24 19904 0x7fa4c491a600 0x7fa3b8c35400 524288 13780254 1763880268 12076631994671482 12076631994836801 12076631995091841 12076631995161984
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 28 936686 936691 4194304 256 0 0 28 24 20608 0x7fa4c491a500 0x7fa3b8c35440 524288 14284271 1828348304 12076631995189024 12076631995374080 12076631995622399 12076631995689605
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 30 936686 936691 4194304 256 0 0 24 24 21312 0x7fa4c491a400 0x7fa3b8c35480 524288 12727172 1629027216 12076631995716886 12076631995897598 12076631996026878 12076631996030650
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 32 936686 936691 4194304 256 0 0 24 24 22016 0x7fa4c491a300 0x7fa3b8c354c0 524288 11350987 1452996020 12076631996079160 12076631996249757 12076631996385277 12076631996388806
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 34 936686 936691 4194304 256 0 0 24 24 22720 0x7fa4c491aa00 0x7fa3b8c35500 524288 12579972 1610252068 12076631996452134 12076631996616476 12076631996747355 12076631996750779
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 936686 936691 4194304 256 0 0 28 24 23680 0x7fa4c491a900 0x7fa3b8c35540 524288 12812013 1639861484 12076631996800953 12076631996964635 12076631997225914 12076631997294401
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 38 936686 936691 4194304 256 0 0 28 24 24384 0x7fa4c491a800 0x7fa3b8c35580 524288 13955090 1786187824 12076631997317964 12076631997507513 12076631997761112 12076631997828504
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 40 936686 936691 4194304 256 0 0 24 24 25088 0x7fa4c491a700 0x7fa3b8c355c0 524288 12648248 1618952704 12076631997855043 12076631998038071 12076631998168471 12076631998172133
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 42 936686 936691 4194304 256 0 0 24 24 25792 0x7fa4c491a600 0x7fa3b8c35600 524288 11189762 1432283564 12076631998221645 12076631998396150 12076631998532150 12076631998535780
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 44 936686 936691 4194304 256 0 0 24 24 26496 0x7fa4c491a500 0x7fa3b8c35640 524288 13050016 1670295384 12076631998597074 12076631998758549 12076631998887829 12076631998891311
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 936686 936691 4194304 256 0 0 28 24 27712 0x7fa4c491a400 0x7fa3b8c35680 524288 13693562 1752750104 12076631998942657 12076631999114228 12076631999373427 12076631999443258
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 48 936686 936691 4194304 256 0 0 28 24 28416 0x7fa4c491a300 0x7fa3b8c356c0 524288 13879294 1776540664 12076631999467823 12076631999648466 12076631999905266 12076631999972562
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 50 936686 936691 4194304 256 0 0 24 24 29120 0x7fa4c491aa00 0x7fa3b8c35700 524288 12094408 1547985556 12076631999999783 12076632000180625 12076632000313424 12076632000317183
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 52 936686 936691 4194304 256 0 0 24 24 30080 0x7fa4c491a900 0x7fa3b8c35740 524288 12382294 1584924164 12076632000369150 12076632000527984 12076632000660783 12076632000664299
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 54 936686 936691 4194304 256 0 0 24 24 30784 0x7fa4c491a800 0x7fa3b8c35780 524288 12566523 1608501928 12076632000726465 12076632000889582 12076632001020462 12076632001024289
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 936686 936691 4194304 256 0 0 28 24 32000 0x7fa4c491a700 0x7fa3b8c357c0 524288 13388619 1713662940 12076632001073971 12076632001253581 12076632001515181 12076632001582848
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 58 936686 936691 4194304 256 0 0 28 24 32960 0x7fa4c491a600 0x7fa3b8c35800 524288 13637840 1745632680 12076632001609788 12076632001788940 12076632002041419 12076632002112032
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 60 936686 936691 4194304 256 0 0 24 24 33920 0x7fa4c491a500 0x7fa3b8c35840 524288 12761042 1633355396 12076632002136287 12076632002318218 12076632002449418 12076632002452956
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 62 936686 936691 4194304 256 0 0 24 24 34880 0x7fa4c491a400 0x7fa3b8c35880 524288 11217114 1435872640 12076632002504522 12076632002667817 12076632002804457 12076632002807966
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 64 936686 936691 4194304 256 0 0 24 24 35840 0x7fa4c491a300 0x7fa3b8c358c0 524288 12495035 1599387404 12076632002871154 12076632003039816 12076632003171175 12076632003175119
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 936686 936691 4194304 256 0 0 28 24 37312 0x7fa4c491aa00 0x7fa3b8c35900 524288 13371610 1711527468 12076632003225263 12076632003396935 12076632003654534 12076632003722938
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 68 936686 936691 4194304 256 0 0 28 24 38272 0x7fa4c491a900 0x7fa3b8c35940 524288 13837964 1771234508 12076632003750319 12076632003928293 12076632004184292 12076632004253135
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 70 936686 936691 4194304 256 0 0 24 24 39232 0x7fa4c491a800 0x7fa3b8c35980 524288 11566995 1480559520 12076632004281047 12076632004459811 12076632004595651 12076632004599128
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 72 936686 936691 4194304 256 0 0 24 24 40192 0x7fa4c491a700 0x7fa3b8c359c0 524288 12757724 1633023048 12076632004649241 12076632004829410 12076632004961250 12076632004964899
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 74 936686 936691 4194304 256 0 0 24 24 41152 0x7fa4c491a600 0x7fa3b8c35a00 524288 12429876 1590980968 12076632005032524 12076632005197249 12076632005327329 12076632005331040
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 936686 936691 4194304 256 0 0 28 24 42624 0x7fa4c491a500 0x7fa3b8c35a40 524288 13457016 1722474288 12076632005381123 12076632005545568 12076632005801887 12076632005870243
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 78 936686 936691 4194304 256 0 0 28 24 43584 0x7fa4c491a400 0x7fa3b8c35a80 524288 13657110 1748062052 12076632005893145 12076632006076446 12076632006336766 12076632006406029
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 80 936686 936691 4194304 256 0 0 24 24 44544 0x7fa4c491a300 0x7fa3b8c35ac0 524288 12748746 1631856924 12076632006432769 12076632006608285 12076632006739324 12076632006742946
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 82 936686 936691 4194304 256 0 0 24 24 45760 0x7fa4c491aa00 0x7fa3b8c35b00 524288 10426734 1334713616 12076632006792678 12076632006956444 12076632007096923 12076632007100561
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 84 936686 936691 4194304 256 0 0 24 24 46720 0x7fa4c491a900 0x7fa3b8c35b40 524288 12588625 1611260212 12076632007163057 12076632007324762 12076632007455162 12076632007458918
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 936686 936691 4194304 256 0 0 28 24 48448 0x7fa4c491a800 0x7fa3b8c35b80 524288 13875290 1776031308 12076632007510233 12076632007673401 12076632007938201 12076632008013810
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 88 936686 936691 4194304 256 0 0 28 24 49408 0x7fa4c491a700 0x7fa3b8c35bc0 524288 14085119 1802903820 12076632008038195 12076632008219640 12076632008474999 12076632008545379
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 90 936686 936691 4194304 256 0 0 24 24 50368 0x7fa4c491a600 0x7fa3b8c35c00 524288 13172884 1686138416 12076632008567961 12076632008750518 12076632008878358 12076632008881915
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 92 936686 936691 4194304 256 0 0 24 24 51584 0x7fa4c491a500 0x7fa3b8c35c40 524288 10440186 1336242800 12076632008932238 12076632009099157 12076632009238677 12076632009242375
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 94 936686 936691 4194304 256 0 0 24 24 52544 0x7fa4c491a400 0x7fa3b8c35c80 524288 12648685 1619016092 12076632009305503 12076632009466676 12076632009597075 12076632009600642
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 936686 936691 4194304 256 0 0 28 24 54272 0x7fa4c491a300 0x7fa3b8c35cc0 524288 13896022 1778697304 12076632009650184 12076632009812115 12076632010083474 12076632010152879
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 98 936686 936691 4194304 256 0 0 28 24 55488 0x7fa4c491aa00 0x7fa3b8c35d00 524288 13695447 1753024176 12076632010178286 12076632010361073 12076632010657072 12076632010724733
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 100 936686 936691 4194304 256 0 0 24 24 56704 0x7fa4c491a900 0x7fa3b8c35d40 524288 11033413 1412272048 12076632010749959 12076632010926031 12076632011063791 12076632011067530
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 102 936686 936691 4194304 256 0 0 24 24 58176 0x7fa4c491a800 0x7fa3b8c35d80 524288 9420400 1205790712 12076632011118144 12076632011282030 12076632011424750 12076632011428281
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 104 936686 936691 4194304 256 0 0 24 24 59392 0x7fa4c491a700 0x7fa3b8c35dc0 524288 12316996 1576606928 12076632011489926 12076632011651469 12076632011784749 12076632011788612
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 936686 936691 4194304 256 0 0 28 24 61376 0x7fa4c491a600 0x7fa3b8c35e00 524288 13748793 1759803552 12076632011838214 12076632012000748 12076632012271627 12076632012314850
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 108 936686 936691 4194304 256 0 0 28 24 62592 0x7fa4c491a500 0x7fa3b8c35e40 524288 13590756 1739682560 12076632012338805 12076632012523946 12076632012781865 12076632012847862
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 110 936686 936691 4194304 256 0 0 24 24 63808 0x7fa4c491a400 0x7fa3b8c35e80 524288 11638260 1489764796 12076632012876605 12076632013057385 12076632013191624 12076632013195368
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 112 936686 936691 4194304 256 0 0 24 24 65280 0x7fa4c491a300 0x7fa3b8c35ec0 524288 8879909 1136630552 12076632013244410 12076632013414664 12076632013553863 12076632013557342
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 114 936686 936691 4194304 256 0 0 24 24 66496 0x7fa4c491aa00 0x7fa3b8c35f00 524288 12450878 1593642436 12076632013619327 12076632013782502 12076632013914022 12076632013917592
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 936686 936691 4194304 256 0 0 28 24 68480 0x7fa4c491a900 0x7fa3b8c35f40 524288 13561968 1735908564 12076632013966843 12076632014138341 12076632014398660 12076632014467595
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 118 936686 936691 4194304 256 0 0 28 24 69696 0x7fa4c491a800 0x7fa3b8c35f80 524288 13479846 1725387392 12076632014493673 12076632014671140 12076632014928259 12076632014995086
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 120 936686 936691 4194304 256 0 0 24 24 70912 0x7fa4c491a700 0x7fa3b8c35fc0 524288 11674039 1494197704 12076632015027055 12076632015203458 12076632015338978 12076632015342612
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 122 936686 936691 4194304 256 0 0 24 24 72384 0x7fa4c491a600 0x7fa3b8c36000 524288 7078457 906093676 12076632015391303 12076632015556257 12076632015695616 12076632015699256
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 124 936686 936691 4194304 256 0 0 24 24 73600 0x7fa4c491a500 0x7fa3b8c36040 524288 12426427 1590556356 12076632015761031 12076632015922496 12076632016054335 12076632016058193
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 936686 936691 4194304 256 0 0 28 24 75840 0x7fa4c491a400 0x7fa3b8c36080 524288 12975973 1660968428 12076632016108226 12076632016285695 12076632016554494 12076632016603939
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 128 936686 936691 4194304 256 0 0 28 24 77056 0x7fa4c491a300 0x7fa3b8c360c0 524288 13050721 1670492132 12076632016628494 12076632016805693 12076632017062332 12076632017113046
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 130 936686 936691 4194304 256 0 0 24 24 78272 0x7fa4c491aa00 0x7fa3b8c36100 524288 12464778 1595380240 12076632017137361 12076632017318171 12076632017450171 12076632017453789
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 132 936686 936691 4194304 256 0 0 24 24 80000 0x7fa4c491a900 0x7fa3b8c36140 524288 7302888 934678224 12076632017502510 12076632017665210 12076632017809850 12076632017813499
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 134 936686 936691 4194304 256 0 0 24 24 81216 0x7fa4c491a800 0x7fa3b8c36180 524288 11572968 1481327076 12076632017875514 12076632018041049 12076632018175609 12076632018179459
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 936686 936691 4194304 256 0 0 28 24 83456 0x7fa4c491a700 0x7fa3b8c361c0 524288 12964342 1659505604 12076632018229482 12076632018400248 12076632018662807 12076632018712851
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 138 936686 936691 4194304 256 0 0 28 24 84928 0x7fa4c491a600 0x7fa3b8c36200 524288 13652339 1747483944 12076632018736005 12076632018914966 12076632019171606 12076632019222810
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 140 936686 936691 4194304 256 0 0 24 24 86400 0x7fa4c491a500 0x7fa3b8c36240 524288 11193312 1432687492 12076632019250552 12076632019427445 12076632019563604 12076632019567371
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 142 936686 936691 4194304 256 0 0 24 24 88128 0x7fa4c491a400 0x7fa3b8c36280 524288 5695137 728931472 12076632019618155 12076632019777844 12076632019928883 12076632019932670
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 144 936686 936691 4194304 256 0 0 24 24 89600 0x7fa4c491a300 0x7fa3b8c362c0 524288 10959406 1402768040 12076632020023449 12076632020184722 12076632020322482 12076632020326072
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 936686 936691 4194304 256 0 0 28 24 92096 0x7fa4c491aa00 0x7fa3b8c36300 524288 12813072 1640044404 12076632020376556 12076632020546321 12076632020815280 12076632020865185
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 148 936686 936691 4194304 256 0 0 28 24 93568 0x7fa4c491a900 0x7fa3b8c36340 524288 13523973 1730967548 12076632020890813 12076632021071920 12076632021327119 12076632021377628
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 150 936686 936691 4194304 256 0 0 24 24 95040 0x7fa4c491a800 0x7fa3b8c36380 524288 11713883 1499301460 12076632021405300 12076632021581678 12076632021716558 12076632021720466
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 152 936686 936691 4194304 256 0 0 24 24 96768 0x7fa4c491a700 0x7fa3b8c363c0 524288 4941367 632540184 12076632021771761 12076632021934157 12076632022093836 12076632022097567
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 154 936686 936691 4194304 256 0 0 24 24 98240 0x7fa4c491a600 0x7fa3b8c36400 524288 10799652 1382412612 12076632022161166 12076632022331916 12076632022469195 12076632022472986
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 936686 936691 4194304 256 0 0 28 24 100736 0x7fa4c491a500 0x7fa3b8c36440 524288 11637447 1489586852 12076632022522528 12076632022686955 12076632022955594 12076632022979057
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 158 936686 936691 4194304 256 0 0 28 24 102208 0x7fa4c491a400 0x7fa3b8c36480 524288 12905568 1651914172 12076632023026165 12076632023186793 12076632023443592 12076632023494265
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 160 936686 936691 4194304 256 0 0 24 24 103680 0x7fa4c491a300 0x7fa3b8c364c0 524288 11704822 1498183668 12076632023519052 12076632023693352 12076632023827911 12076632023831653
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 162 936686 936691 4194304 256 0 0 24 24 105664 0x7fa4c491aa00 0x7fa3b8c36500 524288 3762652 481574592 12076632023882107 12076632024057190 12076632024222470 12076632024226297
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 164 936686 936691 4194304 256 0 0 24 24 107136 0x7fa4c491a900 0x7fa3b8c36540 524288 12605205 1613459792 12076632024292961 12076632024473029 12076632024604069 12076632024607827
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 936686 936691 4194304 256 0 0 28 24 109888 0x7fa4c491a800 0x7fa3b8c36580 524288 10444034 1336771500 12076632024656838 12076632024826308 12076632025090787 12076632025141429
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 168 936686 936691 4194304 256 0 0 28 24 111360 0x7fa4c491a700 0x7fa3b8c365c0 524288 13406164 1715990536 12076632025164843 12076632025347266 12076632025605986 12076632025653522
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 170 936686 936691 4194304 256 0 0 24 24 112832 0x7fa4c491a600 0x7fa3b8c36600 524288 11540052 1477134588 12076632025682526 12076632025854945 12076632025989344 12076632025993064
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 172 936686 936691 4194304 256 0 0 24 24 114816 0x7fa4c491a500 0x7fa3b8c36640 524288 3620430 463424412 12076632026044579 12076632026209184 12076632026383263 12076632026387066
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 174 936686 936691 4194304 256 0 0 24 24 116288 0x7fa4c491a400 0x7fa3b8c36680 524288 11668692 1493571988 12076632026449573 12076632026609982 12076632026745982 12076632026749681
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 936686 936691 4194304 256 0 0 28 24 119040 0x7fa4c491a300 0x7fa3b8c366c0 524288 8056353 1031230972 12076632026798572 12076632026965501 12076632027230941 12076632027282121
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 178 936686 936691 4194304 256 0 0 28 24 120768 0x7fa4c491aa00 0x7fa3b8c36700 524288 13749320 1759956576 12076632027305415 12076632027492220 12076632027752699 12076632027799995
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 180 936686 936691 4194304 256 0 0 24 24 122496 0x7fa4c491a900 0x7fa3b8c36740 524288 10784351 1380429000 12076632027826113 12076632028002458 12076632028141818 12076632028145487
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 182 936686 936691 4194304 256 0 0 24 24 124736 0x7fa4c491a800 0x7fa3b8c36780 524288 3311186 423791844 12076632028195270 12076632028364217 12076632028547096 12076632028550881
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 184 936686 936691 4194304 256 0 0 24 24 126464 0x7fa4c491a700 0x7fa3b8c367c0 524288 11121544 1423671032 12076632028615211 12076632028774776 12076632028912055 12076632028915730
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 936686 936691 4194304 256 0 0 20 24 127936 0x7fa4c491a600 0x7fa3b8c36800 524288 4286397 548630380 12076632028964851 12076632029138615 12076632029404534 12076632029428644
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 188 936686 936691 4194304 256 0 0 28 24 129664 0x7fa4c491a500 0x7fa3b8c36840 524288 13462371 1723138352 12076632029470582 12076632029629973 12076632029893652 12076632029940606
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 190 936686 936691 4194304 256 0 0 24 24 131392 0x7fa4c491a400 0x7fa3b8c36880 524288 12055338 1543171640 12076632029965813 12076632030148691 12076632030281971 12076632030285869
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 192 936686 936691 4194304 256 0 0 24 24 133632 0x7fa4c491a300 0x7fa3b8c368c0 524288 3580745 458347708 12076632030335832 12076632030500690 12076632030693010 12076632030740785
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 194 936686 936691 4194304 256 0 0 24 24 135360 0x7fa4c491aa00 0x7fa3b8c36900 524288 10762855 1377632076 12076632030778806 12076632030936049 12076632031074929 12076632031078844
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 936686 936691 4194304 256 0 0 20 24 136832 0x7fa4c491a900 0x7fa3b8c36940 524288 2965668 379544784 12076632031129438 12076632031301968 12076632031587567 12076632031637383
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 198 936686 936691 4194304 256 0 0 28 24 138560 0x7fa4c491a800 0x7fa3b8c36980 524288 13724870 1756829964 12076632031664984 12076632031841006 12076632032101005 12076632032149555
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 200 936686 936691 4194304 256 0 0 24 24 140288 0x7fa4c491a700 0x7fa3b8c369c0 524288 12556783 1607226172 12076632032177487 12076632032353645 12076632032486924 12076632032490890
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 202 936686 936691 4194304 256 0 0 24 24 142784 0x7fa4c491a600 0x7fa3b8c36a00 524288 3509537 449168532 12076632032541094 12076632032703083 12076632032913163 12076632032960313
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 204 936686 936691 4194304 256 0 0 24 24 144768 0x7fa4c491a500 0x7fa3b8c36a40 524288 9577535 1225947856 12076632032998785 12076632033167082 12076632033310442 12076632033314402
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 936686 936691 4194304 256 0 0 20 24 145728 0x7fa4c491a400 0x7fa3b8c36a80 524288 2549341 326373608 12076632033365447 12076632033528041 12076632033835560 12076632033882228
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 208 936686 936691 4194304 256 0 0 28 24 147712 0x7fa4c491a300 0x7fa3b8c36ac0 524288 13938329 1784048764 12076632033904650 12076632034089479 12076632034352038 12076632034402696
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 210 936686 936691 4194304 256 0 0 24 24 149696 0x7fa4c491aa00 0x7fa3b8c36b00 524288 9647066 1234926464 12076632034426060 12076632034604838 12076632034744357 12076632034748249
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 212 936686 936691 4194304 256 0 0 24 24 152192 0x7fa4c491a900 0x7fa3b8c36b40 524288 3497597 447756936 12076632034796669 12076632034959076 12076632035187236 12076632035237569
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 214 936686 936691 4194304 256 0 0 24 24 154176 0x7fa4c491a800 0x7fa3b8c36b80 524288 10935167 1399592344 12076632035275720 12076632035441315 12076632035577155 12076632035581098
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 936686 936691 4194304 256 0 0 20 24 155648 0x7fa4c491a700 0x7fa3b8c36bc0 524288 2487821 318415480 12076632035630039 12076632035796354 12076632036126913 12076632036176236
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 218 936686 936691 4194304 256 0 0 28 24 157632 0x7fa4c491a600 0x7fa3b8c36c00 524288 13487975 1726388348 12076632036200771 12076632036381632 12076632036638911 12076632036686435
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 220 936686 936691 4194304 256 0 0 24 24 159616 0x7fa4c491a500 0x7fa3b8c36c40 524288 10837100 1387119932 12076632036712363 12076632036887390 12076632037028510 12076632037032228
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 222 936686 936691 4194304 256 0 0 24 24 162368 0x7fa4c491a400 0x7fa3b8c36c80 524288 3418032 437393740 12076632037082782 12076632037247576 12076632037493816 12076632037520967
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 224 936686 936691 4194304 256 0 0 24 24 164608 0x7fa4c491a300 0x7fa3b8c36cc0 524288 9739267 1246664408 12076632037571831 12076632037734934 12076632037875574 12076632037878542
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 936686 936691 4194304 256 0 0 20 24 166336 0x7fa4c491aa00 0x7fa3b8c36d00 524288 2392954 306166508 12076632037926591 12076632038102133 12076632038479893 12076632038529072
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 228 936686 936691 4194304 256 0 0 28 24 168576 0x7fa4c491a900 0x7fa3b8c36d40 524288 11973629 1532529168 12076632038558877 12076632038733492 12076632038999891 12076632039047356
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 230 936686 936691 4194304 256 0 0 24 24 170816 0x7fa4c491a800 0x7fa3b8c36d80 524288 9364067 1198516552 12076632039084305 12076632039248691 12076632039388531 12076632039391546
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 232 936686 936691 4194304 256 0 0 24 24 174080 0x7fa4c491a700 0x7fa3b8c36dc0 524288 3430122 439102892 12076632039440808 12076632039615090 12076632039895090 12076632039917334
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 234 936686 936691 4194304 256 0 0 24 24 176576 0x7fa4c491a600 0x7fa3b8c36e00 524288 8700235 1113566308 12076632039971595 12076632040143409 12076632040283249 12076632040286551
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 936686 936691 4194304 256 0 0 20 24 177792 0x7fa4c491a500 0x7fa3b8c36e40 524288 2361529 302112880 12076632040336604 12076632040499408 12076632040947727 12076632040994448
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 238 936686 936691 4194304 256 0 0 28 24 180288 0x7fa4c491a400 0x7fa3b8c36e80 524288 10828654 1386005372 12076632041026187 12076632041206767 12076632041475406 12076632041522701
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 240 936686 936691 4194304 256 0 0 24 24 182784 0x7fa4c491a300 0x7fa3b8c36ec0 524288 7486533 958334076 12076632041549200 12076632041729006 12076632041869006 12076632041871770
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 242 936686 936691 4194304 256 0 0 24 24 186304 0x7fa4c491aa00 0x7fa3b8c36f00 524288 3449786 441526416 12076632041920781 12076632042089965 12076632042405644 12076632042455185
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 244 936686 936691 4194304 256 0 0 24 24 189312 0x7fa4c491a900 0x7fa3b8c36f40 524288 4153049 531489656 12076632042496352 12076632042660524 12076632042814124 12076632042817058
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 936686 936691 4194304 256 0 0 20 24 190784 0x7fa4c491a800 0x7fa3b8c36f80 524288 2386279 305359020 12076632042866139 12076632043043563 12076632043563402 12076632043613570
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 248 936686 936691 4194304 256 0 0 28 24 193792 0x7fa4c491a700 0x7fa3b8c36fc0 524288 7969875 1020139468 12076632043638085 12076632043818442 12076632044118121 12076632044167029
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 250 936686 936691 4194304 256 0 0 24 24 196800 0x7fa4c491a600 0x7fa3b8c37000 524288 3407015 435995508 12076632044190914 12076632044376840 12076632044532040 12076632044535024
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 252 936686 936691 4194304 256 0 0 24 24 201088 0x7fa4c491a500 0x7fa3b8c37040 524288 3473919 444763716 12076632044584306 12076632044752360 12076632045163879 12076632045187578
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 254 936686 936691 4194304 256 0 0 24 24 204608 0x7fa4c491a400 0x7fa3b8c37080 524288 3272315 418740372 12076632045246337 12076632045413478 12076632045590598 12076632045594014
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 936686 936691 4194304 256 0 0 20 24 206080 0x7fa4c491a300 0x7fa3b8c370c0 524288 2294983 293732696 12076632045643756 12076632045807557 12076632046418916 12076632046469482
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 258 936686 936691 4194304 256 0 0 28 24 209600 0x7fa4c491aa00 0x7fa3b8c37100 524288 4396336 562643820 12076632046492745 12076632046680036 12076632047007875 12076632047056684
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 260 936686 936691 4194304 256 0 0 24 24 213120 0x7fa4c491a900 0x7fa3b8c37140 524288 3356672 429650728 12076632047089546 12076632047260994 12076632047440194 12076632047443404
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 262 936686 936691 4194304 256 0 0 24 24 218176 0x7fa4c491a800 0x7fa3b8c37180 524288 3698088 473353416 12076632047493357 12076632047655714 12076632048111233 12076632048160708
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 264 936686 936691 4194304 256 0 0 24 24 222208 0x7fa4c491a700 0x7fa3b8c371c0 524288 3115363 398663524 12076632048197096 12076632048360512 12076632048560352 12076632048608731
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 936686 936691 4194304 256 0 0 20 24 223936 0x7fa4c491a600 0x7fa3b8c37200 524288 2353399 301326212 12076632048638747 12076632048819391 12076632049524030 12076632049574578
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 268 936686 936691 4194304 256 0 0 28 24 227968 0x7fa4c491a500 0x7fa3b8c37240 524288 3759297 481240984 12076632049597982 12076632049780989 12076632050154908 12076632050204870
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 270 936686 936691 4194304 256 0 0 24 24 232000 0x7fa4c491a400 0x7fa3b8c37280 524288 3337562 427130436 12076632050230498 12076632050409788 12076632050614107 12076632050661219
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 272 936686 936691 4194304 256 0 0 24 24 237824 0x7fa4c491a300 0x7fa3b8c372c0 524288 4483183 573876308 12076632050687679 12076632050863067 12076632051389626 12076632051440479
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 274 936686 936691 4194304 256 0 0 24 24 242368 0x7fa4c491aa00 0x7fa3b8c37300 524288 3191474 408441500 12076632051481154 12076632051645305 12076632051870265 12076632051916845
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 936686 936691 4194304 256 0 0 20 24 243584 0x7fa4c491a900 0x7fa3b8c37340 524288 2314303 296064368 12076632051943294 12076632052123864 12076632052925143 12076632052974532
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 278 936686 936691 4194304 256 0 0 28 24 248128 0x7fa4c491a800 0x7fa3b8c37380 524288 3330637 426356880 12076632052998307 12076632053183222 12076632053605461 12076632053655018
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 280 936686 936691 4194304 256 0 0 24 24 252672 0x7fa4c491a700 0x7fa3b8c373c0 524288 3178098 406760076 12076632053678402 12076632053858101 12076632054084020 12076632054134019
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 282 936686 936691 4194304 256 0 0 24 24 259264 0x7fa4c491a600 0x7fa3b8c37400 524288 4681601 599231332 12076632054161791 12076632054342900 12076632054940659 12076632054989581
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 284 936686 936691 4194304 256 0 0 24 24 264832 0x7fa4c491a500 0x7fa3b8c37440 524288 3300771 422651168 12076632055030657 12076632055198738 12076632055468177 12076632055518154
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 936686 936691 4194304 256 0 0 20 24 266304 0x7fa4c491a400 0x7fa3b8c37480 524288 2318734 296756940 12076632055546176 12076632055725617 12076632056713135 12076632056783137
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 288 936686 936691 4194304 256 0 0 28 24 271872 0x7fa4c491a300 0x7fa3b8c374c0 524288 3537473 452802788 12076632056818092 12076632056985934 12076632057502733 12076632057571854
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 290 936686 936691 4194304 256 0 0 24 24 277440 0x7fa4c491aa00 0x7fa3b8c37500 524288 3306185 423158436 12076632057603863 12076632057780493 12076632058053772 12076632058122468
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 292 936686 936691 4194304 256 0 0 12 24 279936 0x7fa4c491a900 0x7fa3b8c37540 524288 2211182 283065684 12076632058155329 12076632058324332 12076632059063530 12076632059131936
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 294 936686 936691 4194304 256 0 0 24 24 286528 0x7fa4c491a800 0x7fa3b8c37580 524288 3343527 427946244 12076632059175547 12076632059338729 12076632059655529 12076632059722444
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 936686 936691 4194304 256 0 0 20 24 288000 0x7fa4c491a700 0x7fa3b8c375c0 524288 2272972 290999932 12076632059747401 12076632059928968 12076632061102246 12076632061171640
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 298 936686 936691 4194304 256 0 0 32 24 294592 0x7fa4c491a600 0x7fa3b8c37600 524288 3455071 442240716 12076632061201365 12076632061387525 12076632061996164 12076632062064481
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 300 936686 936691 4194304 256 0 0 24 24 301184 0x7fa4c491a500 0x7fa3b8c37640 524288 3344160 428037120 12076632062093996 12076632062276483 12076632062596643 12076632062663014
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 302 936686 936691 4194304 256 0 0 12 24 304960 0x7fa4c491a400 0x7fa3b8c37680 524288 2215325 283556952 12076632062686568 12076632062871682 12076632063751680 12076632063820357
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 304 936686 936691 4194304 256 0 0 24 24 313600 0x7fa4c491a300 0x7fa3b8c376c0 524288 3332364 426460868 12076632063861203 12076632064032160 12076632064444959 12076632064513807
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 936686 936691 4194304 256 0 0 20 24 314816 0x7fa4c491aa00 0x7fa3b8c37700 524288 2296507 293956708 12076632064536629 12076632064719038 12076632066269595 12076632066338411
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 308 936686 936691 4194304 256 0 0 20 24 317568 0x7fa4c491a900 0x7fa3b8c37740 524288 2267842 290215000 12076632066369378 12076632066552955 12076632067348313 12076632067416947
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 310 936686 936691 4194304 256 0 0 12 24 320320 0x7fa4c491a800 0x7fa3b8c37780 524288 2156090 275898460 12076632067446322 12076632067628632 12076632068067031 12076632068135273
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 312 936686 936691 4194304 256 0 0 12 24 324096 0x7fa4c491a700 0x7fa3b8c377c0 524288 2232883 285813132 12076632068165610 12076632068346391 12076632069505588 12076632069574180
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 314 936686 936691 4194304 256 0 0 12 24 328896 0x7fa4c491a600 0x7fa3b8c37800 524288 2225959 285007468 12076632069618492 12076632069786388 12076632070573266 12076632070643479
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 936686 936691 4194304 256 0 0 20 24 330112 0x7fa4c491a500 0x7fa3b8c37840 524288 2662622 340672136 12076632070676410 12076632070851826 12076632073906059 12076632073976108
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 318 936686 936691 4194304 256 0 0 20 24 332864 0x7fa4c491a400 0x7fa3b8c37880 524288 2315165 296215488 12076632074010582 12076632074194539 12076632075739016 12076632075809107
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 320 936686 936691 4194304 256 0 0 12 24 335616 0x7fa4c491a300 0x7fa3b8c378c0 524288 2180249 278951920 12076632075842059 12076632076032295 12076632076822053 12076632076890990
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 322 936686 936691 4194304 256 0 0 12 24 339392 0x7fa4c491aa00 0x7fa3b8c37900 524288 2566313 328514036 12076632076915155 12076632077120613 12076632079403168 12076632079473193
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 324 936686 936691 4194304 256 0 0 12 24 344192 0x7fa4c491a900 0x7fa3b8c37940 524288 2340991 299613432 12076632079518137 12076632079686847 12076632081222524 12076632081291946
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 936686 936691 4194304 256 0 0 20 24 345408 0x7fa4c491a800 0x7fa3b8c37980 524288 2837649 363088816 12076632081322042 12076632081503164 12076632087560911 12076632087632931
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 328 936686 936691 4194304 256 0 0 20 24 348160 0x7fa4c491a700 0x7fa3b8c379c0 524288 3308509 423416964 12076632087658479 12076632087838991 12076632090885384 12076632090958577
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 330 936686 936691 4194304 256 0 0 12 24 350912 0x7fa4c491a600 0x7fa3b8c37a00 524288 2303191 294805748 12076632090985548 12076632091177224 12076632092716581 12076632092788411
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 332 936686 936691 4194304 256 0 0 12 24 0 0x7fa4c491a500 0x7fa3b8c37a40 524288 2535117 324431768 12076632092814990 12076632093004740 12076632097533531 12076632097603959
@@ -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",0,0,0,937062,937067,33554432,256,0,0,8,32,6464,0x0,0x7f30a5604180,499674,499674,16219,3997400,524288,371768834,3801967,0,1501859028,12076634246773666,12076634492293789,12076634492615709,12076634492722711
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,937062,937067,32768,256,0,0,24,24,12480,0x0,0x7f30a5635100,27467,27467,20214,219744,512,1126759,75366,0,4521000,12076634507281913,12076634507609674,12076634507615914,12076634507624380
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,937062,937067,4194304,256,0,0,24,24,12928,0x7f31b1191900,0x7f30a5635140,217853,217853,21633,1742832,65536,133671007,1576099,0,536498696,12076634507695903,12076634507934314,12076634508067113,12076634508071402
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,937062,937067,4194304,256,0,0,36,24,13632,0x7f31b1191800,0x7f30a5635180,389621,389621,26804,3116976,65536,253060814,2948271,0,1014058364,12076634508150749,12076634508354473,12076634508602952,12076634508672009
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,937062,937067,4194304,256,0,0,28,24,14080,0x7f31b1191700,0x7f30a56351c0,403772,403772,26436,3230184,65536,276105211,3052243,0,1106238632,12076634508705912,12076634508912072,12076634509168551,12076634509238653
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,937062,937067,4194304,256,0,0,24,24,14528,0x7f31b1191600,0x7f30a5635200,217957,217957,19106,1743664,65536,133545621,1580634,0,535998284,12076634509266064,12076634509473830,12076634509607270,12076634509610645
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,937062,937067,4194304,256,0,0,24,24,14976,0x7f31b1191500,0x7f30a5635240,229069,229069,19969,1832560,65536,121094689,1662134,0,486187148,12076634509672260,12076634509869669,12076634510009989,12076634510013484
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,937062,937067,4194304,256,0,0,24,24,15424,0x7f31b1191400,0x7f30a5635280,212108,212108,18602,1696872,65536,156194765,1531178,0,626596552,12076634510103422,12076634510288548,12076634510418468,12076634510421754
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,937062,937067,4194304,256,0,0,28,24,16128,0x7f31b1191300,0x7f30a56352c0,395493,395493,31193,3163952,65536,350214228,2994677,0,1402673352,12076634510485032,12076634510682148,12076634510933987,12076634510974372
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,937062,937067,4194304,256,0,0,28,24,16832,0x7f31b1191a00,0x7f30a5635300,467516,467516,17173,3740136,65536,304554434,3042045,0,1220032660,12076634511021389,12076634511221666,12076634511520386,12076634511586971
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,937062,937067,4194304,256,0,0,24,24,17536,0x7f31b1191900,0x7f30a5635340,225357,225357,22606,1802864,65536,126884404,1624746,0,509347128,12076634511614202,12076634511821665,12076634511958625,12076634511961738
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,937062,937067,4194304,256,0,0,24,24,18240,0x7f31b1191800,0x7f30a5635380,214853,214853,19943,1718832,65536,138156049,1552593,0,554439388,12076634512019917,12076634512227264,12076634512358624,12076634512362043
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,937062,937067,4194304,256,0,0,24,24,18944,0x7f31b1191700,0x7f30a56353c0,212085,212085,21709,1696688,65536,162677854,1518896,0,652530312,12076634512440970,12076634512621503,12076634512750303,12076634512753651
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,937062,937067,4194304,256,0,0,28,24,19904,0x7f31b1191600,0x7f30a5635400,448589,448589,14903,3588720,65536,352429805,2980195,0,1411536664,12076634512815597,12076634513007902,12076634513294302,12076634513361963
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,937062,937067,4194304,256,0,0,28,24,20608,0x7f31b1191500,0x7f30a5635440,398365,398365,30407,3186928,65536,322399376,3015454,0,1291412136,12076634513388011,12076634513596861,12076634513850621,12076634513916414
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,937062,937067,4194304,256,0,0,24,24,21312,0x7f31b1191400,0x7f30a5635480,212733,212733,21416,1701872,65536,152200936,1534437,0,610620496,12076634513941962,12076634514154300,12076634514284220,12076634514287725
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,937062,937067,4194304,256,0,0,24,24,22016,0x7f31b1191300,0x7f30a56354c0,212636,212636,21337,1701096,65536,160391048,1536825,0,643379376,12076634514348127,12076634514545339,12076634514675419,12076634514678532
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,937062,937067,4194304,256,0,0,24,24,22720,0x7f31b1191a00,0x7f30a5635500,222621,222621,21873,1780976,65536,144958356,1613854,0,581645868,12076634514752189,12076634514932378,12076634515069178,12076634515072334
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,937062,937067,4194304,256,0,0,28,24,23680,0x7f31b1191900,0x7f30a5635540,397556,397556,30136,3180456,65536,341121024,3002753,0,1366301448,12076634515133218,12076634515327737,12076634515581337,12076634515646482
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,937062,937067,4194304,256,0,0,28,24,24384,0x7f31b1191800,0x7f30a5635580,403172,403172,24087,3225384,65536,224707461,3040116,0,900648000,12076634515675667,12076634515871416,12076634516129336,12076634516199712
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,937062,937067,4194304,256,0,0,24,24,25088,0x7f31b1191700,0x7f30a56355c0,216284,216284,24062,1730280,65536,126988676,1563585,0,509770336,12076634516228164,12076634516426135,12076634516558295,12076634516561545
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,937062,937067,4194304,256,0,0,24,24,25792,0x7f31b1191600,0x7f30a5635600,219124,219124,22867,1753000,65536,136862429,1589426,0,549267012,12076634516622708,12076634516813174,12076634516948054,12076634516951169
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,937062,937067,4194304,256,0,0,24,24,26496,0x7f31b1191500,0x7f30a5635640,213709,213709,22349,1709680,65536,157553694,1533157,0,632031676,12076634517030537,12076634517211413,12076634517341493,12076634517344561
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,937062,937067,4194304,256,0,0,28,24,27712,0x7f31b1191400,0x7f30a5635680,399981,399981,28230,3199856,65536,292218439,3025047,0,1170691640,12076634517402739,12076634517594932,12076634517850932,12076634517917136
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,937062,937067,4194304,256,0,0,28,24,28416,0x7f31b1191300,0x7f30a56356c0,405413,405413,28751,3243312,65536,293488110,3058758,0,1175768556,12076634517942824,12076634518149171,12076634518407570,12076634518473942
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,937062,937067,4194304,256,0,0,24,24,29120,0x7f31b1191a00,0x7f30a5635700,210541,210541,18560,1684336,65536,158231458,1524200,0,634744128,12076634518498998,12076634518696210,12076634518825490,12076634518828672
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,937062,937067,4194304,256,0,0,24,24,30080,0x7f31b1191900,0x7f30a5635740,221165,221165,25093,1769328,65536,153672197,1587171,0,616501944,12076634518889094,12076634519077649,12076634519212209,12076634519215481
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,937062,937067,4194304,256,0,0,24,24,30784,0x7f31b1191800,0x7f30a5635780,214733,214733,20244,1717872,65536,146270057,1557059,0,586895320,12076634519290751,12076634519467568,12076634519599568,12076634519602501
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,937062,937067,4194304,256,0,0,28,24,32000,0x7f31b1191700,0x7f30a56357c0,395148,395148,31161,3161192,65536,348917173,2987788,0,1397488220,12076634519664046,12076634519856527,12076634520109807,12076634520179775
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,937062,937067,4194304,256,0,0,28,24,32960,0x7f31b1191600,0x7f30a5635800,391717,391717,30699,3133744,65536,352352859,2970795,0,1411229772,12076634520210833,12076634520405326,12076634520656205,12076634520723025
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,937062,937067,4194304,256,0,0,24,24,33920,0x7f31b1191500,0x7f30a5635840,211165,211165,22356,1689328,65536,159141992,1519622,0,638391120,12076634520747351,12076634520946445,12076634521075405,12076634521078877
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,937062,937067,4194304,256,0,0,24,24,34880,0x7f31b1191400,0x7f30a5635880,222669,222669,22358,1781360,65536,140744300,1613811,0,564813204,12076634521142015,12076634521321964,12076634521459724,12076634521462892
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,937062,937067,4194304,256,0,0,24,24,35840,0x7f31b1191300,0x7f30a56358c0,210276,210276,22634,1682216,65536,138811194,1514446,0,557073360,12076634521536088,12076634521712523,12076634521841163,12076634521844321
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,937062,937067,4194304,256,0,0,28,24,37312,0x7f31b1191a00,0x7f30a5635900,410381,410381,24119,3283056,65536,309213186,3095322,0,1238665668,12076634521904974,12076634522099402,12076634522362922,12076634522429620
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,937062,937067,4194304,256,0,0,28,24,38272,0x7f31b1191900,0x7f30a5635940,397700,397700,29036,3181608,65536,290946828,3013211,0,1165600192,12076634522455268,12076634522659721,12076634522913640,12076634522980154
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,937062,937067,4194304,256,0,0,24,24,39232,0x7f31b1191800,0x7f30a5635980,222484,222484,22018,1779880,65536,128990349,1612365,0,517801864,12076634523013546,12076634523210600,12076634523347879,12076634523351094
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,937062,937067,4194304,256,0,0,24,24,40192,0x7f31b1191700,0x7f30a56359c0,222764,222764,24204,1782120,65536,146331742,1615165,0,587163692,12076634523411156,12076634523601639,12076634523738919,12076634523742191
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,937062,937067,4194304,256,0,0,24,24,41152,0x7f31b1191600,0x7f30a5635a00,212021,212021,22550,1696176,65536,157151524,1525336,0,630423560,12076634523815207,12076634523991078,12076634524121478,12076634524125254
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,937062,937067,4194304,256,0,0,28,24,42624,0x7f31b1191500,0x7f30a5635a40,401045,401045,26402,3208368,65536,336390145,3004654,0,1347376740,12076634524185225,12076634524375077,12076634524632037,12076634524698570
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,937062,937067,4194304,256,0,0,28,24,43584,0x7f31b1191400,0x7f30a5635a80,401900,401900,26390,3215208,65536,295687943,3049472,0,1184568052,12076634524722816,12076634524918436,12076634525176195,12076634525244576
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,937062,937067,4194304,256,0,0,24,24,44544,0x7f31b1191300,0x7f30a5635ac0,211773,211773,25302,1694192,65536,150606101,1519106,0,604274304,12076634525273139,12076634525467875,12076634525597154,12076634525600558
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,937062,937067,4194304,256,0,0,24,24,45760,0x7f31b1191a00,0x7f30a5635b00,220996,220996,25671,1767976,65536,155539914,1586010,0,623980732,12076634525660279,12076634525852834,12076634525988034,12076634525991365
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,937062,937067,4194304,256,0,0,24,24,46720,0x7f31b1191900,0x7f30a5635b40,218309,218309,23155,1746480,65536,153186453,1572643,0,614577888,12076634526065333,12076634526243073,12076634526376673,12076634526380178
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,937062,937067,4194304,256,0,0,28,24,48448,0x7f31b1191800,0x7f30a5635b80,413652,413652,33352,3309224,65536,288767588,3135220,0,1156887128,12076634526440901,12076634526625632,12076634526892192,12076634526958564
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,937062,937067,4194304,256,0,0,28,24,49408,0x7f31b1191700,0x7f30a5635bc0,398316,398316,33638,3186536,65536,340782112,3013266,0,1364942872,12076634526986887,12076634527187231,12076634527441950,12076634527482839
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,937062,937067,4194304,256,0,0,24,24,50368,0x7f31b1191600,0x7f30a5635c00,205276,205276,21119,1642216,65536,171403607,1481515,0,687438856,12076634527516492,12076634527715070,12076634527841149,12076634527844392
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,937062,937067,4194304,256,0,0,24,24,51584,0x7f31b1191500,0x7f30a5635c40,220756,220756,26419,1766056,65536,159827176,1589517,0,641144504,12076634527905185,12076634528120349,12076634528256349,12076634528259995
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,937062,937067,4194304,256,0,0,24,24,52544,0x7f31b1191400,0x7f30a5635c80,214117,214117,22063,1712944,65536,148578942,1546808,0,596133776,12076634528333842,12076634528514748,12076634528646268,12076634528649429
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,937062,937067,4194304,256,0,0,28,24,54272,0x7f31b1191300,0x7f30a5635cc0,414036,414036,32477,3312296,65536,326939111,3126424,0,1309573220,12076634528709702,12076634528904027,12076634529170587,12076634529238565
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,937062,937067,4194304,256,0,0,28,24,55488,0x7f31b1191a00,0x7f30a5635d00,389733,389733,31059,3117872,65536,341729609,2953917,0,1368736252,12076634529266878,12076634529463066,12076634529713785,12076634529779682
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,937062,937067,4194304,256,0,0,24,24,56704,0x7f31b1191900,0x7f30a5635d40,219156,219156,22779,1753256,65536,151748826,1574610,0,608822620,12076634529804548,12076634530000025,12076634530134264,12076634530137818
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,937062,937067,4194304,256,0,0,24,24,58176,0x7f31b1191800,0x7f30a5635d80,223341,223341,26808,1786736,65536,159849644,1611787,0,641246944,12076634530199333,12076634530387384,12076634530525624,12076634530529216
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,937062,937067,4194304,256,0,0,24,24,59392,0x7f31b1191700,0x7f30a5635dc0,214917,214917,25443,1719344,65536,162346752,1524728,0,651208456,12076634530601581,12076634530778263,12076634530908023,12076634530911397
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,937062,937067,4194304,256,0,0,28,24,61376,0x7f31b1191600,0x7f30a5635e00,408484,408484,31258,3267880,65536,320329657,3092366,0,1283139824,12076634530971860,12076634531165142,12076634531428822,12076634531469916
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,937062,937067,4194304,256,0,0,28,24,62592,0x7f31b1191500,0x7f30a5635e40,392756,392756,33027,3142056,65536,334521193,2972456,0,1339901580,12076634531509049,12076634531687221,12076634531939700,12076634532015320
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,937062,937067,4194304,256,0,0,24,24,63808,0x7f31b1191400,0x7f30a5635e80,279308,279308,14600,2234472,65536,144221695,1546141,0,578708168,12076634532041669,12076634532250260,12076634532424979,12076634532428349
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,937062,937067,4194304,256,0,0,24,24,65280,0x7f31b1191300,0x7f30a5635ec0,226748,226748,29457,1813992,65536,178093356,1602668,0,714235712,12076634532488801,12076634532676339,12076634532814258,12076634532817633
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,937062,937067,4194304,256,0,0,24,24,66496,0x7f31b1191a00,0x7f30a5635f00,212613,212613,24369,1700912,65536,161056055,1531647,0,646065348,12076634532892883,12076634533076338,12076634533207058,12076634533210664
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,937062,937067,4194304,256,0,0,28,24,68480,0x7f31b1191900,0x7f30a5635f40,412309,412309,32858,3298480,65536,334313937,3122389,0,1339107212,12076634533272058,12076634533460977,12076634533726416,12076634533793017
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,937062,937067,4194304,256,0,0,28,24,69696,0x7f31b1191800,0x7f30a5635f80,398371,398371,32510,3186976,65536,340219487,3015834,0,1362692336,12076634533821500,12076634534015056,12076634534271375,12076634534338342
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,937062,937067,4194304,256,0,0,24,24,70912,0x7f31b1191700,0x7f30a5635fc0,228188,228188,26741,1825512,65536,149209986,1647545,0,598707016,12076634534364611,12076634534562895,12076634534702894,12076634534706386
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,937062,937067,4194304,256,0,0,24,24,72384,0x7f31b1191600,0x7f30a5636000,225708,225708,27996,1805672,65536,177250903,1624430,0,710843524,12076634534768331,12076634534956494,12076634535096813,12076634535100429
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,937062,937067,4194304,256,0,0,24,24,73600,0x7f31b1191500,0x7f30a5636040,211220,211220,22475,1689768,65536,160254032,1514284,0,642854776,12076634535174577,12076634535353933,12076634535483213,12076634535486688
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,937062,937067,4194304,256,0,0,28,24,75840,0x7f31b1191400,0x7f30a5636080,412789,412789,34054,3302320,65536,296733323,3121128,0,1188766220,12076634535547371,12076634535732812,12076634535999531,12076634536067077
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,937062,937067,4194304,256,0,0,28,24,77056,0x7f31b1191300,0x7f30a56360c0,398948,398948,26692,3191592,65536,249430262,3001335,0,999539228,12076634536092825,12076634536295051,12076634536551850,12076634536615818
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,937062,937067,4194304,256,0,0,24,24,78272,0x7f31b1191a00,0x7f30a5636100,219732,219732,21810,1757864,65536,146729488,1589753,0,588782344,12076634536640754,12076634536837610,12076634536973129,12076634536976529
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,937062,937067,4194304,256,0,0,24,24,80000,0x7f31b1191900,0x7f30a5636140,231853,231853,26909,1854832,65536,196977740,1689369,0,789781756,12076634537038584,12076634537226409,12076634537370248,12076634537373768
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,937062,937067,4194304,256,0,0,24,24,81216,0x7f31b1191800,0x7f30a5636180,217245,217245,22366,1737968,65536,149848899,1578330,0,601235936,12076634537446193,12076634537621608,12076634537755847,12076634537759095
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,937062,937067,4194304,256,0,0,28,24,83456,0x7f31b1191700,0x7f30a56361c0,412789,412789,33823,3302320,65536,328378877,3136724,0,1315331968,12076634537819016,12076634538011047,12076634538278246,12076634538344273
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,937062,937067,4194304,256,0,0,28,24,84928,0x7f31b1191600,0x7f30a5636200,443228,443228,14224,3545832,65536,352134637,2957912,0,1410361884,12076634538370261,12076634538570246,12076634538857285,12076634538923270
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,937062,937067,4194304,256,0,0,24,24,86400,0x7f31b1191500,0x7f30a5636240,222836,222836,24641,1782696,65536,145710036,1601147,0,584707564,12076634538947946,12076634539151204,12076634539287684,12076634539291164
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,937062,937067,4194304,256,0,0,24,24,88128,0x7f31b1191400,0x7f30a5636280,239925,239925,25988,1919408,65536,208509762,1760336,0,835909668,12076634539352438,12076634539539364,12076634539689443,12076634539692852
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,937062,937067,4194304,256,0,0,24,24,89600,0x7f31b1191300,0x7f30a56362c0,222461,222461,24485,1779696,65536,148799551,1614425,0,597037216,12076634539780374,12076634539956803,12076634540093762,12076634540097414
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,937062,937067,4194304,256,0,0,28,24,92096,0x7f31b1191a00,0x7f30a5636300,413860,413860,32816,3310888,65536,342079203,3146167,0,1370187588,12076634540157266,12076634540344802,12076634540613441,12076634540679657
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,937062,937067,4194304,256,0,0,28,24,93568,0x7f31b1191900,0x7f30a5636340,400508,400508,30364,3204072,65536,325601236,3033729,0,1304223612,12076634540707349,12076634540900960,12076634541159040,12076634541228759
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,937062,937067,4194304,256,0,0,24,24,95040,0x7f31b1191800,0x7f30a5636380,215420,215420,22810,1723368,65536,152585967,1559429,0,612212692,12076634541255168,12076634541456959,12076634541590079,12076634541593427
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,937062,937067,4194304,256,0,0,24,24,96768,0x7f31b1191700,0x7f30a56363c0,255541,255541,30610,2044336,65536,222286816,1859187,0,890991504,12076634541652958,12076634541839998,12076634541998398,12076634542006746
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,937062,937067,4194304,256,0,0,24,24,98240,0x7f31b1191600,0x7f30a5636400,216668,216668,22070,1733352,65536,155741010,1570265,0,624841512,12076634542076425,12076634542254077,12076634542388157,12076634542391301
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,937062,937067,4194304,256,0,0,28,24,100736,0x7f31b1191500,0x7f30a5636440,417628,417628,34074,3341032,65536,333216758,3118039,0,1334683008,12076634542450792,12076634542640317,12076634542910716,12076634542957294
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,937062,937067,4194304,256,0,0,28,24,102208,0x7f31b1191400,0x7f30a5636480,397324,397324,30824,3178600,65536,337128771,3018503,0,1350334456,12076634542981539,12076634543186555,12076634543443355,12076634543488522
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,937062,937067,4194304,256,0,0,24,24,103680,0x7f31b1191300,0x7f30a56364c0,225229,225229,24290,1801840,65536,142448607,1626904,0,571637828,12076634543530180,12076634543704954,12076634543843994,12076634543847129
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,937062,937067,4194304,256,0,0,24,24,105664,0x7f31b1191a00,0x7f30a5636500,262797,262797,28081,2102384,65536,233830271,1940837,0,937170592,12076634543909976,12076634544116153,12076634544281593,12076634544284773
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,937062,937067,4194304,256,0,0,24,24,107136,0x7f31b1191900,0x7f30a5636540,221141,221141,24416,1769136,65536,144513711,1597678,0,579896612,12076634544358721,12076634544537752,12076634544673752,12076634544677273
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,937062,937067,4194304,256,0,0,28,24,109888,0x7f31b1191800,0x7f30a5636580,408485,408485,36448,3267888,65536,324005800,3077103,0,1297869708,12076634544736423,12076634544931832,12076634545196471,12076634545265778
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,937062,937067,4194304,256,0,0,28,24,111360,0x7f31b1191700,0x7f30a56365c0,398084,398084,38085,3184680,65536,335870488,2989272,0,1345296084,12076634545291696,12076634545487190,12076634545741750,12076634545808177
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,937062,937067,4194304,256,0,0,24,24,112832,0x7f31b1191600,0x7f30a5636600,225389,225389,23366,1803120,65536,143201439,1633713,0,574668904,12076634545835267,12076634546034069,12076634546174229,12076634546177504
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,937062,937067,4194304,256,0,0,24,24,114816,0x7f31b1191500,0x7f30a5636640,274788,274788,30015,2198312,65536,245834907,2034390,0,985205140,12076634546240341,12076634546426388,12076634546599348,12076634546602735
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,937062,937067,4194304,256,0,0,24,24,116288,0x7f31b1191400,0x7f30a5636680,212845,212845,21768,1702768,65536,154990814,1519836,0,621814824,12076634546674859,12076634546851027,12076634546982387,12076634546985697
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,937062,937067,4194304,256,0,0,28,24,119040,0x7f31b1191300,0x7f30a56366c0,406924,406924,36478,3255400,65536,315620737,3056185,0,1264314736,12076634547046330,12076634547239506,12076634547502386,12076634547567880
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,937062,937067,4194304,256,0,0,28,24,120768,0x7f31b1191a00,0x7f30a5636700,395605,395605,32088,3164848,65536,318104197,2984256,0,1274235812,12076634547596163,12076634547788305,12076634548044305,12076634548112944
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,937062,937067,4194304,256,0,0,24,24,122496,0x7f31b1191900,0x7f30a5636740,228092,228092,25336,1824744,65536,143630960,1655089,0,576381056,12076634548138692,12076634548339344,12076634548480304,12076634548483744
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,937062,937067,4194304,256,0,0,24,24,124736,0x7f31b1191800,0x7f30a5636780,288765,288765,29964,2310128,65536,259925815,2149141,0,1041559524,12076634548543705,12076634548728143,12076634548911663,12076634548915016
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,937062,937067,4194304,256,0,0,24,24,126464,0x7f31b1191700,0x7f30a56367c0,226421,226421,25398,1811376,65536,145020314,1625891,0,581981220,12076634549021955,12076634549203822,12076634549343342,12076634549347000
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,937062,937067,4194304,256,0,0,20,24,127936,0x7f31b1191600,0x7f30a5636800,411885,411885,36923,3295088,65536,377379464,3118343,0,1511338396,12076634549406931,12076634549594221,12076634549861421,12076634549902813
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,937062,937067,4194304,256,0,0,28,24,129664,0x7f31b1191500,0x7f30a5636840,400772,400772,29019,3206184,65536,270661366,3012149,0,1084466864,12076634549939552,12076634550131340,12076634550390059,12076634550456674
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,937062,937067,4194304,256,0,0,24,24,131392,0x7f31b1191400,0x7f30a5636880,223493,223493,28641,1787952,65536,156747337,1596842,0,628841760,12076634550483403,12076634550681099,12076634550818218,12076634550821683
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,937062,937067,4194304,256,0,0,24,24,133632,0x7f31b1191300,0x7f30a56368c0,300748,300748,31432,2405992,65536,272500640,2248458,0,1091849984,12076634550885241,12076634551073738,12076634551264457,12076634551332072
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,937062,937067,4194304,256,0,0,24,24,135360,0x7f31b1191a00,0x7f30a5636900,221837,221837,24841,1774704,65536,154654268,1601667,0,620482812,12076634551376685,12076634551554377,12076634551691497,12076634551694897
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,937062,937067,4194304,256,0,0,20,24,136832,0x7f31b1191900,0x7f30a5636940,436893,436893,39784,3495152,65536,402285022,3324829,0,1610960776,12076634551755520,12076634551941416,12076634552225095,12076634552292028
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,937062,937067,4194304,256,0,0,28,24,138560,0x7f31b1191800,0x7f30a5636980,400429,400429,33584,3203440,65536,329960243,3008473,0,1321683344,12076634552320531,12076634552515655,12076634552773094,12076634552839366
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,937062,937067,4194304,256,0,0,24,24,140288,0x7f31b1191700,0x7f30a56369c0,220708,220708,27469,1765672,65536,151431805,1583632,0,607560160,12076634552864162,12076634553076133,12076634553212453,12076634553215966
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,937062,937067,4194304,256,0,0,24,24,142784,0x7f31b1191600,0x7f30a5636a00,330308,330308,32883,2642472,65536,300457787,2479819,0,1203689148,12076634553276469,12076634553467493,12076634553678052,12076634553744239
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,937062,937067,4194304,256,0,0,24,24,144768,0x7f31b1191500,0x7f30a5636a40,223524,223524,23556,1788200,65536,157776974,1611436,0,632997452,12076634553780316,12076634553964291,12076634554102531,12076634554106102
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,937062,937067,4194304,256,0,0,20,24,145728,0x7f31b1191400,0x7f30a5636a80,470173,470173,40408,3761392,65536,437901688,3595251,0,1753426996,12076634554166254,12076634554354531,12076634554661730,12076634554727688
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,937062,937067,4194304,256,0,0,28,24,147712,0x7f31b1191300,0x7f30a5636ac0,405245,405245,34161,3241968,65536,335140714,3063259,0,1342389428,12076634554754929,12076634554951169,12076634555213249,12076634555279745
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,937062,937067,4194304,256,0,0,24,24,149696,0x7f31b1191a00,0x7f30a5636b00,225836,225836,22182,1806696,65536,154006034,1634745,0,617898908,12076634555304291,12076634555503466,12076634555643946,12076634555651266
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,937062,937067,4194304,256,0,0,24,24,152192,0x7f31b1191900,0x7f30a5636b40,356653,356653,35781,2853232,65536,325389722,2683365,0,1303415364,12076634555706769,12076634555893704,12076634556121223,12076634556189638
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,937062,937067,4194304,256,0,0,24,24,154176,0x7f31b1191800,0x7f30a5636b80,218700,218700,25714,1749608,65536,154046907,1576350,0,618063224,12076634556229913,12076634556409383,12076634556544902,12076634556548375
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,937062,937067,4194304,256,0,0,20,24,155648,0x7f31b1191700,0x7f30a5636bc0,503797,503797,43958,4030384,65536,471894300,3865747,0,1889397832,12076634556611292,12076634556801222,12076634557130821,12076634557200308
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,937062,937067,4194304,256,0,0,28,24,157632,0x7f31b1191600,0x7f30a5636c00,407340,407340,28640,3258728,65536,312702803,3052368,0,1252629116,12076634557226436,12076634557424421,12076634557688420,12076634557729282
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,937062,937067,4194304,256,0,0,24,24,159616,0x7f31b1191500,0x7f30a5636c40,226132,226132,25877,1809064,65536,153078598,1635564,0,614185492,12076634557772462,12076634557950339,12076634558090179,12076634558093649
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,937062,937067,4194304,256,0,0,24,24,162368,0x7f31b1191400,0x7f30a5636c80,381924,381924,36449,3055400,65536,349844373,2887948,0,1401225252,12076634558156556,12076634558340738,12076634558586178,12076634558653100
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,937062,937067,4194304,256,0,0,24,24,164608,0x7f31b1191300,0x7f30a5636cc0,225636,225636,28452,1805096,65536,163004818,1620463,0,653901864,12076634558689598,12076634558868257,12076634559008577,12076634559012278
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,937062,937067,4194304,256,0,0,20,24,166336,0x7f31b1191a00,0x7f30a5636d00,575053,575053,46909,4600432,65536,542304783,4444623,0,2171037532,12076634559063984,12076634559260256,12076634559638336,12076634559704396
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,937062,937067,4194304,256,0,0,28,24,168576,0x7f31b1191900,0x7f30a5636d40,407580,407580,33723,3260648,65536,300540763,3069434,0,1203998740,12076634559729943,12076634559931455,12076634560195934,12076634560262333
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,937062,937067,4194304,256,0,0,24,24,170816,0x7f31b1191800,0x7f30a5636d80,221692,221692,25854,1773544,65536,161817687,1597624,0,649149348,12076634560287300,12076634560486494,12076634560624573,12076634560628034
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,937062,937067,4194304,256,0,0,24,24,174080,0x7f31b1191700,0x7f30a5636dc0,479652,479652,16068,3837224,65536,400919451,3297056,0,1605528676,12076634560680361,12076634560872413,12076634561182652,12076634561253146
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,937062,937067,4194304,256,0,0,24,24,176576,0x7f31b1191600,0x7f30a5636e00,226229,226229,27604,1809840,65536,171830292,1631065,0,689219544,12076634561291798,12076634561482171,12076634561622011,12076634561625890
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,937062,937067,4194304,256,0,0,20,24,177792,0x7f31b1191500,0x7f30a5636e40,642308,642308,49986,5138472,65536,610109508,4982908,0,2442259024,12076634561686523,12076634561873050,12076634562297370,12076634562320632
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,937062,937067,4194304,256,0,0,28,24,180288,0x7f31b1191400,0x7f30a5636e80,405085,405085,38149,3240688,65536,316171611,3009971,0,1266529976,12076634562375825,12076634562555289,12076634562816408,12076634562837233
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,937062,937067,4194304,256,0,0,24,24,182784,0x7f31b1191300,0x7f30a5636ec0,224084,224084,25472,1792680,65536,181419219,1619155,0,727554372,12076634562893057,12076634563075768,12076634563215447,12076634563219103
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,937062,937067,4194304,256,0,0,24,24,186304,0x7f31b1191a00,0x7f30a5636f00,486588,486588,42862,3892712,65536,454898081,3728515,0,1821450016,12076634563280988,12076634563480887,12076634563795926,12076634563817416
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,937062,937067,4194304,256,0,0,24,24,189312,0x7f31b1191900,0x7f30a5636f40,242541,242541,26466,1940336,65536,213332854,1779150,0,855228180,12076634563892296,12076634564077046,12076634564229205,12076634564232879
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,937062,937067,4194304,256,0,0,20,24,190784,0x7f31b1191800,0x7f30a5636f80,784108,784108,60015,6272872,65536,750338005,6105956,0,3003173004,12076634564285056,12076634564488245,12076634565005523,12076634565048666
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,937062,937067,4194304,256,0,0,28,24,193792,0x7f31b1191700,0x7f30a5636fc0,462325,462325,41381,3698608,65536,395240212,3527463,0,1582802604,12076634565094482,12076634565274643,12076634565577202,12076634565643924
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,937062,937067,4194304,256,0,0,24,24,196800,0x7f31b1191600,0x7f30a5637000,246109,246109,27784,1968880,65536,217168109,1806572,0,870553892,12076634565678829,12076634565865202,12076634566019761,12076634566023700
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,937062,937067,4194304,256,0,0,24,24,201088,0x7f31b1191500,0x7f30a5637040,592933,592933,48021,4743472,65536,560063963,4582944,0,2242112928,12076634566085235,12076634566269841,12076634566656240,12076634566723241
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,937062,937067,4194304,256,0,0,24,24,204608,0x7f31b1191400,0x7f30a5637080,280285,280285,32285,2242288,65536,249208230,2057641,0,998719992,12076634566764228,12076634566942639,12076634567118159,12076634567121853
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,937062,937067,4194304,256,0,0,20,24,206080,0x7f31b1191300,0x7f30a56370c0,941756,941756,14101,7534056,65536,890432974,7231462,0,3563553184,12076634567184139,12076634567381838,12076634568006157,12076634568057143
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,937062,937067,4194304,256,0,0,28,24,209600,0x7f31b1191a00,0x7f30a5637100,507660,507660,43040,4061288,65536,461305602,3890339,0,1847067668,12076634568083071,12076634568279756,12076634568611435,12076634568675082
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,937062,937067,4194304,256,0,0,24,24,213120,0x7f31b1191900,0x7f30a5637140,280405,280405,28596,2243248,65536,253336450,2087346,0,1015233064,12076634568699477,12076634568894155,12076634569072874,12076634569076559
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,937062,937067,4194304,256,0,0,24,24,218176,0x7f31b1191800,0x7f30a5637180,697597,697597,54537,5580784,65536,664191411,5417658,0,2658618900,12076634569137282,12076634569324714,12076634569780713,12076634569820142
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,937062,937067,4194304,256,0,0,24,24,222208,0x7f31b1191700,0x7f30a56371c0,311908,311908,30116,2495272,65536,284878944,2343878,0,1141402000,12076634569871588,12076634570055592,12076634570255592,12076634570322897
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,937062,937067,4194304,256,0,0,20,24,223936,0x7f31b1191600,0x7f30a5637200,1074565,1074565,15319,8596528,65536,1026825089,8361806,0,4109121200,12076634570348595,12076634570543431,12076634571254629,12076634571321024
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,937062,937067,4194304,256,0,0,28,24,227968,0x7f31b1191500,0x7f30a5637240,569653,569653,48021,4557232,65536,530371934,4383864,0,2123328560,12076634571346331,12076634571549829,12076634571923908,12076634571989848
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,937062,937067,4194304,256,0,0,24,24,232000,0x7f31b1191400,0x7f30a5637280,317245,317245,31036,2537968,65536,289326641,2381524,0,1159204808,12076634572019904,12076634572227907,12076634572431907,12076634572500057
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,937062,937067,4194304,256,0,0,24,24,237824,0x7f31b1191300,0x7f30a56372c0,802213,802213,60272,6417712,65536,768040034,6253577,0,3074015504,12076634572524202,12076634572719586,12076634573245505,12076634573312158
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,937062,937067,4194304,256,0,0,24,24,242368,0x7f31b1191a00,0x7f30a5637300,347797,347797,32627,2782384,65536,318789642,2623936,0,1277049252,12076634573353665,12076634573529664,12076634573753184,12076634573818800
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,937062,937067,4194304,256,0,0,20,24,243584,0x7f31b1191900,0x7f30a5637340,1208453,1208453,86374,9667632,65536,1168332366,9488416,0,4675150496,12076634573846241,12076634574053983,12076634574853821,12076634574922784
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,937062,937067,4194304,256,0,0,28,24,248128,0x7f31b1191800,0x7f30a5637380,638796,638796,50862,5110376,65536,604054320,4952300,0,2418060228,12076634574954663,12076634575159741,12076634575582300,12076634575648644
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,937062,937067,4194304,256,0,0,24,24,252672,0x7f31b1191700,0x7f30a56373c0,353580,353580,33948,2828648,65536,324112464,2665953,0,1298340420,12076634575673781,12076634575870139,12076634576097178,12076634576165074
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,937062,937067,4194304,256,0,0,24,24,259264,0x7f31b1191600,0x7f30a5637400,907972,907972,66668,7263784,65536,871808204,7100172,0,3489082580,12076634576192956,12076634576392698,12076634576989176,12076634577055932
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,937062,937067,4194304,256,0,0,24,24,264832,0x7f31b1191500,0x7f30a5637440,420029,420029,39580,3360240,65536,386607378,3170786,0,1548333812,12076634577092850,12076634577279576,12076634577549015,12076634577615372
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,937062,937067,4194304,256,0,0,20,24,266304,0x7f31b1191400,0x7f30a5637480,1486188,1486188,99240,11889512,65536,1446440968,11735967,0,5787585524,12076634577639457,12076634577835895,12076634578822292,12076634578892327
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,937062,937067,4194304,256,0,0,28,24,271872,0x7f31b1191300,0x7f30a56374c0,779469,779469,62018,6235760,65536,741190979,6050695,0,2966600364,12076634578918406,12076634579119252,12076634579634931,12076634579684581
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,937062,937067,4194304,256,0,0,24,24,277440,0x7f31b1191a00,0x7f30a5637500,421452,421452,38444,3371624,65536,390033242,3211048,0,1562019048,12076634579709507,12076634579904850,12076634580177649,12076634580247919
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,937062,937067,4194304,256,0,0,12,24,279936,0x7f31b1191900,0x7f30a5637540,1125589,1125589,79521,9004720,65536,1088541766,8842982,0,4355992024,12076634580276031,12076634580473649,12076634581212847,12076634581268868
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,937062,937067,4194304,256,0,0,24,24,286528,0x7f31b1191800,0x7f30a5637580,487197,487197,42516,3897584,65536,454902748,3736289,0,1821503676,12076634581309874,12076634581489006,12076634581805326,12076634581854848
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,937062,937067,4194304,256,0,0,20,24,288000,0x7f31b1191700,0x7f30a56375c0,1768453,1768453,117917,14147632,65536,1724990770,13979184,0,6901783928,12076634581883371,12076634582092845,12076634583267082,12076634583563887
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,937062,937067,4194304,256,0,0,32,24,294592,0x7f31b1191600,0x7f30a5637600,918692,918692,64768,7349544,65536,807675935,7172718,0,3232557552,12076634583598371,12076634583798721,12076634584410400,12076634584459012
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,937062,937067,4194304,256,0,0,24,24,301184,0x7f31b1191500,0x7f30a5637640,495188,495188,44861,3961512,65536,462565391,3791743,0,1852172552,12076634584494178,12076634584679519,12076634585000798,12076634585094735
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,937062,937067,4194304,256,0,0,12,24,304960,0x7f31b1191400,0x7f30a5637680,1336324,1336324,91200,10690600,65536,1298621629,10526806,0,5196313352,12076634585122847,12076634585329598,12076634586208316,12076634586259401
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,937062,937067,4194304,256,0,0,24,24,313600,0x7f31b1191300,0x7f30a56376c0,630380,630380,53869,5043048,65536,590581195,4863819,0,2364224928,12076634586306950,12076634586488795,12076634586899354,12076634586946790
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,937062,937067,4194304,256,0,0,20,24,314816,0x7f31b1191a00,0x7f30a5637700,2331940,2331940,149601,18655528,65536,2284557933,18495718,0,9140053388,12076634586979761,12076634587190394,12076634588740950,12076634588791461
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,937062,937067,4194304,256,0,0,20,24,317568,0x7f31b1191900,0x7f30a5637740,1199868,1199868,85074,9598952,65536,1161498246,9433358,0,4647813612,12076634588825635,12076634589030229,12076634589826548,12076634589875217
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,937062,937067,4194304,256,0,0,12,24,320320,0x7f31b1191800,0x7f30a5637780,639124,639124,50051,5113000,65536,608084295,4952297,0,2434171872,12076634589900133,12076634590105267,12076634590520306,12076634590569148
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,937062,937067,4194304,256,0,0,12,24,324096,0x7f31b1191700,0x7f30a56377c0,1757892,1757892,117158,14063144,65536,1714873517,13896555,0,6861319168,12076634590598723,12076634590790705,12076634591950063,12076634592004989
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,937062,937067,4194304,256,0,0,12,24,328896,0x7f31b1191600,0x7f30a5637800,1197780,1197780,82504,9582248,65536,1162231712,9420247,0,4650752948,12076634592045584,12076634592226382,12076634593012780,12076634593059921
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,937062,937067,4194304,256,0,0,20,24,330112,0x7f31b1191500,0x7f30a5637840,4583812,4583812,211273,36670504,65536,4515494636,36504397,0,18063799832,12076634593107028,12076634593282380,12076634596337893,12076634596388553
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,937062,937067,4194304,256,0,0,20,24,332864,0x7f31b1191400,0x7f30a5637880,2324436,2324436,151493,18595496,65536,2275127854,18421263,0,9102333000,12076634596420652,12076634596617732,12076634598164129,12076634598235348
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,937062,937067,4194304,256,0,0,12,24,335616,0x7f31b1191300,0x7f30a56378c0,1201508,1201508,82495,9612072,65536,1164122494,9454092,0,4658313948,12076634598267928,12076634598462688,12076634599253246,12076634599321308
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,937062,937067,4194304,256,0,0,12,24,339392,0x7f31b1191a00,0x7f30a5637900,3443268,3443268,214620,27546152,65536,3385357309,27381420,0,13543259488,12076634599342307,12076634599558206,12076634601841081,12076634601909913
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,937062,937067,4194304,256,0,0,12,24,344192,0x7f31b1191900,0x7f30a5637940,2323188,2323188,149197,18585512,65536,2274824901,18413418,0,9101128852,12076634601955628,12076634602146200,12076634603681556,12076634603750837
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,937062,937067,4194304,256,0,0,20,24,345408,0x7f31b1191800,0x7f30a5637980,9085596,9085596,472686,72684776,65536,8976560945,72523826,0,35908064460,12076634603782336,12076634603982356,12076634610042502,12076634610114464
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,937062,937067,4194304,256,0,0,20,24,348160,0x7f31b1191700,0x7f30a56379c0,4572572,4572572,211846,36580584,65536,4502571004,36416224,0,18012108720,12076634610150401,12076634610350021,12076634613397535,12076634613464596
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,937062,937067,4194304,256,0,0,12,24,350912,0x7f31b1191600,0x7f30a5637a00,2327092,2327092,149864,18616744,65536,2280060719,18455117,0,9122067764,12076634613497297,12076634613694974,12076634615234810,12076634615302405
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,937062,937067,4194304,256,0,0,12,24,0,0x7f31b1191500,0x7f30a5637a40,6811828,6811828,339834,54494632,65536,6722926938,54334488,0,26893535824,12076634615338832,12076634615533667,12076634620063098,12076634620137478
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 937062 937067 33554432 256 0 0 8 32 6464 0x0 0x7f30a5604180 499674 499674 16219 3997400 524288 371768834 3801967 0 1501859028 12076634246773666 12076634492293789 12076634492615709 12076634492722711
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 937062 937067 32768 256 0 0 24 24 12480 0x0 0x7f30a5635100 27467 27467 20214 219744 512 1126759 75366 0 4521000 12076634507281913 12076634507609674 12076634507615914 12076634507624380
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 4 937062 937067 4194304 256 0 0 24 24 12928 0x7f31b1191900 0x7f30a5635140 217853 217853 21633 1742832 65536 133671007 1576099 0 536498696 12076634507695903 12076634507934314 12076634508067113 12076634508071402
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 937062 937067 4194304 256 0 0 36 24 13632 0x7f31b1191800 0x7f30a5635180 389621 389621 26804 3116976 65536 253060814 2948271 0 1014058364 12076634508150749 12076634508354473 12076634508602952 12076634508672009
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 8 937062 937067 4194304 256 0 0 28 24 14080 0x7f31b1191700 0x7f30a56351c0 403772 403772 26436 3230184 65536 276105211 3052243 0 1106238632 12076634508705912 12076634508912072 12076634509168551 12076634509238653
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 10 937062 937067 4194304 256 0 0 24 24 14528 0x7f31b1191600 0x7f30a5635200 217957 217957 19106 1743664 65536 133545621 1580634 0 535998284 12076634509266064 12076634509473830 12076634509607270 12076634509610645
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 12 937062 937067 4194304 256 0 0 24 24 14976 0x7f31b1191500 0x7f30a5635240 229069 229069 19969 1832560 65536 121094689 1662134 0 486187148 12076634509672260 12076634509869669 12076634510009989 12076634510013484
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 14 937062 937067 4194304 256 0 0 24 24 15424 0x7f31b1191400 0x7f30a5635280 212108 212108 18602 1696872 65536 156194765 1531178 0 626596552 12076634510103422 12076634510288548 12076634510418468 12076634510421754
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 937062 937067 4194304 256 0 0 28 24 16128 0x7f31b1191300 0x7f30a56352c0 395493 395493 31193 3163952 65536 350214228 2994677 0 1402673352 12076634510485032 12076634510682148 12076634510933987 12076634510974372
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 18 937062 937067 4194304 256 0 0 28 24 16832 0x7f31b1191a00 0x7f30a5635300 467516 467516 17173 3740136 65536 304554434 3042045 0 1220032660 12076634511021389 12076634511221666 12076634511520386 12076634511586971
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 20 937062 937067 4194304 256 0 0 24 24 17536 0x7f31b1191900 0x7f30a5635340 225357 225357 22606 1802864 65536 126884404 1624746 0 509347128 12076634511614202 12076634511821665 12076634511958625 12076634511961738
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 22 937062 937067 4194304 256 0 0 24 24 18240 0x7f31b1191800 0x7f30a5635380 214853 214853 19943 1718832 65536 138156049 1552593 0 554439388 12076634512019917 12076634512227264 12076634512358624 12076634512362043
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 24 937062 937067 4194304 256 0 0 24 24 18944 0x7f31b1191700 0x7f30a56353c0 212085 212085 21709 1696688 65536 162677854 1518896 0 652530312 12076634512440970 12076634512621503 12076634512750303 12076634512753651
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 937062 937067 4194304 256 0 0 28 24 19904 0x7f31b1191600 0x7f30a5635400 448589 448589 14903 3588720 65536 352429805 2980195 0 1411536664 12076634512815597 12076634513007902 12076634513294302 12076634513361963
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 28 937062 937067 4194304 256 0 0 28 24 20608 0x7f31b1191500 0x7f30a5635440 398365 398365 30407 3186928 65536 322399376 3015454 0 1291412136 12076634513388011 12076634513596861 12076634513850621 12076634513916414
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 30 937062 937067 4194304 256 0 0 24 24 21312 0x7f31b1191400 0x7f30a5635480 212733 212733 21416 1701872 65536 152200936 1534437 0 610620496 12076634513941962 12076634514154300 12076634514284220 12076634514287725
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 32 937062 937067 4194304 256 0 0 24 24 22016 0x7f31b1191300 0x7f30a56354c0 212636 212636 21337 1701096 65536 160391048 1536825 0 643379376 12076634514348127 12076634514545339 12076634514675419 12076634514678532
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 34 937062 937067 4194304 256 0 0 24 24 22720 0x7f31b1191a00 0x7f30a5635500 222621 222621 21873 1780976 65536 144958356 1613854 0 581645868 12076634514752189 12076634514932378 12076634515069178 12076634515072334
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 937062 937067 4194304 256 0 0 28 24 23680 0x7f31b1191900 0x7f30a5635540 397556 397556 30136 3180456 65536 341121024 3002753 0 1366301448 12076634515133218 12076634515327737 12076634515581337 12076634515646482
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 38 937062 937067 4194304 256 0 0 28 24 24384 0x7f31b1191800 0x7f30a5635580 403172 403172 24087 3225384 65536 224707461 3040116 0 900648000 12076634515675667 12076634515871416 12076634516129336 12076634516199712
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 40 937062 937067 4194304 256 0 0 24 24 25088 0x7f31b1191700 0x7f30a56355c0 216284 216284 24062 1730280 65536 126988676 1563585 0 509770336 12076634516228164 12076634516426135 12076634516558295 12076634516561545
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 42 937062 937067 4194304 256 0 0 24 24 25792 0x7f31b1191600 0x7f30a5635600 219124 219124 22867 1753000 65536 136862429 1589426 0 549267012 12076634516622708 12076634516813174 12076634516948054 12076634516951169
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 44 937062 937067 4194304 256 0 0 24 24 26496 0x7f31b1191500 0x7f30a5635640 213709 213709 22349 1709680 65536 157553694 1533157 0 632031676 12076634517030537 12076634517211413 12076634517341493 12076634517344561
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 937062 937067 4194304 256 0 0 28 24 27712 0x7f31b1191400 0x7f30a5635680 399981 399981 28230 3199856 65536 292218439 3025047 0 1170691640 12076634517402739 12076634517594932 12076634517850932 12076634517917136
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 48 937062 937067 4194304 256 0 0 28 24 28416 0x7f31b1191300 0x7f30a56356c0 405413 405413 28751 3243312 65536 293488110 3058758 0 1175768556 12076634517942824 12076634518149171 12076634518407570 12076634518473942
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 50 937062 937067 4194304 256 0 0 24 24 29120 0x7f31b1191a00 0x7f30a5635700 210541 210541 18560 1684336 65536 158231458 1524200 0 634744128 12076634518498998 12076634518696210 12076634518825490 12076634518828672
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 52 937062 937067 4194304 256 0 0 24 24 30080 0x7f31b1191900 0x7f30a5635740 221165 221165 25093 1769328 65536 153672197 1587171 0 616501944 12076634518889094 12076634519077649 12076634519212209 12076634519215481
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 54 937062 937067 4194304 256 0 0 24 24 30784 0x7f31b1191800 0x7f30a5635780 214733 214733 20244 1717872 65536 146270057 1557059 0 586895320 12076634519290751 12076634519467568 12076634519599568 12076634519602501
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 937062 937067 4194304 256 0 0 28 24 32000 0x7f31b1191700 0x7f30a56357c0 395148 395148 31161 3161192 65536 348917173 2987788 0 1397488220 12076634519664046 12076634519856527 12076634520109807 12076634520179775
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 58 937062 937067 4194304 256 0 0 28 24 32960 0x7f31b1191600 0x7f30a5635800 391717 391717 30699 3133744 65536 352352859 2970795 0 1411229772 12076634520210833 12076634520405326 12076634520656205 12076634520723025
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 60 937062 937067 4194304 256 0 0 24 24 33920 0x7f31b1191500 0x7f30a5635840 211165 211165 22356 1689328 65536 159141992 1519622 0 638391120 12076634520747351 12076634520946445 12076634521075405 12076634521078877
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 62 937062 937067 4194304 256 0 0 24 24 34880 0x7f31b1191400 0x7f30a5635880 222669 222669 22358 1781360 65536 140744300 1613811 0 564813204 12076634521142015 12076634521321964 12076634521459724 12076634521462892
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 64 937062 937067 4194304 256 0 0 24 24 35840 0x7f31b1191300 0x7f30a56358c0 210276 210276 22634 1682216 65536 138811194 1514446 0 557073360 12076634521536088 12076634521712523 12076634521841163 12076634521844321
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 937062 937067 4194304 256 0 0 28 24 37312 0x7f31b1191a00 0x7f30a5635900 410381 410381 24119 3283056 65536 309213186 3095322 0 1238665668 12076634521904974 12076634522099402 12076634522362922 12076634522429620
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 68 937062 937067 4194304 256 0 0 28 24 38272 0x7f31b1191900 0x7f30a5635940 397700 397700 29036 3181608 65536 290946828 3013211 0 1165600192 12076634522455268 12076634522659721 12076634522913640 12076634522980154
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 70 937062 937067 4194304 256 0 0 24 24 39232 0x7f31b1191800 0x7f30a5635980 222484 222484 22018 1779880 65536 128990349 1612365 0 517801864 12076634523013546 12076634523210600 12076634523347879 12076634523351094
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 72 937062 937067 4194304 256 0 0 24 24 40192 0x7f31b1191700 0x7f30a56359c0 222764 222764 24204 1782120 65536 146331742 1615165 0 587163692 12076634523411156 12076634523601639 12076634523738919 12076634523742191
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 74 937062 937067 4194304 256 0 0 24 24 41152 0x7f31b1191600 0x7f30a5635a00 212021 212021 22550 1696176 65536 157151524 1525336 0 630423560 12076634523815207 12076634523991078 12076634524121478 12076634524125254
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 937062 937067 4194304 256 0 0 28 24 42624 0x7f31b1191500 0x7f30a5635a40 401045 401045 26402 3208368 65536 336390145 3004654 0 1347376740 12076634524185225 12076634524375077 12076634524632037 12076634524698570
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 78 937062 937067 4194304 256 0 0 28 24 43584 0x7f31b1191400 0x7f30a5635a80 401900 401900 26390 3215208 65536 295687943 3049472 0 1184568052 12076634524722816 12076634524918436 12076634525176195 12076634525244576
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 80 937062 937067 4194304 256 0 0 24 24 44544 0x7f31b1191300 0x7f30a5635ac0 211773 211773 25302 1694192 65536 150606101 1519106 0 604274304 12076634525273139 12076634525467875 12076634525597154 12076634525600558
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 82 937062 937067 4194304 256 0 0 24 24 45760 0x7f31b1191a00 0x7f30a5635b00 220996 220996 25671 1767976 65536 155539914 1586010 0 623980732 12076634525660279 12076634525852834 12076634525988034 12076634525991365
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 84 937062 937067 4194304 256 0 0 24 24 46720 0x7f31b1191900 0x7f30a5635b40 218309 218309 23155 1746480 65536 153186453 1572643 0 614577888 12076634526065333 12076634526243073 12076634526376673 12076634526380178
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 937062 937067 4194304 256 0 0 28 24 48448 0x7f31b1191800 0x7f30a5635b80 413652 413652 33352 3309224 65536 288767588 3135220 0 1156887128 12076634526440901 12076634526625632 12076634526892192 12076634526958564
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 88 937062 937067 4194304 256 0 0 28 24 49408 0x7f31b1191700 0x7f30a5635bc0 398316 398316 33638 3186536 65536 340782112 3013266 0 1364942872 12076634526986887 12076634527187231 12076634527441950 12076634527482839
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 90 937062 937067 4194304 256 0 0 24 24 50368 0x7f31b1191600 0x7f30a5635c00 205276 205276 21119 1642216 65536 171403607 1481515 0 687438856 12076634527516492 12076634527715070 12076634527841149 12076634527844392
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 92 937062 937067 4194304 256 0 0 24 24 51584 0x7f31b1191500 0x7f30a5635c40 220756 220756 26419 1766056 65536 159827176 1589517 0 641144504 12076634527905185 12076634528120349 12076634528256349 12076634528259995
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 94 937062 937067 4194304 256 0 0 24 24 52544 0x7f31b1191400 0x7f30a5635c80 214117 214117 22063 1712944 65536 148578942 1546808 0 596133776 12076634528333842 12076634528514748 12076634528646268 12076634528649429
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 937062 937067 4194304 256 0 0 28 24 54272 0x7f31b1191300 0x7f30a5635cc0 414036 414036 32477 3312296 65536 326939111 3126424 0 1309573220 12076634528709702 12076634528904027 12076634529170587 12076634529238565
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 98 937062 937067 4194304 256 0 0 28 24 55488 0x7f31b1191a00 0x7f30a5635d00 389733 389733 31059 3117872 65536 341729609 2953917 0 1368736252 12076634529266878 12076634529463066 12076634529713785 12076634529779682
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 100 937062 937067 4194304 256 0 0 24 24 56704 0x7f31b1191900 0x7f30a5635d40 219156 219156 22779 1753256 65536 151748826 1574610 0 608822620 12076634529804548 12076634530000025 12076634530134264 12076634530137818
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 102 937062 937067 4194304 256 0 0 24 24 58176 0x7f31b1191800 0x7f30a5635d80 223341 223341 26808 1786736 65536 159849644 1611787 0 641246944 12076634530199333 12076634530387384 12076634530525624 12076634530529216
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 104 937062 937067 4194304 256 0 0 24 24 59392 0x7f31b1191700 0x7f30a5635dc0 214917 214917 25443 1719344 65536 162346752 1524728 0 651208456 12076634530601581 12076634530778263 12076634530908023 12076634530911397
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 937062 937067 4194304 256 0 0 28 24 61376 0x7f31b1191600 0x7f30a5635e00 408484 408484 31258 3267880 65536 320329657 3092366 0 1283139824 12076634530971860 12076634531165142 12076634531428822 12076634531469916
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 108 937062 937067 4194304 256 0 0 28 24 62592 0x7f31b1191500 0x7f30a5635e40 392756 392756 33027 3142056 65536 334521193 2972456 0 1339901580 12076634531509049 12076634531687221 12076634531939700 12076634532015320
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 110 937062 937067 4194304 256 0 0 24 24 63808 0x7f31b1191400 0x7f30a5635e80 279308 279308 14600 2234472 65536 144221695 1546141 0 578708168 12076634532041669 12076634532250260 12076634532424979 12076634532428349
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 112 937062 937067 4194304 256 0 0 24 24 65280 0x7f31b1191300 0x7f30a5635ec0 226748 226748 29457 1813992 65536 178093356 1602668 0 714235712 12076634532488801 12076634532676339 12076634532814258 12076634532817633
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 114 937062 937067 4194304 256 0 0 24 24 66496 0x7f31b1191a00 0x7f30a5635f00 212613 212613 24369 1700912 65536 161056055 1531647 0 646065348 12076634532892883 12076634533076338 12076634533207058 12076634533210664
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 937062 937067 4194304 256 0 0 28 24 68480 0x7f31b1191900 0x7f30a5635f40 412309 412309 32858 3298480 65536 334313937 3122389 0 1339107212 12076634533272058 12076634533460977 12076634533726416 12076634533793017
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 118 937062 937067 4194304 256 0 0 28 24 69696 0x7f31b1191800 0x7f30a5635f80 398371 398371 32510 3186976 65536 340219487 3015834 0 1362692336 12076634533821500 12076634534015056 12076634534271375 12076634534338342
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 120 937062 937067 4194304 256 0 0 24 24 70912 0x7f31b1191700 0x7f30a5635fc0 228188 228188 26741 1825512 65536 149209986 1647545 0 598707016 12076634534364611 12076634534562895 12076634534702894 12076634534706386
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 122 937062 937067 4194304 256 0 0 24 24 72384 0x7f31b1191600 0x7f30a5636000 225708 225708 27996 1805672 65536 177250903 1624430 0 710843524 12076634534768331 12076634534956494 12076634535096813 12076634535100429
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 124 937062 937067 4194304 256 0 0 24 24 73600 0x7f31b1191500 0x7f30a5636040 211220 211220 22475 1689768 65536 160254032 1514284 0 642854776 12076634535174577 12076634535353933 12076634535483213 12076634535486688
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 937062 937067 4194304 256 0 0 28 24 75840 0x7f31b1191400 0x7f30a5636080 412789 412789 34054 3302320 65536 296733323 3121128 0 1188766220 12076634535547371 12076634535732812 12076634535999531 12076634536067077
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 128 937062 937067 4194304 256 0 0 28 24 77056 0x7f31b1191300 0x7f30a56360c0 398948 398948 26692 3191592 65536 249430262 3001335 0 999539228 12076634536092825 12076634536295051 12076634536551850 12076634536615818
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 130 937062 937067 4194304 256 0 0 24 24 78272 0x7f31b1191a00 0x7f30a5636100 219732 219732 21810 1757864 65536 146729488 1589753 0 588782344 12076634536640754 12076634536837610 12076634536973129 12076634536976529
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 132 937062 937067 4194304 256 0 0 24 24 80000 0x7f31b1191900 0x7f30a5636140 231853 231853 26909 1854832 65536 196977740 1689369 0 789781756 12076634537038584 12076634537226409 12076634537370248 12076634537373768
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 134 937062 937067 4194304 256 0 0 24 24 81216 0x7f31b1191800 0x7f30a5636180 217245 217245 22366 1737968 65536 149848899 1578330 0 601235936 12076634537446193 12076634537621608 12076634537755847 12076634537759095
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 937062 937067 4194304 256 0 0 28 24 83456 0x7f31b1191700 0x7f30a56361c0 412789 412789 33823 3302320 65536 328378877 3136724 0 1315331968 12076634537819016 12076634538011047 12076634538278246 12076634538344273
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 138 937062 937067 4194304 256 0 0 28 24 84928 0x7f31b1191600 0x7f30a5636200 443228 443228 14224 3545832 65536 352134637 2957912 0 1410361884 12076634538370261 12076634538570246 12076634538857285 12076634538923270
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 140 937062 937067 4194304 256 0 0 24 24 86400 0x7f31b1191500 0x7f30a5636240 222836 222836 24641 1782696 65536 145710036 1601147 0 584707564 12076634538947946 12076634539151204 12076634539287684 12076634539291164
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 142 937062 937067 4194304 256 0 0 24 24 88128 0x7f31b1191400 0x7f30a5636280 239925 239925 25988 1919408 65536 208509762 1760336 0 835909668 12076634539352438 12076634539539364 12076634539689443 12076634539692852
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 144 937062 937067 4194304 256 0 0 24 24 89600 0x7f31b1191300 0x7f30a56362c0 222461 222461 24485 1779696 65536 148799551 1614425 0 597037216 12076634539780374 12076634539956803 12076634540093762 12076634540097414
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 937062 937067 4194304 256 0 0 28 24 92096 0x7f31b1191a00 0x7f30a5636300 413860 413860 32816 3310888 65536 342079203 3146167 0 1370187588 12076634540157266 12076634540344802 12076634540613441 12076634540679657
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 148 937062 937067 4194304 256 0 0 28 24 93568 0x7f31b1191900 0x7f30a5636340 400508 400508 30364 3204072 65536 325601236 3033729 0 1304223612 12076634540707349 12076634540900960 12076634541159040 12076634541228759
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 150 937062 937067 4194304 256 0 0 24 24 95040 0x7f31b1191800 0x7f30a5636380 215420 215420 22810 1723368 65536 152585967 1559429 0 612212692 12076634541255168 12076634541456959 12076634541590079 12076634541593427
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 152 937062 937067 4194304 256 0 0 24 24 96768 0x7f31b1191700 0x7f30a56363c0 255541 255541 30610 2044336 65536 222286816 1859187 0 890991504 12076634541652958 12076634541839998 12076634541998398 12076634542006746
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 154 937062 937067 4194304 256 0 0 24 24 98240 0x7f31b1191600 0x7f30a5636400 216668 216668 22070 1733352 65536 155741010 1570265 0 624841512 12076634542076425 12076634542254077 12076634542388157 12076634542391301
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 937062 937067 4194304 256 0 0 28 24 100736 0x7f31b1191500 0x7f30a5636440 417628 417628 34074 3341032 65536 333216758 3118039 0 1334683008 12076634542450792 12076634542640317 12076634542910716 12076634542957294
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 158 937062 937067 4194304 256 0 0 28 24 102208 0x7f31b1191400 0x7f30a5636480 397324 397324 30824 3178600 65536 337128771 3018503 0 1350334456 12076634542981539 12076634543186555 12076634543443355 12076634543488522
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 160 937062 937067 4194304 256 0 0 24 24 103680 0x7f31b1191300 0x7f30a56364c0 225229 225229 24290 1801840 65536 142448607 1626904 0 571637828 12076634543530180 12076634543704954 12076634543843994 12076634543847129
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 162 937062 937067 4194304 256 0 0 24 24 105664 0x7f31b1191a00 0x7f30a5636500 262797 262797 28081 2102384 65536 233830271 1940837 0 937170592 12076634543909976 12076634544116153 12076634544281593 12076634544284773
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 164 937062 937067 4194304 256 0 0 24 24 107136 0x7f31b1191900 0x7f30a5636540 221141 221141 24416 1769136 65536 144513711 1597678 0 579896612 12076634544358721 12076634544537752 12076634544673752 12076634544677273
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 937062 937067 4194304 256 0 0 28 24 109888 0x7f31b1191800 0x7f30a5636580 408485 408485 36448 3267888 65536 324005800 3077103 0 1297869708 12076634544736423 12076634544931832 12076634545196471 12076634545265778
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 168 937062 937067 4194304 256 0 0 28 24 111360 0x7f31b1191700 0x7f30a56365c0 398084 398084 38085 3184680 65536 335870488 2989272 0 1345296084 12076634545291696 12076634545487190 12076634545741750 12076634545808177
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 170 937062 937067 4194304 256 0 0 24 24 112832 0x7f31b1191600 0x7f30a5636600 225389 225389 23366 1803120 65536 143201439 1633713 0 574668904 12076634545835267 12076634546034069 12076634546174229 12076634546177504
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 172 937062 937067 4194304 256 0 0 24 24 114816 0x7f31b1191500 0x7f30a5636640 274788 274788 30015 2198312 65536 245834907 2034390 0 985205140 12076634546240341 12076634546426388 12076634546599348 12076634546602735
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 174 937062 937067 4194304 256 0 0 24 24 116288 0x7f31b1191400 0x7f30a5636680 212845 212845 21768 1702768 65536 154990814 1519836 0 621814824 12076634546674859 12076634546851027 12076634546982387 12076634546985697
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 937062 937067 4194304 256 0 0 28 24 119040 0x7f31b1191300 0x7f30a56366c0 406924 406924 36478 3255400 65536 315620737 3056185 0 1264314736 12076634547046330 12076634547239506 12076634547502386 12076634547567880
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 178 937062 937067 4194304 256 0 0 28 24 120768 0x7f31b1191a00 0x7f30a5636700 395605 395605 32088 3164848 65536 318104197 2984256 0 1274235812 12076634547596163 12076634547788305 12076634548044305 12076634548112944
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 180 937062 937067 4194304 256 0 0 24 24 122496 0x7f31b1191900 0x7f30a5636740 228092 228092 25336 1824744 65536 143630960 1655089 0 576381056 12076634548138692 12076634548339344 12076634548480304 12076634548483744
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 182 937062 937067 4194304 256 0 0 24 24 124736 0x7f31b1191800 0x7f30a5636780 288765 288765 29964 2310128 65536 259925815 2149141 0 1041559524 12076634548543705 12076634548728143 12076634548911663 12076634548915016
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 184 937062 937067 4194304 256 0 0 24 24 126464 0x7f31b1191700 0x7f30a56367c0 226421 226421 25398 1811376 65536 145020314 1625891 0 581981220 12076634549021955 12076634549203822 12076634549343342 12076634549347000
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 937062 937067 4194304 256 0 0 20 24 127936 0x7f31b1191600 0x7f30a5636800 411885 411885 36923 3295088 65536 377379464 3118343 0 1511338396 12076634549406931 12076634549594221 12076634549861421 12076634549902813
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 188 937062 937067 4194304 256 0 0 28 24 129664 0x7f31b1191500 0x7f30a5636840 400772 400772 29019 3206184 65536 270661366 3012149 0 1084466864 12076634549939552 12076634550131340 12076634550390059 12076634550456674
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 190 937062 937067 4194304 256 0 0 24 24 131392 0x7f31b1191400 0x7f30a5636880 223493 223493 28641 1787952 65536 156747337 1596842 0 628841760 12076634550483403 12076634550681099 12076634550818218 12076634550821683
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 192 937062 937067 4194304 256 0 0 24 24 133632 0x7f31b1191300 0x7f30a56368c0 300748 300748 31432 2405992 65536 272500640 2248458 0 1091849984 12076634550885241 12076634551073738 12076634551264457 12076634551332072
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 194 937062 937067 4194304 256 0 0 24 24 135360 0x7f31b1191a00 0x7f30a5636900 221837 221837 24841 1774704 65536 154654268 1601667 0 620482812 12076634551376685 12076634551554377 12076634551691497 12076634551694897
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 937062 937067 4194304 256 0 0 20 24 136832 0x7f31b1191900 0x7f30a5636940 436893 436893 39784 3495152 65536 402285022 3324829 0 1610960776 12076634551755520 12076634551941416 12076634552225095 12076634552292028
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 198 937062 937067 4194304 256 0 0 28 24 138560 0x7f31b1191800 0x7f30a5636980 400429 400429 33584 3203440 65536 329960243 3008473 0 1321683344 12076634552320531 12076634552515655 12076634552773094 12076634552839366
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 200 937062 937067 4194304 256 0 0 24 24 140288 0x7f31b1191700 0x7f30a56369c0 220708 220708 27469 1765672 65536 151431805 1583632 0 607560160 12076634552864162 12076634553076133 12076634553212453 12076634553215966
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 202 937062 937067 4194304 256 0 0 24 24 142784 0x7f31b1191600 0x7f30a5636a00 330308 330308 32883 2642472 65536 300457787 2479819 0 1203689148 12076634553276469 12076634553467493 12076634553678052 12076634553744239
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 204 937062 937067 4194304 256 0 0 24 24 144768 0x7f31b1191500 0x7f30a5636a40 223524 223524 23556 1788200 65536 157776974 1611436 0 632997452 12076634553780316 12076634553964291 12076634554102531 12076634554106102
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 937062 937067 4194304 256 0 0 20 24 145728 0x7f31b1191400 0x7f30a5636a80 470173 470173 40408 3761392 65536 437901688 3595251 0 1753426996 12076634554166254 12076634554354531 12076634554661730 12076634554727688
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 208 937062 937067 4194304 256 0 0 28 24 147712 0x7f31b1191300 0x7f30a5636ac0 405245 405245 34161 3241968 65536 335140714 3063259 0 1342389428 12076634554754929 12076634554951169 12076634555213249 12076634555279745
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 210 937062 937067 4194304 256 0 0 24 24 149696 0x7f31b1191a00 0x7f30a5636b00 225836 225836 22182 1806696 65536 154006034 1634745 0 617898908 12076634555304291 12076634555503466 12076634555643946 12076634555651266
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 212 937062 937067 4194304 256 0 0 24 24 152192 0x7f31b1191900 0x7f30a5636b40 356653 356653 35781 2853232 65536 325389722 2683365 0 1303415364 12076634555706769 12076634555893704 12076634556121223 12076634556189638
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 214 937062 937067 4194304 256 0 0 24 24 154176 0x7f31b1191800 0x7f30a5636b80 218700 218700 25714 1749608 65536 154046907 1576350 0 618063224 12076634556229913 12076634556409383 12076634556544902 12076634556548375
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 937062 937067 4194304 256 0 0 20 24 155648 0x7f31b1191700 0x7f30a5636bc0 503797 503797 43958 4030384 65536 471894300 3865747 0 1889397832 12076634556611292 12076634556801222 12076634557130821 12076634557200308
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 218 937062 937067 4194304 256 0 0 28 24 157632 0x7f31b1191600 0x7f30a5636c00 407340 407340 28640 3258728 65536 312702803 3052368 0 1252629116 12076634557226436 12076634557424421 12076634557688420 12076634557729282
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 220 937062 937067 4194304 256 0 0 24 24 159616 0x7f31b1191500 0x7f30a5636c40 226132 226132 25877 1809064 65536 153078598 1635564 0 614185492 12076634557772462 12076634557950339 12076634558090179 12076634558093649
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 222 937062 937067 4194304 256 0 0 24 24 162368 0x7f31b1191400 0x7f30a5636c80 381924 381924 36449 3055400 65536 349844373 2887948 0 1401225252 12076634558156556 12076634558340738 12076634558586178 12076634558653100
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 224 937062 937067 4194304 256 0 0 24 24 164608 0x7f31b1191300 0x7f30a5636cc0 225636 225636 28452 1805096 65536 163004818 1620463 0 653901864 12076634558689598 12076634558868257 12076634559008577 12076634559012278
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 937062 937067 4194304 256 0 0 20 24 166336 0x7f31b1191a00 0x7f30a5636d00 575053 575053 46909 4600432 65536 542304783 4444623 0 2171037532 12076634559063984 12076634559260256 12076634559638336 12076634559704396
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 228 937062 937067 4194304 256 0 0 28 24 168576 0x7f31b1191900 0x7f30a5636d40 407580 407580 33723 3260648 65536 300540763 3069434 0 1203998740 12076634559729943 12076634559931455 12076634560195934 12076634560262333
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 230 937062 937067 4194304 256 0 0 24 24 170816 0x7f31b1191800 0x7f30a5636d80 221692 221692 25854 1773544 65536 161817687 1597624 0 649149348 12076634560287300 12076634560486494 12076634560624573 12076634560628034
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 232 937062 937067 4194304 256 0 0 24 24 174080 0x7f31b1191700 0x7f30a5636dc0 479652 479652 16068 3837224 65536 400919451 3297056 0 1605528676 12076634560680361 12076634560872413 12076634561182652 12076634561253146
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 234 937062 937067 4194304 256 0 0 24 24 176576 0x7f31b1191600 0x7f30a5636e00 226229 226229 27604 1809840 65536 171830292 1631065 0 689219544 12076634561291798 12076634561482171 12076634561622011 12076634561625890
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 937062 937067 4194304 256 0 0 20 24 177792 0x7f31b1191500 0x7f30a5636e40 642308 642308 49986 5138472 65536 610109508 4982908 0 2442259024 12076634561686523 12076634561873050 12076634562297370 12076634562320632
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 238 937062 937067 4194304 256 0 0 28 24 180288 0x7f31b1191400 0x7f30a5636e80 405085 405085 38149 3240688 65536 316171611 3009971 0 1266529976 12076634562375825 12076634562555289 12076634562816408 12076634562837233
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 240 937062 937067 4194304 256 0 0 24 24 182784 0x7f31b1191300 0x7f30a5636ec0 224084 224084 25472 1792680 65536 181419219 1619155 0 727554372 12076634562893057 12076634563075768 12076634563215447 12076634563219103
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 242 937062 937067 4194304 256 0 0 24 24 186304 0x7f31b1191a00 0x7f30a5636f00 486588 486588 42862 3892712 65536 454898081 3728515 0 1821450016 12076634563280988 12076634563480887 12076634563795926 12076634563817416
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 244 937062 937067 4194304 256 0 0 24 24 189312 0x7f31b1191900 0x7f30a5636f40 242541 242541 26466 1940336 65536 213332854 1779150 0 855228180 12076634563892296 12076634564077046 12076634564229205 12076634564232879
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 937062 937067 4194304 256 0 0 20 24 190784 0x7f31b1191800 0x7f30a5636f80 784108 784108 60015 6272872 65536 750338005 6105956 0 3003173004 12076634564285056 12076634564488245 12076634565005523 12076634565048666
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 248 937062 937067 4194304 256 0 0 28 24 193792 0x7f31b1191700 0x7f30a5636fc0 462325 462325 41381 3698608 65536 395240212 3527463 0 1582802604 12076634565094482 12076634565274643 12076634565577202 12076634565643924
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 250 937062 937067 4194304 256 0 0 24 24 196800 0x7f31b1191600 0x7f30a5637000 246109 246109 27784 1968880 65536 217168109 1806572 0 870553892 12076634565678829 12076634565865202 12076634566019761 12076634566023700
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 252 937062 937067 4194304 256 0 0 24 24 201088 0x7f31b1191500 0x7f30a5637040 592933 592933 48021 4743472 65536 560063963 4582944 0 2242112928 12076634566085235 12076634566269841 12076634566656240 12076634566723241
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 254 937062 937067 4194304 256 0 0 24 24 204608 0x7f31b1191400 0x7f30a5637080 280285 280285 32285 2242288 65536 249208230 2057641 0 998719992 12076634566764228 12076634566942639 12076634567118159 12076634567121853
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 937062 937067 4194304 256 0 0 20 24 206080 0x7f31b1191300 0x7f30a56370c0 941756 941756 14101 7534056 65536 890432974 7231462 0 3563553184 12076634567184139 12076634567381838 12076634568006157 12076634568057143
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 258 937062 937067 4194304 256 0 0 28 24 209600 0x7f31b1191a00 0x7f30a5637100 507660 507660 43040 4061288 65536 461305602 3890339 0 1847067668 12076634568083071 12076634568279756 12076634568611435 12076634568675082
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 260 937062 937067 4194304 256 0 0 24 24 213120 0x7f31b1191900 0x7f30a5637140 280405 280405 28596 2243248 65536 253336450 2087346 0 1015233064 12076634568699477 12076634568894155 12076634569072874 12076634569076559
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 262 937062 937067 4194304 256 0 0 24 24 218176 0x7f31b1191800 0x7f30a5637180 697597 697597 54537 5580784 65536 664191411 5417658 0 2658618900 12076634569137282 12076634569324714 12076634569780713 12076634569820142
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 264 937062 937067 4194304 256 0 0 24 24 222208 0x7f31b1191700 0x7f30a56371c0 311908 311908 30116 2495272 65536 284878944 2343878 0 1141402000 12076634569871588 12076634570055592 12076634570255592 12076634570322897
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 937062 937067 4194304 256 0 0 20 24 223936 0x7f31b1191600 0x7f30a5637200 1074565 1074565 15319 8596528 65536 1026825089 8361806 0 4109121200 12076634570348595 12076634570543431 12076634571254629 12076634571321024
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 268 937062 937067 4194304 256 0 0 28 24 227968 0x7f31b1191500 0x7f30a5637240 569653 569653 48021 4557232 65536 530371934 4383864 0 2123328560 12076634571346331 12076634571549829 12076634571923908 12076634571989848
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 270 937062 937067 4194304 256 0 0 24 24 232000 0x7f31b1191400 0x7f30a5637280 317245 317245 31036 2537968 65536 289326641 2381524 0 1159204808 12076634572019904 12076634572227907 12076634572431907 12076634572500057
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 272 937062 937067 4194304 256 0 0 24 24 237824 0x7f31b1191300 0x7f30a56372c0 802213 802213 60272 6417712 65536 768040034 6253577 0 3074015504 12076634572524202 12076634572719586 12076634573245505 12076634573312158
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 274 937062 937067 4194304 256 0 0 24 24 242368 0x7f31b1191a00 0x7f30a5637300 347797 347797 32627 2782384 65536 318789642 2623936 0 1277049252 12076634573353665 12076634573529664 12076634573753184 12076634573818800
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 937062 937067 4194304 256 0 0 20 24 243584 0x7f31b1191900 0x7f30a5637340 1208453 1208453 86374 9667632 65536 1168332366 9488416 0 4675150496 12076634573846241 12076634574053983 12076634574853821 12076634574922784
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 278 937062 937067 4194304 256 0 0 28 24 248128 0x7f31b1191800 0x7f30a5637380 638796 638796 50862 5110376 65536 604054320 4952300 0 2418060228 12076634574954663 12076634575159741 12076634575582300 12076634575648644
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 280 937062 937067 4194304 256 0 0 24 24 252672 0x7f31b1191700 0x7f30a56373c0 353580 353580 33948 2828648 65536 324112464 2665953 0 1298340420 12076634575673781 12076634575870139 12076634576097178 12076634576165074
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 282 937062 937067 4194304 256 0 0 24 24 259264 0x7f31b1191600 0x7f30a5637400 907972 907972 66668 7263784 65536 871808204 7100172 0 3489082580 12076634576192956 12076634576392698 12076634576989176 12076634577055932
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 284 937062 937067 4194304 256 0 0 24 24 264832 0x7f31b1191500 0x7f30a5637440 420029 420029 39580 3360240 65536 386607378 3170786 0 1548333812 12076634577092850 12076634577279576 12076634577549015 12076634577615372
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 937062 937067 4194304 256 0 0 20 24 266304 0x7f31b1191400 0x7f30a5637480 1486188 1486188 99240 11889512 65536 1446440968 11735967 0 5787585524 12076634577639457 12076634577835895 12076634578822292 12076634578892327
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 288 937062 937067 4194304 256 0 0 28 24 271872 0x7f31b1191300 0x7f30a56374c0 779469 779469 62018 6235760 65536 741190979 6050695 0 2966600364 12076634578918406 12076634579119252 12076634579634931 12076634579684581
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 290 937062 937067 4194304 256 0 0 24 24 277440 0x7f31b1191a00 0x7f30a5637500 421452 421452 38444 3371624 65536 390033242 3211048 0 1562019048 12076634579709507 12076634579904850 12076634580177649 12076634580247919
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 292 937062 937067 4194304 256 0 0 12 24 279936 0x7f31b1191900 0x7f30a5637540 1125589 1125589 79521 9004720 65536 1088541766 8842982 0 4355992024 12076634580276031 12076634580473649 12076634581212847 12076634581268868
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 294 937062 937067 4194304 256 0 0 24 24 286528 0x7f31b1191800 0x7f30a5637580 487197 487197 42516 3897584 65536 454902748 3736289 0 1821503676 12076634581309874 12076634581489006 12076634581805326 12076634581854848
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 937062 937067 4194304 256 0 0 20 24 288000 0x7f31b1191700 0x7f30a56375c0 1768453 1768453 117917 14147632 65536 1724990770 13979184 0 6901783928 12076634581883371 12076634582092845 12076634583267082 12076634583563887
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 298 937062 937067 4194304 256 0 0 32 24 294592 0x7f31b1191600 0x7f30a5637600 918692 918692 64768 7349544 65536 807675935 7172718 0 3232557552 12076634583598371 12076634583798721 12076634584410400 12076634584459012
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 300 937062 937067 4194304 256 0 0 24 24 301184 0x7f31b1191500 0x7f30a5637640 495188 495188 44861 3961512 65536 462565391 3791743 0 1852172552 12076634584494178 12076634584679519 12076634585000798 12076634585094735
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 302 937062 937067 4194304 256 0 0 12 24 304960 0x7f31b1191400 0x7f30a5637680 1336324 1336324 91200 10690600 65536 1298621629 10526806 0 5196313352 12076634585122847 12076634585329598 12076634586208316 12076634586259401
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 304 937062 937067 4194304 256 0 0 24 24 313600 0x7f31b1191300 0x7f30a56376c0 630380 630380 53869 5043048 65536 590581195 4863819 0 2364224928 12076634586306950 12076634586488795 12076634586899354 12076634586946790
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 937062 937067 4194304 256 0 0 20 24 314816 0x7f31b1191a00 0x7f30a5637700 2331940 2331940 149601 18655528 65536 2284557933 18495718 0 9140053388 12076634586979761 12076634587190394 12076634588740950 12076634588791461
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 308 937062 937067 4194304 256 0 0 20 24 317568 0x7f31b1191900 0x7f30a5637740 1199868 1199868 85074 9598952 65536 1161498246 9433358 0 4647813612 12076634588825635 12076634589030229 12076634589826548 12076634589875217
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 310 937062 937067 4194304 256 0 0 12 24 320320 0x7f31b1191800 0x7f30a5637780 639124 639124 50051 5113000 65536 608084295 4952297 0 2434171872 12076634589900133 12076634590105267 12076634590520306 12076634590569148
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 312 937062 937067 4194304 256 0 0 12 24 324096 0x7f31b1191700 0x7f30a56377c0 1757892 1757892 117158 14063144 65536 1714873517 13896555 0 6861319168 12076634590598723 12076634590790705 12076634591950063 12076634592004989
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 314 937062 937067 4194304 256 0 0 12 24 328896 0x7f31b1191600 0x7f30a5637800 1197780 1197780 82504 9582248 65536 1162231712 9420247 0 4650752948 12076634592045584 12076634592226382 12076634593012780 12076634593059921
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 937062 937067 4194304 256 0 0 20 24 330112 0x7f31b1191500 0x7f30a5637840 4583812 4583812 211273 36670504 65536 4515494636 36504397 0 18063799832 12076634593107028 12076634593282380 12076634596337893 12076634596388553
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 318 937062 937067 4194304 256 0 0 20 24 332864 0x7f31b1191400 0x7f30a5637880 2324436 2324436 151493 18595496 65536 2275127854 18421263 0 9102333000 12076634596420652 12076634596617732 12076634598164129 12076634598235348
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 320 937062 937067 4194304 256 0 0 12 24 335616 0x7f31b1191300 0x7f30a56378c0 1201508 1201508 82495 9612072 65536 1164122494 9454092 0 4658313948 12076634598267928 12076634598462688 12076634599253246 12076634599321308
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 322 937062 937067 4194304 256 0 0 12 24 339392 0x7f31b1191a00 0x7f30a5637900 3443268 3443268 214620 27546152 65536 3385357309 27381420 0 13543259488 12076634599342307 12076634599558206 12076634601841081 12076634601909913
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 324 937062 937067 4194304 256 0 0 12 24 344192 0x7f31b1191900 0x7f30a5637940 2323188 2323188 149197 18585512 65536 2274824901 18413418 0 9101128852 12076634601955628 12076634602146200 12076634603681556 12076634603750837
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 937062 937067 4194304 256 0 0 20 24 345408 0x7f31b1191800 0x7f30a5637980 9085596 9085596 472686 72684776 65536 8976560945 72523826 0 35908064460 12076634603782336 12076634603982356 12076634610042502 12076634610114464
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 328 937062 937067 4194304 256 0 0 20 24 348160 0x7f31b1191700 0x7f30a56379c0 4572572 4572572 211846 36580584 65536 4502571004 36416224 0 18012108720 12076634610150401 12076634610350021 12076634613397535 12076634613464596
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 330 937062 937067 4194304 256 0 0 12 24 350912 0x7f31b1191600 0x7f30a5637a00 2327092 2327092 149864 18616744 65536 2280060719 18455117 0 9122067764 12076634613497297 12076634613694974 12076634615234810 12076634615302405
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 332 937062 937067 4194304 256 0 0 12 24 0 0x7f31b1191500 0x7f30a5637a40 6811828 6811828 339834 54494632 65536 6722926938 54334488 0 26893535824 12076634615338832 12076634615533667 12076634620063098 12076634620137478
@@ -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]",1,6059957.0,6059957.0,6059957.0,9.169486064060209
"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",1,4525889.0,4525889.0,4525889.0,6.848245971544582
"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",1,3056459.0,3056459.0,3056459.0,4.624811398145466
"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",1,3046218.0,3046218.0,3046218.0,4.609315461989146
"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",1,2282865.0,2282865.0,2282865.0,3.4542652371346545
"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",1,1551667.0,1551667.0,1551667.0,2.347869618969592
"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",1,1545589.0,1545589.0,1545589.0,2.33867283155058
"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",1,1538549.0,1538549.0,1538549.0,2.3280204157180933
"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",1,1534869.0,1534869.0,1534869.0,2.322452107442021
"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",1,1174711.0,1174711.0,1174711.0,1.7774872237209325
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 6059957.0 6059957.0 6059957.0 9.169486064060209
3 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 1 4525889.0 4525889.0 4525889.0 6.848245971544582
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 3056459.0 3056459.0 3056459.0 4.624811398145466
5 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 1 3046218.0 3046218.0 3046218.0 4.609315461989146
6 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 1 2282865.0 2282865.0 2282865.0 3.4542652371346545
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 1551667.0 1551667.0 1551667.0 2.347869618969592
8 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 1 1545589.0 1545589.0 1545589.0 2.33867283155058
9 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 1 1538549.0 1538549.0 1538549.0 2.3280204157180933
10 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 1 1534869.0 1534869.0 1534869.0 2.322452107442021
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 1174711.0 1174711.0 1174711.0 1.7774872237209325
@@ -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
invdev
vesuvius
AMD EPYC 7542 32-Core Processor
""
4.18.0-240.15.1.el8_3.x86_64
4.2.0-21
Thu Sep 22 11:36:21 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 invdev
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 11:36:21 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),0.5975933105679886,0.03348482766137937,1.4312219520664826,Instr/cycle
IPC (Issue),0.8437262750969097,0.516887005106089,0.9995913989478523,Instr/cycle
SALU Util,2.1239105491088672,0.030661253039176935,23.4402499204585,Pct
VALU Util,59.71163511528943,0.9045069646557197,99.10770722537578,Pct
VALU Active Threads,63.967840400497316,63.71866596497203,64.0,Threads
MFMA Util,,,,Pct
MFMA Instr Cycles,,,,Cycles/instr
1 Metric Avg Min Max Unit
2 IPC (Avg) 0.5975933105679886 0.03348482766137937 1.4312219520664826 Instr/cycle
3 IPC (Issue) 0.8437262750969097 0.516887005106089 0.9995913989478523 Instr/cycle
4 SALU Util 2.1239105491088672 0.030661253039176935 23.4402499204585 Pct
5 VALU Util 59.71163511528943 0.9045069646557197 99.10770722537578 Pct
6 VALU Active Threads 63.967840400497316 63.71866596497203 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,33617.72709436474,2860.667678833008,547916.0441894531,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 33617.72709436474 2860.667678833008 547916.0441894531 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,30.48465697184559
Cache Hit,99.49184173484623
1 Metric Value
2 Bandwidth 30.48465697184559
3 Cache Hit 99.49184173484623
@@ -0,0 +1,6 @@
L1I Metric,Mean,Min,Max,Unit
Req,162.66467065868264,12.0,3215.0,Req per wave
Hits,162.47033331636896,11.995920181274414,3214.982421875,Hits per wave
Misses - Non Duplicated,0.001976789828546033,0.00018310546875,0.09375,Misses per wave
Misses - Duplicated,0.3044349304930179,0.005184173583984375,3.78515625,Misses per wave
Cache Hit,99.49184173484623,75.7568359375,99.99933127192645,Pct
1 L1I Metric Mean Min Max Unit
2 Req 162.66467065868264 12.0 3215.0 Req per wave
3 Hits 162.47033331636896 11.995920181274414 3214.982421875 Hits per wave
4 Misses - Non Duplicated 0.001976789828546033 0.00018310546875 0.09375 Misses per wave
5 Misses - Duplicated 0.3044349304930179 0.005184173583984375 3.78515625 Misses per wave
6 Cache Hit 99.49184173484623 75.7568359375 99.99933127192645 Pct
@@ -0,0 +1,3 @@
Metric,Value
Bandwidth,0.9319487411909382
Cache Hit,98.02737992680716
1 Metric Value
2 Bandwidth 0.9319487411909382
3 Cache Hit 98.02737992680716
@@ -0,0 +1,13 @@
Metric,Mean,Min,Max,Unit
Req,1.8083832335329342,1.0,8.0,Req per wave
Hits,1.7799111440510094,0.0,7.991498947143555,Req per wave
Misses - Non Duplicated,0.0012866722609468563,0.000274658203125,0.09375,Req per wave
Misses- Duplicated,0.027185417220977965,0.008226394653320312,0.90625,Req per wave
Cache Hit,98.02737992680716,0.0,99.89373683929443,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 1.7799111440510094 0.0 7.991498947143555 Req per wave
4 Misses - Non Duplicated 0.0012866722609468563 0.000274658203125 0.09375 Req per wave
5 Misses- Duplicated 0.027185417220977965 0.008226394653320312 0.90625 Req per wave
6 Cache Hit 98.02737992680716 0.0 99.89373683929443 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,58.918391555340804,1.4646736852191202,92.9530980607751,Pct
TC2TA Addr Stall,45.754781443371314,0.06181588483054525,82.26050238232082,Pct
TC2TA Data Stall,0.3689563539634891,0.0,61.61571111190268,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 58.918391555340804 1.4646736852191202 92.9530980607751 Pct
3 TC2TA Addr Stall 45.754781443371314 0.06181588483054525 82.26050238232082 Pct
4 TC2TA Data Stall 0.3689563539634891 0.0 61.61571111190268 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,74.751150727649,16.331851056955013,93.62385202496499,Pct
TC2TD Stall,64.72709260144231,14.150343800427454,89.76664239190806,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 74.751150727649 16.331851056955013 93.62385202496499 Pct
3 TC2TD Stall 64.72709260144231 14.150343800427454 89.76664239190806 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,80.5569462029343
Cache BW,2.444133673381755
Cache Hit,20.508982035928145
1 Metric Value
2 Buffer Coalescing 69.91017964071857
3 Cache Util 80.5569462029343
4 Cache BW 2.444133673381755
5 Cache Hit 20.508982035928145
@@ -0,0 +1,6 @@
Metric,Mean,Min,Max,Unit
Stalled on L2 Data,61.06097035104162,14.089563978027304,85.58938424407913,Pct
Stalled on L2 Req,30.678100401776167,0.001727639669449954,66.68526538656958,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 61.06097035104162 14.089563978027304 85.58938424407913 Pct
3 Stalled on L2 Req 30.678100401776167 0.001727639669449954 66.68526538656958 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,1539.15823146683,410.68083572387695,3052.9560546875,Cycles
L1-L2 Read Latency,770.8525427278266,353.21870398521423,2134.9337158203125,Cycles
L1-L2 Write Latency,326.6591252088547,326.6591252088547,326.6591252088547,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 1539.15823146683 410.68083572387695 3052.9560546875 Cycles
14 L1-L2 Read Latency 770.8525427278266 353.21870398521423 2134.9337158203125 Cycles
15 L1-L2 Write Latency 326.6591252088547 326.6591252088547 326.6591252088547 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,97.72473256031196,91.943359375,98.99501204490662,Pct
Hits,68.49913352692198,29.421875,125.92437744140625, per wave
Misses (Translation),0.15957631322438132,0.029264450073242188,0.234375, 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 97.72473256031196 91.943359375 98.99501204490662 Pct
4 Hits 68.49913352692198 29.421875 125.92437744140625 per wave
5 Misses (Translation) 0.15957631322438132 0.029264450073242188 0.234375 per wave
6 Misses (Permission) 0.0 0.0 0.0 per wave
@@ -0,0 +1,5 @@
Metric,Value,Unit
L2 Util,87.79207734273452,Pct
Cache Hit,0.39312978682338157,Pct
L2-EA Rd BW,836.7945529629085,Gb/s
L2-EA Wr BW,4.9441118194225755,Gb/s
1 Metric Value Unit
2 L2 Util 87.79207734273452 Pct
3 Cache Hit 0.39312978682338157 Pct
4 L2-EA Rd BW 836.7945529629085 Gb/s
5 L2-EA Wr BW 4.9441118194225755 Gb/s
@@ -0,0 +1,16 @@
Metric,Avg,Min,Max,Unit
Read BW,2841.070183120088,1.3280029296875,4100.2421875,Bytes per wave
Write BW,3.065900425711078,0.0,512.00537109375,Bytes per wave
Read (32B),0.0,0.0,0.0,Req per wave
Read (Uncached 32B),0.06361485098650356,0.013214111328125,0.859375,Req per wave
Read (64B),44.39172161125138,0.020750045776367188,64.0662841796875,Req per wave
HBM Read,44.39103551396353,0.020856857299804688,64.06233215332031,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),0.047904694151735594,0.0,8.000083923339844,Req per wave
HBM Write,0.0479046598879877,0.0,8.000078201293945,Req per wave
Read Latency,430.00322182359974,240.23385872025406,1209.4209945767075,Cycles
Write Latency,146.77487585674817,146.77487585674817,146.77487585674817,Cycles
Atomic Latency,,,,Cycles
Read Stall,4.957433824645539,0.0,17.428999259788046,Pct
Write Stall,0.008722643384427253,0.0,1.456681445199351,Pct
1 Metric Avg Min Max Unit
2 Read BW 2841.070183120088 1.3280029296875 4100.2421875 Bytes per wave
3 Write BW 3.065900425711078 0.0 512.00537109375 Bytes per wave
4 Read (32B) 0.0 0.0 0.0 Req per wave
5 Read (Uncached 32B) 0.06361485098650356 0.013214111328125 0.859375 Req per wave
6 Read (64B) 44.39172161125138 0.020750045776367188 64.0662841796875 Req per wave
7 HBM Read 44.39103551396353 0.020856857299804688 64.06233215332031 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) 0.047904694151735594 0.0 8.000083923339844 Req per wave
11 HBM Write 0.0479046598879877 0.0 8.000078201293945 Req per wave
12 Read Latency 430.00322182359974 240.23385872025406 1209.4209945767075 Cycles
13 Write Latency 146.77487585674817 146.77487585674817 146.77487585674817 Cycles
14 Atomic Latency Cycles
15 Read Stall 4.957433824645539 0.0 17.428999259788046 Pct
16 Write Stall 0.008722643384427253 0.0 1.456681445199351 Pct
@@ -0,0 +1,19 @@
Metric,Avg,Min,Max,Unit
Req,44.51646839073318,16.021080017089844,64.09146118164062,Req per wave
Streaming Req,0.0,0.0,0.0,Req per wave
Read Req,44.41944935507403,0.02120208740234375,64.08999633789062,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,44.43882501339484,8.020273208618164,64.05502319335938,Misses per wave
Cache Hit,0.39312978682338157,0.010081784003855388,49.9392475409719,Pct
Writeback,0.04873507608196693,0.0004730224609375,8.000162124633789, per wave
NC Req,0.0012861240409805389,0.00018310546875,0.09375,Req per wave
UC Req,0.029743788485041635,0.0052490234375,0.333984375,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),0.047156316791465896,0.0,7.875104904174805, per wave
Writeback (TC Req),0.0007484230452668881,0.0,0.12498664855957031, per wave
Evict (Normal),42.33440820614021,0.0,62.00164794921875, per wave
Evict (TC Req),0.0,0.0,0.0, per wave
1 Metric Avg Min Max Unit
2 Req 44.51646839073318 16.021080017089844 64.09146118164062 Req per wave
3 Streaming Req 0.0 0.0 0.0 Req per wave
4 Read Req 44.41944935507403 0.02120208740234375 64.08999633789062 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 44.43882501339484 8.020273208618164 64.05502319335938 Misses per wave
10 Cache Hit 0.39312978682338157 0.010081784003855388 49.9392475409719 Pct
11 Writeback 0.04873507608196693 0.0004730224609375 8.000162124633789 per wave
12 NC Req 0.0012861240409805389 0.00018310546875 0.09375 Req per wave
13 UC Req 0.029743788485041635 0.0052490234375 0.333984375 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) 0.047156316791465896 0.0 7.875104904174805 per wave
17 Writeback (TC Req) 0.0007484230452668881 0.0 0.12498664855957031 per wave
18 Evict (Normal) 42.33440820614021 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,6.21412174430436,0.0,22.27508544921875,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,0.002550753290781718,0.0,0.4259757995605469,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 6.21412174430436 0.0 22.27508544921875 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 0.002550753290781718 0.0 0.4259757995605469 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
0,0.359797764270722,1.3899759075598803,1.3869818955838322,0.0029940119760479044,0.0,1.386243260549214,0.0014970973580183383,0.0,428.76458906456276,132.75596582239854,,0.0,0.0,0.13291867193347678,0.0,0.0,9.913644390905688e-06,0.0
1,0.3654665110334509,1.3912592905010293,1.3882652785249814,0.0029940119760479044,0.0,1.386243214864217,0.0014970059880239522,0.0,431.2799339354621,132.92140197753906,,0.0,0.0,0.13969119865737276,0.0,0.0,1.0301966867047156e-05,0.0
2,0.3568017238180907,1.389967136040419,1.3869731240643712,0.0029940119760479044,0.0,1.3862430778092254,0.0014970059880239522,0.0,431.3440824627215,132.13844299316406,,0.0,0.0,0.1581764449616392,0.0,0.0,1.02791243684506e-05,0.0
3,0.3575652880602528,1.3907993567917876,1.3878053448157397,0.0029940119760479044,0.0,1.3927909714019227,0.0014970288305225486,0.0,537.0043303085895,228.22724567801396,,0.0,0.0,0.3155908641700973,0.0,0.0,0.0005266680688915138,0.0
4,0.35659037293283263,1.3899759075598803,1.3869818955838322,0.0029940119760479044,0.0,1.386243260549214,0.0014970516730211452,0.0,426.64853266415207,134.78310293264977,,0.0,0.0,0.20486678620298465,0.0,0.0,9.274054430202095e-06,0.0
5,0.36279067181399044,1.3899759075598803,1.3869818955838322,0.0029940119760479044,0.0,1.386243260549214,0.0014970516730211452,0.0,438.4541853188356,133.50823949464433,,0.0,0.0,0.18955317514385292,0.0,0.0,9.673798155641842e-06,0.0
6,0.3589398273883731,1.3899715218001496,1.3869775098241017,0.0029940119760479044,0.0,1.3862967348384285,0.0014970516730211452,0.0,432.6861707124791,139.0076444200311,,0.0,0.0,0.15964494351141467,0.0,0.0,1.3100172945125374e-05,0.0
7,0.3602145621489667,1.3899759075598803,1.3869818955838322,0.0029940119760479044,0.0,1.3954783799405583,0.0014970516730211452,0.0,441.02389170509844,233.41417193078826,,0.0,0.0,0.4300740864462481,0.0,0.0,0.0005217683529425524,0.0
8,0.35360132978293934,1.4010727933780875,1.3980787814020397,0.0029940119760479044,0.0,1.386243260549214,0.0014970516730211452,0.0,510.80071661469043,132.3720742164851,,0.0,0.0,0.13634861015274138,0.0,0.0,1.2506267981614896e-05,0.0
9,0.3603820185069739,1.389972070020116,1.386978058044068,0.0029940119760479044,0.0,1.3862431691792196,0.0014970059880239522,0.0,425.67310660092704,132.41432189941406,,0.0,0.0,0.1388039046418881,0.0,0.0,1.2677586721089072e-05,0.0
10,0.35658626900038287,1.389971990071371,1.386977978095323,0.0029940119760479044,0.0,1.3862694037888579,0.0014970059880239522,0.0,421.5321782500137,130.96766662597656,,0.0,0.0,0.17939347135806513,0.0,0.0,8.737255713183009e-06,0.0
11,0.3604390230545021,1.389967136040419,1.3869731240643712,0.0029940119760479044,0.0,1.3871099392097153,0.0014970059880239522,0.0,428.18978154762067,127.42288208007812,,0.0,0.0,0.20966599515812126,0.0,0.0,9.308318178096932e-06,0.0
12,0.3595841527203406,1.3900158476686764,1.3870218356926285,0.0029940119760479044,0.0,1.3862435346591973,0.0014970059880239522,0.0,419.1353219831154,132.39913940429688,,0.0,0.0,0.16268025472492514,0.0,0.0,1.539584405407934e-05,0.0
13,0.3640730353860431,1.3899715218001496,1.3869775098241017,0.0029940119760479044,0.0,1.3862431691792196,0.0014970516730211452,0.0,426.49291832043434,132.85541212731545,,0.0,0.0,0.14986570438225114,0.0,0.0,1.3362861678985778e-05,0.0
14,0.6082974782277631,1.3922082592627245,1.3892142472866766,0.0029940119760479044,0.0,1.3862898021401047,0.0014970059880239522,0.0,429.0744812274499,139.2489776611328,,0.0,0.0,0.14040361050360217,0.0,0.0,9.216948183710704e-06,0.0
15,0.35662516494921787,1.400022723717604,1.3970287117415559,0.0029940119760479044,0.0,1.3862430778092254,0.0014970059880239522,0.0,553.5876791304053,141.17298126220703,,0.0,0.0,0.15595944341785178,0.0,0.0,1.6480862737415794e-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 0.359797764270722 1.3899759075598803 1.3869818955838322 0.0029940119760479044 0.0 1.386243260549214 0.0014970973580183383 0.0 428.76458906456276 132.75596582239854 0.0 0.0 0.13291867193347678 0.0 0.0 9.913644390905688e-06 0.0
3 1 0.3654665110334509 1.3912592905010293 1.3882652785249814 0.0029940119760479044 0.0 1.386243214864217 0.0014970059880239522 0.0 431.2799339354621 132.92140197753906 0.0 0.0 0.13969119865737276 0.0 0.0 1.0301966867047156e-05 0.0
4 2 0.3568017238180907 1.389967136040419 1.3869731240643712 0.0029940119760479044 0.0 1.3862430778092254 0.0014970059880239522 0.0 431.3440824627215 132.13844299316406 0.0 0.0 0.1581764449616392 0.0 0.0 1.02791243684506e-05 0.0
5 3 0.3575652880602528 1.3907993567917876 1.3878053448157397 0.0029940119760479044 0.0 1.3927909714019227 0.0014970288305225486 0.0 537.0043303085895 228.22724567801396 0.0 0.0 0.3155908641700973 0.0 0.0 0.0005266680688915138 0.0
6 4 0.35659037293283263 1.3899759075598803 1.3869818955838322 0.0029940119760479044 0.0 1.386243260549214 0.0014970516730211452 0.0 426.64853266415207 134.78310293264977 0.0 0.0 0.20486678620298465 0.0 0.0 9.274054430202095e-06 0.0
7 5 0.36279067181399044 1.3899759075598803 1.3869818955838322 0.0029940119760479044 0.0 1.386243260549214 0.0014970516730211452 0.0 438.4541853188356 133.50823949464433 0.0 0.0 0.18955317514385292 0.0 0.0 9.673798155641842e-06 0.0
8 6 0.3589398273883731 1.3899715218001496 1.3869775098241017 0.0029940119760479044 0.0 1.3862967348384285 0.0014970516730211452 0.0 432.6861707124791 139.0076444200311 0.0 0.0 0.15964494351141467 0.0 0.0 1.3100172945125374e-05 0.0
9 7 0.3602145621489667 1.3899759075598803 1.3869818955838322 0.0029940119760479044 0.0 1.3954783799405583 0.0014970516730211452 0.0 441.02389170509844 233.41417193078826 0.0 0.0 0.4300740864462481 0.0 0.0 0.0005217683529425524 0.0
10 8 0.35360132978293934 1.4010727933780875 1.3980787814020397 0.0029940119760479044 0.0 1.386243260549214 0.0014970516730211452 0.0 510.80071661469043 132.3720742164851 0.0 0.0 0.13634861015274138 0.0 0.0 1.2506267981614896e-05 0.0
11 9 0.3603820185069739 1.389972070020116 1.386978058044068 0.0029940119760479044 0.0 1.3862431691792196 0.0014970059880239522 0.0 425.67310660092704 132.41432189941406 0.0 0.0 0.1388039046418881 0.0 0.0 1.2677586721089072e-05 0.0
12 10 0.35658626900038287 1.389971990071371 1.386977978095323 0.0029940119760479044 0.0 1.3862694037888579 0.0014970059880239522 0.0 421.5321782500137 130.96766662597656 0.0 0.0 0.17939347135806513 0.0 0.0 8.737255713183009e-06 0.0
13 11 0.3604390230545021 1.389967136040419 1.3869731240643712 0.0029940119760479044 0.0 1.3871099392097153 0.0014970059880239522 0.0 428.18978154762067 127.42288208007812 0.0 0.0 0.20966599515812126 0.0 0.0 9.308318178096932e-06 0.0
14 12 0.3595841527203406 1.3900158476686764 1.3870218356926285 0.0029940119760479044 0.0 1.3862435346591973 0.0014970059880239522 0.0 419.1353219831154 132.39913940429688 0.0 0.0 0.16268025472492514 0.0 0.0 1.539584405407934e-05 0.0
15 13 0.3640730353860431 1.3899715218001496 1.3869775098241017 0.0029940119760479044 0.0 1.3862431691792196 0.0014970516730211452 0.0 426.49291832043434 132.85541212731545 0.0 0.0 0.14986570438225114 0.0 0.0 1.3362861678985778e-05 0.0
16 14 0.6082974782277631 1.3922082592627245 1.3892142472866766 0.0029940119760479044 0.0 1.3862898021401047 0.0014970059880239522 0.0 429.0744812274499 139.2489776611328 0.0 0.0 0.14040361050360217 0.0 0.0 9.216948183710704e-06 0.0
17 15 0.35662516494921787 1.400022723717604 1.3970287117415559 0.0029940119760479044 0.0 1.3862430778092254 0.0014970059880239522 0.0 553.5876791304053 141.17298126220703 0.0 0.0 0.15595944341785178 0.0 0.0 1.6480862737415794e-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
16,0.3612977421304405,1.3900109936377245,1.3870169816616766,0.0029940119760479044,0.0,1.386243991509169,0.0014970059880239522,0.0,428.7955307569659,129.6676788330078,,0.0,0.0,0.16047175059061564,0.0,0.0,2.0227032507251124e-05,0.0
17,0.36690603161649904,1.3912855251106673,1.3882915131346194,0.0029940119760479044,0.0,1.386243214864217,0.0014970059880239522,0.0,458.4228788099578,130.3526840209961,,0.0,0.0,0.15668802775308757,0.0,0.0,2.493258721814184e-05,0.0
18,0.6082929097977524,1.3922083049477219,1.3892142929716738,0.0029940119760479044,0.0,1.386290316096323,0.0014970516730211452,0.0,437.9833451917447,131.4376850071714,,0.0,0.0,0.14861512326908682,0.0,0.0,1.0324809365643713e-05,0.0
19,0.3564678985448229,1.3911897350928026,1.3881957231167548,0.0029940119760479044,0.0,1.3862428950692365,0.0014970059880239522,0.0,463.3768725066005,224.56124114990234,,0.0,0.0,0.15167236328125,0.0,0.0,0.0005218711441862369,0.0
20,0.35693748670211767,1.3928968349616684,1.3899028229856205,0.0029940119760479044,0.0,1.3862433519192086,0.0014970973580183383,0.0,444.80822438227756,134.33664174549892,,0.0,0.0,0.17021078692224925,0.0,0.0,1.3305755432494387e-05,0.0
21,0.3636989442376576,1.3899896130590381,1.3869956010829902,0.0029940119760479044,0.0,1.3862435346591973,0.0014970973580183383,0.0,439.0100385570635,135.00602685382972,,0.0,0.0,0.16142556196201346,0.0,0.0,1.9416123807073353e-05,0.0
22,0.3597969825898013,1.3899802933196108,1.386986281343563,0.0029940119760479044,0.0,1.3875289277402227,0.0014970059880239522,0.0,423.07803226443326,139.92764282226562,,0.0,0.0,0.1403159866789858,0.0,0.0,1.7645830165840196e-05,0.0
23,0.36000958471288586,1.3899759075598803,1.3869818955838322,0.0029940119760479044,0.0,1.386243260549214,0.0014970059880239522,0.0,447.4851383623292,141.7116928100586,,0.0,0.0,0.15878789296407186,0.0,0.0,1.8879325090054265e-05,0.0
24,0.35637714141192556,1.389967136040419,1.3869731240643712,0.0029940119760479044,0.0,1.3862430778092254,0.0014970059880239522,0.0,425.9619694277513,129.0684356689453,,0.0,0.0,0.13005586726936752,0.0,0.0,1.2574795477404566e-05,0.0
25,0.36086313590376146,1.3899539787612276,1.3869599667851797,0.0029940119760479044,0.0,1.3875283795202564,0.0014970059880239522,0.0,430.5300893450829,130.3259506225586,,0.0,0.0,0.1204376220703125,0.0,0.0,1.3065909197230539e-05,0.0
26,0.5053691232746963,1.3912395545822418,1.388245542606194,0.0029940119760479044,0.0,1.3862428950692365,0.0014970059880239522,0.0,428.31505439812605,131.62374877929688,,0.0,0.0,0.1808796956867515,0.0,0.0,8.954259449850299e-06,0.0
27,0.3585049569470193,1.3899627502806886,1.3869687383046407,0.0029940119760479044,0.0,1.3871677649949126,0.0014970059880239522,0.0,431.101537031859,127.87411499023438,,0.0,0.0,0.19836508014244947,0.0,0.0,1.0975820575645584e-05,0.0
28,0.36065695238662526,1.390006607877994,1.3870125959019461,0.0029940119760479044,0.0,1.3862439001391749,0.0014970516730211452,0.0,426.54947264089344,133.66159327413104,,0.0,0.0,0.13694525621608347,0.0,0.0,1.3374282928284057e-05,0.0
29,0.3640717800237613,1.3899802933196108,1.386986281343563,0.0029940119760479044,0.0,1.3862433519192086,0.0014970059880239522,0.0,436.63676302765475,133.9394989013672,,0.0,0.0,0.17161550921594312,0.0,0.0,1.9987186271987276e-05,0.0
30,0.4495938970351085,1.390519741766467,1.387525729790419,0.0029940119760479044,0.0,1.386254864538501,0.0014970059880239522,0.0,425.61898520929986,139.60790252685547,,0.0,0.0,0.21411324689488212,0.0,0.0,1.210652425617515e-05,0.0
31,0.3604382401738407,1.3899715218001496,1.3869775098241017,0.0029940119760479044,0.0,1.3970883192416437,0.0014970516730211452,0.0,434.053788987114,243.208237968812,,0.0,0.0,0.9139493839469498,0.0,0.0,0.0005794685043974551,0.0
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 0.3612977421304405 1.3900109936377245 1.3870169816616766 0.0029940119760479044 0.0 1.386243991509169 0.0014970059880239522 0.0 428.7955307569659 129.6676788330078 0.0 0.0 0.16047175059061564 0.0 0.0 2.0227032507251124e-05 0.0
3 17 0.36690603161649904 1.3912855251106673 1.3882915131346194 0.0029940119760479044 0.0 1.386243214864217 0.0014970059880239522 0.0 458.4228788099578 130.3526840209961 0.0 0.0 0.15668802775308757 0.0 0.0 2.493258721814184e-05 0.0
4 18 0.6082929097977524 1.3922083049477219 1.3892142929716738 0.0029940119760479044 0.0 1.386290316096323 0.0014970516730211452 0.0 437.9833451917447 131.4376850071714 0.0 0.0 0.14861512326908682 0.0 0.0 1.0324809365643713e-05 0.0
5 19 0.3564678985448229 1.3911897350928026 1.3881957231167548 0.0029940119760479044 0.0 1.3862428950692365 0.0014970059880239522 0.0 463.3768725066005 224.56124114990234 0.0 0.0 0.15167236328125 0.0 0.0 0.0005218711441862369 0.0
6 20 0.35693748670211767 1.3928968349616684 1.3899028229856205 0.0029940119760479044 0.0 1.3862433519192086 0.0014970973580183383 0.0 444.80822438227756 134.33664174549892 0.0 0.0 0.17021078692224925 0.0 0.0 1.3305755432494387e-05 0.0
7 21 0.3636989442376576 1.3899896130590381 1.3869956010829902 0.0029940119760479044 0.0 1.3862435346591973 0.0014970973580183383 0.0 439.0100385570635 135.00602685382972 0.0 0.0 0.16142556196201346 0.0 0.0 1.9416123807073353e-05 0.0
8 22 0.3597969825898013 1.3899802933196108 1.386986281343563 0.0029940119760479044 0.0 1.3875289277402227 0.0014970059880239522 0.0 423.07803226443326 139.92764282226562 0.0 0.0 0.1403159866789858 0.0 0.0 1.7645830165840196e-05 0.0
9 23 0.36000958471288586 1.3899759075598803 1.3869818955838322 0.0029940119760479044 0.0 1.386243260549214 0.0014970059880239522 0.0 447.4851383623292 141.7116928100586 0.0 0.0 0.15878789296407186 0.0 0.0 1.8879325090054265e-05 0.0
10 24 0.35637714141192556 1.389967136040419 1.3869731240643712 0.0029940119760479044 0.0 1.3862430778092254 0.0014970059880239522 0.0 425.9619694277513 129.0684356689453 0.0 0.0 0.13005586726936752 0.0 0.0 1.2574795477404566e-05 0.0
11 25 0.36086313590376146 1.3899539787612276 1.3869599667851797 0.0029940119760479044 0.0 1.3875283795202564 0.0014970059880239522 0.0 430.5300893450829 130.3259506225586 0.0 0.0 0.1204376220703125 0.0 0.0 1.3065909197230539e-05 0.0
12 26 0.5053691232746963 1.3912395545822418 1.388245542606194 0.0029940119760479044 0.0 1.3862428950692365 0.0014970059880239522 0.0 428.31505439812605 131.62374877929688 0.0 0.0 0.1808796956867515 0.0 0.0 8.954259449850299e-06 0.0
13 27 0.3585049569470193 1.3899627502806886 1.3869687383046407 0.0029940119760479044 0.0 1.3871677649949126 0.0014970059880239522 0.0 431.101537031859 127.87411499023438 0.0 0.0 0.19836508014244947 0.0 0.0 1.0975820575645584e-05 0.0
14 28 0.36065695238662526 1.390006607877994 1.3870125959019461 0.0029940119760479044 0.0 1.3862439001391749 0.0014970516730211452 0.0 426.54947264089344 133.66159327413104 0.0 0.0 0.13694525621608347 0.0 0.0 1.3374282928284057e-05 0.0
15 29 0.3640717800237613 1.3899802933196108 1.386986281343563 0.0029940119760479044 0.0 1.3862433519192086 0.0014970059880239522 0.0 436.63676302765475 133.9394989013672 0.0 0.0 0.17161550921594312 0.0 0.0 1.9987186271987276e-05 0.0
16 30 0.4495938970351085 1.390519741766467 1.387525729790419 0.0029940119760479044 0.0 1.386254864538501 0.0014970059880239522 0.0 425.61898520929986 139.60790252685547 0.0 0.0 0.21411324689488212 0.0 0.0 1.210652425617515e-05 0.0
17 31 0.3604382401738407 1.3899715218001496 1.3869775098241017 0.0029940119760479044 0.0 1.3970883192416437 0.0014970516730211452 0.0 434.053788987114 243.208237968812 0.0 0.0 0.9139493839469498 0.0 0.0 0.0005794685043974551 0.0
@@ -0,0 +1,55 @@
Metric,Value,Alias
Wave Life,33618.0,wave_life_
Active CUs,94/120,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,1539.0,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,771.0,l2_rd_lat_
L2 Wr Lat,327.0,l2_wr_lat_
Fabric Rd Lat,430.0,fabric_rd_lat_
Fabric Wr Lat,147.0,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,31.0,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 33618.0 wave_life_
3 Active CUs 94/120 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 1539.0 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 771.0 l2_rd_lat_
40 L2 Wr Lat 327.0 l2_wr_lat_
41 Fabric Rd Lat 430.0 fabric_rd_lat_
42 Fabric Wr Lat 147.0 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 31.0 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,94,Cus,120,78.33333333333333
SALU Util,2.1239105491088672,Pct,100,2.1239105491088672
VALU Util,59.71163511528944,Pct,100,59.71163511528944
MFMA Util,,Pct,100,
VALU Active Threads/Wave,63.967840400497316,Threads,64,99.94975062577706
IPC - Issue,0.8437262750969097,Instr/cycle,5,16.874525501938194
LDS_Per_Workgroup BW,0.0,Gb/sec,23070.72,0.0
LDS_Per_Workgroup Bank Conflict,,Conflicts/access,32,
Instr Cache Hit Rate,99.99318745374036,Pct,100,99.99318745374036
Instr Cache BW,1406.6059705869952,Gb/s,4614.144,30.484656971845595
Scalar L1D Cache Hit Rate,99.35620448519533,Pct,100,99.35620448519533
Scalar L1D Cache BW,43.001456924737205,Gb/s,4614.144,0.9319487411909382
Vector L1D Cache Hit Rate,20.508982035928145,Pct,100,20.508982035928145
Vector L1D Cache BW,1216.9011142906327,Gb/s,11535.36,10.549311978912081
L2 Cache Hit Rate,0.39312978682338157,Pct,100,0.39312978682338157
L2-Fabric Read BW,836.7945529629085,Gb/s,1228.8,68.09851505232002
L2-Fabric Write BW,4.9441118194225755,Gb/s,1228.8,0.40235284988790493
L2-Fabric Read Latency,430.00322182359974,Cycles,,
L2-Fabric Write Latency,146.77487585674817,Cycles,,
Wave Occupancy,3208.8936703038016,Wavefronts,4800,66.85195146466253
Instr Fetch BW,681.3774175015478,Gb/s,2307.072,29.534293576513775
Instr Fetch Latency,18.427677559787053,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 94 Cus 120 78.33333333333333
10 SALU Util 2.1239105491088672 Pct 100 2.1239105491088672
11 VALU Util 59.71163511528944 Pct 100 59.71163511528944
12 MFMA Util Pct 100
13 VALU Active Threads/Wave 63.967840400497316 Threads 64 99.94975062577706
14 IPC - Issue 0.8437262750969097 Instr/cycle 5 16.874525501938194
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 99.99318745374036 Pct 100 99.99318745374036
18 Instr Cache BW 1406.6059705869952 Gb/s 4614.144 30.484656971845595
19 Scalar L1D Cache Hit Rate 99.35620448519533 Pct 100 99.35620448519533
20 Scalar L1D Cache BW 43.001456924737205 Gb/s 4614.144 0.9319487411909382
21 Vector L1D Cache Hit Rate 20.508982035928145 Pct 100 20.508982035928145
22 Vector L1D Cache BW 1216.9011142906327 Gb/s 11535.36 10.549311978912081
23 L2 Cache Hit Rate 0.39312978682338157 Pct 100 0.39312978682338157
24 L2-Fabric Read BW 836.7945529629085 Gb/s 1228.8 68.09851505232002
25 L2-Fabric Write BW 4.9441118194225755 Gb/s 1228.8 0.40235284988790493
26 L2-Fabric Read Latency 430.00322182359974 Cycles
27 L2-Fabric Write Latency 146.77487585674817 Cycles
28 Wave Occupancy 3208.8936703038016 Wavefronts 4800 66.85195146466253
29 Instr Fetch BW 681.3774175015478 Gb/s 2307.072 29.534293576513775
30 Instr Fetch Latency 18.427677559787053 Cycles
@@ -0,0 +1,9 @@
Metric,Avg,Min,Max,Unit
GPU Busy Cycles,614556.5748502994,27831,9087599,Cycles/kernel
CPF Busy,614556.5748502994,27831,9087599,Cycles/kernel
CPF Util,100.0,100.0,100.0,Pct
CPF Stall,0.00099662590033571,0.0,0.04285931294893774,Cycles/kernel
L2Cache Intf Busy,4290.610778443114,4020,6716,Cycles/kernel
L2Cache Intf Util,1.3440566612571894,0.04649796581029336,15.291072821385521,Pct
L2Cache Intf Stall,0.0,0.0,0.0,Pct
UTCL1 Stall,4.730538922155689,0,158,Cycles/kernel
1 Metric Avg Min Max Unit
2 GPU Busy Cycles 614556.5748502994 27831 9087599 Cycles/kernel
3 CPF Busy 614556.5748502994 27831 9087599 Cycles/kernel
4 CPF Util 100.0 100.0 100.0 Pct
5 CPF Stall 0.00099662590033571 0.0 0.04285931294893774 Cycles/kernel
6 L2Cache Intf Busy 4290.610778443114 4020 6716 Cycles/kernel
7 L2Cache Intf Util 1.3440566612571894 0.04649796581029336 15.291072821385521 Pct
8 L2Cache Intf Stall 0.0 0.0 0.0 Pct
9 UTCL1 Stall 4.730538922155689 0 158 Cycles/kernel
@@ -0,0 +1,13 @@
Metric,Avg,Min,Max,Unit
GPU Busy Cycles,614556.5748502994,27831,9087599,Cycles
CPC Busy Cycles,611941.9281437126,27831,9024826,Cycles
CPC Util,99.60821977946165,83.05592326555413,100.0,Pct
CPC Stall Cycles,14849.425149700599,11554,71175,Cycles
CPC Stall Rate,4.191041472418264,0.7706277562815954,42.29815673170206,Pct
CPC Packet Decoding,45098.838323353295,13940,473900,Cycles
SPI Intf Busy Cycles,559114.3652694611,696,8537933,Cycles
SPI Intf Util,88.29142197634089,2.500808451007869,97.34985525376953,Pct
L2Cache Intf Util,0.2459876862777102,0.008671870082180275,2.19839918872913,Pct
UTCL1 Stall Cycles,2538.293413173653,2329,3002,Cycles
UTCL2 Intf Busy Cycles,2961.443113772455,2733,3844,Cycles
UTCL2 Intf Util,0.941418304086639,0.032418281666009165,10.29444078224566,Pct
1 Metric Avg Min Max Unit
2 GPU Busy Cycles 614556.5748502994 27831 9087599 Cycles
3 CPC Busy Cycles 611941.9281437126 27831 9024826 Cycles
4 CPC Util 99.60821977946165 83.05592326555413 100.0 Pct
5 CPC Stall Cycles 14849.425149700599 11554 71175 Cycles
6 CPC Stall Rate 4.191041472418264 0.7706277562815954 42.29815673170206 Pct
7 CPC Packet Decoding 45098.838323353295 13940 473900 Cycles
8 SPI Intf Busy Cycles 559114.3652694611 696 8537933 Cycles
9 SPI Intf Util 88.29142197634089 2.500808451007869 97.34985525376953 Pct
10 L2Cache Intf Util 0.2459876862777102 0.008671870082180275 2.19839918872913 Pct
11 UTCL1 Stall Cycles 2538.293413173653 2329 3002 Cycles
12 UTCL2 Intf Busy Cycles 2961.443113772455 2733 3844 Cycles
13 UTCL2 Intf Util 0.941418304086639 0.032418281666009165 10.29444078224566 Pct
@@ -0,0 +1,9 @@
Metric,Avg,Min,Max,Unit
GPU Busy,614556.5748502994,27831,9087599,Cycles
CS Busy,4748491.784431138,81931,72540209,Cycles
SPI Busy,597069.9820359282,11187,9069034,Cycles
SQ Busy,4751839.401197605,75900,72526860,Cycles
Dispatched Workgroups,16973.413173652694,128,131072,Workgroups
Dispatched Wavefronts,67893.65269461078,512,524288,Wavefronts
Wave Alloc Failed,282030.94011976046,116,1624809,Cycles
Wave Alloc Failed - CS,331276.36526946106,628,1061618,Cycles
1 Metric Avg Min Max Unit
2 GPU Busy 614556.5748502994 27831 9087599 Cycles
3 CS Busy 4748491.784431138 81931 72540209 Cycles
4 SPI Busy 597069.9820359282 11187 9069034 Cycles
5 SQ Busy 4751839.401197605 75900 72526860 Cycles
6 Dispatched Workgroups 16973.413173652694 128 131072 Workgroups
7 Dispatched Wavefronts 67893.65269461078 512 524288 Wavefronts
8 Wave Alloc Failed 282030.94011976046 116 1624809 Cycles
9 Wave Alloc Failed - CS 331276.36526946106 628 1061618 Cycles
@@ -0,0 +1,15 @@
Metric,Avg,Min,Max,Unit
Wave request Failed (CS),331276.36526946106,628,1061618,Cycles
CS Stall,19966.97005988024,0,790844,Cycles
CS Stall Rate,5.153448157066879,0.0,87.71483837765415,Pct
Scratch Stall,0.0,0,0,Cycles
Insufficient SIMD Waveslots,64892.16766467066,0,774244,Simd
Insufficient SIMD VGPRs,527589.6886227545,0,30743007,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) 331276.36526946106 628 1061618 Cycles
3 CS Stall 19966.97005988024 0 790844 Cycles
4 CS Stall Rate 5.153448157066879 0.0 87.71483837765415 Pct
5 Scratch Stall 0.0 0 0 Cycles
6 Insufficient SIMD Waveslots 64892.16766467066 0 774244 Simd
7 Insufficient SIMD VGPRs 527589.6886227545 0 30743007 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),395738.29341317364,6720,6059957,Ns
Kernel Time (Cycles),614556.5748502994,27831,9087599,Cycle
Instr/wavefront,842.5329341317365,62.0,20596.0,Instr/wavefront
Wave Cycles,33617.72709436474,2860.667678833008,547916.0441894531,Cycles/wave
Dependency Wait Cycles,4401.749248938646,1085.9686889648438,26389.158752441406,Cycles/wave
Issue Wait Cycles,25316.336952894748,104.7265625,443210.8854370117,Cycles/wave
Active Cycles,3899.6208393759357,248.0,78316.0,Cycles/wave
Wavefront Occupancy,3208.8936703038016,164.5975170204245,3952.1969125635787,Wavefronts
1 Metric Avg Min Max Unit
2 Kernel Time (Nanosec) 395738.29341317364 6720 6059957 Ns
3 Kernel Time (Cycles) 614556.5748502994 27831 9087599 Cycle
4 Instr/wavefront 842.5329341317365 62.0 20596.0 Instr/wavefront
5 Wave Cycles 33617.72709436474 2860.667678833008 547916.0441894531 Cycles/wave
6 Dependency Wait Cycles 4401.749248938646 1085.9686889648438 26389.158752441406 Cycles/wave
7 Issue Wait Cycles 25316.336952894748 104.7265625 443210.8854370117 Cycles/wave
8 Active Cycles 3899.6208393759357 248.0 78316.0 Cycles/wave
9 Wavefront Occupancy 3208.8936703038016 164.5975170204245 3952.1969125635787 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
invdev,vesuvius,AMD EPYC 7542 32-Core Processor,,4.18.0-240.15.1.el8_3.x86_64,4.2.0-21,Thu Sep 22 11:36:21 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 invdev vesuvius AMD EPYC 7542 32-Core Processor 4.18.0-240.15.1.el8_3.x86_64 4.2.0-21 Thu Sep 22 11:36:21 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",0,0,0,937113,937118,33554432,256,0,0,8,32,6464,0x0,0x7f12eac04180,12076635381227990,12076635381273678,12076635381598795,12076635381689318
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,937113,937118,32768,256,0,0,24,24,12480,0x0,0x7f12eac35100,12076635396787522,12076635396887551,12076635396894271,12076635396915901
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,937113,937118,4194304,256,0,0,24,24,12928,0x7f141aca3900,0x7f12eac35140,12076635396946107,12076635396958910,12076635397089629,12076635397093471
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,937113,937118,4194304,256,0,0,36,24,13632,0x7f141aca3800,0x7f12eac35180,12076635397153844,12076635397172188,12076635397417626,12076635397502262
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,937113,937118,4194304,256,0,0,28,24,14080,0x7f141aca3700,0x7f12eac351c0,12076635397530284,12076635397541945,12076635397788343,12076635397870096
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,937113,937118,4194304,256,0,0,24,24,14528,0x7f141aca3600,0x7f12eac35200,12076635397898148,12076635397909782,12076635398035381,12076635398039221
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,937113,937118,4194304,256,0,0,24,24,14976,0x7f141aca3500,0x7f12eac35240,12076635398076520,12076635398088341,12076635398213780,12076635398217131
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,937113,937118,4194304,256,0,0,24,24,15424,0x7f141aca3400,0x7f12eac35280,12076635398270070,12076635398281939,12076635398406418,12076635398409309
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,937113,937118,4194304,256,0,0,28,24,16128,0x7f141aca3300,0x7f12eac352c0,12076635398437431,12076635398448658,12076635398696176,12076635398741717
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,937113,937118,4194304,256,0,0,28,24,16832,0x7f141aca3a00,0x7f12eac35300,12076635398764199,12076635398777615,12076635399025613,12076635399071551
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,937113,937118,4194304,256,0,0,24,24,17536,0x7f141aca3900,0x7f12eac35340,12076635399094343,12076635399107533,12076635399232652,12076635399235516
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,937113,937118,4194304,256,0,0,24,24,18240,0x7f141aca3800,0x7f12eac35380,12076635399263287,12076635399276171,12076635399401610,12076635399404741
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,937113,937118,4194304,256,0,0,24,24,18944,0x7f141aca3700,0x7f12eac353c0,12076635399444655,12076635399456170,12076635399581449,12076635399584315
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,937113,937118,4194304,256,0,0,28,24,19904,0x7f141aca3600,0x7f12eac35400,12076635399611585,12076635399623689,12076635399870247,12076635399893239
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,937113,937118,4194304,256,0,0,28,24,20608,0x7f141aca3500,0x7f12eac35440,12076635399918546,12076635399929606,12076635400177284,12076635400223223
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,937113,937118,4194304,256,0,0,24,24,21312,0x7f141aca3400,0x7f12eac35480,12076635400245675,12076635400257444,12076635400382403,12076635400385244
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,937113,937118,4194304,256,0,0,24,24,22016,0x7f141aca3300,0x7f12eac354c0,12076635400412726,12076635400425762,12076635400550881,12076635400554048
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,937113,937118,4194304,256,0,0,24,24,22720,0x7f141aca3a00,0x7f12eac35500,12076635400591819,12076635400602881,12076635400727040,12076635400730136
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,937113,937118,4194304,256,0,0,28,24,23680,0x7f141aca3900,0x7f12eac35540,12076635400756735,12076635400768959,12076635401016317,12076635401041185
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,937113,937118,4194304,256,0,0,28,24,24384,0x7f141aca3800,0x7f12eac35580,12076635401064799,12076635401076317,12076635401318875,12076635401363364
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,937113,937118,4194304,256,0,0,24,24,25088,0x7f141aca3700,0x7f12eac355c0,12076635401384904,12076635401395994,12076635401520153,12076635401523091
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,937113,937118,4194304,256,0,0,24,24,25792,0x7f141aca3600,0x7f12eac35600,12076635401549149,12076635401560473,12076635401685592,12076635401688719
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,937113,937118,4194304,256,0,0,24,24,26496,0x7f141aca3500,0x7f12eac35640,12076635401727772,12076635401738712,12076635401862391,12076635401865458
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,937113,937118,4194304,256,0,0,28,24,27712,0x7f141aca3400,0x7f12eac35680,12076635401892097,12076635401906710,12076635402152788,12076635402202364
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,937113,937118,4194304,256,0,0,28,24,28416,0x7f141aca3300,0x7f12eac356c0,12076635402225738,12076635402238868,12076635402483186,12076635402528471
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,937113,937118,4194304,256,0,0,24,24,29120,0x7f141aca3a00,0x7f12eac35700,12076635402552285,12076635402565585,12076635402689584,12076635402692556
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,937113,937118,4194304,256,0,0,24,24,30080,0x7f141aca3900,0x7f12eac35740,12076635402719877,12076635402731344,12076635402856303,12076635402859487
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,937113,937118,4194304,256,0,0,24,24,30784,0x7f141aca3800,0x7f12eac35780,12076635402897117,12076635402908142,12076635403032941,12076635403036506
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,937113,937118,4194304,256,0,0,28,24,32000,0x7f141aca3700,0x7f12eac357c0,12076635403063136,12076635403075181,12076635403325419,12076635403348526
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,937113,937118,4194304,256,0,0,28,24,32960,0x7f141aca3600,0x7f12eac35800,12076635403370758,12076635403382378,12076635403629736,12076635403674102
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,937113,937118,4194304,256,0,0,24,24,33920,0x7f141aca3500,0x7f12eac35840,12076635403695322,12076635403708456,12076635403832775,12076635403835713
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,937113,937118,4194304,256,0,0,24,24,34880,0x7f141aca3400,0x7f12eac35880,12076635403861561,12076635403873894,12076635403999973,12076635404017561
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,937113,937118,4194304,256,0,0,24,24,35840,0x7f141aca3300,0x7f12eac358c0,12076635404049080,12076635404060933,12076635404185572,12076635404188699
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,937113,937118,4194304,256,0,0,28,24,37312,0x7f141aca3a00,0x7f12eac35900,12076635404214627,12076635404226211,12076635404472609,12076635404497944
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,937113,937118,4194304,256,0,0,28,24,38272,0x7f141aca3900,0x7f12eac35940,12076635404521208,12076635404532769,12076635404779487,12076635404800427
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,937113,937118,4194304,256,0,0,24,24,39232,0x7f141aca3800,0x7f12eac35980,12076635404822338,12076635404835327,12076635404959806,12076635404962619
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,937113,937118,4194304,256,0,0,24,24,40192,0x7f141aca3700,0x7f12eac359c0,12076635404990110,12076635405002845,12076635405128444,12076635405131603
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,937113,937118,4194304,256,0,0,24,24,41152,0x7f141aca3600,0x7f12eac35a00,12076635405168913,12076635405183324,12076635405307323,12076635405310125
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,937113,937118,4194304,256,0,0,28,24,42624,0x7f141aca3500,0x7f12eac35a40,12076635405337246,12076635405350202,12076635405599000,12076635405648124
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,937113,937118,4194304,256,0,0,28,24,43584,0x7f141aca3400,0x7f12eac35a80,12076635405670105,12076635405682840,12076635405928118,12076635405950376
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,937113,937118,4194304,256,0,0,24,24,44544,0x7f141aca3300,0x7f12eac35ac0,12076635405973099,12076635405985877,12076635406110996,12076635406114031
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,937113,937118,4194304,256,0,0,24,24,45760,0x7f141aca3a00,0x7f12eac35b00,12076635406142003,12076635406154996,12076635406281235,12076635406284337
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,937113,937118,4194304,256,0,0,24,24,46720,0x7f141aca3900,0x7f12eac35b40,12076635406320164,12076635406332754,12076635406457553,12076635406460555
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,937113,937118,4194304,256,0,0,28,24,48448,0x7f141aca3800,0x7f12eac35b80,12076635406486964,12076635406499633,12076635406758511,12076635406779148
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,937113,937118,4194304,256,0,0,28,24,49408,0x7f141aca3700,0x7f12eac35bc0,12076635406801009,12076635406814031,12076635407059469,12076635407081470
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,937113,937118,4194304,256,0,0,24,24,50368,0x7f141aca3600,0x7f12eac35c00,12076635407105164,12076635407117868,12076635407242507,12076635407245415
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,937113,937118,4194304,256,0,0,24,24,51584,0x7f141aca3500,0x7f12eac35c40,12076635407272956,12076635407285547,12076635407412426,12076635407415111
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,937113,937118,4194304,256,0,0,24,24,52544,0x7f141aca3400,0x7f12eac35c80,12076635407453933,12076635407466825,12076635407592104,12076635407594845
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,937113,937118,4194304,256,0,0,28,24,54272,0x7f141aca3300,0x7f12eac35cc0,12076635407622326,12076635407634984,12076635407894822,12076635407915882
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,937113,937118,4194304,256,0,0,28,24,55488,0x7f141aca3a00,0x7f12eac35d00,12076635407936881,12076635407950021,12076635408198179,12076635408219407
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,937113,937118,4194304,256,0,0,24,24,56704,0x7f141aca3900,0x7f12eac35d40,12076635408241548,12076635408253539,12076635408378498,12076635408381258
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,937113,937118,4194304,256,0,0,24,24,58176,0x7f141aca3800,0x7f12eac35d80,12076635408408118,12076635408420098,12076635408548897,12076635408551755
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,937113,937118,4194304,256,0,0,24,24,59392,0x7f141aca3700,0x7f12eac35dc0,12076635408587912,12076635408600736,12076635408726175,12076635408729045
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,937113,937118,4194304,256,0,0,28,24,61376,0x7f141aca3600,0x7f12eac35e00,12076635408756175,12076635408769215,12076635409028413,12076635409055091
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,937113,937118,4194304,256,0,0,28,24,62592,0x7f141aca3500,0x7f12eac35e40,12076635409078054,12076635409090492,12076635409336090,12076635409357213
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,937113,937118,4194304,256,0,0,24,24,63808,0x7f141aca3400,0x7f12eac35e80,12076635409381038,12076635409393050,12076635409518009,12076635409521078
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,937113,937118,4194304,256,0,0,24,24,65280,0x7f141aca3300,0x7f12eac35ec0,12076635409548990,12076635409561048,12076635409691127,12076635409693990
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,937113,937118,4194304,256,0,0,24,24,66496,0x7f141aca3a00,0x7f12eac35f00,12076635409730868,12076635409743767,12076635409869366,12076635409872251
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,937113,937118,4194304,256,0,0,28,24,68480,0x7f141aca3900,0x7f12eac35f40,12076635409898220,12076635409911446,12076635410171763,12076635410196424
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,937113,937118,4194304,256,0,0,28,24,69696,0x7f141aca3800,0x7f12eac35f80,12076635410219377,12076635410232083,12076635410475601,12076635410496182
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,937113,937118,4194304,256,0,0,24,24,70912,0x7f141aca3700,0x7f12eac35fc0,12076635410518233,12076635410531761,12076635410656720,12076635410659586
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,937113,937118,4194304,256,0,0,24,24,72384,0x7f141aca3600,0x7f12eac36000,12076635410686656,12076635410698799,12076635410835438,12076635410838318
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,937113,937118,4194304,256,0,0,24,24,73600,0x7f141aca3500,0x7f12eac36040,12076635410876219,12076635410889358,12076635411013837,12076635411016830
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,937113,937118,4194304,256,0,0,28,24,75840,0x7f141aca3400,0x7f12eac36080,12076635411045444,12076635411057996,12076635411323434,12076635411347035
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,937113,937118,4194304,256,0,0,28,24,77056,0x7f141aca3300,0x7f12eac360c0,12076635411368895,12076635411381194,12076635411663431,12076635411684903
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,937113,937118,4194304,256,0,0,24,24,78272,0x7f141aca3a00,0x7f12eac36100,12076635411706433,12076635411719591,12076635411844870,12076635411848087
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,937113,937118,4194304,256,0,0,24,24,80000,0x7f141aca3900,0x7f12eac36140,12076635411875357,12076635411888710,12076635412030948,12076635412034073
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,937113,937118,4194304,256,0,0,24,24,81216,0x7f141aca3800,0x7f12eac36180,12076635412071552,12076635412083908,12076635412208867,12076635412211873
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,937113,937118,4194304,256,0,0,28,24,83456,0x7f141aca3700,0x7f12eac361c0,12076635412238493,12076635412251267,12076635412509185,12076635412532029
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,937113,937118,4194304,256,0,0,28,24,84928,0x7f141aca3600,0x7f12eac36200,12076635412553829,12076635412566624,12076635412815422,12076635412838900
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,937113,937118,4194304,256,0,0,24,24,86400,0x7f141aca3500,0x7f12eac36240,12076635412861842,12076635412874782,12076635413000861,12076635413015598
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,937113,937118,4194304,256,0,0,24,24,88128,0x7f141aca3400,0x7f12eac36280,12076635413038771,12076635413051260,12076635413201019,12076635413203899
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,937113,937118,4194304,256,0,0,24,24,89600,0x7f141aca3300,0x7f12eac362c0,12076635413254533,12076635413268058,12076635413393977,12076635413397338
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,937113,937118,4194304,256,0,0,28,24,92096,0x7f141aca3a00,0x7f12eac36300,12076635413425220,12076635413437177,12076635413692695,12076635413714188
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,937113,937118,4194304,256,0,0,28,24,93568,0x7f141aca3900,0x7f12eac36340,12076635413736950,12076635413748855,12076635413996053,12076635414023323
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,937113,937118,4194304,256,0,0,24,24,95040,0x7f141aca3800,0x7f12eac36380,12076635414046696,12076635414059412,12076635414185011,12076635414188169
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,937113,937118,4194304,256,0,0,24,24,96768,0x7f141aca3700,0x7f12eac363c0,12076635414216081,12076635414228851,12076635414386609,12076635414389504
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,937113,937118,4194304,256,0,0,24,24,98240,0x7f141aca3600,0x7f12eac36400,12076635414427425,12076635414440049,12076635414564528,12076635414567485
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,937113,937118,4194304,256,0,0,28,24,100736,0x7f141aca3500,0x7f12eac36440,12076635414594676,12076635414607408,12076635414869965,12076635414894984
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,937113,937118,4194304,256,0,0,28,24,102208,0x7f141aca3400,0x7f12eac36480,12076635414916214,12076635414928365,12076635415172683,12076635415199030
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,937113,937118,4194304,256,0,0,24,24,103680,0x7f141aca3300,0x7f12eac364c0,12076635415220600,12076635415233003,12076635415358602,12076635415361933
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,937113,937118,4194304,256,0,0,24,24,105664,0x7f141aca3a00,0x7f12eac36500,12076635415388332,12076635415401481,12076635415566920,12076635415570130
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,937113,937118,4194304,256,0,0,24,24,107136,0x7f141aca3900,0x7f12eac36540,12076635415606828,12076635415618919,12076635415744198,12076635415747270
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,937113,937118,4194304,256,0,0,28,24,109888,0x7f141aca3800,0x7f12eac36580,12076635415776765,12076635415790918,12076635416046596,12076635416067956
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,937113,937118,4194304,256,0,0,28,24,111360,0x7f141aca3700,0x7f12eac365c0,12076635416090648,12076635416103236,12076635416352994,12076635416374456
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,937113,937118,4194304,256,0,0,24,24,112832,0x7f141aca3600,0x7f12eac36600,12076635416397138,12076635416410273,12076635416534592,12076635416537670
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,937113,937118,4194304,256,0,0,24,24,114816,0x7f141aca3500,0x7f12eac36640,12076635416564570,12076635416576672,12076635416748990,12076635416751969
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,937113,937118,4194304,256,0,0,24,24,116288,0x7f141aca3400,0x7f12eac36680,12076635416789027,12076635416801950,12076635416927389,12076635416930350
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,937113,937118,4194304,256,0,0,28,24,119040,0x7f141aca3300,0x7f12eac366c0,12076635416957781,12076635416970429,12076635417226906,12076635417249093
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,937113,937118,4194304,256,0,0,28,24,120768,0x7f141aca3a00,0x7f12eac36700,12076635417270323,12076635417283226,12076635417531864,12076635417553399
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,937113,937118,4194304,256,0,0,24,24,122496,0x7f141aca3900,0x7f12eac36740,12076635417575741,12076635417587864,12076635417713303,12076635417716332
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,937113,937118,4194304,256,0,0,24,24,124736,0x7f141aca3800,0x7f12eac36780,12076635417743282,12076635417755862,12076635417938421,12076635417941381
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,937113,937118,4194304,256,0,0,24,24,126464,0x7f141aca3700,0x7f12eac367c0,12076635417979311,12076635417991540,12076635418116979,12076635418120384
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,937113,937118,4194304,256,0,0,20,24,127936,0x7f141aca3600,0x7f12eac36800,12076635418147274,12076635418159699,12076635418423217,12076635418446440
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,937113,937118,4194304,256,0,0,28,24,129664,0x7f141aca3500,0x7f12eac36840,12076635418471607,12076635418484016,12076635418732334,12076635418753562
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,937113,937118,4194304,256,0,0,24,24,131392,0x7f141aca3400,0x7f12eac36880,12076635418775743,12076635418787854,12076635418914253,12076635418917236
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,937113,937118,4194304,256,0,0,24,24,133632,0x7f141aca3300,0x7f12eac368c0,12076635418943816,12076635418956812,12076635419147851,12076635419163013
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,937113,937118,4194304,256,0,0,24,24,135360,0x7f141aca3a00,0x7f12eac36900,12076635419194602,12076635419207370,12076635419333769,12076635419337057
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,937113,937118,4194304,256,0,0,20,24,136832,0x7f141aca3900,0x7f12eac36940,12076635419364268,12076635419377609,12076635419660647,12076635419684864
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,937113,937118,4194304,256,0,0,28,24,138560,0x7f141aca3800,0x7f12eac36980,12076635419706344,12076635419718566,12076635419964484,12076635419988038
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,937113,937118,4194304,256,0,0,24,24,140288,0x7f141aca3700,0x7f12eac369c0,12076635420018034,12076635420031364,12076635420157603,12076635420160659
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,937113,937118,4194304,256,0,0,24,24,142784,0x7f141aca3600,0x7f12eac36a00,12076635420188791,12076635420201602,12076635420411681,12076635420432535
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,937113,937118,4194304,256,0,0,24,24,144768,0x7f141aca3500,0x7f12eac36a40,12076635420463543,12076635420476320,12076635420603359,12076635420606388
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,937113,937118,4194304,256,0,0,20,24,145728,0x7f141aca3400,0x7f12eac36a80,12076635420633869,12076635420647039,12076635420953436,12076635420974854
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,937113,937118,4194304,256,0,0,28,24,147712,0x7f141aca3300,0x7f12eac36ac0,12076635420996624,12076635421013596,12076635421265754,12076635421288186
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,937113,937118,4194304,256,0,0,24,24,149696,0x7f141aca3a00,0x7f12eac36b00,12076635421308895,12076635421322073,12076635421450552,12076635421453774
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,937113,937118,4194304,256,0,0,24,24,152192,0x7f141aca3900,0x7f12eac36b40,12076635421480304,12076635421492792,12076635421720630,12076635421746299
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,937113,937118,4194304,256,0,0,24,24,154176,0x7f141aca3800,0x7f12eac36b80,12076635421779290,12076635421791990,12076635421919189,12076635421922366
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,937113,937118,4194304,256,0,0,20,24,155648,0x7f141aca3700,0x7f12eac36bc0,12076635421949787,12076635421962868,12076635422291346,12076635422314596
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,937113,937118,4194304,256,0,0,28,24,157632,0x7f141aca3600,0x7f12eac36c00,12076635422336677,12076635422349105,12076635422596943,12076635422617269
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,937113,937118,4194304,256,0,0,24,24,159616,0x7f141aca3500,0x7f12eac36c40,12076635422639530,12076635422651983,12076635422779182,12076635422782316
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,937113,937118,4194304,256,0,0,24,24,162368,0x7f141aca3400,0x7f12eac36c80,12076635422809646,12076635422822221,12076635423065899,12076635423091801
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,937113,937118,4194304,256,0,0,24,24,164608,0x7f141aca3300,0x7f12eac36cc0,12076635423124723,12076635423139659,12076635423270058,12076635423273309
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,937113,937118,4194304,256,0,0,20,24,166336,0x7f141aca3a00,0x7f12eac36d00,12076635423301031,12076635423312777,12076635423687974,12076635423709731
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,937113,937118,4194304,256,0,0,28,24,168576,0x7f141aca3900,0x7f12eac36d40,12076635423730770,12076635423742694,12076635424001732,12076635424023525
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,937113,937118,4194304,256,0,0,24,24,170816,0x7f141aca3800,0x7f12eac36d80,12076635424047569,12076635424060451,12076635424190530,12076635424193631
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,937113,937118,4194304,256,0,0,24,24,174080,0x7f141aca3700,0x7f12eac36dc0,12076635424219148,12076635424231010,12076635424509408,12076635424534595
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,937113,937118,4194304,256,0,0,24,24,176576,0x7f141aca3600,0x7f12eac36e00,12076635424565022,12076635424577727,12076635424713406,12076635424716554
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,937113,937118,4194304,256,0,0,20,24,177792,0x7f141aca3500,0x7f12eac36e40,12076635424744405,12076635424757086,12076635425204442,12076635425230269
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,937113,937118,4194304,256,0,0,28,24,180288,0x7f141aca3400,0x7f12eac36e80,12076635425252380,12076635425264602,12076635425524119,12076635425549924
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,937113,937118,4194304,256,0,0,24,24,182784,0x7f141aca3300,0x7f12eac36ec0,12076635425572696,12076635425584759,12076635425719318,12076635425722324
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,937113,937118,4194304,256,0,0,24,24,186304,0x7f141aca3a00,0x7f12eac36f00,12076635425748804,12076635425761078,12076635426074995,12076635426102401
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,937113,937118,4194304,256,0,0,24,24,189312,0x7f141aca3900,0x7f12eac36f40,12076635426135062,12076635426147634,12076635426299153,12076635426302303
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,937113,937118,4194304,256,0,0,20,24,190784,0x7f141aca3800,0x7f12eac36f80,12076635426328512,12076635426341713,12076635426859309,12076635426879818
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,937113,937118,4194304,256,0,0,28,24,193792,0x7f141aca3700,0x7f12eac36fc0,12076635426901057,12076635426913388,12076635427212746,12076635427240078
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,937113,937118,4194304,256,0,0,24,24,196800,0x7f141aca3600,0x7f12eac37000,12076635427265745,12076635427278665,12076635427434024,12076635427437244
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,937113,937118,4194304,256,0,0,24,24,201088,0x7f141aca3500,0x7f12eac37040,12076635427463754,12076635427476104,12076635427860741,12076635427886119
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,937113,937118,4194304,256,0,0,24,24,204608,0x7f141aca3400,0x7f12eac37080,12076635427916947,12076635427930180,12076635428104899,12076635428108794
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,937113,937118,4194304,256,0,0,20,24,206080,0x7f141aca3300,0x7f12eac370c0,12076635428135433,12076635428147778,12076635428758333,12076635428784581
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,937113,937118,4194304,256,0,0,28,24,209600,0x7f141aca3a00,0x7f12eac37100,12076635428805870,12076635428818013,12076635429175290,12076635429199422
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,937113,937118,4194304,256,0,0,24,24,213120,0x7f141aca3900,0x7f12eac37140,12076635429223247,12076635429236089,12076635429413208,12076635429416767
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,937113,937118,4194304,256,0,0,24,24,218176,0x7f141aca3800,0x7f12eac37180,12076635429444298,12076635429456888,12076635429912884,12076635429938858
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,937113,937118,4194304,256,0,0,24,24,222208,0x7f141aca3700,0x7f12eac371c0,12076635429972841,12076635429985363,12076635430184402,12076635430205363
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,937113,937118,4194304,256,0,0,20,24,223936,0x7f141aca3600,0x7f12eac37200,12076635430227164,12076635430240401,12076635430944556,12076635430970617
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,937113,937118,4194304,256,0,0,28,24,227968,0x7f141aca3500,0x7f12eac37240,12076635430994101,12076635431006155,12076635431378312,12076635431409674
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,937113,937118,4194304,256,0,0,24,24,232000,0x7f141aca3400,0x7f12eac37280,12076635431433167,12076635431445832,12076635431648870,12076635431673885
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,937113,937118,4194304,256,0,0,24,24,237824,0x7f141aca3300,0x7f12eac372c0,12076635431696076,12076635431708549,12076635432234465,12076635432258733
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,937113,937118,4194304,256,0,0,24,24,242368,0x7f141aca3a00,0x7f12eac37300,12076635432296844,12076635432309185,12076635432533183,12076635432559693
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,937113,937118,4194304,256,0,0,20,24,243584,0x7f141aca3900,0x7f12eac37340,12076635432582325,12076635432595102,12076635433394136,12076635433420905
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,937113,937118,4194304,256,0,0,28,24,248128,0x7f141aca3800,0x7f12eac37380,12076635433443767,12076635433456215,12076635433877812,12076635433901298
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,937113,937118,4194304,256,0,0,24,24,252672,0x7f141aca3700,0x7f12eac373c0,12076635433923951,12076635433936851,12076635434162610,12076635434191508
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,937113,937118,4194304,256,0,0,24,24,259264,0x7f141aca3600,0x7f12eac37400,12076635434215783,12076635434227889,12076635434824844,12076635434854411
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,937113,937118,4194304,256,0,0,24,24,264832,0x7f141aca3500,0x7f12eac37440,12076635434890048,12076635434903884,12076635435203881,12076635435232575
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,937113,937118,4194304,256,0,0,20,24,266304,0x7f141aca3400,0x7f12eac37480,12076635435256760,12076635435270281,12076635436256033,12076635436283199
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,937113,937118,4194304,256,0,0,28,24,271872,0x7f141aca3300,0x7f12eac374c0,12076635436306232,12076635436319232,12076635436835228,12076635436862476
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,937113,937118,4194304,256,0,0,24,24,277440,0x7f141aca3a00,0x7f12eac37500,12076635436887413,12076635436900028,12076635437171865,12076635437199734
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,937113,937118,4194304,256,0,0,12,24,279936,0x7f141aca3900,0x7f12eac37540,12076635437222847,12076635437235065,12076635437973619,12076635437994582
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,937113,937118,4194304,256,0,0,24,24,286528,0x7f141aca3800,0x7f12eac37580,12076635438036270,12076635438049938,12076635438394735,12076635438417038
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,937113,937118,4194304,256,0,0,20,24,288000,0x7f141aca3700,0x7f12eac375c0,12076635438442155,12076635438454575,12076635439629286,12076635439659199
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,937113,937118,4194304,256,0,0,32,24,294592,0x7f141aca3600,0x7f12eac37600,12076635439681911,12076635439694245,12076635440303680,12076635440333854
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,937113,937118,4194304,256,0,0,24,24,301184,0x7f141aca3500,0x7f12eac37640,12076635440356846,12076635440369280,12076635440687677,12076635440715453
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,937113,937118,4194304,256,0,0,12,24,304960,0x7f141aca3400,0x7f12eac37680,12076635440738787,12076635440751356,12076635441629109,12076635441659079
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,937113,937118,4194304,256,0,0,24,24,313600,0x7f141aca3300,0x7f12eac376c0,12076635441694455,12076635441707029,12076635442116465,12076635442145554
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,937113,937118,4194304,256,0,0,20,24,314816,0x7f141aca3a00,0x7f12eac37700,12076635442166994,12076635442179825,12076635443731492,12076635443782178
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,937113,937118,4194304,256,0,0,20,24,317568,0x7f141aca3900,0x7f12eac37740,12076635443805832,12076635443818496,12076635444614331,12076635444671001
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,937113,937118,4194304,256,0,0,12,24,320320,0x7f141aca3800,0x7f12eac37780,12076635444692712,12076635444705209,12076635445119766,12076635445169909
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,937113,937118,4194304,256,0,0,12,24,324096,0x7f141aca3700,0x7f12eac377c0,12076635445192501,12076635445205686,12076635446364558,12076635446415336
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,937113,937118,4194304,256,0,0,12,24,328896,0x7f141aca3600,0x7f12eac37800,12076635446449770,12076635446462477,12076635447247272,12076635447297717
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,937113,937118,4194304,256,0,0,20,24,330112,0x7f141aca3500,0x7f12eac37840,12076635447320820,12076635447334311,12076635450390770,12076635450441415
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,937113,937118,4194304,256,0,0,20,24,332864,0x7f141aca3400,0x7f12eac37880,12076635450465380,12076635450477969,12076635452023558,12076635452074603
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,937113,937118,4194304,256,0,0,12,24,335616,0x7f141aca3300,0x7f12eac378c0,12076635452099299,12076635452111878,12076635452901312,12076635452951614
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,937113,937118,4194304,256,0,0,12,24,339392,0x7f141aca3a00,0x7f12eac37900,12076635452975879,12076635452989471,12076635455272336,12076635455325831
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,937113,937118,4194304,256,0,0,12,24,344192,0x7f141aca3900,0x7f12eac37940,12076635455360435,12076635455373615,12076635456908484,12076635456958598
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,937113,937118,4194304,256,0,0,20,24,345408,0x7f141aca3800,0x7f12eac37980,12076635456981360,12076635456994724,12076635463054681,12076635463108808
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,937113,937118,4194304,256,0,0,20,24,348160,0x7f141aca3700,0x7f12eac379c0,12076635463132151,12076635463145081,12076635466191299,12076635466241976
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,937113,937118,4194304,256,0,0,12,24,350912,0x7f141aca3600,0x7f12eac37a00,12076635466265570,12076635466278339,12076635467816888,12076635467867189
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,937113,937118,4194304,256,0,0,12,24,0,0x7f141aca3500,0x7f12eac37a40,12076635467890693,12076635467903287,12076635472429176,12076635472482624
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 937113 937118 33554432 256 0 0 8 32 6464 0x0 0x7f12eac04180 12076635381227990 12076635381273678 12076635381598795 12076635381689318
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 937113 937118 32768 256 0 0 24 24 12480 0x0 0x7f12eac35100 12076635396787522 12076635396887551 12076635396894271 12076635396915901
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 4 937113 937118 4194304 256 0 0 24 24 12928 0x7f141aca3900 0x7f12eac35140 12076635396946107 12076635396958910 12076635397089629 12076635397093471
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 937113 937118 4194304 256 0 0 36 24 13632 0x7f141aca3800 0x7f12eac35180 12076635397153844 12076635397172188 12076635397417626 12076635397502262
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 8 937113 937118 4194304 256 0 0 28 24 14080 0x7f141aca3700 0x7f12eac351c0 12076635397530284 12076635397541945 12076635397788343 12076635397870096
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 10 937113 937118 4194304 256 0 0 24 24 14528 0x7f141aca3600 0x7f12eac35200 12076635397898148 12076635397909782 12076635398035381 12076635398039221
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 12 937113 937118 4194304 256 0 0 24 24 14976 0x7f141aca3500 0x7f12eac35240 12076635398076520 12076635398088341 12076635398213780 12076635398217131
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 14 937113 937118 4194304 256 0 0 24 24 15424 0x7f141aca3400 0x7f12eac35280 12076635398270070 12076635398281939 12076635398406418 12076635398409309
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 937113 937118 4194304 256 0 0 28 24 16128 0x7f141aca3300 0x7f12eac352c0 12076635398437431 12076635398448658 12076635398696176 12076635398741717
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 18 937113 937118 4194304 256 0 0 28 24 16832 0x7f141aca3a00 0x7f12eac35300 12076635398764199 12076635398777615 12076635399025613 12076635399071551
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 20 937113 937118 4194304 256 0 0 24 24 17536 0x7f141aca3900 0x7f12eac35340 12076635399094343 12076635399107533 12076635399232652 12076635399235516
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 22 937113 937118 4194304 256 0 0 24 24 18240 0x7f141aca3800 0x7f12eac35380 12076635399263287 12076635399276171 12076635399401610 12076635399404741
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 24 937113 937118 4194304 256 0 0 24 24 18944 0x7f141aca3700 0x7f12eac353c0 12076635399444655 12076635399456170 12076635399581449 12076635399584315
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 937113 937118 4194304 256 0 0 28 24 19904 0x7f141aca3600 0x7f12eac35400 12076635399611585 12076635399623689 12076635399870247 12076635399893239
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 28 937113 937118 4194304 256 0 0 28 24 20608 0x7f141aca3500 0x7f12eac35440 12076635399918546 12076635399929606 12076635400177284 12076635400223223
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 30 937113 937118 4194304 256 0 0 24 24 21312 0x7f141aca3400 0x7f12eac35480 12076635400245675 12076635400257444 12076635400382403 12076635400385244
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 32 937113 937118 4194304 256 0 0 24 24 22016 0x7f141aca3300 0x7f12eac354c0 12076635400412726 12076635400425762 12076635400550881 12076635400554048
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 34 937113 937118 4194304 256 0 0 24 24 22720 0x7f141aca3a00 0x7f12eac35500 12076635400591819 12076635400602881 12076635400727040 12076635400730136
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 937113 937118 4194304 256 0 0 28 24 23680 0x7f141aca3900 0x7f12eac35540 12076635400756735 12076635400768959 12076635401016317 12076635401041185
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 38 937113 937118 4194304 256 0 0 28 24 24384 0x7f141aca3800 0x7f12eac35580 12076635401064799 12076635401076317 12076635401318875 12076635401363364
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 40 937113 937118 4194304 256 0 0 24 24 25088 0x7f141aca3700 0x7f12eac355c0 12076635401384904 12076635401395994 12076635401520153 12076635401523091
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 42 937113 937118 4194304 256 0 0 24 24 25792 0x7f141aca3600 0x7f12eac35600 12076635401549149 12076635401560473 12076635401685592 12076635401688719
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 44 937113 937118 4194304 256 0 0 24 24 26496 0x7f141aca3500 0x7f12eac35640 12076635401727772 12076635401738712 12076635401862391 12076635401865458
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 937113 937118 4194304 256 0 0 28 24 27712 0x7f141aca3400 0x7f12eac35680 12076635401892097 12076635401906710 12076635402152788 12076635402202364
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 48 937113 937118 4194304 256 0 0 28 24 28416 0x7f141aca3300 0x7f12eac356c0 12076635402225738 12076635402238868 12076635402483186 12076635402528471
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 50 937113 937118 4194304 256 0 0 24 24 29120 0x7f141aca3a00 0x7f12eac35700 12076635402552285 12076635402565585 12076635402689584 12076635402692556
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 52 937113 937118 4194304 256 0 0 24 24 30080 0x7f141aca3900 0x7f12eac35740 12076635402719877 12076635402731344 12076635402856303 12076635402859487
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 54 937113 937118 4194304 256 0 0 24 24 30784 0x7f141aca3800 0x7f12eac35780 12076635402897117 12076635402908142 12076635403032941 12076635403036506
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 937113 937118 4194304 256 0 0 28 24 32000 0x7f141aca3700 0x7f12eac357c0 12076635403063136 12076635403075181 12076635403325419 12076635403348526
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 58 937113 937118 4194304 256 0 0 28 24 32960 0x7f141aca3600 0x7f12eac35800 12076635403370758 12076635403382378 12076635403629736 12076635403674102
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 60 937113 937118 4194304 256 0 0 24 24 33920 0x7f141aca3500 0x7f12eac35840 12076635403695322 12076635403708456 12076635403832775 12076635403835713
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 62 937113 937118 4194304 256 0 0 24 24 34880 0x7f141aca3400 0x7f12eac35880 12076635403861561 12076635403873894 12076635403999973 12076635404017561
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 64 937113 937118 4194304 256 0 0 24 24 35840 0x7f141aca3300 0x7f12eac358c0 12076635404049080 12076635404060933 12076635404185572 12076635404188699
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 937113 937118 4194304 256 0 0 28 24 37312 0x7f141aca3a00 0x7f12eac35900 12076635404214627 12076635404226211 12076635404472609 12076635404497944
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 68 937113 937118 4194304 256 0 0 28 24 38272 0x7f141aca3900 0x7f12eac35940 12076635404521208 12076635404532769 12076635404779487 12076635404800427
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 70 937113 937118 4194304 256 0 0 24 24 39232 0x7f141aca3800 0x7f12eac35980 12076635404822338 12076635404835327 12076635404959806 12076635404962619
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 72 937113 937118 4194304 256 0 0 24 24 40192 0x7f141aca3700 0x7f12eac359c0 12076635404990110 12076635405002845 12076635405128444 12076635405131603
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 74 937113 937118 4194304 256 0 0 24 24 41152 0x7f141aca3600 0x7f12eac35a00 12076635405168913 12076635405183324 12076635405307323 12076635405310125
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 937113 937118 4194304 256 0 0 28 24 42624 0x7f141aca3500 0x7f12eac35a40 12076635405337246 12076635405350202 12076635405599000 12076635405648124
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 78 937113 937118 4194304 256 0 0 28 24 43584 0x7f141aca3400 0x7f12eac35a80 12076635405670105 12076635405682840 12076635405928118 12076635405950376
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 80 937113 937118 4194304 256 0 0 24 24 44544 0x7f141aca3300 0x7f12eac35ac0 12076635405973099 12076635405985877 12076635406110996 12076635406114031
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 82 937113 937118 4194304 256 0 0 24 24 45760 0x7f141aca3a00 0x7f12eac35b00 12076635406142003 12076635406154996 12076635406281235 12076635406284337
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 84 937113 937118 4194304 256 0 0 24 24 46720 0x7f141aca3900 0x7f12eac35b40 12076635406320164 12076635406332754 12076635406457553 12076635406460555
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 937113 937118 4194304 256 0 0 28 24 48448 0x7f141aca3800 0x7f12eac35b80 12076635406486964 12076635406499633 12076635406758511 12076635406779148
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 88 937113 937118 4194304 256 0 0 28 24 49408 0x7f141aca3700 0x7f12eac35bc0 12076635406801009 12076635406814031 12076635407059469 12076635407081470
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 90 937113 937118 4194304 256 0 0 24 24 50368 0x7f141aca3600 0x7f12eac35c00 12076635407105164 12076635407117868 12076635407242507 12076635407245415
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 92 937113 937118 4194304 256 0 0 24 24 51584 0x7f141aca3500 0x7f12eac35c40 12076635407272956 12076635407285547 12076635407412426 12076635407415111
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 94 937113 937118 4194304 256 0 0 24 24 52544 0x7f141aca3400 0x7f12eac35c80 12076635407453933 12076635407466825 12076635407592104 12076635407594845
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 937113 937118 4194304 256 0 0 28 24 54272 0x7f141aca3300 0x7f12eac35cc0 12076635407622326 12076635407634984 12076635407894822 12076635407915882
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 98 937113 937118 4194304 256 0 0 28 24 55488 0x7f141aca3a00 0x7f12eac35d00 12076635407936881 12076635407950021 12076635408198179 12076635408219407
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 100 937113 937118 4194304 256 0 0 24 24 56704 0x7f141aca3900 0x7f12eac35d40 12076635408241548 12076635408253539 12076635408378498 12076635408381258
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 102 937113 937118 4194304 256 0 0 24 24 58176 0x7f141aca3800 0x7f12eac35d80 12076635408408118 12076635408420098 12076635408548897 12076635408551755
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 104 937113 937118 4194304 256 0 0 24 24 59392 0x7f141aca3700 0x7f12eac35dc0 12076635408587912 12076635408600736 12076635408726175 12076635408729045
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 937113 937118 4194304 256 0 0 28 24 61376 0x7f141aca3600 0x7f12eac35e00 12076635408756175 12076635408769215 12076635409028413 12076635409055091
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 108 937113 937118 4194304 256 0 0 28 24 62592 0x7f141aca3500 0x7f12eac35e40 12076635409078054 12076635409090492 12076635409336090 12076635409357213
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 110 937113 937118 4194304 256 0 0 24 24 63808 0x7f141aca3400 0x7f12eac35e80 12076635409381038 12076635409393050 12076635409518009 12076635409521078
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 112 937113 937118 4194304 256 0 0 24 24 65280 0x7f141aca3300 0x7f12eac35ec0 12076635409548990 12076635409561048 12076635409691127 12076635409693990
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 114 937113 937118 4194304 256 0 0 24 24 66496 0x7f141aca3a00 0x7f12eac35f00 12076635409730868 12076635409743767 12076635409869366 12076635409872251
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 937113 937118 4194304 256 0 0 28 24 68480 0x7f141aca3900 0x7f12eac35f40 12076635409898220 12076635409911446 12076635410171763 12076635410196424
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 118 937113 937118 4194304 256 0 0 28 24 69696 0x7f141aca3800 0x7f12eac35f80 12076635410219377 12076635410232083 12076635410475601 12076635410496182
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 120 937113 937118 4194304 256 0 0 24 24 70912 0x7f141aca3700 0x7f12eac35fc0 12076635410518233 12076635410531761 12076635410656720 12076635410659586
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 122 937113 937118 4194304 256 0 0 24 24 72384 0x7f141aca3600 0x7f12eac36000 12076635410686656 12076635410698799 12076635410835438 12076635410838318
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 124 937113 937118 4194304 256 0 0 24 24 73600 0x7f141aca3500 0x7f12eac36040 12076635410876219 12076635410889358 12076635411013837 12076635411016830
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 937113 937118 4194304 256 0 0 28 24 75840 0x7f141aca3400 0x7f12eac36080 12076635411045444 12076635411057996 12076635411323434 12076635411347035
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 128 937113 937118 4194304 256 0 0 28 24 77056 0x7f141aca3300 0x7f12eac360c0 12076635411368895 12076635411381194 12076635411663431 12076635411684903
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 130 937113 937118 4194304 256 0 0 24 24 78272 0x7f141aca3a00 0x7f12eac36100 12076635411706433 12076635411719591 12076635411844870 12076635411848087
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 132 937113 937118 4194304 256 0 0 24 24 80000 0x7f141aca3900 0x7f12eac36140 12076635411875357 12076635411888710 12076635412030948 12076635412034073
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 134 937113 937118 4194304 256 0 0 24 24 81216 0x7f141aca3800 0x7f12eac36180 12076635412071552 12076635412083908 12076635412208867 12076635412211873
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 937113 937118 4194304 256 0 0 28 24 83456 0x7f141aca3700 0x7f12eac361c0 12076635412238493 12076635412251267 12076635412509185 12076635412532029
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 138 937113 937118 4194304 256 0 0 28 24 84928 0x7f141aca3600 0x7f12eac36200 12076635412553829 12076635412566624 12076635412815422 12076635412838900
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 140 937113 937118 4194304 256 0 0 24 24 86400 0x7f141aca3500 0x7f12eac36240 12076635412861842 12076635412874782 12076635413000861 12076635413015598
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 142 937113 937118 4194304 256 0 0 24 24 88128 0x7f141aca3400 0x7f12eac36280 12076635413038771 12076635413051260 12076635413201019 12076635413203899
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 144 937113 937118 4194304 256 0 0 24 24 89600 0x7f141aca3300 0x7f12eac362c0 12076635413254533 12076635413268058 12076635413393977 12076635413397338
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 937113 937118 4194304 256 0 0 28 24 92096 0x7f141aca3a00 0x7f12eac36300 12076635413425220 12076635413437177 12076635413692695 12076635413714188
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 148 937113 937118 4194304 256 0 0 28 24 93568 0x7f141aca3900 0x7f12eac36340 12076635413736950 12076635413748855 12076635413996053 12076635414023323
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 150 937113 937118 4194304 256 0 0 24 24 95040 0x7f141aca3800 0x7f12eac36380 12076635414046696 12076635414059412 12076635414185011 12076635414188169
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 152 937113 937118 4194304 256 0 0 24 24 96768 0x7f141aca3700 0x7f12eac363c0 12076635414216081 12076635414228851 12076635414386609 12076635414389504
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 154 937113 937118 4194304 256 0 0 24 24 98240 0x7f141aca3600 0x7f12eac36400 12076635414427425 12076635414440049 12076635414564528 12076635414567485
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 937113 937118 4194304 256 0 0 28 24 100736 0x7f141aca3500 0x7f12eac36440 12076635414594676 12076635414607408 12076635414869965 12076635414894984
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 158 937113 937118 4194304 256 0 0 28 24 102208 0x7f141aca3400 0x7f12eac36480 12076635414916214 12076635414928365 12076635415172683 12076635415199030
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 160 937113 937118 4194304 256 0 0 24 24 103680 0x7f141aca3300 0x7f12eac364c0 12076635415220600 12076635415233003 12076635415358602 12076635415361933
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 162 937113 937118 4194304 256 0 0 24 24 105664 0x7f141aca3a00 0x7f12eac36500 12076635415388332 12076635415401481 12076635415566920 12076635415570130
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 164 937113 937118 4194304 256 0 0 24 24 107136 0x7f141aca3900 0x7f12eac36540 12076635415606828 12076635415618919 12076635415744198 12076635415747270
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 937113 937118 4194304 256 0 0 28 24 109888 0x7f141aca3800 0x7f12eac36580 12076635415776765 12076635415790918 12076635416046596 12076635416067956
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 168 937113 937118 4194304 256 0 0 28 24 111360 0x7f141aca3700 0x7f12eac365c0 12076635416090648 12076635416103236 12076635416352994 12076635416374456
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 170 937113 937118 4194304 256 0 0 24 24 112832 0x7f141aca3600 0x7f12eac36600 12076635416397138 12076635416410273 12076635416534592 12076635416537670
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 172 937113 937118 4194304 256 0 0 24 24 114816 0x7f141aca3500 0x7f12eac36640 12076635416564570 12076635416576672 12076635416748990 12076635416751969
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 174 937113 937118 4194304 256 0 0 24 24 116288 0x7f141aca3400 0x7f12eac36680 12076635416789027 12076635416801950 12076635416927389 12076635416930350
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 937113 937118 4194304 256 0 0 28 24 119040 0x7f141aca3300 0x7f12eac366c0 12076635416957781 12076635416970429 12076635417226906 12076635417249093
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 178 937113 937118 4194304 256 0 0 28 24 120768 0x7f141aca3a00 0x7f12eac36700 12076635417270323 12076635417283226 12076635417531864 12076635417553399
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 180 937113 937118 4194304 256 0 0 24 24 122496 0x7f141aca3900 0x7f12eac36740 12076635417575741 12076635417587864 12076635417713303 12076635417716332
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 182 937113 937118 4194304 256 0 0 24 24 124736 0x7f141aca3800 0x7f12eac36780 12076635417743282 12076635417755862 12076635417938421 12076635417941381
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 184 937113 937118 4194304 256 0 0 24 24 126464 0x7f141aca3700 0x7f12eac367c0 12076635417979311 12076635417991540 12076635418116979 12076635418120384
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 937113 937118 4194304 256 0 0 20 24 127936 0x7f141aca3600 0x7f12eac36800 12076635418147274 12076635418159699 12076635418423217 12076635418446440
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 188 937113 937118 4194304 256 0 0 28 24 129664 0x7f141aca3500 0x7f12eac36840 12076635418471607 12076635418484016 12076635418732334 12076635418753562
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 190 937113 937118 4194304 256 0 0 24 24 131392 0x7f141aca3400 0x7f12eac36880 12076635418775743 12076635418787854 12076635418914253 12076635418917236
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 192 937113 937118 4194304 256 0 0 24 24 133632 0x7f141aca3300 0x7f12eac368c0 12076635418943816 12076635418956812 12076635419147851 12076635419163013
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 194 937113 937118 4194304 256 0 0 24 24 135360 0x7f141aca3a00 0x7f12eac36900 12076635419194602 12076635419207370 12076635419333769 12076635419337057
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 937113 937118 4194304 256 0 0 20 24 136832 0x7f141aca3900 0x7f12eac36940 12076635419364268 12076635419377609 12076635419660647 12076635419684864
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 198 937113 937118 4194304 256 0 0 28 24 138560 0x7f141aca3800 0x7f12eac36980 12076635419706344 12076635419718566 12076635419964484 12076635419988038
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 200 937113 937118 4194304 256 0 0 24 24 140288 0x7f141aca3700 0x7f12eac369c0 12076635420018034 12076635420031364 12076635420157603 12076635420160659
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 202 937113 937118 4194304 256 0 0 24 24 142784 0x7f141aca3600 0x7f12eac36a00 12076635420188791 12076635420201602 12076635420411681 12076635420432535
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 204 937113 937118 4194304 256 0 0 24 24 144768 0x7f141aca3500 0x7f12eac36a40 12076635420463543 12076635420476320 12076635420603359 12076635420606388
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 937113 937118 4194304 256 0 0 20 24 145728 0x7f141aca3400 0x7f12eac36a80 12076635420633869 12076635420647039 12076635420953436 12076635420974854
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 208 937113 937118 4194304 256 0 0 28 24 147712 0x7f141aca3300 0x7f12eac36ac0 12076635420996624 12076635421013596 12076635421265754 12076635421288186
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 210 937113 937118 4194304 256 0 0 24 24 149696 0x7f141aca3a00 0x7f12eac36b00 12076635421308895 12076635421322073 12076635421450552 12076635421453774
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 212 937113 937118 4194304 256 0 0 24 24 152192 0x7f141aca3900 0x7f12eac36b40 12076635421480304 12076635421492792 12076635421720630 12076635421746299
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 214 937113 937118 4194304 256 0 0 24 24 154176 0x7f141aca3800 0x7f12eac36b80 12076635421779290 12076635421791990 12076635421919189 12076635421922366
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 937113 937118 4194304 256 0 0 20 24 155648 0x7f141aca3700 0x7f12eac36bc0 12076635421949787 12076635421962868 12076635422291346 12076635422314596
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 218 937113 937118 4194304 256 0 0 28 24 157632 0x7f141aca3600 0x7f12eac36c00 12076635422336677 12076635422349105 12076635422596943 12076635422617269
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 220 937113 937118 4194304 256 0 0 24 24 159616 0x7f141aca3500 0x7f12eac36c40 12076635422639530 12076635422651983 12076635422779182 12076635422782316
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 222 937113 937118 4194304 256 0 0 24 24 162368 0x7f141aca3400 0x7f12eac36c80 12076635422809646 12076635422822221 12076635423065899 12076635423091801
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 224 937113 937118 4194304 256 0 0 24 24 164608 0x7f141aca3300 0x7f12eac36cc0 12076635423124723 12076635423139659 12076635423270058 12076635423273309
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 937113 937118 4194304 256 0 0 20 24 166336 0x7f141aca3a00 0x7f12eac36d00 12076635423301031 12076635423312777 12076635423687974 12076635423709731
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 228 937113 937118 4194304 256 0 0 28 24 168576 0x7f141aca3900 0x7f12eac36d40 12076635423730770 12076635423742694 12076635424001732 12076635424023525
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 230 937113 937118 4194304 256 0 0 24 24 170816 0x7f141aca3800 0x7f12eac36d80 12076635424047569 12076635424060451 12076635424190530 12076635424193631
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 232 937113 937118 4194304 256 0 0 24 24 174080 0x7f141aca3700 0x7f12eac36dc0 12076635424219148 12076635424231010 12076635424509408 12076635424534595
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 234 937113 937118 4194304 256 0 0 24 24 176576 0x7f141aca3600 0x7f12eac36e00 12076635424565022 12076635424577727 12076635424713406 12076635424716554
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 937113 937118 4194304 256 0 0 20 24 177792 0x7f141aca3500 0x7f12eac36e40 12076635424744405 12076635424757086 12076635425204442 12076635425230269
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 238 937113 937118 4194304 256 0 0 28 24 180288 0x7f141aca3400 0x7f12eac36e80 12076635425252380 12076635425264602 12076635425524119 12076635425549924
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 240 937113 937118 4194304 256 0 0 24 24 182784 0x7f141aca3300 0x7f12eac36ec0 12076635425572696 12076635425584759 12076635425719318 12076635425722324
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 242 937113 937118 4194304 256 0 0 24 24 186304 0x7f141aca3a00 0x7f12eac36f00 12076635425748804 12076635425761078 12076635426074995 12076635426102401
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 244 937113 937118 4194304 256 0 0 24 24 189312 0x7f141aca3900 0x7f12eac36f40 12076635426135062 12076635426147634 12076635426299153 12076635426302303
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 937113 937118 4194304 256 0 0 20 24 190784 0x7f141aca3800 0x7f12eac36f80 12076635426328512 12076635426341713 12076635426859309 12076635426879818
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 248 937113 937118 4194304 256 0 0 28 24 193792 0x7f141aca3700 0x7f12eac36fc0 12076635426901057 12076635426913388 12076635427212746 12076635427240078
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 250 937113 937118 4194304 256 0 0 24 24 196800 0x7f141aca3600 0x7f12eac37000 12076635427265745 12076635427278665 12076635427434024 12076635427437244
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 252 937113 937118 4194304 256 0 0 24 24 201088 0x7f141aca3500 0x7f12eac37040 12076635427463754 12076635427476104 12076635427860741 12076635427886119
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 254 937113 937118 4194304 256 0 0 24 24 204608 0x7f141aca3400 0x7f12eac37080 12076635427916947 12076635427930180 12076635428104899 12076635428108794
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 937113 937118 4194304 256 0 0 20 24 206080 0x7f141aca3300 0x7f12eac370c0 12076635428135433 12076635428147778 12076635428758333 12076635428784581
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 258 937113 937118 4194304 256 0 0 28 24 209600 0x7f141aca3a00 0x7f12eac37100 12076635428805870 12076635428818013 12076635429175290 12076635429199422
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 260 937113 937118 4194304 256 0 0 24 24 213120 0x7f141aca3900 0x7f12eac37140 12076635429223247 12076635429236089 12076635429413208 12076635429416767
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 262 937113 937118 4194304 256 0 0 24 24 218176 0x7f141aca3800 0x7f12eac37180 12076635429444298 12076635429456888 12076635429912884 12076635429938858
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 264 937113 937118 4194304 256 0 0 24 24 222208 0x7f141aca3700 0x7f12eac371c0 12076635429972841 12076635429985363 12076635430184402 12076635430205363
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 937113 937118 4194304 256 0 0 20 24 223936 0x7f141aca3600 0x7f12eac37200 12076635430227164 12076635430240401 12076635430944556 12076635430970617
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 268 937113 937118 4194304 256 0 0 28 24 227968 0x7f141aca3500 0x7f12eac37240 12076635430994101 12076635431006155 12076635431378312 12076635431409674
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 270 937113 937118 4194304 256 0 0 24 24 232000 0x7f141aca3400 0x7f12eac37280 12076635431433167 12076635431445832 12076635431648870 12076635431673885
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 272 937113 937118 4194304 256 0 0 24 24 237824 0x7f141aca3300 0x7f12eac372c0 12076635431696076 12076635431708549 12076635432234465 12076635432258733
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 274 937113 937118 4194304 256 0 0 24 24 242368 0x7f141aca3a00 0x7f12eac37300 12076635432296844 12076635432309185 12076635432533183 12076635432559693
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 937113 937118 4194304 256 0 0 20 24 243584 0x7f141aca3900 0x7f12eac37340 12076635432582325 12076635432595102 12076635433394136 12076635433420905
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 278 937113 937118 4194304 256 0 0 28 24 248128 0x7f141aca3800 0x7f12eac37380 12076635433443767 12076635433456215 12076635433877812 12076635433901298
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 280 937113 937118 4194304 256 0 0 24 24 252672 0x7f141aca3700 0x7f12eac373c0 12076635433923951 12076635433936851 12076635434162610 12076635434191508
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 282 937113 937118 4194304 256 0 0 24 24 259264 0x7f141aca3600 0x7f12eac37400 12076635434215783 12076635434227889 12076635434824844 12076635434854411
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 284 937113 937118 4194304 256 0 0 24 24 264832 0x7f141aca3500 0x7f12eac37440 12076635434890048 12076635434903884 12076635435203881 12076635435232575
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 937113 937118 4194304 256 0 0 20 24 266304 0x7f141aca3400 0x7f12eac37480 12076635435256760 12076635435270281 12076635436256033 12076635436283199
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 288 937113 937118 4194304 256 0 0 28 24 271872 0x7f141aca3300 0x7f12eac374c0 12076635436306232 12076635436319232 12076635436835228 12076635436862476
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 290 937113 937118 4194304 256 0 0 24 24 277440 0x7f141aca3a00 0x7f12eac37500 12076635436887413 12076635436900028 12076635437171865 12076635437199734
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 292 937113 937118 4194304 256 0 0 12 24 279936 0x7f141aca3900 0x7f12eac37540 12076635437222847 12076635437235065 12076635437973619 12076635437994582
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 294 937113 937118 4194304 256 0 0 24 24 286528 0x7f141aca3800 0x7f12eac37580 12076635438036270 12076635438049938 12076635438394735 12076635438417038
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 937113 937118 4194304 256 0 0 20 24 288000 0x7f141aca3700 0x7f12eac375c0 12076635438442155 12076635438454575 12076635439629286 12076635439659199
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 298 937113 937118 4194304 256 0 0 32 24 294592 0x7f141aca3600 0x7f12eac37600 12076635439681911 12076635439694245 12076635440303680 12076635440333854
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 300 937113 937118 4194304 256 0 0 24 24 301184 0x7f141aca3500 0x7f12eac37640 12076635440356846 12076635440369280 12076635440687677 12076635440715453
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 302 937113 937118 4194304 256 0 0 12 24 304960 0x7f141aca3400 0x7f12eac37680 12076635440738787 12076635440751356 12076635441629109 12076635441659079
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 304 937113 937118 4194304 256 0 0 24 24 313600 0x7f141aca3300 0x7f12eac376c0 12076635441694455 12076635441707029 12076635442116465 12076635442145554
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 937113 937118 4194304 256 0 0 20 24 314816 0x7f141aca3a00 0x7f12eac37700 12076635442166994 12076635442179825 12076635443731492 12076635443782178
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 308 937113 937118 4194304 256 0 0 20 24 317568 0x7f141aca3900 0x7f12eac37740 12076635443805832 12076635443818496 12076635444614331 12076635444671001
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 310 937113 937118 4194304 256 0 0 12 24 320320 0x7f141aca3800 0x7f12eac37780 12076635444692712 12076635444705209 12076635445119766 12076635445169909
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 312 937113 937118 4194304 256 0 0 12 24 324096 0x7f141aca3700 0x7f12eac377c0 12076635445192501 12076635445205686 12076635446364558 12076635446415336
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 314 937113 937118 4194304 256 0 0 12 24 328896 0x7f141aca3600 0x7f12eac37800 12076635446449770 12076635446462477 12076635447247272 12076635447297717
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 937113 937118 4194304 256 0 0 20 24 330112 0x7f141aca3500 0x7f12eac37840 12076635447320820 12076635447334311 12076635450390770 12076635450441415
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 318 937113 937118 4194304 256 0 0 20 24 332864 0x7f141aca3400 0x7f12eac37880 12076635450465380 12076635450477969 12076635452023558 12076635452074603
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 320 937113 937118 4194304 256 0 0 12 24 335616 0x7f141aca3300 0x7f12eac378c0 12076635452099299 12076635452111878 12076635452901312 12076635452951614
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 322 937113 937118 4194304 256 0 0 12 24 339392 0x7f141aca3a00 0x7f12eac37900 12076635452975879 12076635452989471 12076635455272336 12076635455325831
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 324 937113 937118 4194304 256 0 0 12 24 344192 0x7f141aca3900 0x7f12eac37940 12076635455360435 12076635455373615 12076635456908484 12076635456958598
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 937113 937118 4194304 256 0 0 20 24 345408 0x7f141aca3800 0x7f12eac37980 12076635456981360 12076635456994724 12076635463054681 12076635463108808
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 328 937113 937118 4194304 256 0 0 20 24 348160 0x7f141aca3700 0x7f12eac379c0 12076635463132151 12076635463145081 12076635466191299 12076635466241976
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 330 937113 937118 4194304 256 0 0 12 24 350912 0x7f141aca3600 0x7f12eac37a00 12076635466265570 12076635466278339 12076635467816888 12076635467867189
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 332 937113 937118 4194304 256 0 0 12 24 0 0x7f141aca3500 0x7f12eac37a40 12076635467890693 12076635467903287 12076635472429176 12076635472482624
@@ -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",0,0,0,236503,236503,33554432,256,0,0,4,32,4160,0x0,0x7fe83c204280,385832,385832,524288,4718592,682094,76386864,17833173257611,17832460487290,17833324063793,17833324177862
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,236503,236503,32768,256,0,0,12,24,13888,0x0,0x7fe83c223f80,34124,34124,512,8192,5540,624020,17833329373303,17833324063793,17833329503317,17833329508120
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,236503,236503,4194304,256,0,0,12,24,14336,0x7fe83f16b380,0x7fe83c223fc0,166451,166451,65536,917504,140662,15737800,17833329547519,17833329503317,17833329887317,17833329890091
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,236503,236503,4194304,256,0,0,16,24,15040,0x7fe83f16b200,0x7fe83c224000,320813,320813,65536,1114112,167869,18973284,17833329928940,17833329887317,17833330326517,17833330329380
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,236503,236503,4194304,256,0,0,16,24,15488,0x7fe83f16b080,0x7fe83c224040,323006,323006,65536,917504,146978,16539568,17833330364489,17833330326517,17833330747798,17833330753919
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,236503,236503,4194304,256,0,0,12,24,15936,0x7fe83cb0bf00,0x7fe83c224080,168550,168550,65536,1048576,159174,17856292,17833330784798,17833330747798,17833331068118,17833331070481
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,236503,236503,4194304,256,0,0,12,24,16384,0x7fe83cb0bd80,0x7fe83c2240c0,168572,168572,65536,983040,148090,16569436,17833331104930,17833331068118,17833331386678,17833331389103
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,236503,236503,4194304,256,0,0,12,24,17088,0x7fe83cb0bc00,0x7fe83c224100,167664,167664,65536,1114112,162610,18224860,17833331435702,17833331386678,17833331703318,17833331705705
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,236503,236503,4194304,256,0,0,16,24,17792,0x7fe83cb0ba80,0x7fe83c224140,320079,320079,65536,1310720,202232,22647988,17833331740015,17833331703318,17833332108599,17833332110925
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,236503,236503,4194304,256,0,0,16,24,18496,0x7fe83cb0b900,0x7fe83c224180,316809,316809,65536,1179648,176290,19855416,17833332143565,17833332108599,17833332528439,17833332530935
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,236503,236503,4194304,256,0,0,16,24,19200,0x7fe83cb0b780,0x7fe83c2241c0,168281,168281,65536,1245184,188620,21166232,17833332564054,17833332528439,17833332839959,17833332842307
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,236503,236503,4194304,256,0,0,16,24,19904,0x7fe83cb0b600,0x7fe83c224200,169494,169494,65536,1245184,202520,22612512,17833332876086,17833332839959,17833333154039,17833333156369
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,236503,236503,4194304,256,0,0,12,24,20608,0x7fe83f16b480,0x7fe83c224240,171299,171299,65536,1245184,200754,22467976,17833333198828,17833333154039,17833333471320,17833333473552
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,236503,236503,4194304,256,0,0,16,24,21312,0x7fe83f16b300,0x7fe83c224280,320776,320776,65536,1441792,216093,24168728,17833333508101,17833333471320,17833333874840,17833333881351
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,236503,236503,4194304,256,0,0,16,24,22016,0x7fe83f16b180,0x7fe83c2242c0,316393,316393,65536,1310720,197617,22204988,17833333911551,17833333874840,17833334286360,17833334289041
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,236503,236503,4194304,256,0,0,16,24,22720,0x7fe83f16b000,0x7fe83c224300,169264,169264,65536,1376256,205151,23034404,17833334324160,17833334286360,17833334608441,17833334610943
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,236503,236503,4194304,256,0,0,12,24,23424,0x7fe83cb0be80,0x7fe83c224340,168263,168263,65536,1441792,221753,24858852,17833334644352,17833334608441,17833334922841,17833334925195
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,236503,236503,4194304,256,0,0,12,24,24128,0x7fe83cb0bd00,0x7fe83c224380,167492,167492,65536,1310720,195746,21931324,17833334967074,17833334922841,17833335246361,17833335248667
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,236503,236503,4194304,256,0,0,16,24,24832,0x7fe83cb0bb80,0x7fe83c2243c0,316291,316291,65536,1572864,232311,26113788,17833335285227,17833335246361,17833335624441,17833335626348
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,236503,236503,4194304,256,0,0,16,24,25536,0x7fe83cb0ba00,0x7fe83c224400,312673,312673,65536,1441792,209241,23385064,17833335661197,17833335624441,17833335999642,17833336001459
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,236503,236503,4194304,256,0,0,12,24,26240,0x7fe83cb0b880,0x7fe83c224440,166555,166555,65536,1507328,224652,25196208,17833336035928,17833335999642,17833336288122,17833336290022
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,236503,236503,4194304,256,0,0,12,24,26944,0x7fe83cb0b700,0x7fe83c224480,168033,168033,65536,1638400,243000,27172084,17833336324411,17833336288122,17833336577882,17833336579724
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,236503,236503,4194304,256,0,0,12,24,27648,0x7fe83f16b580,0x7fe83c2244c0,169325,169325,65536,1441792,215804,24164768,17833336621253,17833336577882,17833336865242,17833336867167
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,236503,236503,4194304,256,0,0,16,24,28608,0x7fe83f16b400,0x7fe83c224500,317983,317983,65536,1703936,251876,28216384,17833336903336,17833336865242,17833337239963,17833337241868
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,236503,236503,4194304,256,0,0,16,24,29312,0x7fe83f16b280,0x7fe83c224540,316071,316071,65536,1572864,233891,26185384,17833337276507,17833337239963,17833337615003,17833337616889
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,236503,236503,4194304,256,0,0,12,24,30016,0x7fe83f16b100,0x7fe83c224580,167827,167827,65536,1638400,243052,27250156,17833337650858,17833337615003,17833337911803,17833337913661
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,236503,236503,4194304,256,0,0,8,24,30976,0x7fe83cb0bf80,0x7fe83c2245c0,167561,167561,65536,1835008,270019,30313992,17833337948630,17833337911803,17833338216123,17833338218214
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,236503,236503,4194304,256,0,0,12,24,31680,0x7fe83cb0be00,0x7fe83c224600,166155,166155,65536,1507328,223562,25065536,17833338260273,17833338216123,17833338505724,17833338507656
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,236503,236503,4194304,256,0,0,16,24,32640,0x7fe83cb0bc80,0x7fe83c224640,313708,313708,65536,1835008,272596,30454488,17833338544396,17833338505724,17833338882684,17833338884677
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,236503,236503,4194304,256,0,0,12,24,33600,0x7fe83cb0bb00,0x7fe83c224680,313561,313561,65536,1703936,248219,27816044,17833338919186,17833338882684,17833339257084,17833339259098
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,236503,236503,4194304,256,0,0,12,24,34560,0x7fe83cb0b980,0x7fe83c2246c0,168531,168531,65536,1769472,264701,29659096,17833339293197,17833339257084,17833339545244,17833339547101
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,236503,236503,4194304,256,0,0,8,24,35520,0x7fe83cb0b800,0x7fe83c224700,168533,168533,65536,2031616,303743,34041364,17833339581850,17833339545244,17833339833885,17833339835803
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,236503,236503,4194304,256,0,0,12,24,36224,0x7fe83cb0b680,0x7fe83c224740,168721,168721,65536,1638400,243880,27433232,17833339877512,17833339833885,17833340126845,17833340128726
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,236503,236503,4194304,256,0,0,12,24,37184,0x7fe83f16b500,0x7fe83c224780,311801,311801,65536,1966080,288908,32275144,17833340163205,17833340126845,17833340509405,17833340511177
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,236503,236503,4194304,256,0,0,12,24,38144,0x7fe83f16b380,0x7fe83c2247c0,314592,314592,65536,1835008,272159,30484976,17833340546636,17833340509405,17833340889245,17833340891087
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,236503,236503,4194304,256,0,0,12,24,39104,0x7fe83f16b200,0x7fe83c224800,168011,168011,65536,1900544,281499,31452584,17833340925936,17833340889245,17833341181406,17833341183040
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,236503,236503,4194304,256,0,0,8,24,40320,0x7fe83f16b080,0x7fe83c224840,168636,168636,65536,2228224,328196,36754620,17833341218079,17833341181406,17833341472606,17833341474483
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,236503,236503,4194304,256,0,0,12,24,41280,0x7fe83cb0bf00,0x7fe83c224880,169134,169134,65536,1703936,257950,28833172,17833341515762,17833341472606,17833341761886,17833341763986
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,236503,236503,4194304,256,0,0,12,24,42240,0x7fe83cb0bd80,0x7fe83c2248c0,311600,311600,65536,2097152,311380,34862612,17833341798245,17833341761886,17833342137566,17833342139966
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,236503,236503,4194304,256,0,0,12,24,43200,0x7fe83cb0bc00,0x7fe83c224900,311542,311542,65536,1966080,284002,31844304,17833342176125,17833342137566,17833342523327,17833342525247
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,236503,236503,4194304,256,0,0,8,24,44160,0x7fe83cb0ba80,0x7fe83c224940,168342,168342,65536,2031616,302765,33940188,17833342559536,17833342523327,17833342815647,17833342817649
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,236503,236503,4194304,256,0,0,12,24,45376,0x7fe83cb0b900,0x7fe83c224980,169165,169165,65536,2424832,362267,40550672,17833342852049,17833342815647,17833343114047,17833343115852
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,236503,236503,4194304,256,0,0,12,24,46336,0x7fe83cb0b780,0x7fe83c2249c0,168186,168186,65536,1835008,272130,30424784,17833343157201,17833343114047,17833343405727,17833343407425
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,236503,236503,4194304,256,0,0,12,24,47552,0x7fe83cb0b600,0x7fe83c224a00,312770,312770,65536,2228224,327050,36634776,17833343441984,17833343405727,17833343780928,17833343782835
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,236503,236503,4194304,256,0,0,12,24,48512,0x7fe83f16b480,0x7fe83c224a40,306056,306056,65536,2097152,309123,34672752,17833343818545,17833343780928,17833344158688,17833344160556
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,236503,236503,4194304,256,0,0,8,24,49472,0x7fe83f16b300,0x7fe83c224a80,167548,167548,65536,2162688,317410,35619068,17833344195655,17833344158688,17833344447968,17833344449669
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,236503,236503,4194304,256,0,0,12,24,50688,0x7fe83f16b180,0x7fe83c224ac0,169504,169504,65536,2621440,384926,43161376,17833344484848,17833344447968,17833344739968,17833344741802
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,236503,236503,4194304,256,0,0,12,24,51648,0x7fe83f16b000,0x7fe83c224b00,165512,165512,65536,1966080,291635,32744156,17833344783641,17833344739968,17833345032609,17833345034574
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,236503,236503,4194304,256,0,0,12,24,52864,0x7fe83cb0be80,0x7fe83c224b40,307635,307635,65536,2359296,355072,39814608,17833345076833,17833345032609,17833345407329,17833345409095
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,236503,236503,4194304,256,0,0,12,24,54080,0x7fe83cb0bd00,0x7fe83c224b80,306044,306044,65536,2228224,328227,36844320,17833345443604,17833345407329,17833345783969,17833345785826
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,236503,236503,4194304,256,0,0,8,24,55296,0x7fe83cb0bb80,0x7fe83c224bc0,168845,168845,65536,2293760,348654,38971364,17833345820455,17833345783969,17833346075329,17833346083318
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,236503,236503,4194304,256,0,0,12,24,56768,0x7fe83cb0ba00,0x7fe83c224c00,169498,169498,65536,2752512,404228,45354672,17833346112458,17833346075329,17833346373410,17833346375231
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,236503,236503,4194304,256,0,0,12,24,57728,0x7fe83cb0b880,0x7fe83c224c40,169071,169071,65536,2031616,303042,33913500,17833346416440,17833346373410,17833346667010,17833346668874
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,236503,236503,4194304,256,0,0,12,24,58944,0x7fe83cb0b700,0x7fe83c224c80,307122,307122,65536,2490368,369401,41428256,17833346706213,17833346667010,17833347040930,17833347042884
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,236503,236503,4194304,256,0,0,12,24,60160,0x7fe83f16b580,0x7fe83c224cc0,308959,308959,65536,2359296,365280,40887324,17833347076864,17833347040930,17833347420450,17833347422375
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,236503,236503,4194304,256,0,0,8,24,61376,0x7fe83f16b400,0x7fe83c224d00,169956,169956,65536,2424832,381780,42729400,17833347457904,17833347420450,17833347711011,17833347712878
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,236503,236503,4194304,256,0,0,12,24,62848,0x7fe83f16b280,0x7fe83c224d40,173407,173407,65536,2949120,441931,49481420,17833347747547,17833347711011,17833348005091,17833348006880
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,236503,236503,4194304,256,0,0,12,24,63808,0x7fe83f16b100,0x7fe83c224d80,166344,166344,65536,2162688,321975,36072248,17833348048719,17833348005091,17833348302691,17833348304553
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,236503,236503,4194304,256,0,0,12,24,65024,0x7fe83cb0bf80,0x7fe83c224dc0,305814,305814,65536,2621440,389080,43384336,17833348339332,17833348302691,17833348678051,17833348680044
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,236503,236503,4194304,256,0,0,12,24,66240,0x7fe83cb0be00,0x7fe83c224e00,304155,304155,65536,2490368,364521,40814816,17833348715763,17833348678051,17833349050532,17833349052354
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,236503,236503,4194304,256,0,0,8,24,67456,0x7fe83cb0bc80,0x7fe83c224e40,170016,170016,65536,2555904,381139,42794068,17833349087144,17833349050532,17833349345252,17833349346957
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,236503,236503,4194304,256,0,0,12,24,68928,0x7fe83cb0bb00,0x7fe83c224e80,177017,177017,65536,3145728,470883,52684580,17833349382036,17833349345252,17833349643652,17833349645520
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,236503,236503,4194304,256,0,0,12,24,70144,0x7fe83cb0b980,0x7fe83c224ec0,166578,166578,65536,2228224,327804,36764916,17833349687679,17833349643652,17833349935492,17833349937203
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,236503,236503,4194304,256,0,0,12,24,71616,0x7fe83cb0b800,0x7fe83c224f00,302457,302457,65536,2752512,406147,45544456,17833349973952,17833349935492,17833350316773,17833350318913
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,236503,236503,4194304,256,0,0,12,24,72832,0x7fe83cb0b680,0x7fe83c224f40,304510,304510,65536,2621440,386423,43272968,17833350354692,17833350316773,17833350692933,17833350694984
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,236503,236503,4194304,256,0,0,8,24,74048,0x7fe83f16b500,0x7fe83c224f80,167339,167339,65536,2686976,399117,44684512,17833350728583,17833350692933,17833350982053,17833350984027
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,236503,236503,4194304,256,0,0,12,24,75776,0x7fe83f16b380,0x7fe83c224fc0,183614,183614,65536,3342336,496613,55633136,17833351018986,17833350982053,17833351282533,17833351284429
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,236503,236503,4194304,256,0,0,12,24,76992,0x7fe83f16b200,0x7fe83c225000,167166,167166,65536,2359296,350153,39373624,17833351338838,17833351282533,17833351576774,17833351578622
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,236503,236503,4194304,256,0,0,12,24,78464,0x7fe83f16b080,0x7fe83c225040,303630,303630,65536,2883584,435848,48734928,17833351615461,17833351576774,17833351958214,17833351960042
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,236503,236503,4194304,256,0,0,12,24,79936,0x7fe83cb0bf00,0x7fe83c225080,303100,303100,65536,2686976,399594,44765504,17833351995661,17833351958214,17833352333094,17833352335093
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,236503,236503,4194304,256,0,0,8,24,81408,0x7fe83cb0bd80,0x7fe83c2250c0,170425,170425,65536,2818048,421112,47160840,17833352369572,17833352333094,17833352623174,17833352625026
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,236503,236503,4194304,256,0,0,12,24,83136,0x7fe83cb0bc00,0x7fe83c225100,192467,192467,65536,3538944,538081,60204324,17833352659005,17833352623174,17833352927655,17833352929528
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,236503,236503,4194304,256,0,0,12,24,84352,0x7fe83cb0ba80,0x7fe83c225140,169322,169322,65536,2424832,359577,40321568,17833352971487,17833352927655,17833353224455,17833353226431
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,236503,236503,4194304,256,0,0,12,24,85824,0x7fe83cb0b900,0x7fe83c225180,308086,308086,65536,3014656,453709,50727012,17833353260050,17833353224455,17833353611495,17833353613361
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,236503,236503,4194304,256,0,0,12,24,87296,0x7fe83cb0b780,0x7fe83c2251c0,303114,303114,65536,2818048,414457,46395432,17833353647860,17833353611495,17833353985735,17833353987472
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,236503,236503,4194304,256,0,0,12,24,88768,0x7fe83cb0b600,0x7fe83c225200,168204,168204,65536,2949120,439817,49244168,17833354022171,17833353985735,17833354291816,17833354293764
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,236503,236503,4194304,256,0,0,12,24,90752,0x7fe83f16b480,0x7fe83c225240,201871,201871,65536,3735552,560870,62806964,17833354328653,17833354291816,17833354605416,17833354607396
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,236503,236503,4194304,256,0,0,12,24,91968,0x7fe83f16b300,0x7fe83c225280,166916,166916,65536,2555904,395655,44391096,17833354649265,17833354605416,17833354895656,17833354897599
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,236503,236503,4194304,256,0,0,12,24,93440,0x7fe83f16b180,0x7fe83c2252c0,304577,304577,65536,3145728,466630,52282620,17833354933938,17833354895656,17833355272616,17833355274500
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,236503,236503,4194304,256,0,0,12,24,94912,0x7fe83f16b000,0x7fe83c225300,301618,301618,65536,2949120,438044,48999416,17833355310369,17833355272616,17833355645897,17833355647791
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,236503,236503,4194304,256,0,0,12,24,96384,0x7fe83cb0be80,0x7fe83c225340,168835,168835,65536,3080192,459338,51414080,17833355681500,17833355645897,17833355934057,17833355936003
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,236503,236503,4194304,256,0,0,12,24,98368,0x7fe83cb0bd00,0x7fe83c225380,211422,211422,65536,3932160,584962,65429388,17833355970523,17833355934057,17833356256617,17833356258445
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,236503,236503,4194304,256,0,0,12,24,99584,0x7fe83cb0bb80,0x7fe83c2253c0,167511,167511,65536,2621440,388846,43578000,17833356300124,17833356256617,17833356552617,17833356554738
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,236503,236503,4194304,256,0,0,12,24,101312,0x7fe83cb0ba00,0x7fe83c225400,304783,304783,65536,3276800,487250,54676880,17833356589057,17833356552617,17833356926858,17833356928709
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,236503,236503,4194304,256,0,0,12,24,102784,0x7fe83cb0b880,0x7fe83c225440,304031,304031,65536,3080192,465994,52152364,17833356962958,17833356926858,17833357302858,17833357304939
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,236503,236503,4194304,256,0,0,12,24,104256,0x7fe83cb0b700,0x7fe83c225480,168847,168847,65536,3211264,472919,52929148,17833357338709,17833357302858,17833357593578,17833357595522
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,236503,236503,4194304,256,0,0,12,24,106240,0x7fe83f16b580,0x7fe83c2254c0,218845,218845,65536,4128768,609203,68267656,17833357630121,17833357593578,17833357919978,17833357921834
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,236503,236503,4194304,256,0,0,12,24,107712,0x7fe83f16b400,0x7fe83c225500,167201,167201,65536,2752512,408007,45704904,17833357964573,17833357919978,17833358219659,17833358221797
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,236503,236503,4194304,256,0,0,16,24,109440,0x7fe83f16b280,0x7fe83c225540,300053,300053,65536,3407872,509053,56999112,17833358258066,17833358219659,17833358597099,17833358598907
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,236503,236503,4194304,256,0,0,16,24,111168,0x7fe83f16b100,0x7fe83c225580,300200,300200,65536,3211264,474244,53131240,17833358633596,17833358597099,17833358972619,17833358974498
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,236503,236503,4194304,256,0,0,8,24,112896,0x7fe83cb0bf80,0x7fe83c2255c0,168788,168788,65536,3276800,492858,55205864,17833359009827,17833358972619,17833359262379,17833359264261
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,236503,236503,4194304,256,0,0,12,24,115136,0x7fe83cb0be00,0x7fe83c225600,232164,232164,65536,4325376,648749,72658560,17833359298580,17833359262379,17833359594060,17833359595993
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,236503,236503,4194304,256,0,0,12,24,116608,0x7fe83cb0bc80,0x7fe83c225640,169376,169376,65536,2818048,429623,48129556,17833359638381,17833359594060,17833359888300,17833359890205
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,236503,236503,4194304,256,0,0,16,24,118336,0x7fe83cb0bb00,0x7fe83c225680,300713,300713,65536,3538944,524423,58732196,17833359923974,17833359888300,17833360260140,17833360262016
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,236503,236503,4194304,256,0,0,16,24,120064,0x7fe83cb0b980,0x7fe83c2256c0,302008,302008,65536,3407872,502770,56356060,17833360296845,17833360260140,17833360630540,17833360632417
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,236503,236503,4194304,256,0,0,12,24,121792,0x7fe83cb0b800,0x7fe83c225700,167077,167077,65536,3407872,513280,57448736,17833360666996,17833360630540,17833360919021,17833360920880
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,236503,236503,4194304,256,0,0,12,24,124032,0x7fe83cb0b680,0x7fe83c225740,240548,240548,65536,4521984,677850,76029392,17833360955349,17833360919021,17833361257421,17833361259191
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,236503,236503,4194304,256,0,0,12,24,125504,0x7fe83f16b500,0x7fe83c225780,169238,169238,65536,3014656,460312,51595968,17833361301430,17833361257421,17833361555981,17833361557714
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,236503,236503,4194304,256,0,0,12,24,127488,0x7fe83f16b380,0x7fe83c2257c0,303321,303321,65536,3801088,565090,63265024,17833361592213,17833361555981,17833361935341,17833361937344
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,236503,236503,4194304,256,0,0,12,24,129216,0x7fe83f16b200,0x7fe83c225800,304169,304169,65536,3670016,555213,62175088,17833361972664,17833361935341,17833362320622,17833362322655
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,236503,236503,4194304,256,0,0,12,24,130944,0x7fe83f16b080,0x7fe83c225840,173257,173257,65536,3670016,558045,62469356,17833362358914,17833362320622,17833362617102,17833362619097
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,236503,236503,4194304,256,0,0,12,24,133440,0x7fe83cb0bf00,0x7fe83c225880,258461,258461,65536,4915200,746817,83594780,17833362654677,17833362617102,17833362965582,17833362967549
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,236503,236503,4194304,256,0,0,12,24,134912,0x7fe83cb0bd80,0x7fe83c2258c0,170911,170911,65536,3145728,467869,52410260,17833363011138,17833362965582,17833363263343,17833363265301
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,236503,236503,4194304,256,0,0,12,24,136896,0x7fe83cb0bc00,0x7fe83c225900,301919,301919,65536,4063232,617922,69219988,17833363300421,17833363263343,17833363636943,17833363638762
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,236503,236503,4194304,256,0,0,12,24,138880,0x7fe83cb0ba80,0x7fe83c225940,301829,301829,65536,3932160,597857,66953784,17833363674591,17833363636943,17833364009263,17833364011223
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,236503,236503,4194304,256,0,0,12,24,140864,0x7fe83cb0b900,0x7fe83c225980,177968,177968,65536,3932160,596056,66734084,17833364045152,17833364009263,17833364312623,17833364314605
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,236503,236503,4194304,256,0,0,12,24,143616,0x7fe83cb0b780,0x7fe83c2259c0,278430,278430,65536,5308416,795390,89144032,17833364348674,17833364312623,17833364671344,17833364673196
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,236503,236503,4194304,256,0,0,12,24,145344,0x7fe83cb0b600,0x7fe83c225a00,168158,168158,65536,3342336,496115,55511576,17833364715915,17833364671344,17833364967984,17833364969829
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,236503,236503,4194304,256,0,0,12,24,147584,0x7fe83f16b480,0x7fe83c225a40,302112,302112,65536,4325376,679360,75998736,17833365004128,17833364967984,17833365343184,17833365345140
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,236503,236503,4194304,256,0,0,12,24,149568,0x7fe83f16b300,0x7fe83c225a80,300038,300038,65536,4194304,640040,71578624,17833365380529,17833365343184,17833365718064,17833365719900
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,236503,236503,4194304,256,0,0,12,24,151552,0x7fe83f16b180,0x7fe83c225ac0,187296,187296,65536,4194304,633708,70979648,17833365753980,17833365718064,17833366021105,17833366023093
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,236503,236503,4194304,256,0,0,12,24,154304,0x7fe83f16b000,0x7fe83c225b00,300034,300034,65536,5701632,866651,97056844,17833366058802,17833366021105,17833366401905,17833366403933
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,236503,236503,4194304,256,0,0,12,24,156288,0x7fe83cb0be80,0x7fe83c225b40,171812,171812,65536,3735552,559895,62694600,17833366446302,17833366401905,17833366700305,17833366702346
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,236503,236503,4194304,256,0,0,12,24,158784,0x7fe83cb0bd00,0x7fe83c225b80,303329,303329,65536,4849664,764136,85670204,17833366739525,17833366700305,17833367079665,17833367081477
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,236503,236503,4194304,256,0,0,12,24,161024,0x7fe83cb0bb80,0x7fe83c225bc0,304282,304282,65536,4718592,738083,82726232,17833367115496,17833367079665,17833367467186,17833367469197
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,236503,236503,4194304,256,0,0,12,24,163264,0x7fe83cb0ba00,0x7fe83c225c00,206411,206411,65536,4718592,716943,80228732,17833367503216,17833367467186,17833367783666,17833367785549
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,236503,236503,4194304,256,0,0,12,24,166528,0x7fe83cb0b880,0x7fe83c225c40,340023,340023,65536,6488064,983106,110076864,17833367819648,17833367783666,17833368182866,17833368209779
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,236503,236503,4194304,256,0,0,12,24,168512,0x7fe83cb0b700,0x7fe83c225c80,184379,184379,65536,4128768,621586,69574528,17833368228628,17833368182866,17833368500787,17833368502701
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,236503,236503,4194304,256,0,0,12,24,171264,0x7fe83f16b580,0x7fe83c225cc0,303703,303703,65536,5373952,859064,96251956,17833368539740,17833368500787,17833368880307,17833368882192
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,236503,236503,4194304,256,0,0,12,24,173760,0x7fe83f16b400,0x7fe83c225d00,306151,306151,65536,5242880,848046,94899672,17833368917151,17833368880307,17833369260947,17833369265292
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,236503,236503,4194304,256,0,0,12,24,176256,0x7fe83f16b280,0x7fe83c225d40,226653,226653,65536,5242880,782651,87709652,17833369297242,17833369260947,17833369588627,17833369590554
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,236503,236503,4194304,256,0,0,12,24,179776,0x7fe83f16b100,0x7fe83c225d80,380709,380709,65536,7274496,1096835,122880504,17833369624613,17833369588627,17833370019028,17833370038103
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,236503,236503,4194304,256,0,0,12,24,182272,0x7fe83cb0bf80,0x7fe83c225dc0,211326,211326,65536,4915200,734226,82202996,17833370063632,17833370019028,17833370349428,17833370351515
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,236503,236503,4194304,256,0,0,12,24,185536,0x7fe83cb0be00,0x7fe83c225e00,308027,308027,65536,6422528,990606,110945628,17833370385265,17833370349428,17833370734868,17833370784165
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,236503,236503,4194304,256,0,0,12,24,188544,0x7fe83cb0bc80,0x7fe83c225e40,311334,311334,65536,6291456,1015562,113688560,17833370794694,17833370734868,17833371160949,17833371207294
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,236503,236503,4194304,256,0,0,12,24,191552,0x7fe83cb0bb00,0x7fe83c225e80,266391,266391,65536,6291456,959541,107455604,17833371218164,17833371160949,17833371546549,17833371548436
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,236503,236503,4194304,256,0,0,12,24,195840,0x7fe83cb0b980,0x7fe83c225ec0,461600,461600,65536,8847360,1334366,149533012,17833371582655,17833371546549,17833372022069,17833372068323
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,236503,236503,4194304,256,0,0,12,24,198592,0x7fe83cb0b800,0x7fe83c225f00,245533,245533,65536,5701632,872385,97746628,17833372087512,17833372022069,17833372399350,17833372401214
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,236503,236503,4194304,256,0,0,12,24,202368,0x7fe83cb0b680,0x7fe83c225f40,333240,333240,65536,7471104,1190293,133416856,17833372438303,17833372399350,17833372805430,17833372827754
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,236503,236503,4194304,256,0,0,12,24,205888,0x7fe83f16b500,0x7fe83c225f80,331906,331906,65536,7340032,1156506,129439136,17833372840983,17833372805430,17833373216470,17833373237694
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,236503,236503,4194304,256,0,0,12,24,209408,0x7fe83f16b380,0x7fe83c225fc0,306784,306784,65536,7340032,1122895,125758168,17833373253713,17833373216470,17833373602070,17833373604035
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,236503,236503,4194304,256,0,0,12,24,214464,0x7fe83f16b200,0x7fe83c226000,542870,542870,65536,10420224,1572795,176191112,17833373638674,17833373602070,17833374129111,17833374151011
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,236503,236503,4194304,256,0,0,12,24,217728,0x7fe83f16b080,0x7fe83c226040,273524,273524,65536,6488064,1001580,112199020,17833374174310,17833374129111,17833374501751,17833374503742
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,236503,236503,4194304,256,0,0,12,24,222016,0x7fe83cb0bf00,0x7fe83c226080,367402,367402,65536,8519680,1353274,151506452,17833374538861,17833374501751,17833374928631,17833374946841
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,236503,236503,4194304,256,0,0,12,24,226048,0x7fe83cb0bd80,0x7fe83c2260c0,365216,365216,65536,8388608,1304526,146097372,17833374965361,17833374928631,17833375353272,17833375371071
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,236503,236503,4194304,256,0,0,12,24,230080,0x7fe83cb0bc00,0x7fe83c226100,347450,347450,65536,8388608,1301080,145747168,17833375389370,17833375353272,17833375759832,17833375776981
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,236503,236503,4194304,256,0,0,12,24,235904,0x7fe83cb0ba80,0x7fe83c226140,623883,623883,65536,11993088,1821460,204012224,17833375795600,17833375759832,17833376342393,17833376359956
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,236503,236503,4194304,256,0,0,12,24,239424,0x7fe83cb0b900,0x7fe83c226180,301927,301927,65536,7274496,1129391,126520252,17833376386155,17833376342393,17833376726873,17833376728867
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,236503,236503,4194304,256,0,0,12,24,244224,0x7fe83cb0b780,0x7fe83c2261c0,397112,397112,65536,9568256,1519909,170238480,17833376763316,17833376726873,17833377172793,17833377191405
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,236503,236503,4194304,256,0,0,12,24,248768,0x7fe83cb0b600,0x7fe83c226200,390579,390579,65536,9437184,1516148,169854668,17833377210205,17833377172793,17833377619354,17833377636884
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,236503,236503,4194304,256,0,0,12,24,253312,0x7fe83f16b480,0x7fe83c226240,388246,388246,65536,9437184,1469651,164646916,17833377656044,17833377619354,17833378054714,17833378073234
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,236503,236503,4194304,256,0,0,8,24,255552,0x7fe83f16b300,0x7fe83c226280,719031,719031,65536,16056320,2305568,258136480,17833378093213,17833378054714,17833378709754,17833378756117
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,236503,236503,4194304,256,0,0,12,24,259840,0x7fe83f16b180,0x7fe83c2262c0,364708,364708,65536,8847360,1370645,153515112,17833378775936,17833378709754,17833379159035,17833379204805
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,236503,236503,4194304,256,0,0,12,24,265664,0x7fe83f16b000,0x7fe83c226300,469173,469173,65536,11665408,1832647,205290624,17833379216425,17833379159035,17833379686075,17833379731762
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,236503,236503,4194304,256,0,0,12,24,271232,0x7fe83cb0be80,0x7fe83c226340,472147,472147,65536,11468800,1836446,205663764,17833379742592,17833379686075,17833380206876,17833380252019
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,236503,236503,4194304,256,0,0,8,24,273216,0x7fe83cb0bd00,0x7fe83c226380,483319,483319,65536,14090240,2020745,226286316,17833380262739,17833380206876,17833380730396,17833380775826
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,236503,236503,4194304,256,0,0,8,24,275712,0x7fe83cb0bb80,0x7fe83c2263c0,880693,880693,65536,19202048,2756489,308858668,17833380786746,17833380730396,17833381509117,17833381554727
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,236503,236503,4194304,256,0,0,12,24,280768,0x7fe83cb0ba00,0x7fe83c226400,426823,426823,65536,10420224,1609659,180348376,17833381573027,17833381509117,17833381995517,17833382013656
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,236503,236503,4194304,256,0,0,12,24,287616,0x7fe83cb0b880,0x7fe83c226440,550151,550151,65536,13762560,2210664,247726852,17833382032035,17833381995517,17833382551997,17833382597981
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,236503,236503,4194304,256,0,0,12,24,294208,0x7fe83cb0b700,0x7fe83c226480,551517,551517,65536,13565952,2140716,239728764,17833382609251,17833382551997,17833383127358,17833383172737
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,236503,236503,4194304,256,0,0,8,24,296960,0x7fe83f16b580,0x7fe83c2264c0,564777,564777,65536,15466496,2228456,249593016,17833383183477,17833383127358,17833383699518,17833383744933
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,236503,236503,4194304,256,0,0,8,24,299968,0x7fe83f16b400,0x7fe83c226500,1044359,1044359,65536,22347776,3211299,359707520,17833383755813,17833383699518,17833384583359,17833384626841
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,236503,236503,4194304,256,0,0,8,24,302720,0x7fe83f16b280,0x7fe83c226540,722945,722945,65536,20250624,2923813,327459048,17833384644931,17833384583359,17833385251039,17833385295565
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,236503,236503,4194304,256,0,0,12,24,305472,0x7fe83f16b100,0x7fe83c226580,725769,725769,65536,20447232,2935642,328720784,17833385306544,17833385251039,17833385941920,17833385960188
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,236503,236503,4194304,256,0,0,12,24,308224,0x7fe83cb0bf80,0x7fe83c2265c0,721755,721755,65536,19595264,2818351,315615332,17833385979718,17833385941920,17833386603840,17833386650201
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,236503,236503,4194304,256,0,0,8,24,310976,0x7fe83cb0be00,0x7fe83c226600,727949,727949,65536,20381696,2928148,327905732,17833386661111,17833386603784,17833387281864,17833387333494
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,236503,236503,4194304,256,0,0,8,24,313216,0x7fe83cb0bc80,0x7fe83c226640,1366307,1366307,65536,31522816,4509238,505473072,17833387344264,17833387281864,17833388391624,17833388436797
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,236503,236503,4194304,256,0,0,8,24,315968,0x7fe83cb0bb00,0x7fe83c226680,1373247,1373247,65536,38993920,5583960,625679232,17833388456356,17833388391624,17833389481225,17833389547849
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,236503,236503,4194304,256,0,0,12,24,318720,0x7fe83cb0b980,0x7fe83c2266c0,1373929,1373929,65536,39124992,5615805,628883484,17833389559129,17833389481225,17833390631786,17833390703550
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,236503,236503,4194304,256,0,0,12,24,321472,0x7fe83cb0b800,0x7fe83c226700,1372851,1372851,65536,38469632,5509601,617057236,17833390715150,17833390631786,17833391778986,17833391848222
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,236503,236503,4194304,256,0,0,8,24,324224,0x7fe83cb0b680,0x7fe83c226740,1375132,1375132,65536,39059456,5596845,626840900,17833391858982,17833391778986,17833392899307,17833392966684
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,236503,236503,4194304,256,0,0,8,24,326464,0x7fe83f16b500,0x7fe83c226780,2664386,2664386,65536,60489728,8652521,969163852,17833392977874,17833392899307,17833394866828,17833394944075
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,236503,236503,4194304,256,0,0,8,24,329216,0x7fe83f16b380,0x7fe83c2267c0,2669534,2669534,65536,77266944,11073873,1240553420,17833394963545,17833394866828,17833396808270,17833396876617
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,236503,236503,4194304,256,0,0,12,24,331968,0x7fe83f16b200,0x7fe83c226800,2672170,2672170,65536,77398016,11071825,1240072748,17833396887957,17833396808270,17833398795791,17833398869628
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,236503,236503,4194304,256,0,0,12,24,334720,0x7fe83f16b080,0x7fe83c226840,2668592,2668592,65536,76218368,10904144,1221576836,17833398880977,17833398795791,17833400781712,17833400848588
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,236503,236503,4194304,256,0,0,8,24,337472,0x7fe83cb0bf00,0x7fe83c226880,2672754,2672754,65536,77332480,11067421,1239281240,17833400859718,17833400781712,17833402716274,17833402787070
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,236503,236503,4194304,256,0,0,8,24,0,0x7fe83cb0bd80,0x7fe83c2268c0,5255776,5255776,65536,120258560,17187452,1925701988,17833402798580,17833402716274,17833406340436,17833406412550
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 236503 236503 33554432 256 0 0 4 32 4160 0x0 0x7fe83c204280 385832 385832 524288 4718592 682094 76386864 17833173257611 17832460487290 17833324063793 17833324177862
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 236503 236503 32768 256 0 0 12 24 13888 0x0 0x7fe83c223f80 34124 34124 512 8192 5540 624020 17833329373303 17833324063793 17833329503317 17833329508120
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 5 236503 236503 4194304 256 0 0 12 24 14336 0x7fe83f16b380 0x7fe83c223fc0 166451 166451 65536 917504 140662 15737800 17833329547519 17833329503317 17833329887317 17833329890091
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 236503 236503 4194304 256 0 0 16 24 15040 0x7fe83f16b200 0x7fe83c224000 320813 320813 65536 1114112 167869 18973284 17833329928940 17833329887317 17833330326517 17833330329380
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 11 236503 236503 4194304 256 0 0 16 24 15488 0x7fe83f16b080 0x7fe83c224040 323006 323006 65536 917504 146978 16539568 17833330364489 17833330326517 17833330747798 17833330753919
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 14 236503 236503 4194304 256 0 0 12 24 15936 0x7fe83cb0bf00 0x7fe83c224080 168550 168550 65536 1048576 159174 17856292 17833330784798 17833330747798 17833331068118 17833331070481
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 17 236503 236503 4194304 256 0 0 12 24 16384 0x7fe83cb0bd80 0x7fe83c2240c0 168572 168572 65536 983040 148090 16569436 17833331104930 17833331068118 17833331386678 17833331389103
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 20 236503 236503 4194304 256 0 0 12 24 17088 0x7fe83cb0bc00 0x7fe83c224100 167664 167664 65536 1114112 162610 18224860 17833331435702 17833331386678 17833331703318 17833331705705
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 236503 236503 4194304 256 0 0 16 24 17792 0x7fe83cb0ba80 0x7fe83c224140 320079 320079 65536 1310720 202232 22647988 17833331740015 17833331703318 17833332108599 17833332110925
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 26 236503 236503 4194304 256 0 0 16 24 18496 0x7fe83cb0b900 0x7fe83c224180 316809 316809 65536 1179648 176290 19855416 17833332143565 17833332108599 17833332528439 17833332530935
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 29 236503 236503 4194304 256 0 0 16 24 19200 0x7fe83cb0b780 0x7fe83c2241c0 168281 168281 65536 1245184 188620 21166232 17833332564054 17833332528439 17833332839959 17833332842307
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 32 236503 236503 4194304 256 0 0 16 24 19904 0x7fe83cb0b600 0x7fe83c224200 169494 169494 65536 1245184 202520 22612512 17833332876086 17833332839959 17833333154039 17833333156369
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 35 236503 236503 4194304 256 0 0 12 24 20608 0x7fe83f16b480 0x7fe83c224240 171299 171299 65536 1245184 200754 22467976 17833333198828 17833333154039 17833333471320 17833333473552
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 236503 236503 4194304 256 0 0 16 24 21312 0x7fe83f16b300 0x7fe83c224280 320776 320776 65536 1441792 216093 24168728 17833333508101 17833333471320 17833333874840 17833333881351
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 41 236503 236503 4194304 256 0 0 16 24 22016 0x7fe83f16b180 0x7fe83c2242c0 316393 316393 65536 1310720 197617 22204988 17833333911551 17833333874840 17833334286360 17833334289041
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 44 236503 236503 4194304 256 0 0 16 24 22720 0x7fe83f16b000 0x7fe83c224300 169264 169264 65536 1376256 205151 23034404 17833334324160 17833334286360 17833334608441 17833334610943
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 47 236503 236503 4194304 256 0 0 12 24 23424 0x7fe83cb0be80 0x7fe83c224340 168263 168263 65536 1441792 221753 24858852 17833334644352 17833334608441 17833334922841 17833334925195
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 50 236503 236503 4194304 256 0 0 12 24 24128 0x7fe83cb0bd00 0x7fe83c224380 167492 167492 65536 1310720 195746 21931324 17833334967074 17833334922841 17833335246361 17833335248667
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 236503 236503 4194304 256 0 0 16 24 24832 0x7fe83cb0bb80 0x7fe83c2243c0 316291 316291 65536 1572864 232311 26113788 17833335285227 17833335246361 17833335624441 17833335626348
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 56 236503 236503 4194304 256 0 0 16 24 25536 0x7fe83cb0ba00 0x7fe83c224400 312673 312673 65536 1441792 209241 23385064 17833335661197 17833335624441 17833335999642 17833336001459
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 59 236503 236503 4194304 256 0 0 12 24 26240 0x7fe83cb0b880 0x7fe83c224440 166555 166555 65536 1507328 224652 25196208 17833336035928 17833335999642 17833336288122 17833336290022
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 62 236503 236503 4194304 256 0 0 12 24 26944 0x7fe83cb0b700 0x7fe83c224480 168033 168033 65536 1638400 243000 27172084 17833336324411 17833336288122 17833336577882 17833336579724
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 65 236503 236503 4194304 256 0 0 12 24 27648 0x7fe83f16b580 0x7fe83c2244c0 169325 169325 65536 1441792 215804 24164768 17833336621253 17833336577882 17833336865242 17833336867167
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 236503 236503 4194304 256 0 0 16 24 28608 0x7fe83f16b400 0x7fe83c224500 317983 317983 65536 1703936 251876 28216384 17833336903336 17833336865242 17833337239963 17833337241868
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 71 236503 236503 4194304 256 0 0 16 24 29312 0x7fe83f16b280 0x7fe83c224540 316071 316071 65536 1572864 233891 26185384 17833337276507 17833337239963 17833337615003 17833337616889
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 74 236503 236503 4194304 256 0 0 12 24 30016 0x7fe83f16b100 0x7fe83c224580 167827 167827 65536 1638400 243052 27250156 17833337650858 17833337615003 17833337911803 17833337913661
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 77 236503 236503 4194304 256 0 0 8 24 30976 0x7fe83cb0bf80 0x7fe83c2245c0 167561 167561 65536 1835008 270019 30313992 17833337948630 17833337911803 17833338216123 17833338218214
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 80 236503 236503 4194304 256 0 0 12 24 31680 0x7fe83cb0be00 0x7fe83c224600 166155 166155 65536 1507328 223562 25065536 17833338260273 17833338216123 17833338505724 17833338507656
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 236503 236503 4194304 256 0 0 16 24 32640 0x7fe83cb0bc80 0x7fe83c224640 313708 313708 65536 1835008 272596 30454488 17833338544396 17833338505724 17833338882684 17833338884677
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 86 236503 236503 4194304 256 0 0 12 24 33600 0x7fe83cb0bb00 0x7fe83c224680 313561 313561 65536 1703936 248219 27816044 17833338919186 17833338882684 17833339257084 17833339259098
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 89 236503 236503 4194304 256 0 0 12 24 34560 0x7fe83cb0b980 0x7fe83c2246c0 168531 168531 65536 1769472 264701 29659096 17833339293197 17833339257084 17833339545244 17833339547101
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 92 236503 236503 4194304 256 0 0 8 24 35520 0x7fe83cb0b800 0x7fe83c224700 168533 168533 65536 2031616 303743 34041364 17833339581850 17833339545244 17833339833885 17833339835803
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 95 236503 236503 4194304 256 0 0 12 24 36224 0x7fe83cb0b680 0x7fe83c224740 168721 168721 65536 1638400 243880 27433232 17833339877512 17833339833885 17833340126845 17833340128726
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 236503 236503 4194304 256 0 0 12 24 37184 0x7fe83f16b500 0x7fe83c224780 311801 311801 65536 1966080 288908 32275144 17833340163205 17833340126845 17833340509405 17833340511177
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 101 236503 236503 4194304 256 0 0 12 24 38144 0x7fe83f16b380 0x7fe83c2247c0 314592 314592 65536 1835008 272159 30484976 17833340546636 17833340509405 17833340889245 17833340891087
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 104 236503 236503 4194304 256 0 0 12 24 39104 0x7fe83f16b200 0x7fe83c224800 168011 168011 65536 1900544 281499 31452584 17833340925936 17833340889245 17833341181406 17833341183040
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 107 236503 236503 4194304 256 0 0 8 24 40320 0x7fe83f16b080 0x7fe83c224840 168636 168636 65536 2228224 328196 36754620 17833341218079 17833341181406 17833341472606 17833341474483
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 110 236503 236503 4194304 256 0 0 12 24 41280 0x7fe83cb0bf00 0x7fe83c224880 169134 169134 65536 1703936 257950 28833172 17833341515762 17833341472606 17833341761886 17833341763986
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 236503 236503 4194304 256 0 0 12 24 42240 0x7fe83cb0bd80 0x7fe83c2248c0 311600 311600 65536 2097152 311380 34862612 17833341798245 17833341761886 17833342137566 17833342139966
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 116 236503 236503 4194304 256 0 0 12 24 43200 0x7fe83cb0bc00 0x7fe83c224900 311542 311542 65536 1966080 284002 31844304 17833342176125 17833342137566 17833342523327 17833342525247
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 119 236503 236503 4194304 256 0 0 8 24 44160 0x7fe83cb0ba80 0x7fe83c224940 168342 168342 65536 2031616 302765 33940188 17833342559536 17833342523327 17833342815647 17833342817649
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 122 236503 236503 4194304 256 0 0 12 24 45376 0x7fe83cb0b900 0x7fe83c224980 169165 169165 65536 2424832 362267 40550672 17833342852049 17833342815647 17833343114047 17833343115852
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 125 236503 236503 4194304 256 0 0 12 24 46336 0x7fe83cb0b780 0x7fe83c2249c0 168186 168186 65536 1835008 272130 30424784 17833343157201 17833343114047 17833343405727 17833343407425
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 236503 236503 4194304 256 0 0 12 24 47552 0x7fe83cb0b600 0x7fe83c224a00 312770 312770 65536 2228224 327050 36634776 17833343441984 17833343405727 17833343780928 17833343782835
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 131 236503 236503 4194304 256 0 0 12 24 48512 0x7fe83f16b480 0x7fe83c224a40 306056 306056 65536 2097152 309123 34672752 17833343818545 17833343780928 17833344158688 17833344160556
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 134 236503 236503 4194304 256 0 0 8 24 49472 0x7fe83f16b300 0x7fe83c224a80 167548 167548 65536 2162688 317410 35619068 17833344195655 17833344158688 17833344447968 17833344449669
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 137 236503 236503 4194304 256 0 0 12 24 50688 0x7fe83f16b180 0x7fe83c224ac0 169504 169504 65536 2621440 384926 43161376 17833344484848 17833344447968 17833344739968 17833344741802
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 140 236503 236503 4194304 256 0 0 12 24 51648 0x7fe83f16b000 0x7fe83c224b00 165512 165512 65536 1966080 291635 32744156 17833344783641 17833344739968 17833345032609 17833345034574
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 236503 236503 4194304 256 0 0 12 24 52864 0x7fe83cb0be80 0x7fe83c224b40 307635 307635 65536 2359296 355072 39814608 17833345076833 17833345032609 17833345407329 17833345409095
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 146 236503 236503 4194304 256 0 0 12 24 54080 0x7fe83cb0bd00 0x7fe83c224b80 306044 306044 65536 2228224 328227 36844320 17833345443604 17833345407329 17833345783969 17833345785826
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 149 236503 236503 4194304 256 0 0 8 24 55296 0x7fe83cb0bb80 0x7fe83c224bc0 168845 168845 65536 2293760 348654 38971364 17833345820455 17833345783969 17833346075329 17833346083318
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 152 236503 236503 4194304 256 0 0 12 24 56768 0x7fe83cb0ba00 0x7fe83c224c00 169498 169498 65536 2752512 404228 45354672 17833346112458 17833346075329 17833346373410 17833346375231
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 155 236503 236503 4194304 256 0 0 12 24 57728 0x7fe83cb0b880 0x7fe83c224c40 169071 169071 65536 2031616 303042 33913500 17833346416440 17833346373410 17833346667010 17833346668874
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 236503 236503 4194304 256 0 0 12 24 58944 0x7fe83cb0b700 0x7fe83c224c80 307122 307122 65536 2490368 369401 41428256 17833346706213 17833346667010 17833347040930 17833347042884
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 161 236503 236503 4194304 256 0 0 12 24 60160 0x7fe83f16b580 0x7fe83c224cc0 308959 308959 65536 2359296 365280 40887324 17833347076864 17833347040930 17833347420450 17833347422375
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 164 236503 236503 4194304 256 0 0 8 24 61376 0x7fe83f16b400 0x7fe83c224d00 169956 169956 65536 2424832 381780 42729400 17833347457904 17833347420450 17833347711011 17833347712878
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 167 236503 236503 4194304 256 0 0 12 24 62848 0x7fe83f16b280 0x7fe83c224d40 173407 173407 65536 2949120 441931 49481420 17833347747547 17833347711011 17833348005091 17833348006880
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 170 236503 236503 4194304 256 0 0 12 24 63808 0x7fe83f16b100 0x7fe83c224d80 166344 166344 65536 2162688 321975 36072248 17833348048719 17833348005091 17833348302691 17833348304553
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 236503 236503 4194304 256 0 0 12 24 65024 0x7fe83cb0bf80 0x7fe83c224dc0 305814 305814 65536 2621440 389080 43384336 17833348339332 17833348302691 17833348678051 17833348680044
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 176 236503 236503 4194304 256 0 0 12 24 66240 0x7fe83cb0be00 0x7fe83c224e00 304155 304155 65536 2490368 364521 40814816 17833348715763 17833348678051 17833349050532 17833349052354
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 179 236503 236503 4194304 256 0 0 8 24 67456 0x7fe83cb0bc80 0x7fe83c224e40 170016 170016 65536 2555904 381139 42794068 17833349087144 17833349050532 17833349345252 17833349346957
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 182 236503 236503 4194304 256 0 0 12 24 68928 0x7fe83cb0bb00 0x7fe83c224e80 177017 177017 65536 3145728 470883 52684580 17833349382036 17833349345252 17833349643652 17833349645520
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 185 236503 236503 4194304 256 0 0 12 24 70144 0x7fe83cb0b980 0x7fe83c224ec0 166578 166578 65536 2228224 327804 36764916 17833349687679 17833349643652 17833349935492 17833349937203
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 236503 236503 4194304 256 0 0 12 24 71616 0x7fe83cb0b800 0x7fe83c224f00 302457 302457 65536 2752512 406147 45544456 17833349973952 17833349935492 17833350316773 17833350318913
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 191 236503 236503 4194304 256 0 0 12 24 72832 0x7fe83cb0b680 0x7fe83c224f40 304510 304510 65536 2621440 386423 43272968 17833350354692 17833350316773 17833350692933 17833350694984
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 194 236503 236503 4194304 256 0 0 8 24 74048 0x7fe83f16b500 0x7fe83c224f80 167339 167339 65536 2686976 399117 44684512 17833350728583 17833350692933 17833350982053 17833350984027
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 197 236503 236503 4194304 256 0 0 12 24 75776 0x7fe83f16b380 0x7fe83c224fc0 183614 183614 65536 3342336 496613 55633136 17833351018986 17833350982053 17833351282533 17833351284429
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 200 236503 236503 4194304 256 0 0 12 24 76992 0x7fe83f16b200 0x7fe83c225000 167166 167166 65536 2359296 350153 39373624 17833351338838 17833351282533 17833351576774 17833351578622
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 236503 236503 4194304 256 0 0 12 24 78464 0x7fe83f16b080 0x7fe83c225040 303630 303630 65536 2883584 435848 48734928 17833351615461 17833351576774 17833351958214 17833351960042
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 206 236503 236503 4194304 256 0 0 12 24 79936 0x7fe83cb0bf00 0x7fe83c225080 303100 303100 65536 2686976 399594 44765504 17833351995661 17833351958214 17833352333094 17833352335093
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 209 236503 236503 4194304 256 0 0 8 24 81408 0x7fe83cb0bd80 0x7fe83c2250c0 170425 170425 65536 2818048 421112 47160840 17833352369572 17833352333094 17833352623174 17833352625026
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 212 236503 236503 4194304 256 0 0 12 24 83136 0x7fe83cb0bc00 0x7fe83c225100 192467 192467 65536 3538944 538081 60204324 17833352659005 17833352623174 17833352927655 17833352929528
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 215 236503 236503 4194304 256 0 0 12 24 84352 0x7fe83cb0ba80 0x7fe83c225140 169322 169322 65536 2424832 359577 40321568 17833352971487 17833352927655 17833353224455 17833353226431
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 236503 236503 4194304 256 0 0 12 24 85824 0x7fe83cb0b900 0x7fe83c225180 308086 308086 65536 3014656 453709 50727012 17833353260050 17833353224455 17833353611495 17833353613361
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 221 236503 236503 4194304 256 0 0 12 24 87296 0x7fe83cb0b780 0x7fe83c2251c0 303114 303114 65536 2818048 414457 46395432 17833353647860 17833353611495 17833353985735 17833353987472
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 224 236503 236503 4194304 256 0 0 12 24 88768 0x7fe83cb0b600 0x7fe83c225200 168204 168204 65536 2949120 439817 49244168 17833354022171 17833353985735 17833354291816 17833354293764
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 227 236503 236503 4194304 256 0 0 12 24 90752 0x7fe83f16b480 0x7fe83c225240 201871 201871 65536 3735552 560870 62806964 17833354328653 17833354291816 17833354605416 17833354607396
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 230 236503 236503 4194304 256 0 0 12 24 91968 0x7fe83f16b300 0x7fe83c225280 166916 166916 65536 2555904 395655 44391096 17833354649265 17833354605416 17833354895656 17833354897599
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 236503 236503 4194304 256 0 0 12 24 93440 0x7fe83f16b180 0x7fe83c2252c0 304577 304577 65536 3145728 466630 52282620 17833354933938 17833354895656 17833355272616 17833355274500
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 236 236503 236503 4194304 256 0 0 12 24 94912 0x7fe83f16b000 0x7fe83c225300 301618 301618 65536 2949120 438044 48999416 17833355310369 17833355272616 17833355645897 17833355647791
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 239 236503 236503 4194304 256 0 0 12 24 96384 0x7fe83cb0be80 0x7fe83c225340 168835 168835 65536 3080192 459338 51414080 17833355681500 17833355645897 17833355934057 17833355936003
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 242 236503 236503 4194304 256 0 0 12 24 98368 0x7fe83cb0bd00 0x7fe83c225380 211422 211422 65536 3932160 584962 65429388 17833355970523 17833355934057 17833356256617 17833356258445
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 245 236503 236503 4194304 256 0 0 12 24 99584 0x7fe83cb0bb80 0x7fe83c2253c0 167511 167511 65536 2621440 388846 43578000 17833356300124 17833356256617 17833356552617 17833356554738
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 236503 236503 4194304 256 0 0 12 24 101312 0x7fe83cb0ba00 0x7fe83c225400 304783 304783 65536 3276800 487250 54676880 17833356589057 17833356552617 17833356926858 17833356928709
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 251 236503 236503 4194304 256 0 0 12 24 102784 0x7fe83cb0b880 0x7fe83c225440 304031 304031 65536 3080192 465994 52152364 17833356962958 17833356926858 17833357302858 17833357304939
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 254 236503 236503 4194304 256 0 0 12 24 104256 0x7fe83cb0b700 0x7fe83c225480 168847 168847 65536 3211264 472919 52929148 17833357338709 17833357302858 17833357593578 17833357595522
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 257 236503 236503 4194304 256 0 0 12 24 106240 0x7fe83f16b580 0x7fe83c2254c0 218845 218845 65536 4128768 609203 68267656 17833357630121 17833357593578 17833357919978 17833357921834
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 260 236503 236503 4194304 256 0 0 12 24 107712 0x7fe83f16b400 0x7fe83c225500 167201 167201 65536 2752512 408007 45704904 17833357964573 17833357919978 17833358219659 17833358221797
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 236503 236503 4194304 256 0 0 16 24 109440 0x7fe83f16b280 0x7fe83c225540 300053 300053 65536 3407872 509053 56999112 17833358258066 17833358219659 17833358597099 17833358598907
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 266 236503 236503 4194304 256 0 0 16 24 111168 0x7fe83f16b100 0x7fe83c225580 300200 300200 65536 3211264 474244 53131240 17833358633596 17833358597099 17833358972619 17833358974498
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 269 236503 236503 4194304 256 0 0 8 24 112896 0x7fe83cb0bf80 0x7fe83c2255c0 168788 168788 65536 3276800 492858 55205864 17833359009827 17833358972619 17833359262379 17833359264261
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 272 236503 236503 4194304 256 0 0 12 24 115136 0x7fe83cb0be00 0x7fe83c225600 232164 232164 65536 4325376 648749 72658560 17833359298580 17833359262379 17833359594060 17833359595993
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 275 236503 236503 4194304 256 0 0 12 24 116608 0x7fe83cb0bc80 0x7fe83c225640 169376 169376 65536 2818048 429623 48129556 17833359638381 17833359594060 17833359888300 17833359890205
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 236503 236503 4194304 256 0 0 16 24 118336 0x7fe83cb0bb00 0x7fe83c225680 300713 300713 65536 3538944 524423 58732196 17833359923974 17833359888300 17833360260140 17833360262016
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 281 236503 236503 4194304 256 0 0 16 24 120064 0x7fe83cb0b980 0x7fe83c2256c0 302008 302008 65536 3407872 502770 56356060 17833360296845 17833360260140 17833360630540 17833360632417
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 284 236503 236503 4194304 256 0 0 12 24 121792 0x7fe83cb0b800 0x7fe83c225700 167077 167077 65536 3407872 513280 57448736 17833360666996 17833360630540 17833360919021 17833360920880
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 287 236503 236503 4194304 256 0 0 12 24 124032 0x7fe83cb0b680 0x7fe83c225740 240548 240548 65536 4521984 677850 76029392 17833360955349 17833360919021 17833361257421 17833361259191
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 290 236503 236503 4194304 256 0 0 12 24 125504 0x7fe83f16b500 0x7fe83c225780 169238 169238 65536 3014656 460312 51595968 17833361301430 17833361257421 17833361555981 17833361557714
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 236503 236503 4194304 256 0 0 12 24 127488 0x7fe83f16b380 0x7fe83c2257c0 303321 303321 65536 3801088 565090 63265024 17833361592213 17833361555981 17833361935341 17833361937344
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 296 236503 236503 4194304 256 0 0 12 24 129216 0x7fe83f16b200 0x7fe83c225800 304169 304169 65536 3670016 555213 62175088 17833361972664 17833361935341 17833362320622 17833362322655
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 299 236503 236503 4194304 256 0 0 12 24 130944 0x7fe83f16b080 0x7fe83c225840 173257 173257 65536 3670016 558045 62469356 17833362358914 17833362320622 17833362617102 17833362619097
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 302 236503 236503 4194304 256 0 0 12 24 133440 0x7fe83cb0bf00 0x7fe83c225880 258461 258461 65536 4915200 746817 83594780 17833362654677 17833362617102 17833362965582 17833362967549
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 305 236503 236503 4194304 256 0 0 12 24 134912 0x7fe83cb0bd80 0x7fe83c2258c0 170911 170911 65536 3145728 467869 52410260 17833363011138 17833362965582 17833363263343 17833363265301
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 236503 236503 4194304 256 0 0 12 24 136896 0x7fe83cb0bc00 0x7fe83c225900 301919 301919 65536 4063232 617922 69219988 17833363300421 17833363263343 17833363636943 17833363638762
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 311 236503 236503 4194304 256 0 0 12 24 138880 0x7fe83cb0ba80 0x7fe83c225940 301829 301829 65536 3932160 597857 66953784 17833363674591 17833363636943 17833364009263 17833364011223
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 314 236503 236503 4194304 256 0 0 12 24 140864 0x7fe83cb0b900 0x7fe83c225980 177968 177968 65536 3932160 596056 66734084 17833364045152 17833364009263 17833364312623 17833364314605
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 317 236503 236503 4194304 256 0 0 12 24 143616 0x7fe83cb0b780 0x7fe83c2259c0 278430 278430 65536 5308416 795390 89144032 17833364348674 17833364312623 17833364671344 17833364673196
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 320 236503 236503 4194304 256 0 0 12 24 145344 0x7fe83cb0b600 0x7fe83c225a00 168158 168158 65536 3342336 496115 55511576 17833364715915 17833364671344 17833364967984 17833364969829
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 236503 236503 4194304 256 0 0 12 24 147584 0x7fe83f16b480 0x7fe83c225a40 302112 302112 65536 4325376 679360 75998736 17833365004128 17833364967984 17833365343184 17833365345140
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 326 236503 236503 4194304 256 0 0 12 24 149568 0x7fe83f16b300 0x7fe83c225a80 300038 300038 65536 4194304 640040 71578624 17833365380529 17833365343184 17833365718064 17833365719900
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 329 236503 236503 4194304 256 0 0 12 24 151552 0x7fe83f16b180 0x7fe83c225ac0 187296 187296 65536 4194304 633708 70979648 17833365753980 17833365718064 17833366021105 17833366023093
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 332 236503 236503 4194304 256 0 0 12 24 154304 0x7fe83f16b000 0x7fe83c225b00 300034 300034 65536 5701632 866651 97056844 17833366058802 17833366021105 17833366401905 17833366403933
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 335 236503 236503 4194304 256 0 0 12 24 156288 0x7fe83cb0be80 0x7fe83c225b40 171812 171812 65536 3735552 559895 62694600 17833366446302 17833366401905 17833366700305 17833366702346
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 236503 236503 4194304 256 0 0 12 24 158784 0x7fe83cb0bd00 0x7fe83c225b80 303329 303329 65536 4849664 764136 85670204 17833366739525 17833366700305 17833367079665 17833367081477
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 341 236503 236503 4194304 256 0 0 12 24 161024 0x7fe83cb0bb80 0x7fe83c225bc0 304282 304282 65536 4718592 738083 82726232 17833367115496 17833367079665 17833367467186 17833367469197
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 344 236503 236503 4194304 256 0 0 12 24 163264 0x7fe83cb0ba00 0x7fe83c225c00 206411 206411 65536 4718592 716943 80228732 17833367503216 17833367467186 17833367783666 17833367785549
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 347 236503 236503 4194304 256 0 0 12 24 166528 0x7fe83cb0b880 0x7fe83c225c40 340023 340023 65536 6488064 983106 110076864 17833367819648 17833367783666 17833368182866 17833368209779
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 350 236503 236503 4194304 256 0 0 12 24 168512 0x7fe83cb0b700 0x7fe83c225c80 184379 184379 65536 4128768 621586 69574528 17833368228628 17833368182866 17833368500787 17833368502701
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 236503 236503 4194304 256 0 0 12 24 171264 0x7fe83f16b580 0x7fe83c225cc0 303703 303703 65536 5373952 859064 96251956 17833368539740 17833368500787 17833368880307 17833368882192
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 356 236503 236503 4194304 256 0 0 12 24 173760 0x7fe83f16b400 0x7fe83c225d00 306151 306151 65536 5242880 848046 94899672 17833368917151 17833368880307 17833369260947 17833369265292
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 359 236503 236503 4194304 256 0 0 12 24 176256 0x7fe83f16b280 0x7fe83c225d40 226653 226653 65536 5242880 782651 87709652 17833369297242 17833369260947 17833369588627 17833369590554
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 362 236503 236503 4194304 256 0 0 12 24 179776 0x7fe83f16b100 0x7fe83c225d80 380709 380709 65536 7274496 1096835 122880504 17833369624613 17833369588627 17833370019028 17833370038103
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 365 236503 236503 4194304 256 0 0 12 24 182272 0x7fe83cb0bf80 0x7fe83c225dc0 211326 211326 65536 4915200 734226 82202996 17833370063632 17833370019028 17833370349428 17833370351515
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 236503 236503 4194304 256 0 0 12 24 185536 0x7fe83cb0be00 0x7fe83c225e00 308027 308027 65536 6422528 990606 110945628 17833370385265 17833370349428 17833370734868 17833370784165
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 371 236503 236503 4194304 256 0 0 12 24 188544 0x7fe83cb0bc80 0x7fe83c225e40 311334 311334 65536 6291456 1015562 113688560 17833370794694 17833370734868 17833371160949 17833371207294
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 374 236503 236503 4194304 256 0 0 12 24 191552 0x7fe83cb0bb00 0x7fe83c225e80 266391 266391 65536 6291456 959541 107455604 17833371218164 17833371160949 17833371546549 17833371548436
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 377 236503 236503 4194304 256 0 0 12 24 195840 0x7fe83cb0b980 0x7fe83c225ec0 461600 461600 65536 8847360 1334366 149533012 17833371582655 17833371546549 17833372022069 17833372068323
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 380 236503 236503 4194304 256 0 0 12 24 198592 0x7fe83cb0b800 0x7fe83c225f00 245533 245533 65536 5701632 872385 97746628 17833372087512 17833372022069 17833372399350 17833372401214
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 236503 236503 4194304 256 0 0 12 24 202368 0x7fe83cb0b680 0x7fe83c225f40 333240 333240 65536 7471104 1190293 133416856 17833372438303 17833372399350 17833372805430 17833372827754
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 386 236503 236503 4194304 256 0 0 12 24 205888 0x7fe83f16b500 0x7fe83c225f80 331906 331906 65536 7340032 1156506 129439136 17833372840983 17833372805430 17833373216470 17833373237694
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 389 236503 236503 4194304 256 0 0 12 24 209408 0x7fe83f16b380 0x7fe83c225fc0 306784 306784 65536 7340032 1122895 125758168 17833373253713 17833373216470 17833373602070 17833373604035
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 392 236503 236503 4194304 256 0 0 12 24 214464 0x7fe83f16b200 0x7fe83c226000 542870 542870 65536 10420224 1572795 176191112 17833373638674 17833373602070 17833374129111 17833374151011
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 395 236503 236503 4194304 256 0 0 12 24 217728 0x7fe83f16b080 0x7fe83c226040 273524 273524 65536 6488064 1001580 112199020 17833374174310 17833374129111 17833374501751 17833374503742
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 236503 236503 4194304 256 0 0 12 24 222016 0x7fe83cb0bf00 0x7fe83c226080 367402 367402 65536 8519680 1353274 151506452 17833374538861 17833374501751 17833374928631 17833374946841
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 401 236503 236503 4194304 256 0 0 12 24 226048 0x7fe83cb0bd80 0x7fe83c2260c0 365216 365216 65536 8388608 1304526 146097372 17833374965361 17833374928631 17833375353272 17833375371071
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 404 236503 236503 4194304 256 0 0 12 24 230080 0x7fe83cb0bc00 0x7fe83c226100 347450 347450 65536 8388608 1301080 145747168 17833375389370 17833375353272 17833375759832 17833375776981
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 407 236503 236503 4194304 256 0 0 12 24 235904 0x7fe83cb0ba80 0x7fe83c226140 623883 623883 65536 11993088 1821460 204012224 17833375795600 17833375759832 17833376342393 17833376359956
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 410 236503 236503 4194304 256 0 0 12 24 239424 0x7fe83cb0b900 0x7fe83c226180 301927 301927 65536 7274496 1129391 126520252 17833376386155 17833376342393 17833376726873 17833376728867
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 236503 236503 4194304 256 0 0 12 24 244224 0x7fe83cb0b780 0x7fe83c2261c0 397112 397112 65536 9568256 1519909 170238480 17833376763316 17833376726873 17833377172793 17833377191405
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 416 236503 236503 4194304 256 0 0 12 24 248768 0x7fe83cb0b600 0x7fe83c226200 390579 390579 65536 9437184 1516148 169854668 17833377210205 17833377172793 17833377619354 17833377636884
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 419 236503 236503 4194304 256 0 0 12 24 253312 0x7fe83f16b480 0x7fe83c226240 388246 388246 65536 9437184 1469651 164646916 17833377656044 17833377619354 17833378054714 17833378073234
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 422 236503 236503 4194304 256 0 0 8 24 255552 0x7fe83f16b300 0x7fe83c226280 719031 719031 65536 16056320 2305568 258136480 17833378093213 17833378054714 17833378709754 17833378756117
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 425 236503 236503 4194304 256 0 0 12 24 259840 0x7fe83f16b180 0x7fe83c2262c0 364708 364708 65536 8847360 1370645 153515112 17833378775936 17833378709754 17833379159035 17833379204805
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 236503 236503 4194304 256 0 0 12 24 265664 0x7fe83f16b000 0x7fe83c226300 469173 469173 65536 11665408 1832647 205290624 17833379216425 17833379159035 17833379686075 17833379731762
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 431 236503 236503 4194304 256 0 0 12 24 271232 0x7fe83cb0be80 0x7fe83c226340 472147 472147 65536 11468800 1836446 205663764 17833379742592 17833379686075 17833380206876 17833380252019
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 434 236503 236503 4194304 256 0 0 8 24 273216 0x7fe83cb0bd00 0x7fe83c226380 483319 483319 65536 14090240 2020745 226286316 17833380262739 17833380206876 17833380730396 17833380775826
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 437 236503 236503 4194304 256 0 0 8 24 275712 0x7fe83cb0bb80 0x7fe83c2263c0 880693 880693 65536 19202048 2756489 308858668 17833380786746 17833380730396 17833381509117 17833381554727
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 440 236503 236503 4194304 256 0 0 12 24 280768 0x7fe83cb0ba00 0x7fe83c226400 426823 426823 65536 10420224 1609659 180348376 17833381573027 17833381509117 17833381995517 17833382013656
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 236503 236503 4194304 256 0 0 12 24 287616 0x7fe83cb0b880 0x7fe83c226440 550151 550151 65536 13762560 2210664 247726852 17833382032035 17833381995517 17833382551997 17833382597981
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 446 236503 236503 4194304 256 0 0 12 24 294208 0x7fe83cb0b700 0x7fe83c226480 551517 551517 65536 13565952 2140716 239728764 17833382609251 17833382551997 17833383127358 17833383172737
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 449 236503 236503 4194304 256 0 0 8 24 296960 0x7fe83f16b580 0x7fe83c2264c0 564777 564777 65536 15466496 2228456 249593016 17833383183477 17833383127358 17833383699518 17833383744933
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 452 236503 236503 4194304 256 0 0 8 24 299968 0x7fe83f16b400 0x7fe83c226500 1044359 1044359 65536 22347776 3211299 359707520 17833383755813 17833383699518 17833384583359 17833384626841
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 455 236503 236503 4194304 256 0 0 8 24 302720 0x7fe83f16b280 0x7fe83c226540 722945 722945 65536 20250624 2923813 327459048 17833384644931 17833384583359 17833385251039 17833385295565
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 236503 236503 4194304 256 0 0 12 24 305472 0x7fe83f16b100 0x7fe83c226580 725769 725769 65536 20447232 2935642 328720784 17833385306544 17833385251039 17833385941920 17833385960188
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 461 236503 236503 4194304 256 0 0 12 24 308224 0x7fe83cb0bf80 0x7fe83c2265c0 721755 721755 65536 19595264 2818351 315615332 17833385979718 17833385941920 17833386603840 17833386650201
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 464 236503 236503 4194304 256 0 0 8 24 310976 0x7fe83cb0be00 0x7fe83c226600 727949 727949 65536 20381696 2928148 327905732 17833386661111 17833386603784 17833387281864 17833387333494
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 467 236503 236503 4194304 256 0 0 8 24 313216 0x7fe83cb0bc80 0x7fe83c226640 1366307 1366307 65536 31522816 4509238 505473072 17833387344264 17833387281864 17833388391624 17833388436797
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 470 236503 236503 4194304 256 0 0 8 24 315968 0x7fe83cb0bb00 0x7fe83c226680 1373247 1373247 65536 38993920 5583960 625679232 17833388456356 17833388391624 17833389481225 17833389547849
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 236503 236503 4194304 256 0 0 12 24 318720 0x7fe83cb0b980 0x7fe83c2266c0 1373929 1373929 65536 39124992 5615805 628883484 17833389559129 17833389481225 17833390631786 17833390703550
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 476 236503 236503 4194304 256 0 0 12 24 321472 0x7fe83cb0b800 0x7fe83c226700 1372851 1372851 65536 38469632 5509601 617057236 17833390715150 17833390631786 17833391778986 17833391848222
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 479 236503 236503 4194304 256 0 0 8 24 324224 0x7fe83cb0b680 0x7fe83c226740 1375132 1375132 65536 39059456 5596845 626840900 17833391858982 17833391778986 17833392899307 17833392966684
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 482 236503 236503 4194304 256 0 0 8 24 326464 0x7fe83f16b500 0x7fe83c226780 2664386 2664386 65536 60489728 8652521 969163852 17833392977874 17833392899307 17833394866828 17833394944075
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 485 236503 236503 4194304 256 0 0 8 24 329216 0x7fe83f16b380 0x7fe83c2267c0 2669534 2669534 65536 77266944 11073873 1240553420 17833394963545 17833394866828 17833396808270 17833396876617
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 236503 236503 4194304 256 0 0 12 24 331968 0x7fe83f16b200 0x7fe83c226800 2672170 2672170 65536 77398016 11071825 1240072748 17833396887957 17833396808270 17833398795791 17833398869628
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 491 236503 236503 4194304 256 0 0 12 24 334720 0x7fe83f16b080 0x7fe83c226840 2668592 2668592 65536 76218368 10904144 1221576836 17833398880977 17833398795791 17833400781712 17833400848588
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 494 236503 236503 4194304 256 0 0 8 24 337472 0x7fe83cb0bf00 0x7fe83c226880 2672754 2672754 65536 77332480 11067421 1239281240 17833400859718 17833400781712 17833402716274 17833402787070
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 497 236503 236503 4194304 256 0 0 8 24 0 0x7fe83cb0bd80 0x7fe83c2268c0 5255776 5255776 65536 120258560 17187452 1925701988 17833402798580 17833402716274 17833406340436 17833406412550
@@ -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",0,0,0,238351,238351,33554432,256,0,0,4,32,4160,0x0,0x7ff888c04280,0,0,0,17852547584485,17851838027568,17852691164011,17852691281181
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,238351,238351,32768,256,0,0,12,24,13888,0x0,0x7ff888c23f80,0,0,0,17852696444493,17852691164011,17852696572335,17852696576630
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,238351,238351,4194304,256,0,0,12,24,14336,0x7ff88bbf2380,0x7ff888c23fc0,0,0,0,17852696612159,17852696572335,17852696936336,17852696938901
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,238351,238351,4194304,256,0,0,16,24,15040,0x7ff88bbf2200,0x7ff888c24000,0,0,0,17852696975310,17852696936336,17852697339696,17852697341881
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,238351,238351,4194304,256,0,0,16,24,15488,0x7ff88bbf2080,0x7ff888c24040,0,0,0,17852697374780,17852697339696,17852697731856,17852697734031
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,238351,238351,4194304,256,0,0,12,24,15936,0x7ff8895c3f00,0x7ff888c24080,0,0,0,17852697767750,17852697731856,17852698036497,17852698038724
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,238351,238351,4194304,256,0,0,12,24,16384,0x7ff8895c3d80,0x7ff888c240c0,0,0,0,17852698071613,17852698036497,17852698369937,17852698372295
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,238351,238351,4194304,256,0,0,12,24,17088,0x7ff8895c3c00,0x7ff888c24100,0,0,0,17852698416344,17852698369937,17852698676817,17852698679058
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,238351,238351,4194304,256,0,0,16,24,17792,0x7ff8895c3a80,0x7ff888c24140,0,0,0,17852698711897,17852698676817,17852699069297,17852699071448
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,238351,238351,4194304,256,0,0,16,24,18496,0x7ff8895c3900,0x7ff888c24180,0,0,0,17852699103227,17852699069297,17852699460338,17852699462438
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,238351,238351,4194304,256,0,0,16,24,19200,0x7ff8895c3780,0x7ff888c241c0,0,0,0,17852699493987,17852699460338,17852699775858,17852699778060
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,238351,238351,4194304,256,0,0,16,24,19904,0x7ff8895c3600,0x7ff888c24200,0,0,0,17852699811880,17852699775858,17852700079858,17852700082053
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,238351,238351,4194304,256,0,0,12,24,20608,0x7ff88bbf2480,0x7ff888c24240,0,0,0,17852700121632,17852700079858,17852700381299,17852700383605
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,238351,238351,4194304,256,0,0,16,24,21312,0x7ff88bbf2300,0x7ff888c24280,0,0,0,17852700416035,17852700381299,17852700771219,17852700773606
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,238351,238351,4194304,256,0,0,16,24,22016,0x7ff88bbf2180,0x7ff888c242c0,0,0,0,17852700806585,17852700771219,17852701160019,17852701162216
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,238351,238351,4194304,256,0,0,16,24,22720,0x7ff88bbf2000,0x7ff888c24300,0,0,0,17852701194595,17852701160019,17852701463540,17852701465598
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,238351,238351,4194304,256,0,0,12,24,23424,0x7ff8895c3e80,0x7ff888c24340,0,0,0,17852701497488,17852701463540,17852701764020,17852701766161
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,238351,238351,4194304,256,0,0,12,24,24128,0x7ff8895c3d00,0x7ff888c24380,0,0,0,17852701805360,17852701764020,17852702066100,17852702068263
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,238351,238351,4194304,256,0,0,16,24,24832,0x7ff8895c3b80,0x7ff888c243c0,0,0,0,17852702100643,17852702066100,17852702483061,17852702485313
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,238351,238351,4194304,256,0,0,16,24,25536,0x7ff8895c3a00,0x7ff888c24400,0,0,0,17852702517042,17852702483061,17852702873781,17852702876263
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,238351,238351,4194304,256,0,0,12,24,26240,0x7ff8895c3880,0x7ff888c24440,0,0,0,17852702907713,17852702873781,17852703202901,17852703204495
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,238351,238351,4194304,256,0,0,12,24,26944,0x7ff8895c3700,0x7ff888c24480,0,0,0,17852703236464,17852703202901,17852703480181,17852703481768
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,238351,238351,4194304,256,0,0,12,24,27648,0x7ff88bbf2580,0x7ff888c244c0,0,0,0,17852703520677,17852703480181,17852703754102,17852703755692
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,238351,238351,4194304,256,0,0,16,24,28608,0x7ff88bbf2400,0x7ff888c24500,0,0,0,17852703787681,17852703754102,17852704118422,17852704119943
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,238351,238351,4194304,256,0,0,16,24,29312,0x7ff88bbf2280,0x7ff888c24540,0,0,0,17852704151352,17852704118422,17852704479702,17852704481324
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,238351,238351,4194304,256,0,0,12,24,30016,0x7ff88bbf2100,0x7ff888c24580,0,0,0,17852704513273,17852704479702,17852704755543,17852704757237
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,238351,238351,4194304,256,0,0,8,24,30976,0x7ff8895c3f80,0x7ff888c245c0,0,0,0,17852704788706,17852704755543,17852705030423,17852705031860
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,238351,238351,4194304,256,0,0,12,24,31680,0x7ff8895c3e00,0x7ff888c24600,0,0,0,17852705070659,17852705030423,17852705307703,17852705309243
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,238351,238351,4194304,256,0,0,16,24,32640,0x7ff8895c3c80,0x7ff888c24640,0,0,0,17852705340412,17852705307703,17852705671863,17852705673524
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,238351,238351,4194304,256,0,0,12,24,33600,0x7ff8895c3b00,0x7ff888c24680,0,0,0,17852705705043,17852705671863,17852706035864,17852706037365
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,238351,238351,4194304,256,0,0,12,24,34560,0x7ff8895c3980,0x7ff888c246c0,0,0,0,17852706068534,17852706035864,17852706325464,17852706327138
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,238351,238351,4194304,256,0,0,8,24,35520,0x7ff8895c3800,0x7ff888c24700,0,0,0,17852706359087,17852706325464,17852706606264,17852706607841
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,238351,238351,4194304,256,0,0,12,24,36224,0x7ff8895c3680,0x7ff888c24740,0,0,0,17852706646370,17852706606264,17852706884824,17852706886384
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,238351,238351,4194304,256,0,0,12,24,37184,0x7ff88bbf2500,0x7ff888c24780,0,0,0,17852706918173,17852706884824,17852707251065,17852707252885
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,238351,238351,4194304,256,0,0,12,24,38144,0x7ff88bbf2380,0x7ff888c247c0,0,0,0,17852707284684,17852707251065,17852707615225,17852707616896
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,238351,238351,4194304,256,0,0,12,24,39104,0x7ff88bbf2200,0x7ff888c24800,0,0,0,17852707648045,17852707615225,17852707890105,17852707891729
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,238351,238351,4194304,256,0,0,8,24,40320,0x7ff88bbf2080,0x7ff888c24840,0,0,0,17852707923748,17852707890105,17852708166586,17852708168142
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,238351,238351,4194304,256,0,0,12,24,41280,0x7ff8895c3f00,0x7ff888c24880,0,0,0,17852708207321,17852708166586,17852708442906,17852708444485
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,238351,238351,4194304,256,0,0,12,24,42240,0x7ff8895c3d80,0x7ff888c248c0,0,0,0,17852708475035,17852708442906,17852708806266,17852708807837
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,238351,238351,4194304,256,0,0,12,24,43200,0x7ff8895c3c00,0x7ff888c24900,0,0,0,17852708841876,17852708806266,17852709173467,17852709175027
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,238351,238351,4194304,256,0,0,8,24,44160,0x7ff8895c3a80,0x7ff888c24940,0,0,0,17852709206277,17852709173467,17852709449627,17852709451181
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,238351,238351,4194304,256,0,0,12,24,45376,0x7ff8895c3900,0x7ff888c24980,0,0,0,17852709482650,17852709449627,17852709728507,17852709730184
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,238351,238351,4194304,256,0,0,12,24,46336,0x7ff8895c3780,0x7ff888c249c0,0,0,0,17852709769003,17852709728507,17852710007227,17852710008837
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,238351,238351,4194304,256,0,0,12,24,47552,0x7ff8895c3600,0x7ff888c24a00,0,0,0,17852710040166,17852710007227,17852710383548,17852710385288
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,238351,238351,4194304,256,0,0,12,24,48512,0x7ff88bbf2480,0x7ff888c24a40,0,0,0,17852710418027,17852710383548,17852710744348,17852710745959
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,238351,238351,4194304,256,0,0,8,24,49472,0x7ff88bbf2300,0x7ff888c24a80,0,0,0,17852710777528,17852710744348,17852711022108,17852711023662
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,238351,238351,4194304,256,0,0,12,24,50688,0x7ff88bbf2180,0x7ff888c24ac0,0,0,0,17852711055971,17852711022108,17852711304188,17852711305805
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,238351,238351,4194304,256,0,0,12,24,51648,0x7ff88bbf2000,0x7ff888c24b00,0,0,0,17852711344854,17852711304188,17852711596989,17852711598567
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,238351,238351,4194304,256,0,0,12,24,52864,0x7ff8895c3e80,0x7ff888c24b40,0,0,0,17852711631277,17852711596989,17852711961149,17852711962848
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,238351,238351,4194304,256,0,0,12,24,54080,0x7ff8895c3d00,0x7ff888c24b80,0,0,0,17852711994718,17852711961149,17852712327549,17852712329159
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,238351,238351,4194304,256,0,0,8,24,55296,0x7ff8895c3b80,0x7ff888c24bc0,0,0,0,17852712360458,17852712327549,17852712604990,17852712606592
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,238351,238351,4194304,256,0,0,12,24,56768,0x7ff8895c3a00,0x7ff888c24c00,0,0,0,17852712639062,17852712604990,17852712884670,17852712886435
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,238351,238351,4194304,256,0,0,12,24,57728,0x7ff8895c3880,0x7ff888c24c40,0,0,0,17852712924404,17852712884670,17852713165470,17852713167208
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,238351,238351,4194304,256,0,0,12,24,58944,0x7ff8895c3700,0x7ff888c24c80,0,0,0,17852713198898,17852713165470,17852713529470,17852713531039
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,238351,238351,4194304,256,0,0,12,24,60160,0x7ff88bbf2580,0x7ff888c24cc0,0,0,0,17852713563649,17852713529470,17852713890751,17852713892420
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,238351,238351,4194304,256,0,0,8,24,61376,0x7ff88bbf2400,0x7ff888c24d00,0,0,0,17852713925370,17852713890751,17852714168991,17852714170743
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,238351,238351,4194304,256,0,0,12,24,62848,0x7ff88bbf2280,0x7ff888c24d40,0,0,0,17852714203523,17852714168991,17852714452831,17852714454446
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,238351,238351,4194304,256,0,0,12,24,63808,0x7ff88bbf2100,0x7ff888c24d80,0,0,0,17852714493475,17852714452831,17852714730591,17852714732310
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,238351,238351,4194304,256,0,0,12,24,65024,0x7ff8895c3f80,0x7ff888c24dc0,0,0,0,17852714764259,17852714730591,17852715097952,17852715099550
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,238351,238351,4194304,256,0,0,12,24,66240,0x7ff8895c3e00,0x7ff888c24e00,0,0,0,17852715131050,17852715097952,17852715461792,17852715463411
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,238351,238351,4194304,256,0,0,8,24,67456,0x7ff8895c3c80,0x7ff888c24e40,0,0,0,17852715495341,17852715461792,17852715739392,17852715741084
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,238351,238351,4194304,256,0,0,12,24,68928,0x7ff8895c3b00,0x7ff888c24e80,0,0,0,17852715773124,17852715739392,17852716027073,17852716028717
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,238351,238351,4194304,256,0,0,12,24,70144,0x7ff8895c3980,0x7ff888c24ec0,0,0,0,17852716068486,17852716027073,17852716306273,17852716307960
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,238351,238351,4194304,256,0,0,12,24,71616,0x7ff8895c3800,0x7ff888c24f00,0,0,0,17852716339270,17852716306273,17852716670113,17852716671741
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,238351,238351,4194304,256,0,0,12,24,72832,0x7ff8895c3680,0x7ff888c24f40,0,0,0,17852716703121,17852716670113,17852717030914,17852717032592
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,238351,238351,4194304,256,0,0,8,24,74048,0x7ff88bbf2500,0x7ff888c24f80,0,0,0,17852717063472,17852717030914,17852717308194,17852717309915
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,238351,238351,4194304,256,0,0,12,24,75776,0x7ff88bbf2380,0x7ff888c24fc0,0,0,0,17852717341515,17852717308194,17852717598274,17852717599928
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,238351,238351,4194304,256,0,0,12,24,76992,0x7ff88bbf2200,0x7ff888c25000,0,0,0,17852717638877,17852717598274,17852717874434,17852717875971
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,238351,238351,4194304,256,0,0,12,24,78464,0x7ff88bbf2080,0x7ff888c25040,0,0,0,17852717908151,17852717874434,17852718242115,17852718243902
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,238351,238351,4194304,256,0,0,12,24,79936,0x7ff8895c3f00,0x7ff888c25080,0,0,0,17852718276721,17852718242115,17852718610275,17852718611863
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,238351,238351,4194304,256,0,0,8,24,81408,0x7ff8895c3d80,0x7ff888c250c0,0,0,0,17852718642982,17852718610275,17852718888355,17852718889966
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,238351,238351,4194304,256,0,0,12,24,83136,0x7ff8895c3c00,0x7ff888c25100,0,0,0,17852718921995,17852718888355,17852719182915,17852719184579
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,238351,238351,4194304,256,0,0,12,24,84352,0x7ff8895c3a80,0x7ff888c25140,0,0,0,17852719235378,17852719182915,17852719468836,17852719471082
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,238351,238351,4194304,256,0,0,12,24,85824,0x7ff8895c3900,0x7ff888c25180,0,0,0,17852719502231,17852719468836,17852719841796,17852719843403
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,238351,238351,4194304,256,0,0,12,24,87296,0x7ff8895c3780,0x7ff888c251c0,0,0,0,17852719875732,17852719841796,17852720205156,17852720206694
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,238351,238351,4194304,256,0,0,12,24,88768,0x7ff8895c3600,0x7ff888c25200,0,0,0,17852720237623,17852720205156,17852720485637,17852720487157
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,238351,238351,4194304,256,0,0,12,24,90752,0x7ff88bbf2480,0x7ff888c25240,0,0,0,17852720519426,17852720485637,17852720791237,17852720792699
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,238351,238351,4194304,256,0,0,12,24,91968,0x7ff88bbf2300,0x7ff888c25280,0,0,0,17852720831258,17852720791237,17852721075237,17852721076832
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,238351,238351,4194304,256,0,0,12,24,93440,0x7ff88bbf2180,0x7ff888c252c0,0,0,0,17852721109001,17852721075237,17852721437477,17852721439053
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,238351,238351,4194304,256,0,0,12,24,94912,0x7ff88bbf2000,0x7ff888c25300,0,0,0,17852721471482,17852721437477,17852721802598,17852721804134
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,238351,238351,4194304,256,0,0,12,24,96384,0x7ff8895c3e80,0x7ff888c25340,0,0,0,17852721835423,17852721802598,17852722083878,17852722085677
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,238351,238351,4194304,256,0,0,12,24,98368,0x7ff8895c3d00,0x7ff888c25380,0,0,0,17852722117666,17852722083878,17852722394278,17852722395829
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,238351,238351,4194304,256,0,0,12,24,99584,0x7ff8895c3b80,0x7ff888c253c0,0,0,0,17852722435088,17852722394278,17852722680359,17852722681982
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,238351,238351,4194304,256,0,0,12,24,101312,0x7ff8895c3a00,0x7ff888c25400,0,0,0,17852722713441,17852722680359,17852723043079,17852723044603
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,238351,238351,4194304,256,0,0,12,24,102784,0x7ff8895c3880,0x7ff888c25440,0,0,0,17852723076572,17852723043079,17852723405639,17852723407144
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,238351,238351,4194304,256,0,0,12,24,104256,0x7ff8895c3700,0x7ff888c25480,0,0,0,17852723438243,17852723405639,17852723683239,17852723685007
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,238351,238351,4194304,256,0,0,12,24,106240,0x7ff88bbf2580,0x7ff888c254c0,0,0,0,17852723715457,17852723683239,17852723995560,17852723997160
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,238351,238351,4194304,256,0,0,12,24,107712,0x7ff88bbf2400,0x7ff888c25500,0,0,0,17852724036629,17852723995560,17852724280840,17852724282463
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,238351,238351,4194304,256,0,0,16,24,109440,0x7ff88bbf2280,0x7ff888c25540,0,0,0,17852724316172,17852724280840,17852724642760,17852724644394
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,238351,238351,4194304,256,0,0,16,24,111168,0x7ff88bbf2100,0x7ff888c25580,0,0,0,17852724677643,17852724642760,17852725009481,17852725011105
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,238351,238351,4194304,256,0,0,8,24,112896,0x7ff8895c3f80,0x7ff888c255c0,0,0,0,17852725042374,17852725009481,17852725289481,17852725291098
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,238351,238351,4194304,256,0,0,12,24,115136,0x7ff8895c3e00,0x7ff888c25600,0,0,0,17852725322377,17852725289481,17852725611561,17852725613050
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,238351,238351,4194304,256,0,0,12,24,116608,0x7ff8895c3c80,0x7ff888c25640,0,0,0,17852725651419,17852725611561,17852725888361,17852725889983
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,238351,238351,4194304,256,0,0,16,24,118336,0x7ff8895c3b00,0x7ff888c25680,0,0,0,17852725921822,17852725888361,17852726253482,17852726255414
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,238351,238351,4194304,256,0,0,16,24,120064,0x7ff8895c3980,0x7ff888c256c0,0,0,0,17852726287623,17852726253482,17852726617482,17852726619115
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,238351,238351,4194304,256,0,0,12,24,121792,0x7ff8895c3800,0x7ff888c25700,0,0,0,17852726650804,17852726617482,17852726896522,17852726898098
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,238351,238351,4194304,256,0,0,12,24,124032,0x7ff8895c3680,0x7ff888c25740,0,0,0,17852726929667,17852726896522,17852727227403,17852727229120
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,238351,238351,4194304,256,0,0,12,24,125504,0x7ff88bbf2500,0x7ff888c25780,0,0,0,17852727267889,17852727227403,17852727511403,17852727512983
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,238351,238351,4194304,256,0,0,12,24,127488,0x7ff88bbf2380,0x7ff888c257c0,0,0,0,17852727544622,17852727511403,17852727872523,17852727874214
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,238351,238351,4194304,256,0,0,12,24,129216,0x7ff88bbf2200,0x7ff888c25800,0,0,0,17852727907013,17852727872523,17852728235724,17852728237265
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,238351,238351,4194304,256,0,0,12,24,130944,0x7ff88bbf2080,0x7ff888c25840,0,0,0,17852728269444,17852728235724,17852728517484,17852728519148
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,238351,238351,4194304,256,0,0,12,24,133440,0x7ff8895c3f00,0x7ff888c25880,0,0,0,17852728551127,17852728517484,17852728857804,17852728859459
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,238351,238351,4194304,256,0,0,12,24,134912,0x7ff8895c3d80,0x7ff888c258c0,0,0,0,17852728899498,17852728857804,17852729139564,17852729141132
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,238351,238351,4194304,256,0,0,12,24,136896,0x7ff8895c3c00,0x7ff888c25900,0,0,0,17852729172291,17852729139564,17852729503085,17852729504743
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,238351,238351,4194304,256,0,0,12,24,138880,0x7ff8895c3a80,0x7ff888c25940,0,0,0,17852729536092,17852729503085,17852729865485,17852729867124
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,238351,238351,4194304,256,0,0,12,24,140864,0x7ff8895c3900,0x7ff888c25980,0,0,0,17852729898743,17852729865485,17852730155885,17852730157467
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,238351,238351,4194304,256,0,0,12,24,143616,0x7ff8895c3780,0x7ff888c259c0,0,0,0,17852730190876,17852730155885,17852730525006,17852730526718
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,238351,238351,4194304,256,0,0,12,24,145344,0x7ff8895c3600,0x7ff888c25a00,0,0,0,17852730566577,17852730525006,17852730809646,17852730811381
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,238351,238351,4194304,256,0,0,12,24,147584,0x7ff88bbf2480,0x7ff888c25a40,0,0,0,17852730843010,17852730809646,17852731174126,17852731175882
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,238351,238351,4194304,256,0,0,12,24,149568,0x7ff88bbf2300,0x7ff888c25a80,0,0,0,17852731208061,17852731174126,17852731537327,17852731538893
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,238351,238351,4194304,256,0,0,12,24,151552,0x7ff88bbf2180,0x7ff888c25ac0,0,0,0,17852731570982,17852731537327,17852731833807,17852731835685
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,238351,238351,4194304,256,0,0,12,24,154304,0x7ff88bbf2000,0x7ff888c25b00,0,0,0,17852731867534,17852731833807,17852732204527,17852732206096
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,238351,238351,4194304,256,0,0,12,24,156288,0x7ff8895c3e80,0x7ff888c25b40,0,0,0,17852732245085,17852732204527,17852732490287,17852732491899
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,238351,238351,4194304,256,0,0,12,24,158784,0x7ff8895c3d00,0x7ff888c25b80,0,0,0,17852732523968,17852732490287,17852732856048,17852732857640
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,238351,238351,4194304,256,0,0,12,24,161024,0x7ff8895c3b80,0x7ff888c25bc0,0,0,0,17852732889679,17852732856048,17852733221648,17852733223301
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,238351,238351,4194304,256,0,0,12,24,163264,0x7ff8895c3a00,0x7ff888c25c00,0,0,0,17852733254330,17852733221648,17852733532368,17852733533913
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,238351,238351,4194304,256,0,0,12,24,166528,0x7ff8895c3880,0x7ff888c25c40,0,0,0,17852733565032,17852733532368,17852733921009,17852733941203
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,238351,238351,4194304,256,0,0,12,24,168512,0x7ff8895c3700,0x7ff888c25c80,0,0,0,17852733962372,17852733921009,17852734230929,17852734232796
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,238351,238351,4194304,256,0,0,12,24,171264,0x7ff88bbf2580,0x7ff888c25cc0,0,0,0,17852734265345,17852734230929,17852734609169,17852734610756
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,238351,238351,4194304,256,0,0,12,24,173760,0x7ff88bbf2400,0x7ff888c25d00,0,0,0,17852734643356,17852734609169,17852734977490,17852734979187
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,238351,238351,4194304,256,0,0,12,24,176256,0x7ff88bbf2280,0x7ff888c25d40,0,0,0,17852735011617,17852734977490,17852735296850,17852735298459
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,238351,238351,4194304,256,0,0,12,24,179776,0x7ff88bbf2100,0x7ff888c25d80,0,0,0,17852735330689,17852735296850,17852735711570,17852735757648
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,238351,238351,4194304,256,0,0,12,24,182272,0x7ff8895c3f80,0x7ff888c25dc0,0,0,0,17852735776978,17852735711570,17852736060851,17852736062501
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,238351,238351,4194304,256,0,0,12,24,185536,0x7ff8895c3e00,0x7ff888c25e00,0,0,0,17852736095700,17852736060851,17852736435731,17852736480820
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,238351,238351,4194304,256,0,0,12,24,188544,0x7ff8895c3c80,0x7ff888c25e40,0,0,0,17852736492510,17852736435731,17852736844051,17852736886710
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,238351,238351,4194304,256,0,0,12,24,191552,0x7ff8895c3b00,0x7ff888c25e80,0,0,0,17852736898080,17852736844051,17852737223732,17852737225292
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,238351,238351,4194304,256,0,0,12,24,195840,0x7ff8895c3980,0x7ff888c25ec0,0,0,0,17852737256371,17852737223732,17852737690612,17852737709180
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,238351,238351,4194304,256,0,0,12,24,198592,0x7ff8895c3800,0x7ff888c25f00,0,0,0,17852737731449,17852737690612,17852738033812,17852738035472
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,238351,238351,4194304,256,0,0,12,24,202368,0x7ff8895c3680,0x7ff888c25f40,0,0,0,17852738067181,17852738033812,17852738456693,17852738501100
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,238351,238351,4194304,256,0,0,12,24,205888,0x7ff88bbf2500,0x7ff888c25f80,0,0,0,17852738514830,17852738456693,17852738880533,17852738924380
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,238351,238351,4194304,256,0,0,12,24,209408,0x7ff88bbf2380,0x7ff888c25fc0,0,0,0,17852738935080,17852738880533,17852739282613,17852739284311
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,238351,238351,4194304,256,0,0,12,24,214464,0x7ff88bbf2200,0x7ff888c26000,0,0,0,17852739317490,17852739282613,17852739807414,17852739849997
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,238351,238351,4194304,256,0,0,12,24,217728,0x7ff88bbf2080,0x7ff888c26040,0,0,0,17852739870166,17852739807414,17852740189654,17852740191278
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,238351,238351,4194304,256,0,0,12,24,222016,0x7ff8895c3f00,0x7ff888c26080,0,0,0,17852740223318,17852740189654,17852740603735,17852740646387
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,238351,238351,4194304,256,0,0,12,24,226048,0x7ff8895c3d80,0x7ff888c260c0,0,0,0,17852740658167,17852740603735,17852741053975,17852741096566
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,238351,238351,4194304,256,0,0,12,24,230080,0x7ff8895c3c00,0x7ff888c26100,0,0,0,17852741108566,17852741053975,17852741477975,17852741520635
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,238351,238351,4194304,256,0,0,12,24,235904,0x7ff8895c3a80,0x7ff888c26140,0,0,0,17852741533345,17852741477975,17852742078136,17852742100261
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,238351,238351,4194304,256,0,0,12,24,239424,0x7ff8895c3900,0x7ff888c26180,0,0,0,17852742120520,17852742078136,17852742462616,17852742464122
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,238351,238351,4194304,256,0,0,12,24,244224,0x7ff8895c3780,0x7ff888c261c0,0,0,0,17852742495881,17852742462616,17852742899737,17852742943690
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,238351,238351,4194304,256,0,0,12,24,248768,0x7ff8895c3600,0x7ff888c26200,0,0,0,17852742956040,17852742899737,17852743360697,17852743403809
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,238351,238351,4194304,256,0,0,12,24,253312,0x7ff88bbf2480,0x7ff888c26240,0,0,0,17852743415308,17852743360697,17852743812697,17852743854887
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,238351,238351,4194304,256,0,0,8,24,255552,0x7ff88bbf2300,0x7ff888c26280,0,0,0,17852743866867,17852743812697,17852744476858,17852744519781
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,238351,238351,4194304,256,0,0,12,24,259840,0x7ff88bbf2180,0x7ff888c262c0,0,0,0,17852744539460,17852744476858,17852744921338,17852744964010
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,238351,238351,4194304,256,0,0,12,24,265664,0x7ff88bbf2000,0x7ff888c26300,0,0,0,17852744975050,17852744921338,17852745435899,17852745478337
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,238351,238351,4194304,256,0,0,12,24,271232,0x7ff8895c3e80,0x7ff888c26340,0,0,0,17852745489317,17852745435899,17852745954459,17852745972385
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,238351,238351,4194304,256,0,0,8,24,273216,0x7ff8895c3d00,0x7ff888c26380,0,0,0,17852745987614,17852745954459,17852746446940,17852746492852
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,238351,238351,4194304,256,0,0,8,24,275712,0x7ff8895c3b80,0x7ff888c263c0,0,0,0,17852746505581,17852746446940,17852747219101,17852747263173
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,238351,238351,4194304,256,0,0,12,24,280768,0x7ff8895c3a00,0x7ff888c26400,0,0,0,17852747283402,17852747219101,17852747705501,17852747747881
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,238351,238351,4194304,256,0,0,12,24,287616,0x7ff8895c3880,0x7ff888c26440,0,0,0,17852747758960,17852747705501,17852748268861,17852748310857
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,238351,238351,4194304,256,0,0,12,24,294208,0x7ff8895c3700,0x7ff888c26480,0,0,0,17852748322856,17852748268861,17852748832222,17852748874753
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,238351,238351,4194304,256,0,0,8,24,296960,0x7ff88bbf2580,0x7ff888c264c0,0,0,0,17852748886262,17852748832222,17852749394782,17852749436889
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,238351,238351,4194304,256,0,0,8,24,299968,0x7ff88bbf2400,0x7ff888c26500,0,0,0,17852749448568,17852749394782,17852750264863,17852750309257
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,238351,238351,4194304,256,0,0,8,24,302720,0x7ff88bbf2280,0x7ff888c26540,0,0,0,17852750329727,17852750264863,17852750929824,17852750974811
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,238351,238351,4194304,256,0,0,12,24,305472,0x7ff88bbf2100,0x7ff888c26580,0,0,0,17852750986220,17852750929824,17852751608704,17852751652374
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,238351,238351,4194304,256,0,0,12,24,308224,0x7ff8895c3f80,0x7ff888c265c0,0,0,0,17852751663494,17852751608704,17852752288225,17852752330757
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,238351,238351,4194304,256,0,0,8,24,310976,0x7ff8895c3e00,0x7ff888c26600,0,0,0,17852752342157,17852752288225,17852752950306,17852752993191
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,238351,238351,4194304,256,0,0,8,24,313216,0x7ff8895c3c80,0x7ff888c26640,0,0,0,17852753004871,17852752950014,17852754036414,17852754087294
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,238351,238351,4194304,256,0,0,8,24,315968,0x7ff8895c3b00,0x7ff888c26680,0,0,0,17852754107573,17852754036414,17852755116734,17852755164557
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,238351,238351,4194304,256,0,0,12,24,318720,0x7ff8895c3980,0x7ff888c266c0,0,0,0,17852755175877,17852755116734,17852756216414,17852756283989
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,238351,238351,4194304,256,0,0,12,24,321472,0x7ff8895c3800,0x7ff888c26700,0,0,0,17852756296649,17852756216414,17852757347295,17852757413671
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,238351,238351,4194304,256,0,0,8,24,324224,0x7ff8895c3680,0x7ff888c26740,0,0,0,17852757426311,17852757347295,17852758455615,17852758522824
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,238351,238351,4194304,256,0,0,8,24,326464,0x7ff88bbf2500,0x7ff888c26780,0,0,0,17852758535493,17852758455615,17852760413696,17852760480545
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,238351,238351,4194304,256,0,0,8,24,329216,0x7ff88bbf2380,0x7ff888c267c0,0,0,0,17852760500774,17852760413696,17852762329856,17852762401667
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,238351,238351,4194304,256,0,0,12,24,331968,0x7ff88bbf2200,0x7ff888c26800,0,0,0,17852762414887,17852762329856,17852764331937,17852764406557
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,238351,238351,4194304,256,0,0,12,24,334720,0x7ff88bbf2080,0x7ff888c26840,0,0,0,17852764419157,17852764331937,17852766312417,17852766383018
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,238351,238351,4194304,256,0,0,8,24,337472,0x7ff8895c3f00,0x7ff888c26880,0,0,0,17852766395418,17852766312417,17852768250018,17852768319691
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,238351,238351,4194304,256,0,0,8,24,0,0x7ff8895c3d80,0x7ff888c268c0,0,0,0,17852768331360,17852768250018,17852771863459,17852771934051
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 238351 238351 33554432 256 0 0 4 32 4160 0x0 0x7ff888c04280 0 0 0 17852547584485 17851838027568 17852691164011 17852691281181
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 238351 238351 32768 256 0 0 12 24 13888 0x0 0x7ff888c23f80 0 0 0 17852696444493 17852691164011 17852696572335 17852696576630
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 5 238351 238351 4194304 256 0 0 12 24 14336 0x7ff88bbf2380 0x7ff888c23fc0 0 0 0 17852696612159 17852696572335 17852696936336 17852696938901
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 238351 238351 4194304 256 0 0 16 24 15040 0x7ff88bbf2200 0x7ff888c24000 0 0 0 17852696975310 17852696936336 17852697339696 17852697341881
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 11 238351 238351 4194304 256 0 0 16 24 15488 0x7ff88bbf2080 0x7ff888c24040 0 0 0 17852697374780 17852697339696 17852697731856 17852697734031
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 14 238351 238351 4194304 256 0 0 12 24 15936 0x7ff8895c3f00 0x7ff888c24080 0 0 0 17852697767750 17852697731856 17852698036497 17852698038724
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 17 238351 238351 4194304 256 0 0 12 24 16384 0x7ff8895c3d80 0x7ff888c240c0 0 0 0 17852698071613 17852698036497 17852698369937 17852698372295
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 20 238351 238351 4194304 256 0 0 12 24 17088 0x7ff8895c3c00 0x7ff888c24100 0 0 0 17852698416344 17852698369937 17852698676817 17852698679058
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 238351 238351 4194304 256 0 0 16 24 17792 0x7ff8895c3a80 0x7ff888c24140 0 0 0 17852698711897 17852698676817 17852699069297 17852699071448
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 26 238351 238351 4194304 256 0 0 16 24 18496 0x7ff8895c3900 0x7ff888c24180 0 0 0 17852699103227 17852699069297 17852699460338 17852699462438
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 29 238351 238351 4194304 256 0 0 16 24 19200 0x7ff8895c3780 0x7ff888c241c0 0 0 0 17852699493987 17852699460338 17852699775858 17852699778060
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 32 238351 238351 4194304 256 0 0 16 24 19904 0x7ff8895c3600 0x7ff888c24200 0 0 0 17852699811880 17852699775858 17852700079858 17852700082053
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 35 238351 238351 4194304 256 0 0 12 24 20608 0x7ff88bbf2480 0x7ff888c24240 0 0 0 17852700121632 17852700079858 17852700381299 17852700383605
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 238351 238351 4194304 256 0 0 16 24 21312 0x7ff88bbf2300 0x7ff888c24280 0 0 0 17852700416035 17852700381299 17852700771219 17852700773606
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 41 238351 238351 4194304 256 0 0 16 24 22016 0x7ff88bbf2180 0x7ff888c242c0 0 0 0 17852700806585 17852700771219 17852701160019 17852701162216
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 44 238351 238351 4194304 256 0 0 16 24 22720 0x7ff88bbf2000 0x7ff888c24300 0 0 0 17852701194595 17852701160019 17852701463540 17852701465598
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 47 238351 238351 4194304 256 0 0 12 24 23424 0x7ff8895c3e80 0x7ff888c24340 0 0 0 17852701497488 17852701463540 17852701764020 17852701766161
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 50 238351 238351 4194304 256 0 0 12 24 24128 0x7ff8895c3d00 0x7ff888c24380 0 0 0 17852701805360 17852701764020 17852702066100 17852702068263
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 238351 238351 4194304 256 0 0 16 24 24832 0x7ff8895c3b80 0x7ff888c243c0 0 0 0 17852702100643 17852702066100 17852702483061 17852702485313
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 56 238351 238351 4194304 256 0 0 16 24 25536 0x7ff8895c3a00 0x7ff888c24400 0 0 0 17852702517042 17852702483061 17852702873781 17852702876263
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 59 238351 238351 4194304 256 0 0 12 24 26240 0x7ff8895c3880 0x7ff888c24440 0 0 0 17852702907713 17852702873781 17852703202901 17852703204495
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 62 238351 238351 4194304 256 0 0 12 24 26944 0x7ff8895c3700 0x7ff888c24480 0 0 0 17852703236464 17852703202901 17852703480181 17852703481768
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 65 238351 238351 4194304 256 0 0 12 24 27648 0x7ff88bbf2580 0x7ff888c244c0 0 0 0 17852703520677 17852703480181 17852703754102 17852703755692
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 238351 238351 4194304 256 0 0 16 24 28608 0x7ff88bbf2400 0x7ff888c24500 0 0 0 17852703787681 17852703754102 17852704118422 17852704119943
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 71 238351 238351 4194304 256 0 0 16 24 29312 0x7ff88bbf2280 0x7ff888c24540 0 0 0 17852704151352 17852704118422 17852704479702 17852704481324
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 74 238351 238351 4194304 256 0 0 12 24 30016 0x7ff88bbf2100 0x7ff888c24580 0 0 0 17852704513273 17852704479702 17852704755543 17852704757237
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 77 238351 238351 4194304 256 0 0 8 24 30976 0x7ff8895c3f80 0x7ff888c245c0 0 0 0 17852704788706 17852704755543 17852705030423 17852705031860
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 80 238351 238351 4194304 256 0 0 12 24 31680 0x7ff8895c3e00 0x7ff888c24600 0 0 0 17852705070659 17852705030423 17852705307703 17852705309243
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 238351 238351 4194304 256 0 0 16 24 32640 0x7ff8895c3c80 0x7ff888c24640 0 0 0 17852705340412 17852705307703 17852705671863 17852705673524
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 86 238351 238351 4194304 256 0 0 12 24 33600 0x7ff8895c3b00 0x7ff888c24680 0 0 0 17852705705043 17852705671863 17852706035864 17852706037365
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 89 238351 238351 4194304 256 0 0 12 24 34560 0x7ff8895c3980 0x7ff888c246c0 0 0 0 17852706068534 17852706035864 17852706325464 17852706327138
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 92 238351 238351 4194304 256 0 0 8 24 35520 0x7ff8895c3800 0x7ff888c24700 0 0 0 17852706359087 17852706325464 17852706606264 17852706607841
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 95 238351 238351 4194304 256 0 0 12 24 36224 0x7ff8895c3680 0x7ff888c24740 0 0 0 17852706646370 17852706606264 17852706884824 17852706886384
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 238351 238351 4194304 256 0 0 12 24 37184 0x7ff88bbf2500 0x7ff888c24780 0 0 0 17852706918173 17852706884824 17852707251065 17852707252885
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 101 238351 238351 4194304 256 0 0 12 24 38144 0x7ff88bbf2380 0x7ff888c247c0 0 0 0 17852707284684 17852707251065 17852707615225 17852707616896
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 104 238351 238351 4194304 256 0 0 12 24 39104 0x7ff88bbf2200 0x7ff888c24800 0 0 0 17852707648045 17852707615225 17852707890105 17852707891729
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 107 238351 238351 4194304 256 0 0 8 24 40320 0x7ff88bbf2080 0x7ff888c24840 0 0 0 17852707923748 17852707890105 17852708166586 17852708168142
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 110 238351 238351 4194304 256 0 0 12 24 41280 0x7ff8895c3f00 0x7ff888c24880 0 0 0 17852708207321 17852708166586 17852708442906 17852708444485
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 238351 238351 4194304 256 0 0 12 24 42240 0x7ff8895c3d80 0x7ff888c248c0 0 0 0 17852708475035 17852708442906 17852708806266 17852708807837
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 116 238351 238351 4194304 256 0 0 12 24 43200 0x7ff8895c3c00 0x7ff888c24900 0 0 0 17852708841876 17852708806266 17852709173467 17852709175027
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 119 238351 238351 4194304 256 0 0 8 24 44160 0x7ff8895c3a80 0x7ff888c24940 0 0 0 17852709206277 17852709173467 17852709449627 17852709451181
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 122 238351 238351 4194304 256 0 0 12 24 45376 0x7ff8895c3900 0x7ff888c24980 0 0 0 17852709482650 17852709449627 17852709728507 17852709730184
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 125 238351 238351 4194304 256 0 0 12 24 46336 0x7ff8895c3780 0x7ff888c249c0 0 0 0 17852709769003 17852709728507 17852710007227 17852710008837
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 238351 238351 4194304 256 0 0 12 24 47552 0x7ff8895c3600 0x7ff888c24a00 0 0 0 17852710040166 17852710007227 17852710383548 17852710385288
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 131 238351 238351 4194304 256 0 0 12 24 48512 0x7ff88bbf2480 0x7ff888c24a40 0 0 0 17852710418027 17852710383548 17852710744348 17852710745959
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 134 238351 238351 4194304 256 0 0 8 24 49472 0x7ff88bbf2300 0x7ff888c24a80 0 0 0 17852710777528 17852710744348 17852711022108 17852711023662
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 137 238351 238351 4194304 256 0 0 12 24 50688 0x7ff88bbf2180 0x7ff888c24ac0 0 0 0 17852711055971 17852711022108 17852711304188 17852711305805
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 140 238351 238351 4194304 256 0 0 12 24 51648 0x7ff88bbf2000 0x7ff888c24b00 0 0 0 17852711344854 17852711304188 17852711596989 17852711598567
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 238351 238351 4194304 256 0 0 12 24 52864 0x7ff8895c3e80 0x7ff888c24b40 0 0 0 17852711631277 17852711596989 17852711961149 17852711962848
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 146 238351 238351 4194304 256 0 0 12 24 54080 0x7ff8895c3d00 0x7ff888c24b80 0 0 0 17852711994718 17852711961149 17852712327549 17852712329159
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 149 238351 238351 4194304 256 0 0 8 24 55296 0x7ff8895c3b80 0x7ff888c24bc0 0 0 0 17852712360458 17852712327549 17852712604990 17852712606592
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 152 238351 238351 4194304 256 0 0 12 24 56768 0x7ff8895c3a00 0x7ff888c24c00 0 0 0 17852712639062 17852712604990 17852712884670 17852712886435
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 155 238351 238351 4194304 256 0 0 12 24 57728 0x7ff8895c3880 0x7ff888c24c40 0 0 0 17852712924404 17852712884670 17852713165470 17852713167208
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 238351 238351 4194304 256 0 0 12 24 58944 0x7ff8895c3700 0x7ff888c24c80 0 0 0 17852713198898 17852713165470 17852713529470 17852713531039
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 161 238351 238351 4194304 256 0 0 12 24 60160 0x7ff88bbf2580 0x7ff888c24cc0 0 0 0 17852713563649 17852713529470 17852713890751 17852713892420
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 164 238351 238351 4194304 256 0 0 8 24 61376 0x7ff88bbf2400 0x7ff888c24d00 0 0 0 17852713925370 17852713890751 17852714168991 17852714170743
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 167 238351 238351 4194304 256 0 0 12 24 62848 0x7ff88bbf2280 0x7ff888c24d40 0 0 0 17852714203523 17852714168991 17852714452831 17852714454446
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 170 238351 238351 4194304 256 0 0 12 24 63808 0x7ff88bbf2100 0x7ff888c24d80 0 0 0 17852714493475 17852714452831 17852714730591 17852714732310
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 238351 238351 4194304 256 0 0 12 24 65024 0x7ff8895c3f80 0x7ff888c24dc0 0 0 0 17852714764259 17852714730591 17852715097952 17852715099550
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 176 238351 238351 4194304 256 0 0 12 24 66240 0x7ff8895c3e00 0x7ff888c24e00 0 0 0 17852715131050 17852715097952 17852715461792 17852715463411
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 179 238351 238351 4194304 256 0 0 8 24 67456 0x7ff8895c3c80 0x7ff888c24e40 0 0 0 17852715495341 17852715461792 17852715739392 17852715741084
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 182 238351 238351 4194304 256 0 0 12 24 68928 0x7ff8895c3b00 0x7ff888c24e80 0 0 0 17852715773124 17852715739392 17852716027073 17852716028717
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 185 238351 238351 4194304 256 0 0 12 24 70144 0x7ff8895c3980 0x7ff888c24ec0 0 0 0 17852716068486 17852716027073 17852716306273 17852716307960
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 238351 238351 4194304 256 0 0 12 24 71616 0x7ff8895c3800 0x7ff888c24f00 0 0 0 17852716339270 17852716306273 17852716670113 17852716671741
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 191 238351 238351 4194304 256 0 0 12 24 72832 0x7ff8895c3680 0x7ff888c24f40 0 0 0 17852716703121 17852716670113 17852717030914 17852717032592
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 194 238351 238351 4194304 256 0 0 8 24 74048 0x7ff88bbf2500 0x7ff888c24f80 0 0 0 17852717063472 17852717030914 17852717308194 17852717309915
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 197 238351 238351 4194304 256 0 0 12 24 75776 0x7ff88bbf2380 0x7ff888c24fc0 0 0 0 17852717341515 17852717308194 17852717598274 17852717599928
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 200 238351 238351 4194304 256 0 0 12 24 76992 0x7ff88bbf2200 0x7ff888c25000 0 0 0 17852717638877 17852717598274 17852717874434 17852717875971
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 238351 238351 4194304 256 0 0 12 24 78464 0x7ff88bbf2080 0x7ff888c25040 0 0 0 17852717908151 17852717874434 17852718242115 17852718243902
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 206 238351 238351 4194304 256 0 0 12 24 79936 0x7ff8895c3f00 0x7ff888c25080 0 0 0 17852718276721 17852718242115 17852718610275 17852718611863
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 209 238351 238351 4194304 256 0 0 8 24 81408 0x7ff8895c3d80 0x7ff888c250c0 0 0 0 17852718642982 17852718610275 17852718888355 17852718889966
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 212 238351 238351 4194304 256 0 0 12 24 83136 0x7ff8895c3c00 0x7ff888c25100 0 0 0 17852718921995 17852718888355 17852719182915 17852719184579
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 215 238351 238351 4194304 256 0 0 12 24 84352 0x7ff8895c3a80 0x7ff888c25140 0 0 0 17852719235378 17852719182915 17852719468836 17852719471082
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 238351 238351 4194304 256 0 0 12 24 85824 0x7ff8895c3900 0x7ff888c25180 0 0 0 17852719502231 17852719468836 17852719841796 17852719843403
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 221 238351 238351 4194304 256 0 0 12 24 87296 0x7ff8895c3780 0x7ff888c251c0 0 0 0 17852719875732 17852719841796 17852720205156 17852720206694
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 224 238351 238351 4194304 256 0 0 12 24 88768 0x7ff8895c3600 0x7ff888c25200 0 0 0 17852720237623 17852720205156 17852720485637 17852720487157
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 227 238351 238351 4194304 256 0 0 12 24 90752 0x7ff88bbf2480 0x7ff888c25240 0 0 0 17852720519426 17852720485637 17852720791237 17852720792699
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 230 238351 238351 4194304 256 0 0 12 24 91968 0x7ff88bbf2300 0x7ff888c25280 0 0 0 17852720831258 17852720791237 17852721075237 17852721076832
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 238351 238351 4194304 256 0 0 12 24 93440 0x7ff88bbf2180 0x7ff888c252c0 0 0 0 17852721109001 17852721075237 17852721437477 17852721439053
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 236 238351 238351 4194304 256 0 0 12 24 94912 0x7ff88bbf2000 0x7ff888c25300 0 0 0 17852721471482 17852721437477 17852721802598 17852721804134
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 239 238351 238351 4194304 256 0 0 12 24 96384 0x7ff8895c3e80 0x7ff888c25340 0 0 0 17852721835423 17852721802598 17852722083878 17852722085677
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 242 238351 238351 4194304 256 0 0 12 24 98368 0x7ff8895c3d00 0x7ff888c25380 0 0 0 17852722117666 17852722083878 17852722394278 17852722395829
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 245 238351 238351 4194304 256 0 0 12 24 99584 0x7ff8895c3b80 0x7ff888c253c0 0 0 0 17852722435088 17852722394278 17852722680359 17852722681982
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 238351 238351 4194304 256 0 0 12 24 101312 0x7ff8895c3a00 0x7ff888c25400 0 0 0 17852722713441 17852722680359 17852723043079 17852723044603
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 251 238351 238351 4194304 256 0 0 12 24 102784 0x7ff8895c3880 0x7ff888c25440 0 0 0 17852723076572 17852723043079 17852723405639 17852723407144
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 254 238351 238351 4194304 256 0 0 12 24 104256 0x7ff8895c3700 0x7ff888c25480 0 0 0 17852723438243 17852723405639 17852723683239 17852723685007
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 257 238351 238351 4194304 256 0 0 12 24 106240 0x7ff88bbf2580 0x7ff888c254c0 0 0 0 17852723715457 17852723683239 17852723995560 17852723997160
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 260 238351 238351 4194304 256 0 0 12 24 107712 0x7ff88bbf2400 0x7ff888c25500 0 0 0 17852724036629 17852723995560 17852724280840 17852724282463
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 238351 238351 4194304 256 0 0 16 24 109440 0x7ff88bbf2280 0x7ff888c25540 0 0 0 17852724316172 17852724280840 17852724642760 17852724644394
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 266 238351 238351 4194304 256 0 0 16 24 111168 0x7ff88bbf2100 0x7ff888c25580 0 0 0 17852724677643 17852724642760 17852725009481 17852725011105
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 269 238351 238351 4194304 256 0 0 8 24 112896 0x7ff8895c3f80 0x7ff888c255c0 0 0 0 17852725042374 17852725009481 17852725289481 17852725291098
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 272 238351 238351 4194304 256 0 0 12 24 115136 0x7ff8895c3e00 0x7ff888c25600 0 0 0 17852725322377 17852725289481 17852725611561 17852725613050
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 275 238351 238351 4194304 256 0 0 12 24 116608 0x7ff8895c3c80 0x7ff888c25640 0 0 0 17852725651419 17852725611561 17852725888361 17852725889983
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 238351 238351 4194304 256 0 0 16 24 118336 0x7ff8895c3b00 0x7ff888c25680 0 0 0 17852725921822 17852725888361 17852726253482 17852726255414
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 281 238351 238351 4194304 256 0 0 16 24 120064 0x7ff8895c3980 0x7ff888c256c0 0 0 0 17852726287623 17852726253482 17852726617482 17852726619115
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 284 238351 238351 4194304 256 0 0 12 24 121792 0x7ff8895c3800 0x7ff888c25700 0 0 0 17852726650804 17852726617482 17852726896522 17852726898098
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 287 238351 238351 4194304 256 0 0 12 24 124032 0x7ff8895c3680 0x7ff888c25740 0 0 0 17852726929667 17852726896522 17852727227403 17852727229120
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 290 238351 238351 4194304 256 0 0 12 24 125504 0x7ff88bbf2500 0x7ff888c25780 0 0 0 17852727267889 17852727227403 17852727511403 17852727512983
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 238351 238351 4194304 256 0 0 12 24 127488 0x7ff88bbf2380 0x7ff888c257c0 0 0 0 17852727544622 17852727511403 17852727872523 17852727874214
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 296 238351 238351 4194304 256 0 0 12 24 129216 0x7ff88bbf2200 0x7ff888c25800 0 0 0 17852727907013 17852727872523 17852728235724 17852728237265
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 299 238351 238351 4194304 256 0 0 12 24 130944 0x7ff88bbf2080 0x7ff888c25840 0 0 0 17852728269444 17852728235724 17852728517484 17852728519148
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 302 238351 238351 4194304 256 0 0 12 24 133440 0x7ff8895c3f00 0x7ff888c25880 0 0 0 17852728551127 17852728517484 17852728857804 17852728859459
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 305 238351 238351 4194304 256 0 0 12 24 134912 0x7ff8895c3d80 0x7ff888c258c0 0 0 0 17852728899498 17852728857804 17852729139564 17852729141132
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 238351 238351 4194304 256 0 0 12 24 136896 0x7ff8895c3c00 0x7ff888c25900 0 0 0 17852729172291 17852729139564 17852729503085 17852729504743
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 311 238351 238351 4194304 256 0 0 12 24 138880 0x7ff8895c3a80 0x7ff888c25940 0 0 0 17852729536092 17852729503085 17852729865485 17852729867124
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 314 238351 238351 4194304 256 0 0 12 24 140864 0x7ff8895c3900 0x7ff888c25980 0 0 0 17852729898743 17852729865485 17852730155885 17852730157467
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 317 238351 238351 4194304 256 0 0 12 24 143616 0x7ff8895c3780 0x7ff888c259c0 0 0 0 17852730190876 17852730155885 17852730525006 17852730526718
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 320 238351 238351 4194304 256 0 0 12 24 145344 0x7ff8895c3600 0x7ff888c25a00 0 0 0 17852730566577 17852730525006 17852730809646 17852730811381
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 238351 238351 4194304 256 0 0 12 24 147584 0x7ff88bbf2480 0x7ff888c25a40 0 0 0 17852730843010 17852730809646 17852731174126 17852731175882
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 326 238351 238351 4194304 256 0 0 12 24 149568 0x7ff88bbf2300 0x7ff888c25a80 0 0 0 17852731208061 17852731174126 17852731537327 17852731538893
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 329 238351 238351 4194304 256 0 0 12 24 151552 0x7ff88bbf2180 0x7ff888c25ac0 0 0 0 17852731570982 17852731537327 17852731833807 17852731835685
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 332 238351 238351 4194304 256 0 0 12 24 154304 0x7ff88bbf2000 0x7ff888c25b00 0 0 0 17852731867534 17852731833807 17852732204527 17852732206096
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 335 238351 238351 4194304 256 0 0 12 24 156288 0x7ff8895c3e80 0x7ff888c25b40 0 0 0 17852732245085 17852732204527 17852732490287 17852732491899
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 238351 238351 4194304 256 0 0 12 24 158784 0x7ff8895c3d00 0x7ff888c25b80 0 0 0 17852732523968 17852732490287 17852732856048 17852732857640
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 341 238351 238351 4194304 256 0 0 12 24 161024 0x7ff8895c3b80 0x7ff888c25bc0 0 0 0 17852732889679 17852732856048 17852733221648 17852733223301
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 344 238351 238351 4194304 256 0 0 12 24 163264 0x7ff8895c3a00 0x7ff888c25c00 0 0 0 17852733254330 17852733221648 17852733532368 17852733533913
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 347 238351 238351 4194304 256 0 0 12 24 166528 0x7ff8895c3880 0x7ff888c25c40 0 0 0 17852733565032 17852733532368 17852733921009 17852733941203
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 350 238351 238351 4194304 256 0 0 12 24 168512 0x7ff8895c3700 0x7ff888c25c80 0 0 0 17852733962372 17852733921009 17852734230929 17852734232796
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 238351 238351 4194304 256 0 0 12 24 171264 0x7ff88bbf2580 0x7ff888c25cc0 0 0 0 17852734265345 17852734230929 17852734609169 17852734610756
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 356 238351 238351 4194304 256 0 0 12 24 173760 0x7ff88bbf2400 0x7ff888c25d00 0 0 0 17852734643356 17852734609169 17852734977490 17852734979187
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 359 238351 238351 4194304 256 0 0 12 24 176256 0x7ff88bbf2280 0x7ff888c25d40 0 0 0 17852735011617 17852734977490 17852735296850 17852735298459
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 362 238351 238351 4194304 256 0 0 12 24 179776 0x7ff88bbf2100 0x7ff888c25d80 0 0 0 17852735330689 17852735296850 17852735711570 17852735757648
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 365 238351 238351 4194304 256 0 0 12 24 182272 0x7ff8895c3f80 0x7ff888c25dc0 0 0 0 17852735776978 17852735711570 17852736060851 17852736062501
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 238351 238351 4194304 256 0 0 12 24 185536 0x7ff8895c3e00 0x7ff888c25e00 0 0 0 17852736095700 17852736060851 17852736435731 17852736480820
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 371 238351 238351 4194304 256 0 0 12 24 188544 0x7ff8895c3c80 0x7ff888c25e40 0 0 0 17852736492510 17852736435731 17852736844051 17852736886710
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 374 238351 238351 4194304 256 0 0 12 24 191552 0x7ff8895c3b00 0x7ff888c25e80 0 0 0 17852736898080 17852736844051 17852737223732 17852737225292
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 377 238351 238351 4194304 256 0 0 12 24 195840 0x7ff8895c3980 0x7ff888c25ec0 0 0 0 17852737256371 17852737223732 17852737690612 17852737709180
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 380 238351 238351 4194304 256 0 0 12 24 198592 0x7ff8895c3800 0x7ff888c25f00 0 0 0 17852737731449 17852737690612 17852738033812 17852738035472
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 238351 238351 4194304 256 0 0 12 24 202368 0x7ff8895c3680 0x7ff888c25f40 0 0 0 17852738067181 17852738033812 17852738456693 17852738501100
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 386 238351 238351 4194304 256 0 0 12 24 205888 0x7ff88bbf2500 0x7ff888c25f80 0 0 0 17852738514830 17852738456693 17852738880533 17852738924380
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 389 238351 238351 4194304 256 0 0 12 24 209408 0x7ff88bbf2380 0x7ff888c25fc0 0 0 0 17852738935080 17852738880533 17852739282613 17852739284311
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 392 238351 238351 4194304 256 0 0 12 24 214464 0x7ff88bbf2200 0x7ff888c26000 0 0 0 17852739317490 17852739282613 17852739807414 17852739849997
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 395 238351 238351 4194304 256 0 0 12 24 217728 0x7ff88bbf2080 0x7ff888c26040 0 0 0 17852739870166 17852739807414 17852740189654 17852740191278
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 238351 238351 4194304 256 0 0 12 24 222016 0x7ff8895c3f00 0x7ff888c26080 0 0 0 17852740223318 17852740189654 17852740603735 17852740646387
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 401 238351 238351 4194304 256 0 0 12 24 226048 0x7ff8895c3d80 0x7ff888c260c0 0 0 0 17852740658167 17852740603735 17852741053975 17852741096566
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 404 238351 238351 4194304 256 0 0 12 24 230080 0x7ff8895c3c00 0x7ff888c26100 0 0 0 17852741108566 17852741053975 17852741477975 17852741520635
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 407 238351 238351 4194304 256 0 0 12 24 235904 0x7ff8895c3a80 0x7ff888c26140 0 0 0 17852741533345 17852741477975 17852742078136 17852742100261
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 410 238351 238351 4194304 256 0 0 12 24 239424 0x7ff8895c3900 0x7ff888c26180 0 0 0 17852742120520 17852742078136 17852742462616 17852742464122
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 238351 238351 4194304 256 0 0 12 24 244224 0x7ff8895c3780 0x7ff888c261c0 0 0 0 17852742495881 17852742462616 17852742899737 17852742943690
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 416 238351 238351 4194304 256 0 0 12 24 248768 0x7ff8895c3600 0x7ff888c26200 0 0 0 17852742956040 17852742899737 17852743360697 17852743403809
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 419 238351 238351 4194304 256 0 0 12 24 253312 0x7ff88bbf2480 0x7ff888c26240 0 0 0 17852743415308 17852743360697 17852743812697 17852743854887
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 422 238351 238351 4194304 256 0 0 8 24 255552 0x7ff88bbf2300 0x7ff888c26280 0 0 0 17852743866867 17852743812697 17852744476858 17852744519781
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 425 238351 238351 4194304 256 0 0 12 24 259840 0x7ff88bbf2180 0x7ff888c262c0 0 0 0 17852744539460 17852744476858 17852744921338 17852744964010
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 238351 238351 4194304 256 0 0 12 24 265664 0x7ff88bbf2000 0x7ff888c26300 0 0 0 17852744975050 17852744921338 17852745435899 17852745478337
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 431 238351 238351 4194304 256 0 0 12 24 271232 0x7ff8895c3e80 0x7ff888c26340 0 0 0 17852745489317 17852745435899 17852745954459 17852745972385
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 434 238351 238351 4194304 256 0 0 8 24 273216 0x7ff8895c3d00 0x7ff888c26380 0 0 0 17852745987614 17852745954459 17852746446940 17852746492852
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 437 238351 238351 4194304 256 0 0 8 24 275712 0x7ff8895c3b80 0x7ff888c263c0 0 0 0 17852746505581 17852746446940 17852747219101 17852747263173
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 440 238351 238351 4194304 256 0 0 12 24 280768 0x7ff8895c3a00 0x7ff888c26400 0 0 0 17852747283402 17852747219101 17852747705501 17852747747881
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 238351 238351 4194304 256 0 0 12 24 287616 0x7ff8895c3880 0x7ff888c26440 0 0 0 17852747758960 17852747705501 17852748268861 17852748310857
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 446 238351 238351 4194304 256 0 0 12 24 294208 0x7ff8895c3700 0x7ff888c26480 0 0 0 17852748322856 17852748268861 17852748832222 17852748874753
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 449 238351 238351 4194304 256 0 0 8 24 296960 0x7ff88bbf2580 0x7ff888c264c0 0 0 0 17852748886262 17852748832222 17852749394782 17852749436889
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 452 238351 238351 4194304 256 0 0 8 24 299968 0x7ff88bbf2400 0x7ff888c26500 0 0 0 17852749448568 17852749394782 17852750264863 17852750309257
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 455 238351 238351 4194304 256 0 0 8 24 302720 0x7ff88bbf2280 0x7ff888c26540 0 0 0 17852750329727 17852750264863 17852750929824 17852750974811
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 238351 238351 4194304 256 0 0 12 24 305472 0x7ff88bbf2100 0x7ff888c26580 0 0 0 17852750986220 17852750929824 17852751608704 17852751652374
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 461 238351 238351 4194304 256 0 0 12 24 308224 0x7ff8895c3f80 0x7ff888c265c0 0 0 0 17852751663494 17852751608704 17852752288225 17852752330757
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 464 238351 238351 4194304 256 0 0 8 24 310976 0x7ff8895c3e00 0x7ff888c26600 0 0 0 17852752342157 17852752288225 17852752950306 17852752993191
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 467 238351 238351 4194304 256 0 0 8 24 313216 0x7ff8895c3c80 0x7ff888c26640 0 0 0 17852753004871 17852752950014 17852754036414 17852754087294
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 470 238351 238351 4194304 256 0 0 8 24 315968 0x7ff8895c3b00 0x7ff888c26680 0 0 0 17852754107573 17852754036414 17852755116734 17852755164557
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 238351 238351 4194304 256 0 0 12 24 318720 0x7ff8895c3980 0x7ff888c266c0 0 0 0 17852755175877 17852755116734 17852756216414 17852756283989
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 476 238351 238351 4194304 256 0 0 12 24 321472 0x7ff8895c3800 0x7ff888c26700 0 0 0 17852756296649 17852756216414 17852757347295 17852757413671
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 479 238351 238351 4194304 256 0 0 8 24 324224 0x7ff8895c3680 0x7ff888c26740 0 0 0 17852757426311 17852757347295 17852758455615 17852758522824
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 482 238351 238351 4194304 256 0 0 8 24 326464 0x7ff88bbf2500 0x7ff888c26780 0 0 0 17852758535493 17852758455615 17852760413696 17852760480545
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 485 238351 238351 4194304 256 0 0 8 24 329216 0x7ff88bbf2380 0x7ff888c267c0 0 0 0 17852760500774 17852760413696 17852762329856 17852762401667
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 238351 238351 4194304 256 0 0 12 24 331968 0x7ff88bbf2200 0x7ff888c26800 0 0 0 17852762414887 17852762329856 17852764331937 17852764406557
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 491 238351 238351 4194304 256 0 0 12 24 334720 0x7ff88bbf2080 0x7ff888c26840 0 0 0 17852764419157 17852764331937 17852766312417 17852766383018
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 494 238351 238351 4194304 256 0 0 8 24 337472 0x7ff8895c3f00 0x7ff888c26880 0 0 0 17852766395418 17852766312417 17852768250018 17852768319691
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 497 238351 238351 4194304 256 0 0 8 24 0 0x7ff8895c3d80 0x7ff888c268c0 0 0 0 17852768331360 17852768250018 17852771863459 17852771934051
@@ -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",0,0,0,236281,236281,33554432,256,0,0,4,32,4160,0x0,0x7f45e2204280,3670016,2905706,325081704,17832236843728,17803198665120,17832381629870,17832381744199
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,236281,236281,32768,256,0,0,12,24,13888,0x0,0x7f45e2223f80,512,96664,10851288,17832386900391,17832381629870,17832387026519,17832387030968
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,236281,236281,4194304,256,0,0,12,24,14336,0x7f45e517a380,0x7f45e2223fc0,65536,639926,71704992,17832387064037,17832387026519,17832387402360,17832387404639
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,236281,236281,4194304,256,0,0,16,24,15040,0x7f45e517a200,0x7f45e2224000,65536,663120,74284736,17832387441058,17832387402360,17832387801401,17832387803559
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,236281,236281,4194304,256,0,0,16,24,15488,0x7f45e517a080,0x7f45e2224040,65536,655382,73467248,17832387836288,17832387801401,17832388189241,17832388191179
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,236281,236281,4194304,256,0,0,12,24,15936,0x7f45e2b1bf00,0x7f45e2224080,65536,670706,75144576,17832388224148,17832388189241,17832388486682,17832388488802
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,236281,236281,4194304,256,0,0,12,24,16384,0x7f45e2b1bd80,0x7f45e22240c0,65536,633498,70989896,17832388520711,17832388486682,17832388784443,17832388786445
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,236281,236281,4194304,256,0,0,12,24,17088,0x7f45e2b1bc00,0x7f45e2224100,131072,682790,76349744,17832388829873,17832388784443,17832389085883,17832389087897
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,236281,236281,4194304,256,0,0,16,24,17792,0x7f45e2b1ba80,0x7f45e2224140,131072,702258,78734048,17832389118956,17832389085883,17832389470044,17832389472077
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,236281,236281,4194304,256,0,0,16,24,18496,0x7f45e2b1b900,0x7f45e2224180,65536,662922,74237584,17832389504707,17832389470044,17832389854525,17832389856588
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,236281,236281,4194304,256,0,0,16,24,19200,0x7f45e2b1b780,0x7f45e22241c0,131072,702944,78662512,17832389887017,17832389854525,17832390165245,17832390167590
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,236281,236281,4194304,256,0,0,16,24,19904,0x7f45e2b1b600,0x7f45e2224200,131072,698592,78249728,17832390198889,17832390165245,17832390471646,17832390473623
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,236281,236281,4194304,256,0,0,12,24,20608,0x7f45e517a480,0x7f45e2224240,131072,699922,78366656,17832390513972,17832390471646,17832390771166,17832390773245
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,236281,236281,4194304,256,0,0,16,24,21312,0x7f45e517a300,0x7f45e2224280,131072,697276,78078456,17832390805924,17832390771166,17832391153567,17832391155576
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,236281,236281,4194304,256,0,0,16,24,22016,0x7f45e517a180,0x7f45e22242c0,65536,671700,75200016,17832391187125,17832391153567,17832391540928,17832391542376
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,236281,236281,4194304,256,0,0,16,24,22720,0x7f45e517a000,0x7f45e2224300,131072,717992,80318352,17832391573205,17832391540928,17832391812928,17832391814339
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,236281,236281,4194304,256,0,0,12,24,23424,0x7f45e2b1be80,0x7f45e2224340,131072,697818,78152560,17832391845858,17832391812928,17832392080929,17832392082433
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,236281,236281,4194304,256,0,0,12,24,24128,0x7f45e2b1bd00,0x7f45e2224380,131072,696712,78052840,17832392120672,17832392080929,17832392351169,17832392352656
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,236281,236281,4194304,256,0,0,16,24,24832,0x7f45e2b1bb80,0x7f45e22243c0,131072,703960,78811040,17832392384785,17832392351169,17832392707170,17832392708527
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,236281,236281,4194304,256,0,0,16,24,25536,0x7f45e2b1ba00,0x7f45e2224400,65536,627350,70207160,17832392739226,17832392707170,17832393068610,17832393070078
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,236281,236281,4194304,256,0,0,12,24,26240,0x7f45e2b1b880,0x7f45e2224440,131072,705208,78953168,17832393101637,17832393068610,17832393338211,17832393339751
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,236281,236281,4194304,256,0,0,12,24,26944,0x7f45e2b1b700,0x7f45e2224480,131072,700642,78443288,17832393370981,17832393338211,17832393606371,17832393607955
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,236281,236281,4194304,256,0,0,12,24,27648,0x7f45e517a580,0x7f45e22244c0,131072,680574,76153088,17832393646754,17832393606371,17832393874692,17832393876138
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,236281,236281,4194304,256,0,0,16,24,28608,0x7f45e517a400,0x7f45e2224500,131072,698066,78128680,17832393908427,17832393874692,17832394231173,17832394232719
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,236281,236281,4194304,256,0,0,16,24,29312,0x7f45e517a280,0x7f45e2224540,65536,676560,75754120,17832394265568,17832394231173,17832394590853,17832394592260
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,236281,236281,4194304,256,0,0,12,24,30016,0x7f45e517a100,0x7f45e2224580,131072,665052,74494800,17832394623679,17832394590853,17832394868134,17832394869783
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,236281,236281,4194304,256,0,0,8,24,30976,0x7f45e2b1bf80,0x7f45e22245c0,131072,662312,74088520,17832394901143,17832394868134,17832395136934,17832395138407
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,236281,236281,4194304,256,0,0,12,24,31680,0x7f45e2b1be00,0x7f45e2224600,131072,693582,77663792,17832395177386,17832395136934,17832395409415,17832395411120
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,236281,236281,4194304,256,0,0,16,24,32640,0x7f45e2b1bc80,0x7f45e2224640,131072,655674,73523104,17832395443299,17832395409415,17832395769415,17832395770881
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,236281,236281,4194304,256,0,0,12,24,33600,0x7f45e2b1bb00,0x7f45e2224680,65536,651942,73037144,17832395802430,17832395769415,17832396129576,17832396130962
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,236281,236281,4194304,256,0,0,12,24,34560,0x7f45e2b1b980,0x7f45e22246c0,131072,697390,78190624,17832396162821,17832396129576,17832396399017,17832396400575
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,236281,236281,4194304,256,0,0,8,24,35520,0x7f45e2b1b800,0x7f45e2224700,131072,705040,79031632,17832396431605,17832396399017,17832396669097,17832396670499
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,236281,236281,4194304,256,0,0,12,24,36224,0x7f45e2b1b680,0x7f45e2224740,131072,702546,78684376,17832396708378,17832396669097,17832396940938,17832396942292
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,236281,236281,4194304,256,0,0,12,24,37184,0x7f45e517a500,0x7f45e2224780,131072,700556,78359944,17832396974431,17832396940938,17832397298858,17832397300373
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,236281,236281,4194304,256,0,0,12,24,38144,0x7f45e517a380,0x7f45e22247c0,65536,670702,75074704,17832397332152,17832397298858,17832397656299,17832397657764
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,236281,236281,4194304,256,0,0,12,24,39104,0x7f45e517a200,0x7f45e2224800,131072,702376,78607656,17832397689003,17832397656299,17832397926859,17832397928307
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,236281,236281,4194304,256,0,0,8,24,40320,0x7f45e517a080,0x7f45e2224840,131072,699218,78252712,17832397960087,17832397926859,17832398207180,17832398208690
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,236281,236281,4194304,256,0,0,12,24,41280,0x7f45e2b1bf00,0x7f45e2224880,131072,702102,78566800,17832398247609,17832398207180,17832398479980,17832398481434
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,236281,236281,4194304,256,0,0,12,24,42240,0x7f45e2b1bd80,0x7f45e22248c0,131072,700322,78462936,17832398512783,17832398479980,17832398840781,17832398842455
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,236281,236281,4194304,256,0,0,12,24,43200,0x7f45e2b1bc00,0x7f45e2224900,65536,678432,76016512,17832398873754,17832398840781,17832399198542,17832399199956
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,236281,236281,4194304,256,0,0,8,24,44160,0x7f45e2b1ba80,0x7f45e2224940,131072,704048,78850440,17832399231725,17832399198542,17832399474062,17832399475529
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,236281,236281,4194304,256,0,0,12,24,45376,0x7f45e2b1b900,0x7f45e2224980,131072,704294,78762488,17832399506378,17832399474062,17832399744143,17832399745442
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,236281,236281,4194304,256,0,0,12,24,46336,0x7f45e2b1b780,0x7f45e22249c0,131072,697140,78101344,17832399784061,17832399744143,17832400014383,17832400015876
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,236281,236281,4194304,256,0,0,12,24,47552,0x7f45e2b1b600,0x7f45e2224a00,131072,691764,77411472,17832400047205,17832400014383,17832400368784,17832400370137
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,236281,236281,4194304,256,0,0,12,24,48512,0x7f45e517a480,0x7f45e2224a40,65536,658738,73825056,17832400402316,17832400368784,17832400729425,17832400730838
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,236281,236281,4194304,256,0,0,8,24,49472,0x7f45e517a300,0x7f45e2224a80,131072,656782,73609296,17832400762547,17832400729425,17832401000945,17832401002361
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,236281,236281,4194304,256,0,0,12,24,50688,0x7f45e517a180,0x7f45e2224ac0,131072,661124,73973224,17832401033580,17832401000945,17832401268146,17832401269644
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,236281,236281,4194304,256,0,0,12,24,51648,0x7f45e517a000,0x7f45e2224b00,131072,684772,76598464,17832401308053,17832401268146,17832401548306,17832401549867
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,236281,236281,4194304,256,0,0,12,24,52864,0x7f45e2b1be80,0x7f45e2224b40,131072,697314,78128704,17832401581147,17832401548306,17832401907827,17832401909338
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,236281,236281,4194304,256,0,0,12,24,54080,0x7f45e2b1bd00,0x7f45e2224b80,65536,669406,75005032,17832401940558,17832401907827,17832402263187,17832402264740
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,236281,236281,4194304,256,0,0,8,24,55296,0x7f45e2b1bb80,0x7f45e2224bc0,131072,700766,78516768,17832402296189,17832402263187,17832402535028,17832402536433
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,236281,236281,4194304,256,0,0,12,24,56768,0x7f45e2b1ba00,0x7f45e2224c00,131072,697972,78177560,17832402567832,17832402535028,17832402805428,17832402806846
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,236281,236281,4194304,256,0,0,12,24,57728,0x7f45e2b1b880,0x7f45e2224c40,131072,700048,78487152,17832402845555,17832402805428,17832403074549,17832403076009
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,236281,236281,4194304,256,0,0,12,24,58944,0x7f45e2b1b700,0x7f45e2224c80,131072,688204,77079128,17832403107349,17832403074549,17832403429910,17832403431351
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,236281,236281,4194304,256,0,0,12,24,60160,0x7f45e517a580,0x7f45e2224cc0,65536,671532,75179760,17832403463430,17832403429910,17832403788470,17832403789782
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,236281,236281,4194304,256,0,0,8,24,61376,0x7f45e517a400,0x7f45e2224d00,131072,698470,78218528,17832403821291,17832403788470,17832404062391,17832404063835
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,236281,236281,4194304,256,0,0,12,24,62848,0x7f45e517a280,0x7f45e2224d40,131072,719656,80602296,17832404096124,17832404062391,17832404342871,17832404344338
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,236281,236281,4194304,256,0,0,12,24,63808,0x7f45e517a100,0x7f45e2224d80,131072,699666,78335584,17832404383487,17832404342871,17832404613432,17832404614811
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,236281,236281,4194304,256,0,0,12,24,65024,0x7f45e2b1bf80,0x7f45e2224dc0,131072,670210,75060888,17832404646430,17832404613432,17832404968153,17832404969772
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,236281,236281,4194304,256,0,0,12,24,66240,0x7f45e2b1be00,0x7f45e2224e00,65536,633208,71027776,17832405001072,17832404968153,17832405322393,17832405323704
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,236281,236281,4194304,256,0,0,8,24,67456,0x7f45e2b1bc80,0x7f45e2224e40,131072,707008,79154256,17832405354693,17832405322393,17832405595354,17832405596747
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,236281,236281,4194304,256,0,0,12,24,68928,0x7f45e2b1bb00,0x7f45e2224e80,131072,697218,78137600,17832405628186,17832405595354,17832405873754,17832405875160
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,236281,236281,4194304,256,0,0,12,24,70144,0x7f45e2b1b980,0x7f45e2224ec0,131072,658308,73724672,17832405914139,17832405873754,17832406146555,17832406148433
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,236281,236281,4194304,256,0,0,12,24,71616,0x7f45e2b1b800,0x7f45e2224f00,131072,701386,78527344,17832406179992,17832406146555,17832406507515,17832406508934
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,236281,236281,4194304,256,0,0,12,24,72832,0x7f45e2b1b680,0x7f45e2224f40,65536,699622,78401520,17832406541013,17832406507515,17832406867356,17832406868765
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,236281,236281,4194304,256,0,0,8,24,74048,0x7f45e517a500,0x7f45e2224f80,131072,671958,75210128,17832406900764,17832406867356,17832407143517,17832407144948
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,236281,236281,4194304,256,0,0,12,24,75776,0x7f45e517a380,0x7f45e2224fc0,131072,672706,75381112,17832407176878,17832407143517,17832407432797,17832407434251
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,236281,236281,4194304,256,0,0,12,24,76992,0x7f45e517a200,0x7f45e2225000,131072,696606,78217128,17832407473750,17832407432797,17832407701278,17832407702625
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,236281,236281,4194304,256,0,0,12,24,78464,0x7f45e517a080,0x7f45e2225040,131072,708204,79429472,17832407734074,17832407701278,17832408057758,17832408059176
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,236281,236281,4194304,256,0,0,12,24,79936,0x7f45e2b1bf00,0x7f45e2225080,65536,661894,74152040,17832408090825,17832408057758,17832408412799,17832408414247
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,236281,236281,4194304,256,0,0,8,24,81408,0x7f45e2b1bd80,0x7f45e22250c0,131072,702324,78672392,17832408445166,17832408412799,17832408681919,17832408683310
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,236281,236281,4194304,256,0,0,12,24,83136,0x7f45e2b1bc00,0x7f45e2225100,131072,703198,78825248,17832408714829,17832408681919,17832408971200,17832408972643
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,236281,236281,4194304,256,0,0,12,24,84352,0x7f45e2b1ba80,0x7f45e2225140,131072,699814,78254928,17832409022692,17832408971200,17832409251040,17832409253036
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,236281,236281,4194304,256,0,0,12,24,85824,0x7f45e2b1b900,0x7f45e2225180,131072,698260,78216224,17832409284085,17832409251040,17832409610241,17832409611667
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,236281,236281,4194304,256,0,0,12,24,87296,0x7f45e2b1b780,0x7f45e22251c0,65536,663758,74336688,17832409642866,17832409610241,17832409971362,17832409972698
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,236281,236281,4194304,256,0,0,12,24,88768,0x7f45e2b1b600,0x7f45e2225200,131072,694200,77848640,17832410003777,17832409971362,17832410252802,17832410254361
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,236281,236281,4194304,256,0,0,12,24,90752,0x7f45e517a480,0x7f45e2225240,131072,704834,78911016,17832410286130,17832410252802,17832410551683,17832410553104
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,236281,236281,4194304,256,0,0,12,24,91968,0x7f45e517a300,0x7f45e2225280,131072,696928,78035104,17832410592273,17832410551683,17832410821763,17832410823297
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,236281,236281,4194304,256,0,0,12,24,93440,0x7f45e517a180,0x7f45e22252c0,131072,696032,78057056,17832410854646,17832410821763,17832411183844,17832411185188
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,236281,236281,4194304,256,0,0,12,24,94912,0x7f45e517a000,0x7f45e2225300,65536,660730,74005000,17832411216967,17832411183844,17832411540005,17832411541479
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,236281,236281,4194304,256,0,0,12,24,96384,0x7f45e2b1be80,0x7f45e2225340,131072,701146,78404240,17832411573128,17832411540005,17832411810245,17832411811662
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,236281,236281,4194304,256,0,0,12,24,98368,0x7f45e2b1bd00,0x7f45e2225380,131072,703188,78765024,17832411843102,17832411810245,17832412111046,17832412112465
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,236281,236281,4194304,256,0,0,12,24,99584,0x7f45e2b1bb80,0x7f45e22253c0,131072,709754,79435024,17832412151434,17832412111046,17832412380646,17832412382098
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,236281,236281,4194304,256,0,0,12,24,101312,0x7f45e2b1ba00,0x7f45e2225400,131072,658220,73796752,17832412413128,17832412380646,17832412737927,17832412739229
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,236281,236281,4194304,256,0,0,12,24,102784,0x7f45e2b1b880,0x7f45e2225440,65536,668226,74799216,17832412770779,17832412737927,17832413094088,17832413095561
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,236281,236281,4194304,256,0,0,12,24,104256,0x7f45e2b1b700,0x7f45e2225480,131072,699192,78287464,17832413126350,17832413094088,17832413365928,17832413367344
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,236281,236281,4194304,256,0,0,12,24,106240,0x7f45e517a580,0x7f45e22254c0,131072,664510,74391096,17832413398753,17832413365928,17832413681769,17832413683106
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,236281,236281,4194304,256,0,0,12,24,107712,0x7f45e517a400,0x7f45e2225500,131072,661860,74059304,17832413722855,17832413681769,17832413960329,17832413961969
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,236281,236281,4194304,256,0,0,16,24,109440,0x7f45e517a280,0x7f45e2225540,131072,737226,82573104,17832413994028,17832413960329,17832414330890,17832414332460
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,236281,236281,4194304,256,0,0,16,24,111168,0x7f45e517a100,0x7f45e2225580,65536,649046,72669000,17832414364689,17832414330890,17832414688490,17832414689831
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,236281,236281,4194304,256,0,0,8,24,112896,0x7f45e2b1bf80,0x7f45e22255c0,131072,700704,78428320,17832414720670,17832414688490,17832414958891,17832414960154
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,236281,236281,4194304,256,0,0,12,24,115136,0x7f45e2b1be00,0x7f45e2225600,131072,698686,78251168,17832414991923,17832414958891,17832415269932,17832415271487
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,236281,236281,4194304,256,0,0,12,24,116608,0x7f45e2b1bc80,0x7f45e2225640,131072,710916,79668896,17832415310446,17832415269932,17832415545452,17832415546950
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,236281,236281,4194304,256,0,0,16,24,118336,0x7f45e2b1bb00,0x7f45e2225680,131072,697310,78148408,17832415578609,17832415545452,17832415904493,17832415905951
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,236281,236281,4194304,256,0,0,16,24,120064,0x7f45e2b1b980,0x7f45e22256c0,65536,661938,74012344,17832415937590,17832415904493,17832416259213,17832416260682
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,236281,236281,4194304,256,0,0,12,24,121792,0x7f45e2b1b800,0x7f45e2225700,131072,692126,77552648,17832416291961,17832416259213,17832416530734,17832416532145
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,236281,236281,4194304,256,0,0,12,24,124032,0x7f45e2b1b680,0x7f45e2225740,131072,698988,78259728,17832416563474,17832416530734,17832416860815,17832416862117
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,236281,236281,4194304,256,0,0,12,24,125504,0x7f45e517a500,0x7f45e2225780,131072,702876,78705712,17832416901386,17832416860815,17832417138575,17832417139930
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,236281,236281,4194304,256,0,0,12,24,127488,0x7f45e517a380,0x7f45e22257c0,131072,693560,77710752,17832417171159,17832417138575,17832417493776,17832417495141
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,236281,236281,4194304,256,0,0,12,24,129216,0x7f45e517a200,0x7f45e2225800,65536,662746,74090080,17832417526740,17832417493776,17832417851056,17832417852392
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,236281,236281,4194304,256,0,0,12,24,130944,0x7f45e517a080,0x7f45e2225840,131072,661518,74056760,17832417884092,17832417851056,17832418128657,17832418130245
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,236281,236281,4194304,256,0,0,12,24,133440,0x7f45e2b1bf00,0x7f45e2225880,131072,653794,73269240,17832418161545,17832418128657,17832418465617,17832418467077
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,236281,236281,4194304,256,0,0,12,24,134912,0x7f45e2b1bd80,0x7f45e22258c0,131072,1023684,114753968,17832418506686,17832418465617,17832418740658,17832418742170
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,236281,236281,4194304,256,0,0,12,24,136896,0x7f45e2b1bc00,0x7f45e2225900,131072,671298,75085032,17832418772820,17832418740658,17832419097139,17832419098551
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,236281,236281,4194304,256,0,0,12,24,138880,0x7f45e2b1ba80,0x7f45e2225940,65536,666606,74689200,17832419130061,17832419097139,17832419452179,17832419453583
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,236281,236281,4194304,256,0,0,12,24,140864,0x7f45e2b1b900,0x7f45e2225980,131072,710322,79534256,17832419484652,17832419452179,17832419735860,17832419737316
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,236281,236281,4194304,256,0,0,12,24,143616,0x7f45e2b1b780,0x7f45e22259c0,131072,736312,82503920,17832419768565,17832419735860,17832420079220,17832420080667
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,236281,236281,4194304,256,0,0,12,24,145344,0x7f45e2b1b600,0x7f45e2225a00,131072,1046700,117191448,17832420119236,17832420079220,17832420355061,17832420356480
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,236281,236281,4194304,256,0,0,12,24,147584,0x7f45e517a480,0x7f45e2225a40,131072,700300,78439888,17832420388939,17832420355061,17832420711382,17832420712981
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,236281,236281,4194304,256,0,0,12,24,149568,0x7f45e517a300,0x7f45e2225a80,65536,656180,73492696,17832420744921,17832420711382,17832421067382,17832421068772
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,236281,236281,4194304,256,0,0,12,24,151552,0x7f45e517a180,0x7f45e2225ac0,131072,661490,74168088,17832421100522,17832421067382,17832421352503,17832421354025
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,236281,236281,4194304,256,0,0,12,24,154304,0x7f45e517a000,0x7f45e2225b00,131072,661534,74112968,17832421385605,17832421352503,17832421716504,17832421717916
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,236281,236281,4194304,256,0,0,12,24,156288,0x7f45e2b1be80,0x7f45e2225b40,131072,1011892,113488728,17832421756865,17832421716504,17832421995064,17832421996489
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,236281,236281,4194304,256,0,0,12,24,158784,0x7f45e2b1bd00,0x7f45e2225b80,131072,696698,78101400,17832422028569,17832421995064,17832422368025,17832422369470
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,236281,236281,4194304,256,0,0,12,24,161024,0x7f45e2b1bb80,0x7f45e2225bc0,65536,656468,73595576,17832422401369,17832422368025,17832422728505,17832422729841
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,236281,236281,4194304,256,0,0,12,24,163264,0x7f45e2b1ba00,0x7f45e2225c00,131072,669734,74996912,17832422761010,17832422728505,17832423026106,17832423027444
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,236281,236281,4194304,256,0,0,12,24,166528,0x7f45e2b1b880,0x7f45e2225c40,131072,690138,77349608,17832423059093,17832423026106,17832423408987,17832423453883
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,236281,236281,4194304,256,0,0,12,24,168512,0x7f45e2b1b700,0x7f45e2225c80,131072,1046912,117125320,17832423472813,17832423408987,17832423731227,17832423732736
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,236281,236281,4194304,256,0,0,12,24,171264,0x7f45e517a580,0x7f45e2225cc0,131072,690800,77384592,17832423764206,17832423731227,17832424090748,17832424092097
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,236281,236281,4194304,256,0,0,12,24,173760,0x7f45e517a400,0x7f45e2225d00,65536,668714,74860336,17832424123747,17832424090748,17832424452029,17832424453478
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,236281,236281,4194304,256,0,0,12,24,176256,0x7f45e517a280,0x7f45e2225d40,131072,706034,79144240,17832424484928,17832424452029,17832424772349,17832424773870
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,236281,236281,4194304,256,0,0,12,24,179776,0x7f45e517a100,0x7f45e2225d80,131072,714758,80019096,17832424805450,17832424772349,17832425182430,17832425201200
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,236281,236281,4194304,256,0,0,12,24,182272,0x7f45e2b1bf80,0x7f45e2225dc0,131072,970250,108608768,17832425223149,17832425182430,17832425496191,17832425497572
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,236281,236281,4194304,256,0,0,12,24,185536,0x7f45e2b1be00,0x7f45e2225e00,131072,692588,77495152,17832425529002,17832425496191,17832425861951,17832425879323
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,236281,236281,4194304,256,0,0,12,24,188544,0x7f45e2b1bc80,0x7f45e2225e40,65536,661972,74144176,17832425894783,17832425861951,17832426234112,17832426255404
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,236281,236281,4194304,256,0,0,12,24,191552,0x7f45e2b1bb00,0x7f45e2225e80,131072,651518,72914568,17832426267983,17832426234112,17832426585633,17832426587085
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,236281,236281,4194304,256,0,0,12,24,195840,0x7f45e2b1b980,0x7f45e2225ec0,131072,671736,75207744,17832426618065,17832426585633,17832427044993,17832427089873
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,236281,236281,4194304,256,0,0,12,24,198592,0x7f45e2b1b800,0x7f45e2225f00,131072,1062116,119035424,17832427108662,17832427044993,17832427406114,17832427407555
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,236281,236281,4194304,256,0,0,12,24,202368,0x7f45e2b1b680,0x7f45e2225f40,131072,1014410,113677256,17832427438934,17832427406114,17832427792675,17832427838994
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,236281,236281,4194304,256,0,0,12,24,205888,0x7f45e517a500,0x7f45e2225f80,65536,657096,73695568,17832427849524,17832427792675,17832428213636,17832428255404
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,236281,236281,4194304,256,0,0,12,24,209408,0x7f45e517a380,0x7f45e2225fc0,131072,717844,80385384,17832428266174,17832428213636,17832428607556,17832428608975
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,236281,236281,4194304,256,0,0,12,24,214464,0x7f45e517a200,0x7f45e2226000,131072,673558,75636112,17832428640334,17832428607556,17832429119877,17832429137962
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,236281,236281,4194304,256,0,0,12,24,217728,0x7f45e517a080,0x7f45e2226040,131072,1041120,116628760,17832429161011,17832429119877,17832429472198,17832429473604
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,236281,236281,4194304,256,0,0,12,24,222016,0x7f45e2b1bf00,0x7f45e2226080,131072,1067732,119659152,17832429504273,17832429472198,17832429880679,17832429898823
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,236281,236281,4194304,256,0,0,12,24,226048,0x7f45e2b1bd80,0x7f45e22260c0,65536,658714,73729664,17832429916513,17832429880679,17832430292359,17832430311503
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,236281,236281,4194304,256,0,0,12,24,230080,0x7f45e2b1bc00,0x7f45e2226100,131072,687526,77019512,17832430325033,17832430292359,17832430692680,17832430710793
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,236281,236281,4194304,256,0,0,12,24,235904,0x7f45e2b1ba80,0x7f45e2226140,131072,666764,74771272,17832430725573,17832430692680,17832431260201,17832431301548
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,236281,236281,4194304,256,0,0,12,24,239424,0x7f45e2b1b900,0x7f45e2226180,131072,1033082,115803352,17832431320018,17832431260201,17832431648682,17832431650150
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,236281,236281,4194304,256,0,0,12,24,244224,0x7f45e2b1b780,0x7f45e22261c0,131072,1018378,114085552,17832431681109,17832431648682,17832432079403,17832432098638
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,236281,236281,4194304,256,0,0,12,24,248768,0x7f45e2b1b600,0x7f45e2226200,65536,707324,79208912,17832432112608,17832432079403,17832432509483,17832432526118
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,236281,236281,4194304,256,0,0,12,24,253312,0x7f45e517a480,0x7f45e2226240,131072,686242,76860856,17832432542687,17832432509483,17832432925964,17832432942478
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,236281,236281,4194304,256,0,0,8,24,255552,0x7f45e517a300,0x7f45e2226280,131072,1038276,116262688,17832432959327,17832432925964,17832433558125,17832433575932
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,236281,236281,4194304,256,0,0,12,24,259840,0x7f45e517a180,0x7f45e22262c0,131072,1036858,116181864,17832433599221,17832433558125,17832433967406,17832433983822
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,236281,236281,4194304,256,0,0,12,24,265664,0x7f45e517a000,0x7f45e2226300,131072,987292,110725048,17832433999841,17832433967406,17832434454927,17832434474699
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,236281,236281,4194304,256,0,0,12,24,271232,0x7f45e2b1be80,0x7f45e2226340,65536,659696,73899072,17832434488319,17832434454927,17832434939088,17832434981337
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,236281,236281,4194304,256,0,0,8,24,273216,0x7f45e2b1bd00,0x7f45e2226380,131072,1018800,114147848,17832434992227,17832434939088,17832435444529,17832435485844
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,236281,236281,4194304,256,0,0,8,24,275712,0x7f45e2b1bb80,0x7f45e22263c0,131072,1031960,115523272,17832435497234,17832435444529,17832436205010,17832436246585
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,236281,236281,4194304,256,0,0,12,24,280768,0x7f45e2b1ba00,0x7f45e2226400,131072,1016270,113811808,17832436266265,17832436205010,17832436678611,17832436698824
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,236281,236281,4194304,256,0,0,12,24,287616,0x7f45e2b1b880,0x7f45e2226440,131072,1032280,115828136,17832436711484,17832436678611,17832437211732,17832437228671
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,236281,236281,4194304,256,0,0,12,24,294208,0x7f45e2b1b700,0x7f45e2226480,65536,659624,74051544,17832437245851,17832437211732,17832437740053,17832437759248
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,236281,236281,4194304,256,0,0,8,24,296960,0x7f45e517a580,0x7f45e22264c0,131072,1005662,112551368,17832437773327,17832437740053,17832438273334,17832438291035
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,236281,236281,4194304,256,0,0,8,24,299968,0x7f45e517a400,0x7f45e2226500,131072,1031584,115645744,17832438307094,17832438273334,17832439116216,17832439157763
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,236281,236281,4194304,256,0,0,8,24,302720,0x7f45e517a280,0x7f45e2226540,131072,1061368,118941344,17832439177303,17832439116216,17832439767897,17832439809577
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,236281,236281,4194304,256,0,0,12,24,305472,0x7f45e517a100,0x7f45e2226580,131072,1036776,116154712,17832439821457,17832439767897,17832440436698,17832440477671
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,236281,236281,4194304,256,0,0,12,24,308224,0x7f45e2b1bf80,0x7f45e22265c0,65536,660196,73909144,17832440489810,17832440436698,17832441100379,17832441118625
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,236281,236281,4194304,256,0,0,8,24,310976,0x7f45e2b1be00,0x7f45e2226600,131072,1039478,116410952,17832441132995,17832441100379,17832441730941,17832441747759
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,236281,236281,4194304,256,0,0,8,24,313216,0x7f45e2b1bc80,0x7f45e2226640,131072,1041146,116504080,17832441763269,17832441730941,17832442784223,17832442804243
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,236281,236281,4194304,256,0,0,8,24,315968,0x7f45e2b1bb00,0x7f45e2226680,131072,1038534,116343664,17832442825283,17832442784223,17832443822464,17832443864977
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,236281,236281,4194304,256,0,0,12,24,318720,0x7f45e2b1b980,0x7f45e22266c0,131072,1034026,115706080,17832443875707,17832443822308,17832444914309,17832444984019
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,236281,236281,4194304,256,0,0,12,24,321472,0x7f45e2b1b800,0x7f45e2226700,65536,654370,73416832,17832444995709,17832444914309,17832446040870,17832446107291
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,236281,236281,4194304,256,0,0,8,24,324224,0x7f45e2b1b680,0x7f45e2226740,131072,1062574,118922864,17832446119451,17832446040870,17832447150632,17832447217504
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,236281,236281,4194304,256,0,0,8,24,326464,0x7f45e517a500,0x7f45e2226780,131072,1035830,116234136,17832447229853,17832447150632,17832449094475,17832449159095
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,236281,236281,4194304,256,0,0,8,24,329216,0x7f45e517a380,0x7f45e22267c0,131072,1037504,116109664,17832449179225,17832449094475,17832451003758,17832451072248
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,236281,236281,4194304,256,0,0,12,24,331968,0x7f45e517a200,0x7f45e2226800,131072,1028376,115273240,17832451084307,17832451003758,17832452981041,17832453045679
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,236281,236281,4194304,256,0,0,12,24,334720,0x7f45e517a080,0x7f45e2226840,65536,662726,74252864,17832453056848,17832452981041,17832454942484,17832455013900
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,236281,236281,4194304,256,0,0,8,24,337472,0x7f45e2b1bf00,0x7f45e2226880,131072,1040770,116756344,17832455025780,17832454942484,17832456880247,17832456947382
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,236281,236281,4194304,256,0,0,8,24,0,0x7f45e2b1bd80,0x7f45e22268c0,131072,1035694,116127016,17832456958722,17832456880247,17832460486492,17832460564112
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 236281 236281 33554432 256 0 0 4 32 4160 0x0 0x7f45e2204280 3670016 2905706 325081704 17832236843728 17803198665120 17832381629870 17832381744199
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 236281 236281 32768 256 0 0 12 24 13888 0x0 0x7f45e2223f80 512 96664 10851288 17832386900391 17832381629870 17832387026519 17832387030968
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 5 236281 236281 4194304 256 0 0 12 24 14336 0x7f45e517a380 0x7f45e2223fc0 65536 639926 71704992 17832387064037 17832387026519 17832387402360 17832387404639
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 236281 236281 4194304 256 0 0 16 24 15040 0x7f45e517a200 0x7f45e2224000 65536 663120 74284736 17832387441058 17832387402360 17832387801401 17832387803559
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 11 236281 236281 4194304 256 0 0 16 24 15488 0x7f45e517a080 0x7f45e2224040 65536 655382 73467248 17832387836288 17832387801401 17832388189241 17832388191179
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 14 236281 236281 4194304 256 0 0 12 24 15936 0x7f45e2b1bf00 0x7f45e2224080 65536 670706 75144576 17832388224148 17832388189241 17832388486682 17832388488802
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 17 236281 236281 4194304 256 0 0 12 24 16384 0x7f45e2b1bd80 0x7f45e22240c0 65536 633498 70989896 17832388520711 17832388486682 17832388784443 17832388786445
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 20 236281 236281 4194304 256 0 0 12 24 17088 0x7f45e2b1bc00 0x7f45e2224100 131072 682790 76349744 17832388829873 17832388784443 17832389085883 17832389087897
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 236281 236281 4194304 256 0 0 16 24 17792 0x7f45e2b1ba80 0x7f45e2224140 131072 702258 78734048 17832389118956 17832389085883 17832389470044 17832389472077
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 26 236281 236281 4194304 256 0 0 16 24 18496 0x7f45e2b1b900 0x7f45e2224180 65536 662922 74237584 17832389504707 17832389470044 17832389854525 17832389856588
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 29 236281 236281 4194304 256 0 0 16 24 19200 0x7f45e2b1b780 0x7f45e22241c0 131072 702944 78662512 17832389887017 17832389854525 17832390165245 17832390167590
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 32 236281 236281 4194304 256 0 0 16 24 19904 0x7f45e2b1b600 0x7f45e2224200 131072 698592 78249728 17832390198889 17832390165245 17832390471646 17832390473623
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 35 236281 236281 4194304 256 0 0 12 24 20608 0x7f45e517a480 0x7f45e2224240 131072 699922 78366656 17832390513972 17832390471646 17832390771166 17832390773245
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 236281 236281 4194304 256 0 0 16 24 21312 0x7f45e517a300 0x7f45e2224280 131072 697276 78078456 17832390805924 17832390771166 17832391153567 17832391155576
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 41 236281 236281 4194304 256 0 0 16 24 22016 0x7f45e517a180 0x7f45e22242c0 65536 671700 75200016 17832391187125 17832391153567 17832391540928 17832391542376
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 44 236281 236281 4194304 256 0 0 16 24 22720 0x7f45e517a000 0x7f45e2224300 131072 717992 80318352 17832391573205 17832391540928 17832391812928 17832391814339
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 47 236281 236281 4194304 256 0 0 12 24 23424 0x7f45e2b1be80 0x7f45e2224340 131072 697818 78152560 17832391845858 17832391812928 17832392080929 17832392082433
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 50 236281 236281 4194304 256 0 0 12 24 24128 0x7f45e2b1bd00 0x7f45e2224380 131072 696712 78052840 17832392120672 17832392080929 17832392351169 17832392352656
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 236281 236281 4194304 256 0 0 16 24 24832 0x7f45e2b1bb80 0x7f45e22243c0 131072 703960 78811040 17832392384785 17832392351169 17832392707170 17832392708527
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 56 236281 236281 4194304 256 0 0 16 24 25536 0x7f45e2b1ba00 0x7f45e2224400 65536 627350 70207160 17832392739226 17832392707170 17832393068610 17832393070078
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 59 236281 236281 4194304 256 0 0 12 24 26240 0x7f45e2b1b880 0x7f45e2224440 131072 705208 78953168 17832393101637 17832393068610 17832393338211 17832393339751
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 62 236281 236281 4194304 256 0 0 12 24 26944 0x7f45e2b1b700 0x7f45e2224480 131072 700642 78443288 17832393370981 17832393338211 17832393606371 17832393607955
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 65 236281 236281 4194304 256 0 0 12 24 27648 0x7f45e517a580 0x7f45e22244c0 131072 680574 76153088 17832393646754 17832393606371 17832393874692 17832393876138
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 236281 236281 4194304 256 0 0 16 24 28608 0x7f45e517a400 0x7f45e2224500 131072 698066 78128680 17832393908427 17832393874692 17832394231173 17832394232719
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 71 236281 236281 4194304 256 0 0 16 24 29312 0x7f45e517a280 0x7f45e2224540 65536 676560 75754120 17832394265568 17832394231173 17832394590853 17832394592260
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 74 236281 236281 4194304 256 0 0 12 24 30016 0x7f45e517a100 0x7f45e2224580 131072 665052 74494800 17832394623679 17832394590853 17832394868134 17832394869783
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 77 236281 236281 4194304 256 0 0 8 24 30976 0x7f45e2b1bf80 0x7f45e22245c0 131072 662312 74088520 17832394901143 17832394868134 17832395136934 17832395138407
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 80 236281 236281 4194304 256 0 0 12 24 31680 0x7f45e2b1be00 0x7f45e2224600 131072 693582 77663792 17832395177386 17832395136934 17832395409415 17832395411120
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 236281 236281 4194304 256 0 0 16 24 32640 0x7f45e2b1bc80 0x7f45e2224640 131072 655674 73523104 17832395443299 17832395409415 17832395769415 17832395770881
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 86 236281 236281 4194304 256 0 0 12 24 33600 0x7f45e2b1bb00 0x7f45e2224680 65536 651942 73037144 17832395802430 17832395769415 17832396129576 17832396130962
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 89 236281 236281 4194304 256 0 0 12 24 34560 0x7f45e2b1b980 0x7f45e22246c0 131072 697390 78190624 17832396162821 17832396129576 17832396399017 17832396400575
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 92 236281 236281 4194304 256 0 0 8 24 35520 0x7f45e2b1b800 0x7f45e2224700 131072 705040 79031632 17832396431605 17832396399017 17832396669097 17832396670499
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 95 236281 236281 4194304 256 0 0 12 24 36224 0x7f45e2b1b680 0x7f45e2224740 131072 702546 78684376 17832396708378 17832396669097 17832396940938 17832396942292
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 236281 236281 4194304 256 0 0 12 24 37184 0x7f45e517a500 0x7f45e2224780 131072 700556 78359944 17832396974431 17832396940938 17832397298858 17832397300373
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 101 236281 236281 4194304 256 0 0 12 24 38144 0x7f45e517a380 0x7f45e22247c0 65536 670702 75074704 17832397332152 17832397298858 17832397656299 17832397657764
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 104 236281 236281 4194304 256 0 0 12 24 39104 0x7f45e517a200 0x7f45e2224800 131072 702376 78607656 17832397689003 17832397656299 17832397926859 17832397928307
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 107 236281 236281 4194304 256 0 0 8 24 40320 0x7f45e517a080 0x7f45e2224840 131072 699218 78252712 17832397960087 17832397926859 17832398207180 17832398208690
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 110 236281 236281 4194304 256 0 0 12 24 41280 0x7f45e2b1bf00 0x7f45e2224880 131072 702102 78566800 17832398247609 17832398207180 17832398479980 17832398481434
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 236281 236281 4194304 256 0 0 12 24 42240 0x7f45e2b1bd80 0x7f45e22248c0 131072 700322 78462936 17832398512783 17832398479980 17832398840781 17832398842455
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 116 236281 236281 4194304 256 0 0 12 24 43200 0x7f45e2b1bc00 0x7f45e2224900 65536 678432 76016512 17832398873754 17832398840781 17832399198542 17832399199956
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 119 236281 236281 4194304 256 0 0 8 24 44160 0x7f45e2b1ba80 0x7f45e2224940 131072 704048 78850440 17832399231725 17832399198542 17832399474062 17832399475529
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 122 236281 236281 4194304 256 0 0 12 24 45376 0x7f45e2b1b900 0x7f45e2224980 131072 704294 78762488 17832399506378 17832399474062 17832399744143 17832399745442
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 125 236281 236281 4194304 256 0 0 12 24 46336 0x7f45e2b1b780 0x7f45e22249c0 131072 697140 78101344 17832399784061 17832399744143 17832400014383 17832400015876
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 236281 236281 4194304 256 0 0 12 24 47552 0x7f45e2b1b600 0x7f45e2224a00 131072 691764 77411472 17832400047205 17832400014383 17832400368784 17832400370137
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 131 236281 236281 4194304 256 0 0 12 24 48512 0x7f45e517a480 0x7f45e2224a40 65536 658738 73825056 17832400402316 17832400368784 17832400729425 17832400730838
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 134 236281 236281 4194304 256 0 0 8 24 49472 0x7f45e517a300 0x7f45e2224a80 131072 656782 73609296 17832400762547 17832400729425 17832401000945 17832401002361
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 137 236281 236281 4194304 256 0 0 12 24 50688 0x7f45e517a180 0x7f45e2224ac0 131072 661124 73973224 17832401033580 17832401000945 17832401268146 17832401269644
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 140 236281 236281 4194304 256 0 0 12 24 51648 0x7f45e517a000 0x7f45e2224b00 131072 684772 76598464 17832401308053 17832401268146 17832401548306 17832401549867
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 236281 236281 4194304 256 0 0 12 24 52864 0x7f45e2b1be80 0x7f45e2224b40 131072 697314 78128704 17832401581147 17832401548306 17832401907827 17832401909338
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 146 236281 236281 4194304 256 0 0 12 24 54080 0x7f45e2b1bd00 0x7f45e2224b80 65536 669406 75005032 17832401940558 17832401907827 17832402263187 17832402264740
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 149 236281 236281 4194304 256 0 0 8 24 55296 0x7f45e2b1bb80 0x7f45e2224bc0 131072 700766 78516768 17832402296189 17832402263187 17832402535028 17832402536433
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 152 236281 236281 4194304 256 0 0 12 24 56768 0x7f45e2b1ba00 0x7f45e2224c00 131072 697972 78177560 17832402567832 17832402535028 17832402805428 17832402806846
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 155 236281 236281 4194304 256 0 0 12 24 57728 0x7f45e2b1b880 0x7f45e2224c40 131072 700048 78487152 17832402845555 17832402805428 17832403074549 17832403076009
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 236281 236281 4194304 256 0 0 12 24 58944 0x7f45e2b1b700 0x7f45e2224c80 131072 688204 77079128 17832403107349 17832403074549 17832403429910 17832403431351
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 161 236281 236281 4194304 256 0 0 12 24 60160 0x7f45e517a580 0x7f45e2224cc0 65536 671532 75179760 17832403463430 17832403429910 17832403788470 17832403789782
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 164 236281 236281 4194304 256 0 0 8 24 61376 0x7f45e517a400 0x7f45e2224d00 131072 698470 78218528 17832403821291 17832403788470 17832404062391 17832404063835
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 167 236281 236281 4194304 256 0 0 12 24 62848 0x7f45e517a280 0x7f45e2224d40 131072 719656 80602296 17832404096124 17832404062391 17832404342871 17832404344338
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 170 236281 236281 4194304 256 0 0 12 24 63808 0x7f45e517a100 0x7f45e2224d80 131072 699666 78335584 17832404383487 17832404342871 17832404613432 17832404614811
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 236281 236281 4194304 256 0 0 12 24 65024 0x7f45e2b1bf80 0x7f45e2224dc0 131072 670210 75060888 17832404646430 17832404613432 17832404968153 17832404969772
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 176 236281 236281 4194304 256 0 0 12 24 66240 0x7f45e2b1be00 0x7f45e2224e00 65536 633208 71027776 17832405001072 17832404968153 17832405322393 17832405323704
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 179 236281 236281 4194304 256 0 0 8 24 67456 0x7f45e2b1bc80 0x7f45e2224e40 131072 707008 79154256 17832405354693 17832405322393 17832405595354 17832405596747
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 182 236281 236281 4194304 256 0 0 12 24 68928 0x7f45e2b1bb00 0x7f45e2224e80 131072 697218 78137600 17832405628186 17832405595354 17832405873754 17832405875160
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 185 236281 236281 4194304 256 0 0 12 24 70144 0x7f45e2b1b980 0x7f45e2224ec0 131072 658308 73724672 17832405914139 17832405873754 17832406146555 17832406148433
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 236281 236281 4194304 256 0 0 12 24 71616 0x7f45e2b1b800 0x7f45e2224f00 131072 701386 78527344 17832406179992 17832406146555 17832406507515 17832406508934
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 191 236281 236281 4194304 256 0 0 12 24 72832 0x7f45e2b1b680 0x7f45e2224f40 65536 699622 78401520 17832406541013 17832406507515 17832406867356 17832406868765
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 194 236281 236281 4194304 256 0 0 8 24 74048 0x7f45e517a500 0x7f45e2224f80 131072 671958 75210128 17832406900764 17832406867356 17832407143517 17832407144948
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 197 236281 236281 4194304 256 0 0 12 24 75776 0x7f45e517a380 0x7f45e2224fc0 131072 672706 75381112 17832407176878 17832407143517 17832407432797 17832407434251
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 200 236281 236281 4194304 256 0 0 12 24 76992 0x7f45e517a200 0x7f45e2225000 131072 696606 78217128 17832407473750 17832407432797 17832407701278 17832407702625
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 236281 236281 4194304 256 0 0 12 24 78464 0x7f45e517a080 0x7f45e2225040 131072 708204 79429472 17832407734074 17832407701278 17832408057758 17832408059176
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 206 236281 236281 4194304 256 0 0 12 24 79936 0x7f45e2b1bf00 0x7f45e2225080 65536 661894 74152040 17832408090825 17832408057758 17832408412799 17832408414247
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 209 236281 236281 4194304 256 0 0 8 24 81408 0x7f45e2b1bd80 0x7f45e22250c0 131072 702324 78672392 17832408445166 17832408412799 17832408681919 17832408683310
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 212 236281 236281 4194304 256 0 0 12 24 83136 0x7f45e2b1bc00 0x7f45e2225100 131072 703198 78825248 17832408714829 17832408681919 17832408971200 17832408972643
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 215 236281 236281 4194304 256 0 0 12 24 84352 0x7f45e2b1ba80 0x7f45e2225140 131072 699814 78254928 17832409022692 17832408971200 17832409251040 17832409253036
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 236281 236281 4194304 256 0 0 12 24 85824 0x7f45e2b1b900 0x7f45e2225180 131072 698260 78216224 17832409284085 17832409251040 17832409610241 17832409611667
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 221 236281 236281 4194304 256 0 0 12 24 87296 0x7f45e2b1b780 0x7f45e22251c0 65536 663758 74336688 17832409642866 17832409610241 17832409971362 17832409972698
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 224 236281 236281 4194304 256 0 0 12 24 88768 0x7f45e2b1b600 0x7f45e2225200 131072 694200 77848640 17832410003777 17832409971362 17832410252802 17832410254361
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 227 236281 236281 4194304 256 0 0 12 24 90752 0x7f45e517a480 0x7f45e2225240 131072 704834 78911016 17832410286130 17832410252802 17832410551683 17832410553104
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 230 236281 236281 4194304 256 0 0 12 24 91968 0x7f45e517a300 0x7f45e2225280 131072 696928 78035104 17832410592273 17832410551683 17832410821763 17832410823297
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 236281 236281 4194304 256 0 0 12 24 93440 0x7f45e517a180 0x7f45e22252c0 131072 696032 78057056 17832410854646 17832410821763 17832411183844 17832411185188
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 236 236281 236281 4194304 256 0 0 12 24 94912 0x7f45e517a000 0x7f45e2225300 65536 660730 74005000 17832411216967 17832411183844 17832411540005 17832411541479
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 239 236281 236281 4194304 256 0 0 12 24 96384 0x7f45e2b1be80 0x7f45e2225340 131072 701146 78404240 17832411573128 17832411540005 17832411810245 17832411811662
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 242 236281 236281 4194304 256 0 0 12 24 98368 0x7f45e2b1bd00 0x7f45e2225380 131072 703188 78765024 17832411843102 17832411810245 17832412111046 17832412112465
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 245 236281 236281 4194304 256 0 0 12 24 99584 0x7f45e2b1bb80 0x7f45e22253c0 131072 709754 79435024 17832412151434 17832412111046 17832412380646 17832412382098
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 236281 236281 4194304 256 0 0 12 24 101312 0x7f45e2b1ba00 0x7f45e2225400 131072 658220 73796752 17832412413128 17832412380646 17832412737927 17832412739229
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 251 236281 236281 4194304 256 0 0 12 24 102784 0x7f45e2b1b880 0x7f45e2225440 65536 668226 74799216 17832412770779 17832412737927 17832413094088 17832413095561
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 254 236281 236281 4194304 256 0 0 12 24 104256 0x7f45e2b1b700 0x7f45e2225480 131072 699192 78287464 17832413126350 17832413094088 17832413365928 17832413367344
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 257 236281 236281 4194304 256 0 0 12 24 106240 0x7f45e517a580 0x7f45e22254c0 131072 664510 74391096 17832413398753 17832413365928 17832413681769 17832413683106
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 260 236281 236281 4194304 256 0 0 12 24 107712 0x7f45e517a400 0x7f45e2225500 131072 661860 74059304 17832413722855 17832413681769 17832413960329 17832413961969
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 236281 236281 4194304 256 0 0 16 24 109440 0x7f45e517a280 0x7f45e2225540 131072 737226 82573104 17832413994028 17832413960329 17832414330890 17832414332460
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 266 236281 236281 4194304 256 0 0 16 24 111168 0x7f45e517a100 0x7f45e2225580 65536 649046 72669000 17832414364689 17832414330890 17832414688490 17832414689831
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 269 236281 236281 4194304 256 0 0 8 24 112896 0x7f45e2b1bf80 0x7f45e22255c0 131072 700704 78428320 17832414720670 17832414688490 17832414958891 17832414960154
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 272 236281 236281 4194304 256 0 0 12 24 115136 0x7f45e2b1be00 0x7f45e2225600 131072 698686 78251168 17832414991923 17832414958891 17832415269932 17832415271487
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 275 236281 236281 4194304 256 0 0 12 24 116608 0x7f45e2b1bc80 0x7f45e2225640 131072 710916 79668896 17832415310446 17832415269932 17832415545452 17832415546950
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 236281 236281 4194304 256 0 0 16 24 118336 0x7f45e2b1bb00 0x7f45e2225680 131072 697310 78148408 17832415578609 17832415545452 17832415904493 17832415905951
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 281 236281 236281 4194304 256 0 0 16 24 120064 0x7f45e2b1b980 0x7f45e22256c0 65536 661938 74012344 17832415937590 17832415904493 17832416259213 17832416260682
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 284 236281 236281 4194304 256 0 0 12 24 121792 0x7f45e2b1b800 0x7f45e2225700 131072 692126 77552648 17832416291961 17832416259213 17832416530734 17832416532145
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 287 236281 236281 4194304 256 0 0 12 24 124032 0x7f45e2b1b680 0x7f45e2225740 131072 698988 78259728 17832416563474 17832416530734 17832416860815 17832416862117
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 290 236281 236281 4194304 256 0 0 12 24 125504 0x7f45e517a500 0x7f45e2225780 131072 702876 78705712 17832416901386 17832416860815 17832417138575 17832417139930
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 236281 236281 4194304 256 0 0 12 24 127488 0x7f45e517a380 0x7f45e22257c0 131072 693560 77710752 17832417171159 17832417138575 17832417493776 17832417495141
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 296 236281 236281 4194304 256 0 0 12 24 129216 0x7f45e517a200 0x7f45e2225800 65536 662746 74090080 17832417526740 17832417493776 17832417851056 17832417852392
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 299 236281 236281 4194304 256 0 0 12 24 130944 0x7f45e517a080 0x7f45e2225840 131072 661518 74056760 17832417884092 17832417851056 17832418128657 17832418130245
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 302 236281 236281 4194304 256 0 0 12 24 133440 0x7f45e2b1bf00 0x7f45e2225880 131072 653794 73269240 17832418161545 17832418128657 17832418465617 17832418467077
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 305 236281 236281 4194304 256 0 0 12 24 134912 0x7f45e2b1bd80 0x7f45e22258c0 131072 1023684 114753968 17832418506686 17832418465617 17832418740658 17832418742170
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 236281 236281 4194304 256 0 0 12 24 136896 0x7f45e2b1bc00 0x7f45e2225900 131072 671298 75085032 17832418772820 17832418740658 17832419097139 17832419098551
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 311 236281 236281 4194304 256 0 0 12 24 138880 0x7f45e2b1ba80 0x7f45e2225940 65536 666606 74689200 17832419130061 17832419097139 17832419452179 17832419453583
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 314 236281 236281 4194304 256 0 0 12 24 140864 0x7f45e2b1b900 0x7f45e2225980 131072 710322 79534256 17832419484652 17832419452179 17832419735860 17832419737316
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 317 236281 236281 4194304 256 0 0 12 24 143616 0x7f45e2b1b780 0x7f45e22259c0 131072 736312 82503920 17832419768565 17832419735860 17832420079220 17832420080667
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 320 236281 236281 4194304 256 0 0 12 24 145344 0x7f45e2b1b600 0x7f45e2225a00 131072 1046700 117191448 17832420119236 17832420079220 17832420355061 17832420356480
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 236281 236281 4194304 256 0 0 12 24 147584 0x7f45e517a480 0x7f45e2225a40 131072 700300 78439888 17832420388939 17832420355061 17832420711382 17832420712981
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 326 236281 236281 4194304 256 0 0 12 24 149568 0x7f45e517a300 0x7f45e2225a80 65536 656180 73492696 17832420744921 17832420711382 17832421067382 17832421068772
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 329 236281 236281 4194304 256 0 0 12 24 151552 0x7f45e517a180 0x7f45e2225ac0 131072 661490 74168088 17832421100522 17832421067382 17832421352503 17832421354025
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 332 236281 236281 4194304 256 0 0 12 24 154304 0x7f45e517a000 0x7f45e2225b00 131072 661534 74112968 17832421385605 17832421352503 17832421716504 17832421717916
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 335 236281 236281 4194304 256 0 0 12 24 156288 0x7f45e2b1be80 0x7f45e2225b40 131072 1011892 113488728 17832421756865 17832421716504 17832421995064 17832421996489
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 236281 236281 4194304 256 0 0 12 24 158784 0x7f45e2b1bd00 0x7f45e2225b80 131072 696698 78101400 17832422028569 17832421995064 17832422368025 17832422369470
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 341 236281 236281 4194304 256 0 0 12 24 161024 0x7f45e2b1bb80 0x7f45e2225bc0 65536 656468 73595576 17832422401369 17832422368025 17832422728505 17832422729841
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 344 236281 236281 4194304 256 0 0 12 24 163264 0x7f45e2b1ba00 0x7f45e2225c00 131072 669734 74996912 17832422761010 17832422728505 17832423026106 17832423027444
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 347 236281 236281 4194304 256 0 0 12 24 166528 0x7f45e2b1b880 0x7f45e2225c40 131072 690138 77349608 17832423059093 17832423026106 17832423408987 17832423453883
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 350 236281 236281 4194304 256 0 0 12 24 168512 0x7f45e2b1b700 0x7f45e2225c80 131072 1046912 117125320 17832423472813 17832423408987 17832423731227 17832423732736
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 236281 236281 4194304 256 0 0 12 24 171264 0x7f45e517a580 0x7f45e2225cc0 131072 690800 77384592 17832423764206 17832423731227 17832424090748 17832424092097
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 356 236281 236281 4194304 256 0 0 12 24 173760 0x7f45e517a400 0x7f45e2225d00 65536 668714 74860336 17832424123747 17832424090748 17832424452029 17832424453478
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 359 236281 236281 4194304 256 0 0 12 24 176256 0x7f45e517a280 0x7f45e2225d40 131072 706034 79144240 17832424484928 17832424452029 17832424772349 17832424773870
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 362 236281 236281 4194304 256 0 0 12 24 179776 0x7f45e517a100 0x7f45e2225d80 131072 714758 80019096 17832424805450 17832424772349 17832425182430 17832425201200
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 365 236281 236281 4194304 256 0 0 12 24 182272 0x7f45e2b1bf80 0x7f45e2225dc0 131072 970250 108608768 17832425223149 17832425182430 17832425496191 17832425497572
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 236281 236281 4194304 256 0 0 12 24 185536 0x7f45e2b1be00 0x7f45e2225e00 131072 692588 77495152 17832425529002 17832425496191 17832425861951 17832425879323
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 371 236281 236281 4194304 256 0 0 12 24 188544 0x7f45e2b1bc80 0x7f45e2225e40 65536 661972 74144176 17832425894783 17832425861951 17832426234112 17832426255404
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 374 236281 236281 4194304 256 0 0 12 24 191552 0x7f45e2b1bb00 0x7f45e2225e80 131072 651518 72914568 17832426267983 17832426234112 17832426585633 17832426587085
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 377 236281 236281 4194304 256 0 0 12 24 195840 0x7f45e2b1b980 0x7f45e2225ec0 131072 671736 75207744 17832426618065 17832426585633 17832427044993 17832427089873
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 380 236281 236281 4194304 256 0 0 12 24 198592 0x7f45e2b1b800 0x7f45e2225f00 131072 1062116 119035424 17832427108662 17832427044993 17832427406114 17832427407555
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 236281 236281 4194304 256 0 0 12 24 202368 0x7f45e2b1b680 0x7f45e2225f40 131072 1014410 113677256 17832427438934 17832427406114 17832427792675 17832427838994
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 386 236281 236281 4194304 256 0 0 12 24 205888 0x7f45e517a500 0x7f45e2225f80 65536 657096 73695568 17832427849524 17832427792675 17832428213636 17832428255404
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 389 236281 236281 4194304 256 0 0 12 24 209408 0x7f45e517a380 0x7f45e2225fc0 131072 717844 80385384 17832428266174 17832428213636 17832428607556 17832428608975
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 392 236281 236281 4194304 256 0 0 12 24 214464 0x7f45e517a200 0x7f45e2226000 131072 673558 75636112 17832428640334 17832428607556 17832429119877 17832429137962
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 395 236281 236281 4194304 256 0 0 12 24 217728 0x7f45e517a080 0x7f45e2226040 131072 1041120 116628760 17832429161011 17832429119877 17832429472198 17832429473604
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 236281 236281 4194304 256 0 0 12 24 222016 0x7f45e2b1bf00 0x7f45e2226080 131072 1067732 119659152 17832429504273 17832429472198 17832429880679 17832429898823
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 401 236281 236281 4194304 256 0 0 12 24 226048 0x7f45e2b1bd80 0x7f45e22260c0 65536 658714 73729664 17832429916513 17832429880679 17832430292359 17832430311503
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 404 236281 236281 4194304 256 0 0 12 24 230080 0x7f45e2b1bc00 0x7f45e2226100 131072 687526 77019512 17832430325033 17832430292359 17832430692680 17832430710793
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 407 236281 236281 4194304 256 0 0 12 24 235904 0x7f45e2b1ba80 0x7f45e2226140 131072 666764 74771272 17832430725573 17832430692680 17832431260201 17832431301548
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 410 236281 236281 4194304 256 0 0 12 24 239424 0x7f45e2b1b900 0x7f45e2226180 131072 1033082 115803352 17832431320018 17832431260201 17832431648682 17832431650150
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 236281 236281 4194304 256 0 0 12 24 244224 0x7f45e2b1b780 0x7f45e22261c0 131072 1018378 114085552 17832431681109 17832431648682 17832432079403 17832432098638
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 416 236281 236281 4194304 256 0 0 12 24 248768 0x7f45e2b1b600 0x7f45e2226200 65536 707324 79208912 17832432112608 17832432079403 17832432509483 17832432526118
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 419 236281 236281 4194304 256 0 0 12 24 253312 0x7f45e517a480 0x7f45e2226240 131072 686242 76860856 17832432542687 17832432509483 17832432925964 17832432942478
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 422 236281 236281 4194304 256 0 0 8 24 255552 0x7f45e517a300 0x7f45e2226280 131072 1038276 116262688 17832432959327 17832432925964 17832433558125 17832433575932
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 425 236281 236281 4194304 256 0 0 12 24 259840 0x7f45e517a180 0x7f45e22262c0 131072 1036858 116181864 17832433599221 17832433558125 17832433967406 17832433983822
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 236281 236281 4194304 256 0 0 12 24 265664 0x7f45e517a000 0x7f45e2226300 131072 987292 110725048 17832433999841 17832433967406 17832434454927 17832434474699
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 431 236281 236281 4194304 256 0 0 12 24 271232 0x7f45e2b1be80 0x7f45e2226340 65536 659696 73899072 17832434488319 17832434454927 17832434939088 17832434981337
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 434 236281 236281 4194304 256 0 0 8 24 273216 0x7f45e2b1bd00 0x7f45e2226380 131072 1018800 114147848 17832434992227 17832434939088 17832435444529 17832435485844
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 437 236281 236281 4194304 256 0 0 8 24 275712 0x7f45e2b1bb80 0x7f45e22263c0 131072 1031960 115523272 17832435497234 17832435444529 17832436205010 17832436246585
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 440 236281 236281 4194304 256 0 0 12 24 280768 0x7f45e2b1ba00 0x7f45e2226400 131072 1016270 113811808 17832436266265 17832436205010 17832436678611 17832436698824
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 236281 236281 4194304 256 0 0 12 24 287616 0x7f45e2b1b880 0x7f45e2226440 131072 1032280 115828136 17832436711484 17832436678611 17832437211732 17832437228671
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 446 236281 236281 4194304 256 0 0 12 24 294208 0x7f45e2b1b700 0x7f45e2226480 65536 659624 74051544 17832437245851 17832437211732 17832437740053 17832437759248
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 449 236281 236281 4194304 256 0 0 8 24 296960 0x7f45e517a580 0x7f45e22264c0 131072 1005662 112551368 17832437773327 17832437740053 17832438273334 17832438291035
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 452 236281 236281 4194304 256 0 0 8 24 299968 0x7f45e517a400 0x7f45e2226500 131072 1031584 115645744 17832438307094 17832438273334 17832439116216 17832439157763
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 455 236281 236281 4194304 256 0 0 8 24 302720 0x7f45e517a280 0x7f45e2226540 131072 1061368 118941344 17832439177303 17832439116216 17832439767897 17832439809577
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 236281 236281 4194304 256 0 0 12 24 305472 0x7f45e517a100 0x7f45e2226580 131072 1036776 116154712 17832439821457 17832439767897 17832440436698 17832440477671
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 461 236281 236281 4194304 256 0 0 12 24 308224 0x7f45e2b1bf80 0x7f45e22265c0 65536 660196 73909144 17832440489810 17832440436698 17832441100379 17832441118625
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 464 236281 236281 4194304 256 0 0 8 24 310976 0x7f45e2b1be00 0x7f45e2226600 131072 1039478 116410952 17832441132995 17832441100379 17832441730941 17832441747759
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 467 236281 236281 4194304 256 0 0 8 24 313216 0x7f45e2b1bc80 0x7f45e2226640 131072 1041146 116504080 17832441763269 17832441730941 17832442784223 17832442804243
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 470 236281 236281 4194304 256 0 0 8 24 315968 0x7f45e2b1bb00 0x7f45e2226680 131072 1038534 116343664 17832442825283 17832442784223 17832443822464 17832443864977
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 236281 236281 4194304 256 0 0 12 24 318720 0x7f45e2b1b980 0x7f45e22266c0 131072 1034026 115706080 17832443875707 17832443822308 17832444914309 17832444984019
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 476 236281 236281 4194304 256 0 0 12 24 321472 0x7f45e2b1b800 0x7f45e2226700 65536 654370 73416832 17832444995709 17832444914309 17832446040870 17832446107291
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 479 236281 236281 4194304 256 0 0 8 24 324224 0x7f45e2b1b680 0x7f45e2226740 131072 1062574 118922864 17832446119451 17832446040870 17832447150632 17832447217504
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 482 236281 236281 4194304 256 0 0 8 24 326464 0x7f45e517a500 0x7f45e2226780 131072 1035830 116234136 17832447229853 17832447150632 17832449094475 17832449159095
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 485 236281 236281 4194304 256 0 0 8 24 329216 0x7f45e517a380 0x7f45e22267c0 131072 1037504 116109664 17832449179225 17832449094475 17832451003758 17832451072248
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 236281 236281 4194304 256 0 0 12 24 331968 0x7f45e517a200 0x7f45e2226800 131072 1028376 115273240 17832451084307 17832451003758 17832452981041 17832453045679
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 491 236281 236281 4194304 256 0 0 12 24 334720 0x7f45e517a080 0x7f45e2226840 65536 662726 74252864 17832453056848 17832452981041 17832454942484 17832455013900
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 494 236281 236281 4194304 256 0 0 8 24 337472 0x7f45e2b1bf00 0x7f45e2226880 131072 1040770 116756344 17832455025780 17832454942484 17832456880247 17832456947382
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 497 236281 236281 4194304 256 0 0 8 24 0 0x7f45e2b1bd80 0x7f45e22268c0 131072 1035694 116127016 17832456958722 17832456880247 17832460486492 17832460564112
@@ -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",0,0,0,238129,238129,33554432,256,0,0,4,32,4160,0x0,0x7fe2c7e04280,524288,5497472,615656480,17851610507915,17849318958956,17851757718801,17851757807931
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,238129,238129,32768,256,0,0,12,24,13888,0x0,0x7fe2c7e23f80,4096,55920,6257708,17851762985423,17851757718801,17851763112570,17851763117229
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,238129,238129,4194304,256,0,0,12,24,14336,0x7fe2d67ec380,0x7fe2c7e23fc0,524288,10960198,1227561992,17851763151509,17851763112570,17851763483290,17851763485710
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,238129,238129,4194304,256,0,0,16,24,15040,0x7fe2d67ec200,0x7fe2c7e24000,524288,11381323,1274672356,17851763522879,17851763483290,17851763890331,17851763892860
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,238129,238129,4194304,256,0,0,16,24,15488,0x7fe2d67ec080,0x7fe2c7e24040,524288,11627241,1302212244,17851763925789,17851763890331,17851764290172,17851764292530
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,238129,238129,4194304,256,0,0,12,24,15936,0x7fe2d414df00,0x7fe2c7e24080,524288,10699863,1198379556,17851764323980,17851764290172,17851764605852,17851764608203
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,238129,238129,4194304,256,0,0,12,24,16384,0x7fe2d414dd80,0x7fe2c7e240c0,524288,11118838,1245185864,17851764640972,17851764605852,17851764908573,17851764910935
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,238129,238129,4194304,256,0,0,12,24,17088,0x7fe2d414dc00,0x7fe2c7e24100,524288,11178497,1251943004,17851764953374,17851764908573,17851765209053,17851765211248
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,238129,238129,4194304,256,0,0,16,24,17792,0x7fe2d414da80,0x7fe2c7e24140,524288,11592460,1298324336,17851765242887,17851765209053,17851765599934,17851765602108
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,238129,238129,4194304,256,0,0,16,24,18496,0x7fe2d414d900,0x7fe2c7e24180,524288,11494634,1287368864,17851765632697,17851765599934,17851765988574,17851765990788
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,238129,238129,4194304,256,0,0,16,24,19200,0x7fe2d414d780,0x7fe2c7e241c0,524288,11287982,1264243188,17851766020358,17851765988574,17851766334655,17851766337010
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,238129,238129,4194304,256,0,0,16,24,19904,0x7fe2d414d600,0x7fe2c7e24200,524288,11023054,1234642988,17851766367699,17851766334655,17851766641056,17851766643422
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,238129,238129,4194304,256,0,0,12,24,20608,0x7fe2d67ec480,0x7fe2c7e24240,524288,11244797,1259455848,17851766682701,17851766641056,17851766954976,17851766957234
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,238129,238129,4194304,256,0,0,16,24,21312,0x7fe2d67ec300,0x7fe2c7e24280,524288,11510571,1289156640,17851766990564,17851766954976,17851767331937,17851767333595
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,238129,238129,4194304,256,0,0,16,24,22016,0x7fe2d67ec180,0x7fe2c7e242c0,524288,11447156,1282083652,17851767364564,17851767331937,17851767690497,17851767692186
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,238129,238129,4194304,256,0,0,16,24,22720,0x7fe2d67ec000,0x7fe2c7e24300,524288,11276589,1263015848,17851767723665,17851767690497,17851767963778,17851767965349
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,238129,238129,4194304,256,0,0,12,24,23424,0x7fe2d414de80,0x7fe2c7e24340,524288,10903637,1221189884,17851767996329,17851767963778,17851768237058,17851768238773
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,238129,238129,4194304,256,0,0,12,24,24128,0x7fe2d414dd00,0x7fe2c7e24380,524288,11051283,1237706736,17851768276892,17851768237058,17851768510659,17851768512396
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,238129,238129,4194304,256,0,0,16,24,24832,0x7fe2d414db80,0x7fe2c7e243c0,524288,11567105,1295514892,17851768543615,17851768510659,17851768871299,17851768873267
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,238129,238129,4194304,256,0,0,16,24,25536,0x7fe2d414da00,0x7fe2c7e24400,524288,11440192,1281276188,17851768903966,17851768871299,17851769237540,17851769239258
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,238129,238129,4194304,256,0,0,12,24,26240,0x7fe2d414d880,0x7fe2c7e24440,524288,11218351,1256413152,17851769269957,17851769237540,17851769511780,17851769513491
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,238129,238129,4194304,256,0,0,12,24,26944,0x7fe2d414d700,0x7fe2c7e24480,524288,10893140,1220038764,17851769544010,17851769511780,17851769786981,17851769788744
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,238129,238129,4194304,256,0,0,12,24,27648,0x7fe2d67ec580,0x7fe2c7e244c0,524288,11184468,1252652572,17851769827593,17851769786981,17851770067781,17851770069447
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,238129,238129,4194304,256,0,0,16,24,28608,0x7fe2d67ec400,0x7fe2c7e24500,524288,11405712,1277359184,17851770101856,17851770067781,17851770434982,17851770436678
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,238129,238129,4194304,256,0,0,16,24,29312,0x7fe2d67ec280,0x7fe2c7e24540,524288,11384947,1275100984,17851770467807,17851770434982,17851770798343,17851770800169
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,238129,238129,4194304,256,0,0,12,24,30016,0x7fe2d67ec100,0x7fe2c7e24580,524288,11239872,1258881312,17851770831338,17851770798343,17851771073223,17851771074972
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,238129,238129,4194304,256,0,0,8,24,30976,0x7fe2d414df80,0x7fe2c7e245c0,524288,10799987,1209563668,17851771105501,17851771073223,17851771344744,17851771346485
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,238129,238129,4194304,256,0,0,12,24,31680,0x7fe2d414de00,0x7fe2c7e24600,524288,11131170,1246673252,17851771384385,17851771344744,17851771619144,17851771620859
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,238129,238129,4194304,256,0,0,16,24,32640,0x7fe2d414dc80,0x7fe2c7e24640,524288,11467964,1284374572,17851771652478,17851771619144,17851771986025,17851771987720
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,238129,238129,4194304,256,0,0,12,24,33600,0x7fe2d414db00,0x7fe2c7e24680,524288,11240089,1258865168,17851772018959,17851771986025,17851772349385,17851772351110
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,238129,238129,4194304,256,0,0,12,24,34560,0x7fe2d414d980,0x7fe2c7e246c0,524288,11111679,1244473400,17851772381930,17851772349385,17851772624266,17851772626054
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,238129,238129,4194304,256,0,0,8,24,35520,0x7fe2d414d800,0x7fe2c7e24700,524288,10752960,1204236396,17851772656993,17851772624266,17851772900906,17851772902707
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,238129,238129,4194304,256,0,0,12,24,36224,0x7fe2d414d680,0x7fe2c7e24740,524288,11148981,1248709068,17851772941226,17851772900906,17851773176907,17851773178670
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,238129,238129,4194304,256,0,0,12,24,37184,0x7fe2d67ec500,0x7fe2c7e24780,524288,11424600,1279548008,17851773209649,17851773176907,17851773539627,17851773541161
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,238129,238129,4194304,256,0,0,12,24,38144,0x7fe2d67ec380,0x7fe2c7e247c0,524288,11391928,1275859604,17851773572850,17851773539627,17851773903308,17851773905072
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,238129,238129,4194304,256,0,0,12,24,39104,0x7fe2d67ec200,0x7fe2c7e24800,524288,10688825,1197121120,17851773936171,17851773903308,17851774175948,17851774177675
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,238129,238129,4194304,256,0,0,8,24,40320,0x7fe2d67ec080,0x7fe2c7e24840,524288,10142263,1135919060,17851774209724,17851774175948,17851774455789,17851774457488
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,238129,238129,4194304,256,0,0,12,24,41280,0x7fe2d414df00,0x7fe2c7e24880,524288,10949440,1226295444,17851774496357,17851774455789,17851774742829,17851774744601
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,238129,238129,4194304,256,0,0,12,24,42240,0x7fe2d414dd80,0x7fe2c7e248c0,524288,11379921,1274545880,17851774774940,17851774742829,17851775110510,17851775112212
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,238129,238129,4194304,256,0,0,12,24,43200,0x7fe2d414dc00,0x7fe2c7e24900,524288,11416790,1278677352,17851775143441,17851775110510,17851775471951,17851775473633
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,238129,238129,4194304,256,0,0,8,24,44160,0x7fe2d414da80,0x7fe2c7e24940,524288,10352192,1159389384,17851775504362,17851775471951,17851775746831,17851775748466
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,238129,238129,4194304,256,0,0,12,24,45376,0x7fe2d414d900,0x7fe2c7e24980,524288,9913960,1110386536,17851775779665,17851775746831,17851776020432,17851776022119
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,238129,238129,4194304,256,0,0,12,24,46336,0x7fe2d414d780,0x7fe2c7e249c0,524288,10513747,1177552012,17851776060108,17851776020432,17851776296912,17851776298582
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,238129,238129,4194304,256,0,0,12,24,47552,0x7fe2d414d600,0x7fe2c7e24a00,524288,11381922,1274753504,17851776329492,17851776296912,17851776657713,17851776659383
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,238129,238129,4194304,256,0,0,12,24,48512,0x7fe2d67ec480,0x7fe2c7e24a40,524288,11333933,1269382580,17851776690293,17851776657713,17851777015633,17851777017335
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,238129,238129,4194304,256,0,0,8,24,49472,0x7fe2d67ec300,0x7fe2c7e24a80,524288,10580465,1185002716,17851777048404,17851777015633,17851777289234,17851777290928
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,238129,238129,4194304,256,0,0,12,24,50688,0x7fe2d67ec180,0x7fe2c7e24ac0,524288,9199320,1030329784,17851777322447,17851777289234,17851777571314,17851777572971
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,238129,238129,4194304,256,0,0,12,24,51648,0x7fe2d67ec000,0x7fe2c7e24b00,524288,10586783,1185637180,17851777611420,17851777571314,17851777859635,17851777861264
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,238129,238129,4194304,256,0,0,12,24,52864,0x7fe2d414de80,0x7fe2c7e24b40,524288,11290441,1264513584,17851777892063,17851777859635,17851778228755,17851778230584
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,238129,238129,4194304,256,0,0,12,24,54080,0x7fe2d414dd00,0x7fe2c7e24b80,524288,11333004,1269285372,17851778262294,17851778228755,17851778596116,17851778597795
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,238129,238129,4194304,256,0,0,8,24,55296,0x7fe2d414db80,0x7fe2c7e24bc0,524288,10333600,1157349612,17851778628455,17851778596116,17851778872916,17851778874719
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,238129,238129,4194304,256,0,0,12,24,56768,0x7fe2d414da00,0x7fe2c7e24c00,524288,7758862,868986468,17851778905648,17851778872916,17851779148117,17851779149842
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,238129,238129,4194304,256,0,0,12,24,57728,0x7fe2d414d880,0x7fe2c7e24c40,524288,10751011,1204055656,17851779187561,17851779148117,17851779424917,17851779426605
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,238129,238129,4194304,256,0,0,12,24,58944,0x7fe2d414d700,0x7fe2c7e24c80,524288,11359499,1272250716,17851779457324,17851779424917,17851779788118,17851779789916
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,238129,238129,4194304,256,0,0,12,24,60160,0x7fe2d67ec580,0x7fe2c7e24cc0,524288,11359245,1272205808,17851779820985,17851779788118,17851780151639,17851780153257
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,238129,238129,4194304,256,0,0,8,24,61376,0x7fe2d67ec400,0x7fe2c7e24d00,524288,10233865,1146208680,17851780183876,17851780151639,17851780432279,17851780434060
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,238129,238129,4194304,256,0,0,12,24,62848,0x7fe2d67ec280,0x7fe2c7e24d40,524288,6790915,760638956,17851780466599,17851780432279,17851780715160,17851780716753
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,238129,238129,4194304,256,0,0,12,24,63808,0x7fe2d67ec100,0x7fe2c7e24d80,524288,10722907,1200890196,17851780755482,17851780715160,17851780993400,17851780994976
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,238129,238129,4194304,256,0,0,12,24,65024,0x7fe2d414df80,0x7fe2c7e24dc0,524288,11235953,1258389508,17851781026845,17851780993400,17851781354361,17851781356027
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,238129,238129,4194304,256,0,0,12,24,66240,0x7fe2d414de00,0x7fe2c7e24e00,524288,11251763,1260196968,17851781387597,17851781354361,17851781716601,17851781718348
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,238129,238129,4194304,256,0,0,8,24,67456,0x7fe2d414dc80,0x7fe2c7e24e40,524288,10603428,1187614532,17851781749108,17851781716601,17851781993562,17851781995242
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,238129,238129,4194304,256,0,0,12,24,68928,0x7fe2d414db00,0x7fe2c7e24e80,524288,5736171,642479920,17851782026071,17851781993562,17851782284602,17851782286414
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,238129,238129,4194304,256,0,0,12,24,70144,0x7fe2d414d980,0x7fe2c7e24ec0,524288,10761174,1205159824,17851782324253,17851782284602,17851782562523,17851782564147
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,238129,238129,4194304,256,0,0,12,24,71616,0x7fe2d414d800,0x7fe2c7e24f00,524288,11277622,1263104348,17851782596237,17851782562523,17851782924923,17851782926658
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,238129,238129,4194304,256,0,0,12,24,72832,0x7fe2d414d680,0x7fe2c7e24f40,524288,11403554,1277177012,17851782958358,17851782924923,17851783294044,17851783295759
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,238129,238129,4194304,256,0,0,8,24,74048,0x7fe2d67ec500,0x7fe2c7e24f80,524288,9971998,1116839528,17851783326518,17851783294044,17851783572605,17851783574332
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,238129,238129,4194304,256,0,0,12,24,75776,0x7fe2d67ec380,0x7fe2c7e24fc0,524288,4788676,536323888,17851783605412,17851783572605,17851783862525,17851783864245
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,238129,238129,4194304,256,0,0,12,24,76992,0x7fe2d67ec200,0x7fe2c7e25000,524288,10496241,1175548992,17851783902714,17851783862525,17851784138365,17851784140138
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,238129,238129,4194304,256,0,0,12,24,78464,0x7fe2d67ec080,0x7fe2c7e25040,524288,11254474,1260459736,17851784171147,17851784138365,17851784500446,17851784502099
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,238129,238129,4194304,256,0,0,12,24,79936,0x7fe2d414df00,0x7fe2c7e25080,524288,11308943,1266564232,17851784534368,17851784500446,17851784865247,17851784866980
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,238129,238129,4194304,256,0,0,8,24,81408,0x7fe2d414dd80,0x7fe2c7e250c0,524288,9969059,1116531716,17851784897639,17851784865247,17851785139647,17851785141433
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,238129,238129,4194304,256,0,0,12,24,83136,0x7fe2d414dc00,0x7fe2c7e25100,524288,4101249,459292572,17851785172763,17851785139647,17851785435168,17851785436936
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,238129,238129,4194304,256,0,0,12,24,84352,0x7fe2d414da80,0x7fe2c7e25140,524288,10552160,1181829580,17851785487385,17851785435168,17851785716928,17851785718719
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,238129,238129,4194304,256,0,0,12,24,85824,0x7fe2d414d900,0x7fe2c7e25180,524288,11311011,1266806536,17851785749208,17851785716928,17851786084129,17851786085730
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,238129,238129,4194304,256,0,0,12,24,87296,0x7fe2d414d780,0x7fe2c7e251c0,524288,11219564,1256568920,17851786117729,17851786084129,17851786457889,17851786459631
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,238129,238129,4194304,256,0,0,12,24,88768,0x7fe2d414d600,0x7fe2c7e25200,524288,9820308,1099748564,17851786490400,17851786457889,17851786735490,17851786737154
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,238129,238129,4194304,256,0,0,12,24,90752,0x7fe2d67ec480,0x7fe2c7e25240,524288,3671648,411187864,17851786768093,17851786735490,17851787037890,17851787039626
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,238129,238129,4194304,256,0,0,12,24,91968,0x7fe2d67ec300,0x7fe2c7e25280,524288,10077664,1128706364,17851787077675,17851787037890,17851787315331,17851787316989
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,238129,238129,4194304,256,0,0,12,24,93440,0x7fe2d67ec180,0x7fe2c7e252c0,524288,11126647,1246159484,17851787348009,17851787315331,17851787674692,17851787676360
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,238129,238129,4194304,256,0,0,12,24,94912,0x7fe2d67ec000,0x7fe2c7e25300,524288,11153488,1249170388,17851787708170,17851787674692,17851788032292,17851788034032
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,238129,238129,4194304,256,0,0,12,24,96384,0x7fe2d414de80,0x7fe2c7e25340,524288,8941596,1001449384,17851788064441,17851788032292,17851788306853,17851788308635
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,238129,238129,4194304,256,0,0,12,24,98368,0x7fe2d414dd00,0x7fe2c7e25380,524288,3497243,391708692,17851788339414,17851788306853,17851788613413,17851788614977
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,238129,238129,4194304,256,0,0,12,24,99584,0x7fe2d414db80,0x7fe2c7e253c0,524288,9670492,1083108004,17851788652536,17851788613413,17851788896934,17851788898650
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,238129,238129,4194304,256,0,0,12,24,101312,0x7fe2d414da00,0x7fe2c7e25400,524288,11021697,1234414332,17851788930049,17851788896934,17851789261734,17851789263381
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,238129,238129,4194304,256,0,0,12,24,102784,0x7fe2d414d880,0x7fe2c7e25440,524288,11132126,1246798012,17851789294310,17851789261734,17851789621895,17851789623662
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,238129,238129,4194304,256,0,0,12,24,104256,0x7fe2d414d700,0x7fe2c7e25480,524288,8689261,973198924,17851789653931,17851789621895,17851789898375,17851789900145
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,238129,238129,4194304,256,0,0,12,24,106240,0x7fe2d67ec580,0x7fe2c7e254c0,524288,3296359,369169100,17851789930734,17851789898375,17851790211816,17851790213657
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,238129,238129,4194304,256,0,0,12,24,107712,0x7fe2d67ec400,0x7fe2c7e25500,524288,10037455,1124195284,17851790252606,17851790211816,17851790489256,17851790491010
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,238129,238129,4194304,256,0,0,16,24,109440,0x7fe2d67ec280,0x7fe2c7e25540,524288,11174234,1251471072,17851790521940,17851790489256,17851790848457,17851790850182
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,238129,238129,4194304,256,0,0,16,24,111168,0x7fe2d67ec100,0x7fe2c7e25580,524288,11156391,1249494572,17851790881871,17851790848457,17851791213898,17851791215562
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,238129,238129,4194304,256,0,0,8,24,112896,0x7fe2d414df80,0x7fe2c7e255c0,524288,8453395,946749724,17851791246402,17851791213898,17851791491658,17851791493396
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,238129,238129,4194304,256,0,0,12,24,115136,0x7fe2d414de00,0x7fe2c7e25600,524288,3024996,338796148,17851791524785,17851791491658,17851791816619,17851791818288
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,238129,238129,4194304,256,0,0,12,24,116608,0x7fe2d414dc80,0x7fe2c7e25640,524288,9898403,1108578380,17851791856967,17851791816619,17851792098539,17851792100221
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,238129,238129,4194304,256,0,0,16,24,118336,0x7fe2d414db00,0x7fe2c7e25680,524288,11104075,1243642512,17851792131210,17851792098539,17851792457420,17851792459142
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,238129,238129,4194304,256,0,0,16,24,120064,0x7fe2d414d980,0x7fe2c7e256c0,524288,11097123,1242879504,17851792489141,17851792457420,17851792817900,17851792819553
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,238129,238129,4194304,256,0,0,12,24,121792,0x7fe2d414d800,0x7fe2c7e25700,524288,7310378,818624588,17851792849692,17851792817900,17851793096141,17851793097826
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,238129,238129,4194304,256,0,0,12,24,124032,0x7fe2d414d680,0x7fe2c7e25740,524288,2941237,329425624,17851793128535,17851793096141,17851793421421,17851793423188
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,238129,238129,4194304,256,0,0,12,24,125504,0x7fe2d67ec500,0x7fe2c7e25780,524288,9559653,1070725500,17851793461137,17851793421421,17851793695662,17851793697541
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,238129,238129,4194304,256,0,0,12,24,127488,0x7fe2d67ec380,0x7fe2c7e257c0,524288,11023374,1234615968,17851793727930,17851793695662,17851794053262,17851794055012
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,238129,238129,4194304,256,0,0,12,24,129216,0x7fe2d67ec200,0x7fe2c7e25800,524288,11082656,1241258564,17851794092211,17851794053262,17851794431823,17851794433593
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,238129,238129,4194304,256,0,0,12,24,130944,0x7fe2d67ec080,0x7fe2c7e25840,524288,6353255,711593988,17851794464132,17851794431823,17851794712304,17851794713966
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,238129,238129,4194304,256,0,0,12,24,133440,0x7fe2d414df00,0x7fe2c7e25880,524288,2939088,329191932,17851794744745,17851794712304,17851795055664,17851795057367
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,238129,238129,4194304,256,0,0,12,24,134912,0x7fe2d414dd80,0x7fe2c7e258c0,524288,8674328,971491172,17851795096216,17851795055664,17851795333105,17851795334710
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,238129,238129,4194304,256,0,0,12,24,136896,0x7fe2d414dc00,0x7fe2c7e25900,524288,10772675,1206512204,17851795365530,17851795333105,17851795695185,17851795696821
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,238129,238129,4194304,256,0,0,12,24,138880,0x7fe2d414da80,0x7fe2c7e25940,524288,10815365,1211244236,17851795728621,17851795695185,17851796056626,17851796058483
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,238129,238129,4194304,256,0,0,12,24,140864,0x7fe2d414d900,0x7fe2c7e25980,524288,5008411,560934772,17851796088352,17851796056626,17851796340466,17851796342176
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,238129,238129,4194304,256,0,0,12,24,143616,0x7fe2d414d780,0x7fe2c7e259c0,524288,2860023,320346980,17851796373065,17851796340466,17851796691027,17851796692677
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,238129,238129,4194304,256,0,0,12,24,145344,0x7fe2d414d600,0x7fe2c7e25a00,524288,6975002,781170540,17851796731096,17851796691027,17851796968787,17851796970440
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,238129,238129,4194304,256,0,0,12,24,147584,0x7fe2d67ec480,0x7fe2c7e25a40,524288,10836988,1213716384,17851797001379,17851796968787,17851797330868,17851797332751
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,238129,238129,4194304,256,0,0,12,24,149568,0x7fe2d67ec300,0x7fe2c7e25a80,524288,10812264,1210981884,17851797363950,17851797330868,17851797699349,17851797701022
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,238129,238129,4194304,256,0,0,12,24,151552,0x7fe2d67ec180,0x7fe2c7e25ac0,524288,3932869,440446248,17851797731601,17851797699349,17851797996469,17851797998205
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,238129,238129,4194304,256,0,0,12,24,154304,0x7fe2d67ec000,0x7fe2c7e25b00,524288,2846565,318818040,17851798029344,17851797996469,17851798366710,17851798368385
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,238129,238129,4194304,256,0,0,12,24,156288,0x7fe2d414de80,0x7fe2c7e25b40,524288,5834515,653448932,17851798406914,17851798366710,17851798658070,17851798659808
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,238129,238129,4194304,256,0,0,12,24,158784,0x7fe2d414dd00,0x7fe2c7e25b80,524288,10823083,1212141256,17851798690347,17851798658070,17851799020311,17851799022009
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,238129,238129,4194304,256,0,0,12,24,161024,0x7fe2d414db80,0x7fe2c7e25bc0,524288,10796310,1209189816,17851799053408,17851799020311,17851799383512,17851799385260
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,238129,238129,4194304,256,0,0,12,24,163264,0x7fe2d414da00,0x7fe2c7e25c00,524288,3807149,426378124,17851799416469,17851799383512,17851799687192,17851799688903
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,238129,238129,4194304,256,0,0,12,24,166528,0x7fe2d414d880,0x7fe2c7e25c40,524288,2876568,322203864,17851799719172,17851799687192,17851800076153,17851800121672
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,238129,238129,4194304,256,0,0,12,24,168512,0x7fe2d414d700,0x7fe2c7e25c80,524288,4400559,492855256,17851800141391,17851800076153,17851800403993,17851800405705
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,238129,238129,4194304,256,0,0,12,24,171264,0x7fe2d67ec580,0x7fe2c7e25cc0,524288,10574190,1184279480,17851800437434,17851800403993,17851800769434,17851800771206
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,238129,238129,4194304,256,0,0,12,24,173760,0x7fe2d67ec400,0x7fe2c7e25d00,524288,9756056,1092609072,17851800803335,17851800769434,17851801141275,17851801142977
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,238129,238129,4194304,256,0,0,12,24,176256,0x7fe2d67ec280,0x7fe2c7e25d40,524288,2937151,328969808,17851801174356,17851801141275,17851801460635,17851801462349
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,238129,238129,4194304,256,0,0,12,24,179776,0x7fe2d67ec100,0x7fe2c7e25d80,524288,2885783,323165516,17851801493368,17851801460635,17851801877596,17851801898488
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,238129,238129,4194304,256,0,0,12,24,182272,0x7fe2d414df80,0x7fe2c7e25dc0,524288,3062370,343015688,17851801918537,17851801877596,17851802207196,17851802209040
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,238129,238129,4194304,256,0,0,12,24,185536,0x7fe2d414de00,0x7fe2c7e25e00,524288,7965851,892150972,17851802241089,17851802207196,17851802586877,17851802634739
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,238129,238129,4194304,256,0,0,12,24,188544,0x7fe2d414dc80,0x7fe2c7e25e40,524288,7295385,817165120,17851802647099,17851802586877,17851803000478,17851803045659
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,238129,238129,4194304,256,0,0,12,24,191552,0x7fe2d414db00,0x7fe2c7e25e80,524288,2808501,314562680,17851803057569,17851803000478,17851803378718,17851803380351
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,238129,238129,4194304,256,0,0,12,24,195840,0x7fe2d414d980,0x7fe2c7e25ec0,524288,2834429,317413852,17851803410380,17851803378718,17851803844639,17851803889878
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,238129,238129,4194304,256,0,0,12,24,198592,0x7fe2d414d800,0x7fe2c7e25f00,524288,2829364,316816148,17851803909458,17851803844639,17851804211040,17851804212750
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,238129,238129,4194304,256,0,0,12,24,202368,0x7fe2d414d680,0x7fe2c7e25f40,524288,7156252,801412676,17851804244429,17851804211040,17851804606400,17851804648529
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,238129,238129,4194304,256,0,0,12,24,205888,0x7fe2d67ec500,0x7fe2c7e25f80,524288,6546543,733169316,17851804661659,17851804606400,17851805024321,17851805066159
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,238129,238129,4194304,256,0,0,12,24,209408,0x7fe2d67ec380,0x7fe2c7e25fc0,524288,2782400,311622300,17851805077389,17851805024321,17851805419362,17851805421170
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,238129,238129,4194304,256,0,0,12,24,214464,0x7fe2d67ec200,0x7fe2c7e26000,524288,2897542,324507732,17851805452989,17851805419362,17851805937923,17851805958267
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,238129,238129,4194304,256,0,0,12,24,217728,0x7fe2d67ec080,0x7fe2c7e26040,524288,2758709,309008928,17851805978236,17851805937923,17851806302243,17851806304268
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,238129,238129,4194304,256,0,0,12,24,222016,0x7fe2d414df00,0x7fe2c7e26080,524288,5361502,600451100,17851806335168,17851806302243,17851806715684,17851806759087
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,238129,238129,4194304,256,0,0,12,24,226048,0x7fe2d414dd80,0x7fe2c7e260c0,524288,5241560,587040032,17851806772477,17851806715684,17851807162405,17851807206206
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,238129,238129,4194304,256,0,0,12,24,230080,0x7fe2d414dc00,0x7fe2c7e26100,524288,2719578,304632596,17851807218236,17851807162405,17851807586246,17851807627715
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,238129,238129,4194304,256,0,0,12,24,235904,0x7fe2d414da80,0x7fe2c7e26140,524288,2929353,328060908,17851807640425,17851807586246,17851808183207,17851808224711
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,238129,238129,4194304,256,0,0,12,24,239424,0x7fe2d414d900,0x7fe2c7e26180,524288,2798443,313443644,17851808244280,17851808183207,17851808586727,17851808588512
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,238129,238129,4194304,256,0,0,12,24,244224,0x7fe2d414d780,0x7fe2c7e261c0,524288,5198688,582256312,17851808619471,17851808586727,17851809020488,17851809062250
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,238129,238129,4194304,256,0,0,12,24,248768,0x7fe2d414d600,0x7fe2c7e26200,524288,3227946,361493392,17851809075529,17851809020488,17851809479849,17851809522538
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,238129,238129,4194304,256,0,0,12,24,253312,0x7fe2d67ec480,0x7fe2c7e26240,524288,2765869,309719692,17851809534718,17851809479849,17851809928650,17851809947908
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,238129,238129,4194304,256,0,0,8,24,255552,0x7fe2d67ec300,0x7fe2c7e26280,524288,2372030,265583500,17851809961547,17851809928650,17851810579051,17851810623291
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,238129,238129,4194304,256,0,0,12,24,259840,0x7fe2d67ec180,0x7fe2c7e262c0,524288,2780688,311398384,17851810643791,17851810579051,17851811023211,17851811067380
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,238129,238129,4194304,256,0,0,12,24,265664,0x7fe2d67ec000,0x7fe2c7e26300,524288,3273190,366588524,17851811079870,17851811023211,17851811539532,17851811581427
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,238129,238129,4194304,256,0,0,12,24,271232,0x7fe2d414de80,0x7fe2c7e26340,524288,3706436,415100620,17851811593917,17851811539532,17851812051693,17851812094375
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,238129,238129,4194304,256,0,0,8,24,273216,0x7fe2d414dd00,0x7fe2c7e26380,524288,2392570,267988172,17851812106724,17851812051693,17851812564014,17851812605892
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,238129,238129,4194304,256,0,0,8,24,275712,0x7fe2d414db80,0x7fe2c7e263c0,524288,2380155,266528932,17851812617972,17851812564014,17851813336815,17851813378153
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,238129,238129,4194304,256,0,0,12,24,280768,0x7fe2d414da00,0x7fe2c7e26400,524288,2651241,296869496,17851813398483,17851813336815,17851813813936,17851813832062
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,238129,238129,4194304,256,0,0,12,24,287616,0x7fe2d414d880,0x7fe2c7e26440,524288,3358527,376130448,17851813847012,17851813813936,17851814349137,17851814394698
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,238129,238129,4194304,256,0,0,12,24,294208,0x7fe2d414d700,0x7fe2c7e26480,524288,3595083,402577832,17851814407058,17851814349137,17851814926578,17851814972024
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,238129,238129,4194304,256,0,0,8,24,296960,0x7fe2d67ec580,0x7fe2c7e264c0,524288,2398306,268633068,17851814983683,17851814926578,17851815496819,17851815538310
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,238129,238129,4194304,256,0,0,8,24,299968,0x7fe2d67ec400,0x7fe2c7e26500,524288,2389962,267666172,17851815550579,17851815496819,17851816367541,17851816409418
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,238129,238129,4194304,256,0,0,8,24,302720,0x7fe2d67ec280,0x7fe2c7e26540,524288,2388205,267475364,17851816429357,17851816367541,17851817028342,17851817069932
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,238129,238129,4194304,256,0,0,12,24,305472,0x7fe2d67ec100,0x7fe2c7e26580,524288,2579021,288843416,17851817081861,17851817028342,17851817710423,17851817752365
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,238129,238129,4194304,256,0,0,12,24,308224,0x7fe2d414df80,0x7fe2c7e265c0,524288,2592302,290292660,17851817764284,17851817710423,17851818386584,17851818432168
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,238129,238129,4194304,256,0,0,8,24,310976,0x7fe2d414de00,0x7fe2c7e26600,524288,2392252,267948208,17851818443947,17851818386584,17851819065625,17851819114581
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,238129,238129,4194304,256,0,0,8,24,313216,0x7fe2d414dc80,0x7fe2c7e26640,524288,2411106,269994500,17851819127690,17851819065625,17851820154427,17851820200824
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,238129,238129,4194304,256,0,0,8,24,315968,0x7fe2d414db00,0x7fe2c7e26680,524288,2438201,273086344,17851820221473,17851820154085,17851821239526,17851821308076
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,238129,238129,4194304,256,0,0,12,24,318720,0x7fe2d414d980,0x7fe2c7e266c0,524288,2595984,290719540,17851821320076,17851821239526,17851822378407,17851822445038
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,238129,238129,4194304,256,0,0,12,24,321472,0x7fe2d414d800,0x7fe2c7e26700,524288,2597137,290863004,17851822458078,17851822378407,17851823516328,17851823583740
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,238129,238129,4194304,256,0,0,8,24,324224,0x7fe2d414d680,0x7fe2c7e26740,524288,2428844,272065092,17851823596109,17851823516328,17851824627689,17851824694792
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,238129,238129,4194304,256,0,0,8,24,326464,0x7fe2d67ec500,0x7fe2c7e26780,524288,2466156,276132408,17851824706782,17851824627689,17851826578251,17851826648574
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,238129,238129,4194304,256,0,0,8,24,329216,0x7fe2d67ec380,0x7fe2c7e267c0,524288,2464191,275993492,17851826670493,17851826578251,17851828504333,17851828576246
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,238129,238129,4194304,256,0,0,12,24,331968,0x7fe2d67ec200,0x7fe2c7e26800,524288,2621651,293624628,17851828588236,17851828504333,17851830489935,17851830560797
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,238129,238129,4194304,256,0,0,12,24,334720,0x7fe2d67ec080,0x7fe2c7e26840,524288,2626645,294164516,17851830573217,17851830489935,17851832474737,17851832543988
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,238129,238129,4194304,256,0,0,8,24,337472,0x7fe2d414df00,0x7fe2c7e26880,524288,2455750,275010384,17851832555917,17851832474737,17851834403859,17851834473550
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,238129,238129,4194304,256,0,0,8,24,0,0x7fe2d414dd80,0x7fe2c7e268c0,524288,2496448,279555072,17851834487209,17851834403859,17851838027063,17851838150278
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 238129 238129 33554432 256 0 0 4 32 4160 0x0 0x7fe2c7e04280 524288 5497472 615656480 17851610507915 17849318958956 17851757718801 17851757807931
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 238129 238129 32768 256 0 0 12 24 13888 0x0 0x7fe2c7e23f80 4096 55920 6257708 17851762985423 17851757718801 17851763112570 17851763117229
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 5 238129 238129 4194304 256 0 0 12 24 14336 0x7fe2d67ec380 0x7fe2c7e23fc0 524288 10960198 1227561992 17851763151509 17851763112570 17851763483290 17851763485710
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 238129 238129 4194304 256 0 0 16 24 15040 0x7fe2d67ec200 0x7fe2c7e24000 524288 11381323 1274672356 17851763522879 17851763483290 17851763890331 17851763892860
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 11 238129 238129 4194304 256 0 0 16 24 15488 0x7fe2d67ec080 0x7fe2c7e24040 524288 11627241 1302212244 17851763925789 17851763890331 17851764290172 17851764292530
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 14 238129 238129 4194304 256 0 0 12 24 15936 0x7fe2d414df00 0x7fe2c7e24080 524288 10699863 1198379556 17851764323980 17851764290172 17851764605852 17851764608203
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 17 238129 238129 4194304 256 0 0 12 24 16384 0x7fe2d414dd80 0x7fe2c7e240c0 524288 11118838 1245185864 17851764640972 17851764605852 17851764908573 17851764910935
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 20 238129 238129 4194304 256 0 0 12 24 17088 0x7fe2d414dc00 0x7fe2c7e24100 524288 11178497 1251943004 17851764953374 17851764908573 17851765209053 17851765211248
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 238129 238129 4194304 256 0 0 16 24 17792 0x7fe2d414da80 0x7fe2c7e24140 524288 11592460 1298324336 17851765242887 17851765209053 17851765599934 17851765602108
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 26 238129 238129 4194304 256 0 0 16 24 18496 0x7fe2d414d900 0x7fe2c7e24180 524288 11494634 1287368864 17851765632697 17851765599934 17851765988574 17851765990788
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 29 238129 238129 4194304 256 0 0 16 24 19200 0x7fe2d414d780 0x7fe2c7e241c0 524288 11287982 1264243188 17851766020358 17851765988574 17851766334655 17851766337010
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 32 238129 238129 4194304 256 0 0 16 24 19904 0x7fe2d414d600 0x7fe2c7e24200 524288 11023054 1234642988 17851766367699 17851766334655 17851766641056 17851766643422
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 35 238129 238129 4194304 256 0 0 12 24 20608 0x7fe2d67ec480 0x7fe2c7e24240 524288 11244797 1259455848 17851766682701 17851766641056 17851766954976 17851766957234
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 238129 238129 4194304 256 0 0 16 24 21312 0x7fe2d67ec300 0x7fe2c7e24280 524288 11510571 1289156640 17851766990564 17851766954976 17851767331937 17851767333595
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 41 238129 238129 4194304 256 0 0 16 24 22016 0x7fe2d67ec180 0x7fe2c7e242c0 524288 11447156 1282083652 17851767364564 17851767331937 17851767690497 17851767692186
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 44 238129 238129 4194304 256 0 0 16 24 22720 0x7fe2d67ec000 0x7fe2c7e24300 524288 11276589 1263015848 17851767723665 17851767690497 17851767963778 17851767965349
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 47 238129 238129 4194304 256 0 0 12 24 23424 0x7fe2d414de80 0x7fe2c7e24340 524288 10903637 1221189884 17851767996329 17851767963778 17851768237058 17851768238773
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 50 238129 238129 4194304 256 0 0 12 24 24128 0x7fe2d414dd00 0x7fe2c7e24380 524288 11051283 1237706736 17851768276892 17851768237058 17851768510659 17851768512396
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 238129 238129 4194304 256 0 0 16 24 24832 0x7fe2d414db80 0x7fe2c7e243c0 524288 11567105 1295514892 17851768543615 17851768510659 17851768871299 17851768873267
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 56 238129 238129 4194304 256 0 0 16 24 25536 0x7fe2d414da00 0x7fe2c7e24400 524288 11440192 1281276188 17851768903966 17851768871299 17851769237540 17851769239258
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 59 238129 238129 4194304 256 0 0 12 24 26240 0x7fe2d414d880 0x7fe2c7e24440 524288 11218351 1256413152 17851769269957 17851769237540 17851769511780 17851769513491
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 62 238129 238129 4194304 256 0 0 12 24 26944 0x7fe2d414d700 0x7fe2c7e24480 524288 10893140 1220038764 17851769544010 17851769511780 17851769786981 17851769788744
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 65 238129 238129 4194304 256 0 0 12 24 27648 0x7fe2d67ec580 0x7fe2c7e244c0 524288 11184468 1252652572 17851769827593 17851769786981 17851770067781 17851770069447
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 238129 238129 4194304 256 0 0 16 24 28608 0x7fe2d67ec400 0x7fe2c7e24500 524288 11405712 1277359184 17851770101856 17851770067781 17851770434982 17851770436678
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 71 238129 238129 4194304 256 0 0 16 24 29312 0x7fe2d67ec280 0x7fe2c7e24540 524288 11384947 1275100984 17851770467807 17851770434982 17851770798343 17851770800169
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 74 238129 238129 4194304 256 0 0 12 24 30016 0x7fe2d67ec100 0x7fe2c7e24580 524288 11239872 1258881312 17851770831338 17851770798343 17851771073223 17851771074972
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 77 238129 238129 4194304 256 0 0 8 24 30976 0x7fe2d414df80 0x7fe2c7e245c0 524288 10799987 1209563668 17851771105501 17851771073223 17851771344744 17851771346485
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 80 238129 238129 4194304 256 0 0 12 24 31680 0x7fe2d414de00 0x7fe2c7e24600 524288 11131170 1246673252 17851771384385 17851771344744 17851771619144 17851771620859
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 238129 238129 4194304 256 0 0 16 24 32640 0x7fe2d414dc80 0x7fe2c7e24640 524288 11467964 1284374572 17851771652478 17851771619144 17851771986025 17851771987720
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 86 238129 238129 4194304 256 0 0 12 24 33600 0x7fe2d414db00 0x7fe2c7e24680 524288 11240089 1258865168 17851772018959 17851771986025 17851772349385 17851772351110
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 89 238129 238129 4194304 256 0 0 12 24 34560 0x7fe2d414d980 0x7fe2c7e246c0 524288 11111679 1244473400 17851772381930 17851772349385 17851772624266 17851772626054
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 92 238129 238129 4194304 256 0 0 8 24 35520 0x7fe2d414d800 0x7fe2c7e24700 524288 10752960 1204236396 17851772656993 17851772624266 17851772900906 17851772902707
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 95 238129 238129 4194304 256 0 0 12 24 36224 0x7fe2d414d680 0x7fe2c7e24740 524288 11148981 1248709068 17851772941226 17851772900906 17851773176907 17851773178670
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 238129 238129 4194304 256 0 0 12 24 37184 0x7fe2d67ec500 0x7fe2c7e24780 524288 11424600 1279548008 17851773209649 17851773176907 17851773539627 17851773541161
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 101 238129 238129 4194304 256 0 0 12 24 38144 0x7fe2d67ec380 0x7fe2c7e247c0 524288 11391928 1275859604 17851773572850 17851773539627 17851773903308 17851773905072
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 104 238129 238129 4194304 256 0 0 12 24 39104 0x7fe2d67ec200 0x7fe2c7e24800 524288 10688825 1197121120 17851773936171 17851773903308 17851774175948 17851774177675
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 107 238129 238129 4194304 256 0 0 8 24 40320 0x7fe2d67ec080 0x7fe2c7e24840 524288 10142263 1135919060 17851774209724 17851774175948 17851774455789 17851774457488
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 110 238129 238129 4194304 256 0 0 12 24 41280 0x7fe2d414df00 0x7fe2c7e24880 524288 10949440 1226295444 17851774496357 17851774455789 17851774742829 17851774744601
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 238129 238129 4194304 256 0 0 12 24 42240 0x7fe2d414dd80 0x7fe2c7e248c0 524288 11379921 1274545880 17851774774940 17851774742829 17851775110510 17851775112212
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 116 238129 238129 4194304 256 0 0 12 24 43200 0x7fe2d414dc00 0x7fe2c7e24900 524288 11416790 1278677352 17851775143441 17851775110510 17851775471951 17851775473633
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 119 238129 238129 4194304 256 0 0 8 24 44160 0x7fe2d414da80 0x7fe2c7e24940 524288 10352192 1159389384 17851775504362 17851775471951 17851775746831 17851775748466
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 122 238129 238129 4194304 256 0 0 12 24 45376 0x7fe2d414d900 0x7fe2c7e24980 524288 9913960 1110386536 17851775779665 17851775746831 17851776020432 17851776022119
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 125 238129 238129 4194304 256 0 0 12 24 46336 0x7fe2d414d780 0x7fe2c7e249c0 524288 10513747 1177552012 17851776060108 17851776020432 17851776296912 17851776298582
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 238129 238129 4194304 256 0 0 12 24 47552 0x7fe2d414d600 0x7fe2c7e24a00 524288 11381922 1274753504 17851776329492 17851776296912 17851776657713 17851776659383
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 131 238129 238129 4194304 256 0 0 12 24 48512 0x7fe2d67ec480 0x7fe2c7e24a40 524288 11333933 1269382580 17851776690293 17851776657713 17851777015633 17851777017335
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 134 238129 238129 4194304 256 0 0 8 24 49472 0x7fe2d67ec300 0x7fe2c7e24a80 524288 10580465 1185002716 17851777048404 17851777015633 17851777289234 17851777290928
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 137 238129 238129 4194304 256 0 0 12 24 50688 0x7fe2d67ec180 0x7fe2c7e24ac0 524288 9199320 1030329784 17851777322447 17851777289234 17851777571314 17851777572971
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 140 238129 238129 4194304 256 0 0 12 24 51648 0x7fe2d67ec000 0x7fe2c7e24b00 524288 10586783 1185637180 17851777611420 17851777571314 17851777859635 17851777861264
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 238129 238129 4194304 256 0 0 12 24 52864 0x7fe2d414de80 0x7fe2c7e24b40 524288 11290441 1264513584 17851777892063 17851777859635 17851778228755 17851778230584
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 146 238129 238129 4194304 256 0 0 12 24 54080 0x7fe2d414dd00 0x7fe2c7e24b80 524288 11333004 1269285372 17851778262294 17851778228755 17851778596116 17851778597795
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 149 238129 238129 4194304 256 0 0 8 24 55296 0x7fe2d414db80 0x7fe2c7e24bc0 524288 10333600 1157349612 17851778628455 17851778596116 17851778872916 17851778874719
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 152 238129 238129 4194304 256 0 0 12 24 56768 0x7fe2d414da00 0x7fe2c7e24c00 524288 7758862 868986468 17851778905648 17851778872916 17851779148117 17851779149842
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 155 238129 238129 4194304 256 0 0 12 24 57728 0x7fe2d414d880 0x7fe2c7e24c40 524288 10751011 1204055656 17851779187561 17851779148117 17851779424917 17851779426605
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 238129 238129 4194304 256 0 0 12 24 58944 0x7fe2d414d700 0x7fe2c7e24c80 524288 11359499 1272250716 17851779457324 17851779424917 17851779788118 17851779789916
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 161 238129 238129 4194304 256 0 0 12 24 60160 0x7fe2d67ec580 0x7fe2c7e24cc0 524288 11359245 1272205808 17851779820985 17851779788118 17851780151639 17851780153257
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 164 238129 238129 4194304 256 0 0 8 24 61376 0x7fe2d67ec400 0x7fe2c7e24d00 524288 10233865 1146208680 17851780183876 17851780151639 17851780432279 17851780434060
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 167 238129 238129 4194304 256 0 0 12 24 62848 0x7fe2d67ec280 0x7fe2c7e24d40 524288 6790915 760638956 17851780466599 17851780432279 17851780715160 17851780716753
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 170 238129 238129 4194304 256 0 0 12 24 63808 0x7fe2d67ec100 0x7fe2c7e24d80 524288 10722907 1200890196 17851780755482 17851780715160 17851780993400 17851780994976
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 238129 238129 4194304 256 0 0 12 24 65024 0x7fe2d414df80 0x7fe2c7e24dc0 524288 11235953 1258389508 17851781026845 17851780993400 17851781354361 17851781356027
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 176 238129 238129 4194304 256 0 0 12 24 66240 0x7fe2d414de00 0x7fe2c7e24e00 524288 11251763 1260196968 17851781387597 17851781354361 17851781716601 17851781718348
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 179 238129 238129 4194304 256 0 0 8 24 67456 0x7fe2d414dc80 0x7fe2c7e24e40 524288 10603428 1187614532 17851781749108 17851781716601 17851781993562 17851781995242
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 182 238129 238129 4194304 256 0 0 12 24 68928 0x7fe2d414db00 0x7fe2c7e24e80 524288 5736171 642479920 17851782026071 17851781993562 17851782284602 17851782286414
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 185 238129 238129 4194304 256 0 0 12 24 70144 0x7fe2d414d980 0x7fe2c7e24ec0 524288 10761174 1205159824 17851782324253 17851782284602 17851782562523 17851782564147
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 238129 238129 4194304 256 0 0 12 24 71616 0x7fe2d414d800 0x7fe2c7e24f00 524288 11277622 1263104348 17851782596237 17851782562523 17851782924923 17851782926658
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 191 238129 238129 4194304 256 0 0 12 24 72832 0x7fe2d414d680 0x7fe2c7e24f40 524288 11403554 1277177012 17851782958358 17851782924923 17851783294044 17851783295759
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 194 238129 238129 4194304 256 0 0 8 24 74048 0x7fe2d67ec500 0x7fe2c7e24f80 524288 9971998 1116839528 17851783326518 17851783294044 17851783572605 17851783574332
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 197 238129 238129 4194304 256 0 0 12 24 75776 0x7fe2d67ec380 0x7fe2c7e24fc0 524288 4788676 536323888 17851783605412 17851783572605 17851783862525 17851783864245
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 200 238129 238129 4194304 256 0 0 12 24 76992 0x7fe2d67ec200 0x7fe2c7e25000 524288 10496241 1175548992 17851783902714 17851783862525 17851784138365 17851784140138
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 238129 238129 4194304 256 0 0 12 24 78464 0x7fe2d67ec080 0x7fe2c7e25040 524288 11254474 1260459736 17851784171147 17851784138365 17851784500446 17851784502099
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 206 238129 238129 4194304 256 0 0 12 24 79936 0x7fe2d414df00 0x7fe2c7e25080 524288 11308943 1266564232 17851784534368 17851784500446 17851784865247 17851784866980
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 209 238129 238129 4194304 256 0 0 8 24 81408 0x7fe2d414dd80 0x7fe2c7e250c0 524288 9969059 1116531716 17851784897639 17851784865247 17851785139647 17851785141433
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 212 238129 238129 4194304 256 0 0 12 24 83136 0x7fe2d414dc00 0x7fe2c7e25100 524288 4101249 459292572 17851785172763 17851785139647 17851785435168 17851785436936
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 215 238129 238129 4194304 256 0 0 12 24 84352 0x7fe2d414da80 0x7fe2c7e25140 524288 10552160 1181829580 17851785487385 17851785435168 17851785716928 17851785718719
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 238129 238129 4194304 256 0 0 12 24 85824 0x7fe2d414d900 0x7fe2c7e25180 524288 11311011 1266806536 17851785749208 17851785716928 17851786084129 17851786085730
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 221 238129 238129 4194304 256 0 0 12 24 87296 0x7fe2d414d780 0x7fe2c7e251c0 524288 11219564 1256568920 17851786117729 17851786084129 17851786457889 17851786459631
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 224 238129 238129 4194304 256 0 0 12 24 88768 0x7fe2d414d600 0x7fe2c7e25200 524288 9820308 1099748564 17851786490400 17851786457889 17851786735490 17851786737154
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 227 238129 238129 4194304 256 0 0 12 24 90752 0x7fe2d67ec480 0x7fe2c7e25240 524288 3671648 411187864 17851786768093 17851786735490 17851787037890 17851787039626
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 230 238129 238129 4194304 256 0 0 12 24 91968 0x7fe2d67ec300 0x7fe2c7e25280 524288 10077664 1128706364 17851787077675 17851787037890 17851787315331 17851787316989
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 238129 238129 4194304 256 0 0 12 24 93440 0x7fe2d67ec180 0x7fe2c7e252c0 524288 11126647 1246159484 17851787348009 17851787315331 17851787674692 17851787676360
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 236 238129 238129 4194304 256 0 0 12 24 94912 0x7fe2d67ec000 0x7fe2c7e25300 524288 11153488 1249170388 17851787708170 17851787674692 17851788032292 17851788034032
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 239 238129 238129 4194304 256 0 0 12 24 96384 0x7fe2d414de80 0x7fe2c7e25340 524288 8941596 1001449384 17851788064441 17851788032292 17851788306853 17851788308635
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 242 238129 238129 4194304 256 0 0 12 24 98368 0x7fe2d414dd00 0x7fe2c7e25380 524288 3497243 391708692 17851788339414 17851788306853 17851788613413 17851788614977
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 245 238129 238129 4194304 256 0 0 12 24 99584 0x7fe2d414db80 0x7fe2c7e253c0 524288 9670492 1083108004 17851788652536 17851788613413 17851788896934 17851788898650
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 238129 238129 4194304 256 0 0 12 24 101312 0x7fe2d414da00 0x7fe2c7e25400 524288 11021697 1234414332 17851788930049 17851788896934 17851789261734 17851789263381
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 251 238129 238129 4194304 256 0 0 12 24 102784 0x7fe2d414d880 0x7fe2c7e25440 524288 11132126 1246798012 17851789294310 17851789261734 17851789621895 17851789623662
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 254 238129 238129 4194304 256 0 0 12 24 104256 0x7fe2d414d700 0x7fe2c7e25480 524288 8689261 973198924 17851789653931 17851789621895 17851789898375 17851789900145
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 257 238129 238129 4194304 256 0 0 12 24 106240 0x7fe2d67ec580 0x7fe2c7e254c0 524288 3296359 369169100 17851789930734 17851789898375 17851790211816 17851790213657
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 260 238129 238129 4194304 256 0 0 12 24 107712 0x7fe2d67ec400 0x7fe2c7e25500 524288 10037455 1124195284 17851790252606 17851790211816 17851790489256 17851790491010
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 238129 238129 4194304 256 0 0 16 24 109440 0x7fe2d67ec280 0x7fe2c7e25540 524288 11174234 1251471072 17851790521940 17851790489256 17851790848457 17851790850182
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 266 238129 238129 4194304 256 0 0 16 24 111168 0x7fe2d67ec100 0x7fe2c7e25580 524288 11156391 1249494572 17851790881871 17851790848457 17851791213898 17851791215562
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 269 238129 238129 4194304 256 0 0 8 24 112896 0x7fe2d414df80 0x7fe2c7e255c0 524288 8453395 946749724 17851791246402 17851791213898 17851791491658 17851791493396
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 272 238129 238129 4194304 256 0 0 12 24 115136 0x7fe2d414de00 0x7fe2c7e25600 524288 3024996 338796148 17851791524785 17851791491658 17851791816619 17851791818288
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 275 238129 238129 4194304 256 0 0 12 24 116608 0x7fe2d414dc80 0x7fe2c7e25640 524288 9898403 1108578380 17851791856967 17851791816619 17851792098539 17851792100221
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 238129 238129 4194304 256 0 0 16 24 118336 0x7fe2d414db00 0x7fe2c7e25680 524288 11104075 1243642512 17851792131210 17851792098539 17851792457420 17851792459142
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 281 238129 238129 4194304 256 0 0 16 24 120064 0x7fe2d414d980 0x7fe2c7e256c0 524288 11097123 1242879504 17851792489141 17851792457420 17851792817900 17851792819553
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 284 238129 238129 4194304 256 0 0 12 24 121792 0x7fe2d414d800 0x7fe2c7e25700 524288 7310378 818624588 17851792849692 17851792817900 17851793096141 17851793097826
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 287 238129 238129 4194304 256 0 0 12 24 124032 0x7fe2d414d680 0x7fe2c7e25740 524288 2941237 329425624 17851793128535 17851793096141 17851793421421 17851793423188
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 290 238129 238129 4194304 256 0 0 12 24 125504 0x7fe2d67ec500 0x7fe2c7e25780 524288 9559653 1070725500 17851793461137 17851793421421 17851793695662 17851793697541
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 238129 238129 4194304 256 0 0 12 24 127488 0x7fe2d67ec380 0x7fe2c7e257c0 524288 11023374 1234615968 17851793727930 17851793695662 17851794053262 17851794055012
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 296 238129 238129 4194304 256 0 0 12 24 129216 0x7fe2d67ec200 0x7fe2c7e25800 524288 11082656 1241258564 17851794092211 17851794053262 17851794431823 17851794433593
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 299 238129 238129 4194304 256 0 0 12 24 130944 0x7fe2d67ec080 0x7fe2c7e25840 524288 6353255 711593988 17851794464132 17851794431823 17851794712304 17851794713966
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 302 238129 238129 4194304 256 0 0 12 24 133440 0x7fe2d414df00 0x7fe2c7e25880 524288 2939088 329191932 17851794744745 17851794712304 17851795055664 17851795057367
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 305 238129 238129 4194304 256 0 0 12 24 134912 0x7fe2d414dd80 0x7fe2c7e258c0 524288 8674328 971491172 17851795096216 17851795055664 17851795333105 17851795334710
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 238129 238129 4194304 256 0 0 12 24 136896 0x7fe2d414dc00 0x7fe2c7e25900 524288 10772675 1206512204 17851795365530 17851795333105 17851795695185 17851795696821
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 311 238129 238129 4194304 256 0 0 12 24 138880 0x7fe2d414da80 0x7fe2c7e25940 524288 10815365 1211244236 17851795728621 17851795695185 17851796056626 17851796058483
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 314 238129 238129 4194304 256 0 0 12 24 140864 0x7fe2d414d900 0x7fe2c7e25980 524288 5008411 560934772 17851796088352 17851796056626 17851796340466 17851796342176
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 317 238129 238129 4194304 256 0 0 12 24 143616 0x7fe2d414d780 0x7fe2c7e259c0 524288 2860023 320346980 17851796373065 17851796340466 17851796691027 17851796692677
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 320 238129 238129 4194304 256 0 0 12 24 145344 0x7fe2d414d600 0x7fe2c7e25a00 524288 6975002 781170540 17851796731096 17851796691027 17851796968787 17851796970440
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 238129 238129 4194304 256 0 0 12 24 147584 0x7fe2d67ec480 0x7fe2c7e25a40 524288 10836988 1213716384 17851797001379 17851796968787 17851797330868 17851797332751
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 326 238129 238129 4194304 256 0 0 12 24 149568 0x7fe2d67ec300 0x7fe2c7e25a80 524288 10812264 1210981884 17851797363950 17851797330868 17851797699349 17851797701022
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 329 238129 238129 4194304 256 0 0 12 24 151552 0x7fe2d67ec180 0x7fe2c7e25ac0 524288 3932869 440446248 17851797731601 17851797699349 17851797996469 17851797998205
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 332 238129 238129 4194304 256 0 0 12 24 154304 0x7fe2d67ec000 0x7fe2c7e25b00 524288 2846565 318818040 17851798029344 17851797996469 17851798366710 17851798368385
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 335 238129 238129 4194304 256 0 0 12 24 156288 0x7fe2d414de80 0x7fe2c7e25b40 524288 5834515 653448932 17851798406914 17851798366710 17851798658070 17851798659808
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 238129 238129 4194304 256 0 0 12 24 158784 0x7fe2d414dd00 0x7fe2c7e25b80 524288 10823083 1212141256 17851798690347 17851798658070 17851799020311 17851799022009
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 341 238129 238129 4194304 256 0 0 12 24 161024 0x7fe2d414db80 0x7fe2c7e25bc0 524288 10796310 1209189816 17851799053408 17851799020311 17851799383512 17851799385260
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 344 238129 238129 4194304 256 0 0 12 24 163264 0x7fe2d414da00 0x7fe2c7e25c00 524288 3807149 426378124 17851799416469 17851799383512 17851799687192 17851799688903
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 347 238129 238129 4194304 256 0 0 12 24 166528 0x7fe2d414d880 0x7fe2c7e25c40 524288 2876568 322203864 17851799719172 17851799687192 17851800076153 17851800121672
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 350 238129 238129 4194304 256 0 0 12 24 168512 0x7fe2d414d700 0x7fe2c7e25c80 524288 4400559 492855256 17851800141391 17851800076153 17851800403993 17851800405705
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 238129 238129 4194304 256 0 0 12 24 171264 0x7fe2d67ec580 0x7fe2c7e25cc0 524288 10574190 1184279480 17851800437434 17851800403993 17851800769434 17851800771206
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 356 238129 238129 4194304 256 0 0 12 24 173760 0x7fe2d67ec400 0x7fe2c7e25d00 524288 9756056 1092609072 17851800803335 17851800769434 17851801141275 17851801142977
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 359 238129 238129 4194304 256 0 0 12 24 176256 0x7fe2d67ec280 0x7fe2c7e25d40 524288 2937151 328969808 17851801174356 17851801141275 17851801460635 17851801462349
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 362 238129 238129 4194304 256 0 0 12 24 179776 0x7fe2d67ec100 0x7fe2c7e25d80 524288 2885783 323165516 17851801493368 17851801460635 17851801877596 17851801898488
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 365 238129 238129 4194304 256 0 0 12 24 182272 0x7fe2d414df80 0x7fe2c7e25dc0 524288 3062370 343015688 17851801918537 17851801877596 17851802207196 17851802209040
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 238129 238129 4194304 256 0 0 12 24 185536 0x7fe2d414de00 0x7fe2c7e25e00 524288 7965851 892150972 17851802241089 17851802207196 17851802586877 17851802634739
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 371 238129 238129 4194304 256 0 0 12 24 188544 0x7fe2d414dc80 0x7fe2c7e25e40 524288 7295385 817165120 17851802647099 17851802586877 17851803000478 17851803045659
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 374 238129 238129 4194304 256 0 0 12 24 191552 0x7fe2d414db00 0x7fe2c7e25e80 524288 2808501 314562680 17851803057569 17851803000478 17851803378718 17851803380351
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 377 238129 238129 4194304 256 0 0 12 24 195840 0x7fe2d414d980 0x7fe2c7e25ec0 524288 2834429 317413852 17851803410380 17851803378718 17851803844639 17851803889878
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 380 238129 238129 4194304 256 0 0 12 24 198592 0x7fe2d414d800 0x7fe2c7e25f00 524288 2829364 316816148 17851803909458 17851803844639 17851804211040 17851804212750
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 238129 238129 4194304 256 0 0 12 24 202368 0x7fe2d414d680 0x7fe2c7e25f40 524288 7156252 801412676 17851804244429 17851804211040 17851804606400 17851804648529
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 386 238129 238129 4194304 256 0 0 12 24 205888 0x7fe2d67ec500 0x7fe2c7e25f80 524288 6546543 733169316 17851804661659 17851804606400 17851805024321 17851805066159
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 389 238129 238129 4194304 256 0 0 12 24 209408 0x7fe2d67ec380 0x7fe2c7e25fc0 524288 2782400 311622300 17851805077389 17851805024321 17851805419362 17851805421170
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 392 238129 238129 4194304 256 0 0 12 24 214464 0x7fe2d67ec200 0x7fe2c7e26000 524288 2897542 324507732 17851805452989 17851805419362 17851805937923 17851805958267
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 395 238129 238129 4194304 256 0 0 12 24 217728 0x7fe2d67ec080 0x7fe2c7e26040 524288 2758709 309008928 17851805978236 17851805937923 17851806302243 17851806304268
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 238129 238129 4194304 256 0 0 12 24 222016 0x7fe2d414df00 0x7fe2c7e26080 524288 5361502 600451100 17851806335168 17851806302243 17851806715684 17851806759087
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 401 238129 238129 4194304 256 0 0 12 24 226048 0x7fe2d414dd80 0x7fe2c7e260c0 524288 5241560 587040032 17851806772477 17851806715684 17851807162405 17851807206206
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 404 238129 238129 4194304 256 0 0 12 24 230080 0x7fe2d414dc00 0x7fe2c7e26100 524288 2719578 304632596 17851807218236 17851807162405 17851807586246 17851807627715
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 407 238129 238129 4194304 256 0 0 12 24 235904 0x7fe2d414da80 0x7fe2c7e26140 524288 2929353 328060908 17851807640425 17851807586246 17851808183207 17851808224711
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 410 238129 238129 4194304 256 0 0 12 24 239424 0x7fe2d414d900 0x7fe2c7e26180 524288 2798443 313443644 17851808244280 17851808183207 17851808586727 17851808588512
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 238129 238129 4194304 256 0 0 12 24 244224 0x7fe2d414d780 0x7fe2c7e261c0 524288 5198688 582256312 17851808619471 17851808586727 17851809020488 17851809062250
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 416 238129 238129 4194304 256 0 0 12 24 248768 0x7fe2d414d600 0x7fe2c7e26200 524288 3227946 361493392 17851809075529 17851809020488 17851809479849 17851809522538
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 419 238129 238129 4194304 256 0 0 12 24 253312 0x7fe2d67ec480 0x7fe2c7e26240 524288 2765869 309719692 17851809534718 17851809479849 17851809928650 17851809947908
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 422 238129 238129 4194304 256 0 0 8 24 255552 0x7fe2d67ec300 0x7fe2c7e26280 524288 2372030 265583500 17851809961547 17851809928650 17851810579051 17851810623291
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 425 238129 238129 4194304 256 0 0 12 24 259840 0x7fe2d67ec180 0x7fe2c7e262c0 524288 2780688 311398384 17851810643791 17851810579051 17851811023211 17851811067380
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 238129 238129 4194304 256 0 0 12 24 265664 0x7fe2d67ec000 0x7fe2c7e26300 524288 3273190 366588524 17851811079870 17851811023211 17851811539532 17851811581427
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 431 238129 238129 4194304 256 0 0 12 24 271232 0x7fe2d414de80 0x7fe2c7e26340 524288 3706436 415100620 17851811593917 17851811539532 17851812051693 17851812094375
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 434 238129 238129 4194304 256 0 0 8 24 273216 0x7fe2d414dd00 0x7fe2c7e26380 524288 2392570 267988172 17851812106724 17851812051693 17851812564014 17851812605892
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 437 238129 238129 4194304 256 0 0 8 24 275712 0x7fe2d414db80 0x7fe2c7e263c0 524288 2380155 266528932 17851812617972 17851812564014 17851813336815 17851813378153
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 440 238129 238129 4194304 256 0 0 12 24 280768 0x7fe2d414da00 0x7fe2c7e26400 524288 2651241 296869496 17851813398483 17851813336815 17851813813936 17851813832062
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 238129 238129 4194304 256 0 0 12 24 287616 0x7fe2d414d880 0x7fe2c7e26440 524288 3358527 376130448 17851813847012 17851813813936 17851814349137 17851814394698
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 446 238129 238129 4194304 256 0 0 12 24 294208 0x7fe2d414d700 0x7fe2c7e26480 524288 3595083 402577832 17851814407058 17851814349137 17851814926578 17851814972024
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 449 238129 238129 4194304 256 0 0 8 24 296960 0x7fe2d67ec580 0x7fe2c7e264c0 524288 2398306 268633068 17851814983683 17851814926578 17851815496819 17851815538310
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 452 238129 238129 4194304 256 0 0 8 24 299968 0x7fe2d67ec400 0x7fe2c7e26500 524288 2389962 267666172 17851815550579 17851815496819 17851816367541 17851816409418
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 455 238129 238129 4194304 256 0 0 8 24 302720 0x7fe2d67ec280 0x7fe2c7e26540 524288 2388205 267475364 17851816429357 17851816367541 17851817028342 17851817069932
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 238129 238129 4194304 256 0 0 12 24 305472 0x7fe2d67ec100 0x7fe2c7e26580 524288 2579021 288843416 17851817081861 17851817028342 17851817710423 17851817752365
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 461 238129 238129 4194304 256 0 0 12 24 308224 0x7fe2d414df80 0x7fe2c7e265c0 524288 2592302 290292660 17851817764284 17851817710423 17851818386584 17851818432168
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 464 238129 238129 4194304 256 0 0 8 24 310976 0x7fe2d414de00 0x7fe2c7e26600 524288 2392252 267948208 17851818443947 17851818386584 17851819065625 17851819114581
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 467 238129 238129 4194304 256 0 0 8 24 313216 0x7fe2d414dc80 0x7fe2c7e26640 524288 2411106 269994500 17851819127690 17851819065625 17851820154427 17851820200824
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 470 238129 238129 4194304 256 0 0 8 24 315968 0x7fe2d414db00 0x7fe2c7e26680 524288 2438201 273086344 17851820221473 17851820154085 17851821239526 17851821308076
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 238129 238129 4194304 256 0 0 12 24 318720 0x7fe2d414d980 0x7fe2c7e266c0 524288 2595984 290719540 17851821320076 17851821239526 17851822378407 17851822445038
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 476 238129 238129 4194304 256 0 0 12 24 321472 0x7fe2d414d800 0x7fe2c7e26700 524288 2597137 290863004 17851822458078 17851822378407 17851823516328 17851823583740
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 479 238129 238129 4194304 256 0 0 8 24 324224 0x7fe2d414d680 0x7fe2c7e26740 524288 2428844 272065092 17851823596109 17851823516328 17851824627689 17851824694792
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 482 238129 238129 4194304 256 0 0 8 24 326464 0x7fe2d67ec500 0x7fe2c7e26780 524288 2466156 276132408 17851824706782 17851824627689 17851826578251 17851826648574
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 485 238129 238129 4194304 256 0 0 8 24 329216 0x7fe2d67ec380 0x7fe2c7e267c0 524288 2464191 275993492 17851826670493 17851826578251 17851828504333 17851828576246
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 238129 238129 4194304 256 0 0 12 24 331968 0x7fe2d67ec200 0x7fe2c7e26800 524288 2621651 293624628 17851828588236 17851828504333 17851830489935 17851830560797
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 491 238129 238129 4194304 256 0 0 12 24 334720 0x7fe2d67ec080 0x7fe2c7e26840 524288 2626645 294164516 17851830573217 17851830489935 17851832474737 17851832543988
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 494 238129 238129 4194304 256 0 0 8 24 337472 0x7fe2d414df00 0x7fe2c7e26880 524288 2455750 275010384 17851832555917 17851832474737 17851834403859 17851834473550
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 497 238129 238129 4194304 256 0 0 8 24 0 0x7fe2d414dd80 0x7fe2c7e268c0 524288 2496448 279555072 17851834487209 17851834403859 17851838027063 17851838150278
@@ -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",0,0,0,236725,236725,33554432,256,0,0,4,32,4160,0x0,0x7fc8d4204280,388118,388118,8813,3104952,524288,245379700,3015215,0,997822932,17834114824366,17833406340767,17834261594719,17834261709089
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,236725,236725,32768,256,0,0,12,24,13888,0x0,0x7fc8d4223f80,34226,34226,30380,273816,512,1732870,162674,0,6944808,17834266862991,17834261594719,17834267004326,17834267009117
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,236725,236725,4194304,256,0,0,12,24,14336,0x7fc8d71bf380,0x7fc8d4223fc0,166068,166068,13553,1328552,65536,78338107,1221027,0,315083700,17834267052826,17834267004326,17834267413606,17834267416207
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,236725,236725,4194304,256,0,0,16,24,15040,0x7fc8d71bf200,0x7fc8d4224000,309075,309075,24040,2472608,65536,207974461,2361927,0,833627480,17834267463736,17834267413606,17834267844007,17834267846456
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,236725,236725,4194304,256,0,0,16,24,15488,0x7fc8d71bf080,0x7fc8d4224040,312717,312717,25835,2501744,65536,225690218,2387810,0,904488700,17834267887865,17834267844007,17834268268807,17834268271026
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,236725,236725,4194304,256,0,0,12,24,15936,0x7fc8d4b91f00,0x7fc8d4224080,165971,165971,14858,1327776,65536,88194064,1222047,0,354501948,17834268313195,17834268268807,17834268603048,17834268605407
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,236725,236725,4194304,256,0,0,12,24,16384,0x7fc8d4b91d80,0x7fc8d42240c0,165219,165219,14018,1321760,65536,79047699,1212215,0,317927864,17834268645846,17834268603048,17834268930728,17834268933069
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,236725,236725,4194304,256,0,0,12,24,17088,0x7fc8d4b91c00,0x7fc8d4224100,164375,164375,14488,1315008,65536,91462162,1207066,0,367580624,17834268987318,17834268930728,17834269259369,17834269261561
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,236725,236725,4194304,256,0,0,16,24,17792,0x7fc8d4b91a80,0x7fc8d4224140,309703,309703,24852,2477632,65536,219777215,2368747,0,880840144,17834269301450,17834269259369,17834269686569,17834269688940
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,236725,236725,4194304,256,0,0,16,24,18496,0x7fc8d4b91900,0x7fc8d4224180,310809,310809,22257,2486480,65536,225212276,2380921,0,902579640,17834269729219,17834269686569,17834270108970,17834270111340
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,236725,236725,4194304,256,0,0,16,24,19200,0x7fc8d4b91780,0x7fc8d42241c0,165404,165404,14552,1323240,65536,80450116,1211697,0,323537692,17834270152509,17834270108970,17834270450890,17834270453171
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,236725,236725,4194304,256,0,0,16,24,19904,0x7fc8d4b91600,0x7fc8d4224200,165585,165585,14733,1324688,65536,89465853,1214515,0,359591852,17834270494250,17834270450890,17834270782411,17834270784683
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,236725,236725,4194304,256,0,0,12,24,20608,0x7fc8d71bf480,0x7fc8d4224240,166366,166366,14862,1330936,65536,91499648,1220000,0,367728464,17834270836062,17834270782411,17834271116011,17834271118425
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,236725,236725,4194304,256,0,0,16,24,21312,0x7fc8d71bf300,0x7fc8d4224280,312319,312319,24507,2498560,65536,233250131,2390649,0,934730296,17834271160384,17834271116011,17834271555532,17834271557414
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,236725,236725,4194304,256,0,0,16,24,22016,0x7fc8d71bf180,0x7fc8d42242c0,308649,308649,21619,2469200,65536,224851158,2359776,0,901134076,17834271600213,17834271555532,17834271944652,17834271946314
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,236725,236725,4194304,256,0,0,16,24,22720,0x7fc8d71bf000,0x7fc8d4224300,163725,163725,14889,1309808,65536,91154035,1208364,0,366346432,17834271989503,17834271944652,17834272252333,17834272254047
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,236725,236725,4194304,256,0,0,12,24,23424,0x7fc8d4b91e80,0x7fc8d4224340,163463,163463,14910,1307712,65536,95401874,1206350,0,383341996,17834272296706,17834272252333,17834272551373,17834272553179
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,236725,236725,4194304,256,0,0,12,24,24128,0x7fc8d4b91d00,0x7fc8d4224380,165174,165174,15006,1321400,65536,93783281,1212963,0,376860444,17834272601598,17834272551373,17834272857294,17834272859102
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,236725,236725,4194304,256,0,0,16,24,24832,0x7fc8d4b91b80,0x7fc8d42243c0,308899,308899,24067,2471200,65536,231007192,2364827,0,925758852,17834272905440,17834272857294,17834273249934,17834273251682
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,236725,236725,4194304,256,0,0,16,24,25536,0x7fc8d4b91a00,0x7fc8d4224400,309717,309717,24064,2477744,65536,223804023,2368967,0,896947924,17834273293911,17834273249934,17834273638895,17834273640612
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,236725,236725,4194304,256,0,0,12,24,26240,0x7fc8d4b91880,0x7fc8d4224440,164390,164390,15085,1315128,65536,93431898,1207629,0,375461760,17834273682421,17834273638895,17834273938095,17834273939705
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,236725,236725,4194304,256,0,0,12,24,26944,0x7fc8d4b91700,0x7fc8d4224480,164938,164938,14955,1319512,65536,107825297,1214954,0,433026808,17834273982454,17834273938095,17834274250575,17834274252317
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,236725,236725,4194304,256,0,0,12,24,27648,0x7fc8d71bf580,0x7fc8d42244c0,163684,163684,15364,1309480,65536,98572989,1202351,0,396025084,17834274303036,17834274250575,17834274560336,17834274561989
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,236725,236725,4194304,256,0,0,16,24,28608,0x7fc8d71bf400,0x7fc8d4224500,309216,309216,24259,2473736,65536,229456145,2366399,0,919555808,17834274608288,17834274560336,17834274967056,17834274968889
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,236725,236725,4194304,256,0,0,16,24,29312,0x7fc8d71bf280,0x7fc8d4224540,306859,306859,22328,2454880,65536,211370468,2340855,0,847210304,17834275011958,17834274967056,17834275359377,17834275361219
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,236725,236725,4194304,256,0,0,12,24,30016,0x7fc8d71bf100,0x7fc8d4224580,162796,162796,14816,1302376,65536,90130881,1195582,0,362264460,17834275404238,17834275359377,17834275659857,17834275661632
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,236725,236725,4194304,256,0,0,8,24,30976,0x7fc8d4b91f80,0x7fc8d42245c0,164176,164176,15291,1313416,65536,94637530,1203733,0,380286336,17834275703781,17834275659857,17834275964978,17834275966724
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,236725,236725,4194304,256,0,0,12,24,31680,0x7fc8d4b91e00,0x7fc8d4224600,164486,164486,15106,1315896,65536,98263113,1206137,0,394774388,17834276016083,17834275964978,17834276271378,17834276273017
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,236725,236725,4194304,256,0,0,16,24,32640,0x7fc8d4b91c80,0x7fc8d4224640,308147,308147,24483,2465184,65536,225461106,2358920,0,903576612,17834276314886,17834276271378,17834276663219,17834276665107
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,236725,236725,4194304,256,0,0,12,24,33600,0x7fc8d4b91b00,0x7fc8d4224680,306784,306784,21822,2454280,65536,212758018,2344118,0,852761708,17834276707936,17834276663219,17834277052179,17834277053737
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,236725,236725,4194304,256,0,0,12,24,34560,0x7fc8d4b91980,0x7fc8d42246c0,164291,164291,15379,1314336,65536,89768986,1209049,0,360811080,17834277096186,17834277052179,17834277355220,17834277357100
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,236725,236725,4194304,256,0,0,8,24,35520,0x7fc8d4b91800,0x7fc8d4224700,166338,166338,16385,1330712,65536,95949531,1221575,0,385529096,17834277398619,17834277355220,17834277660660,17834277662272
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,236725,236725,4194304,256,0,0,12,24,36224,0x7fc8d4b91680,0x7fc8d4224740,162847,162847,15060,1302784,65536,97505447,1200686,0,391750292,17834277710811,17834277660660,17834277967700,17834277969325
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,236725,236725,4194304,256,0,0,12,24,37184,0x7fc8d71bf500,0x7fc8d4224780,306864,306864,24043,2454920,65536,228596035,2350247,0,916117520,17834278011794,17834277967700,17834278362581,17834278364495
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,236725,236725,4194304,256,0,0,12,24,38144,0x7fc8d71bf380,0x7fc8d42247c0,307280,307280,22874,2458248,65536,219189165,2355632,0,878486864,17834278407854,17834278362581,17834278758901,17834278760595
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,236725,236725,4194304,256,0,0,12,24,39104,0x7fc8d71bf200,0x7fc8d4224800,163646,163646,15305,1309176,65536,92738259,1205867,0,372683892,17834278802324,17834278758901,17834279065622,17834279067307
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,236725,236725,4194304,256,0,0,8,24,40320,0x7fc8d71bf080,0x7fc8d4224840,162812,162812,15305,1302504,65536,91513072,1197944,0,367781628,17834279109276,17834279065622,17834279368342,17834279369940
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,236725,236725,4194304,256,0,0,12,24,41280,0x7fc8d4b91f00,0x7fc8d4224880,163697,163697,14743,1309584,65536,97528475,1204580,0,391844768,17834279418069,17834279368342,17834279676023,17834279677612
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,236725,236725,4194304,256,0,0,12,24,42240,0x7fc8d4b91d80,0x7fc8d42248c0,306817,306817,23855,2454544,65536,224074796,2348571,0,898027912,17834279723881,17834279676023,17834280077463,17834280079182
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,236725,236725,4194304,256,0,0,12,24,43200,0x7fc8d4b91c00,0x7fc8d4224900,303088,303088,21848,2424712,65536,215098226,2320002,0,862124472,17834280121761,17834280077463,17834280466424,17834280468003
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,236725,236725,4194304,256,0,0,8,24,44160,0x7fc8d4b91a80,0x7fc8d4224940,162715,162715,14617,1301728,65536,100141673,1199730,0,402297404,17834280509402,17834280466424,17834280770264,17834280771805
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,236725,236725,4194304,256,0,0,12,24,45376,0x7fc8d4b91900,0x7fc8d4224980,163608,163608,15486,1308872,65536,91950043,1202769,0,369547032,17834280813514,17834280770264,17834281073305,17834281075087
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,236725,236725,4194304,256,0,0,12,24,46336,0x7fc8d4b91780,0x7fc8d42249c0,162297,162297,14425,1298384,65536,94382812,1195314,0,379256192,17834281124096,17834281073305,17834281384345,17834281386110
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,236725,236725,4194304,256,0,0,12,24,47552,0x7fc8d4b91600,0x7fc8d4224a00,306664,306664,24786,2453320,65536,225485821,2347896,0,903674356,17834281432619,17834281384345,17834281788666,17834281790470
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,236725,236725,4194304,256,0,0,12,24,48512,0x7fc8d71bf480,0x7fc8d4224a40,304669,304669,22899,2437360,65536,214318449,2330625,0,859002420,17834281832979,17834281788666,17834282182906,17834282184770
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,236725,236725,4194304,256,0,0,8,24,49472,0x7fc8d71bf300,0x7fc8d4224a80,164032,164032,14631,1312264,65536,88858198,1205412,0,357162416,17834282227459,17834282182906,17834282489146,17834282490792
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,236725,236725,4194304,256,0,0,12,24,50688,0x7fc8d71bf180,0x7fc8d4224ac0,163201,163201,15807,1305616,65536,96721866,1200217,0,388622312,17834282533281,17834282489146,17834282793627,17834282795345
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,236725,236725,4194304,256,0,0,12,24,51648,0x7fc8d71bf000,0x7fc8d4224b00,161463,161463,14952,1291712,65536,88740842,1187214,0,356698560,17834282844754,17834282793627,17834283100827,17834283102377
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,236725,236725,4194304,256,0,0,12,24,52864,0x7fc8d4b91e80,0x7fc8d4224b40,303745,303745,22710,2429968,65536,201836625,2316360,0,809078756,17834283144876,17834283100827,17834283496508,17834283498217
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,236725,236725,4194304,256,0,0,12,24,54080,0x7fc8d4b91d00,0x7fc8d4224b80,301047,301047,21601,2408384,65536,210437020,2303682,0,843478572,17834283539956,17834283496508,17834283892508,17834283894117
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,236725,236725,4194304,256,0,0,8,24,55296,0x7fc8d4b91b80,0x7fc8d4224bc0,162428,162428,14903,1299432,65536,88474318,1194758,0,355627208,17834283936316,17834283892508,17834284193629,17834284195250
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,236725,236725,4194304,256,0,0,12,24,56768,0x7fc8d4b91a00,0x7fc8d4224c00,163629,163629,16950,1309040,65536,101217691,1198725,0,406601800,17834284237269,17834284193629,17834284495869,17834284497512
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,236725,236725,4194304,256,0,0,12,24,57728,0x7fc8d4b91880,0x7fc8d4224c40,163391,163391,14597,1307136,65536,91714320,1200360,0,368585112,17834284546191,17834284495869,17834284805790,17834284807455
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,236725,236725,4194304,256,0,0,12,24,58944,0x7fc8d4b91700,0x7fc8d4224c80,300221,300221,21845,2401776,65536,212739892,2297136,0,852693288,17834284848824,17834284805790,17834285192510,17834285194135
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,236725,236725,4194304,256,0,0,12,24,60160,0x7fc8d71bf580,0x7fc8d4224cc0,301545,301545,20283,2412368,65536,205629479,2301410,0,824246612,17834285238724,17834285192510,17834285579871,17834285581566
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,236725,236725,4194304,256,0,0,8,24,61376,0x7fc8d71bf400,0x7fc8d4224d00,163132,163132,15667,1305064,65536,95210655,1200481,0,382572852,17834285623274,17834285579871,17834285881151,17834285882808
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,236725,236725,4194304,256,0,0,12,24,62848,0x7fc8d71bf280,0x7fc8d4224d40,169065,169065,16375,1352528,65536,97879669,1245323,0,393262852,17834285924347,17834285881151,17834286199391,17834286201270
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,236725,236725,4194304,256,0,0,12,24,63808,0x7fc8d71bf100,0x7fc8d4224d80,162702,162702,15058,1301624,65536,92605328,1194089,0,372151888,17834286252129,17834286199391,17834286509952,17834286511732
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,236725,236725,4194304,256,0,0,12,24,65024,0x7fc8d4b91f80,0x7fc8d4224dc0,302903,302903,22609,2423232,65536,215042701,2319421,0,861904624,17834286559221,17834286509952,17834286905152,17834286906793
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,236725,236725,4194304,256,0,0,12,24,66240,0x7fc8d4b91e00,0x7fc8d4224e00,299934,299934,20991,2399480,65536,211568934,2288440,0,848010412,17834286949312,17834286905152,17834287299553,17834287301333
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,236725,236725,4194304,256,0,0,8,24,67456,0x7fc8d4b91c80,0x7fc8d4224e40,164917,164917,15176,1319344,65536,92895653,1215543,0,373328368,17834287342372,17834287299553,17834287601473,17834287603155
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,236725,236725,4194304,256,0,0,12,24,68928,0x7fc8d4b91b00,0x7fc8d4224e80,177796,177796,16578,1422376,65536,104994509,1313234,0,421714412,17834287645334,17834287601473,17834287915234,17834287916868
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,236725,236725,4194304,256,0,0,12,24,70144,0x7fc8d4b91980,0x7fc8d4224ec0,160811,160811,14705,1286496,65536,89629786,1181277,0,360258064,17834287965816,17834287915234,17834288223074,17834288224820
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,236725,236725,4194304,256,0,0,12,24,71616,0x7fc8d4b91800,0x7fc8d4224f00,302087,302087,23294,2416704,65536,219851616,2309099,0,881138856,17834288266549,17834288223074,17834288616835,17834288618460
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,236725,236725,4194304,256,0,0,12,24,72832,0x7fc8d4b91680,0x7fc8d4224f40,303611,303611,23005,2428896,65536,222137973,2319977,0,890282592,17834288661129,17834288616835,17834289007715,17834289009390
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,236725,236725,4194304,256,0,0,8,24,74048,0x7fc8d71bf500,0x7fc8d4224f80,163161,163161,15630,1305296,65536,91235959,1194973,0,366677940,17834289050369,17834289007715,17834289310436,17834289312333
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,236725,236725,4194304,256,0,0,12,24,75776,0x7fc8d71bf380,0x7fc8d4224fc0,183219,183219,17101,1465760,65536,109826885,1356619,0,441057852,17834289355122,17834289310436,17834289625796,17834289627395
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,236725,236725,4194304,256,0,0,12,24,76992,0x7fc8d71bf200,0x7fc8d4225000,162997,162997,15184,1303984,65536,88666144,1192526,0,356405896,17834289690813,17834289625796,17834289938917,17834289940647
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,236725,236725,4194304,256,0,0,12,24,78464,0x7fc8d71bf080,0x7fc8d4225040,301969,301969,22124,2415760,65536,214738349,2310781,0,860686468,17834289987216,17834289938917,17834290365157,17834290367057
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,236725,236725,4194304,256,0,0,12,24,79936,0x7fc8d4b91f00,0x7fc8d4225080,302753,302753,23164,2422032,65536,210241017,2311664,0,842698468,17834290408876,17834290365157,17834290767398,17834290769027
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,236725,236725,4194304,256,0,0,8,24,81408,0x7fc8d4b91d80,0x7fc8d42250c0,162581,162581,15730,1300656,65536,93338046,1195432,0,375088052,17834290811296,17834290767398,17834291075238,17834291077019
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,236725,236725,4194304,256,0,0,12,24,83136,0x7fc8d4b91c00,0x7fc8d4225100,192516,192516,18259,1540136,65536,115988784,1429576,0,465701400,17834291118798,17834291075238,17834291400198,17834291402111
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,236725,236725,4194304,256,0,0,12,24,84352,0x7fc8d4b91a80,0x7fc8d4225140,162889,162889,15404,1303120,65536,96009514,1198118,0,385765176,17834291450040,17834291400198,17834291712679,17834291714363
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,236725,236725,4194304,256,0,0,12,24,85824,0x7fc8d4b91900,0x7fc8d4225180,303894,303894,22975,2431160,65536,220298015,2321393,0,882931436,17834291756322,17834291712679,17834292106279,17834292108014
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,236725,236725,4194304,256,0,0,12,24,87296,0x7fc8d4b91780,0x7fc8d42251c0,299823,299823,22016,2398592,65536,213726362,2293812,0,856641476,17834292152253,17834292106279,17834292497480,17834292499214
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,236725,236725,4194304,256,0,0,12,24,88768,0x7fc8d4b91600,0x7fc8d4225200,162456,162456,15936,1299656,65536,96275564,1197182,0,386834488,17834292541063,17834292497480,17834292804840,17834292806386
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,236725,236725,4194304,256,0,0,12,24,90752,0x7fc8d71bf480,0x7fc8d4225240,203471,203471,18200,1627776,65536,117796929,1513037,0,472938496,17834292847715,17834292804840,17834293142121,17834293143698
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,236725,236725,4194304,256,0,0,12,24,91968,0x7fc8d71bf300,0x7fc8d4225280,162292,162292,15476,1298344,65536,93981779,1192840,0,377663004,17834293192997,17834293142121,17834293452041,17834293453861
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,236725,236725,4194304,256,0,0,12,24,93440,0x7fc8d71bf180,0x7fc8d42252c0,301740,301740,23035,2413928,65536,223216311,2308970,0,894601568,17834293501559,17834293452041,17834293849802,17834293851431
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,236725,236725,4194304,256,0,0,12,24,94912,0x7fc8d71bf000,0x7fc8d4225300,299586,299586,21971,2396696,65536,212866702,2295181,0,853196760,17834293895900,17834293849802,17834294243242,17834294245081
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,236725,236725,4194304,256,0,0,12,24,96384,0x7fc8d4b91e80,0x7fc8d4225340,162618,162618,15249,1300952,65536,98466108,1197652,0,395598028,17834294286870,17834294243242,17834294553963,17834294555623
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,236725,236725,4194304,256,0,0,12,24,98368,0x7fc8d4b91d00,0x7fc8d4225380,211130,211130,19059,1689048,65536,139997082,1578277,0,561732788,17834294597952,17834294553963,17834294888843,17834294890575
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,236725,236725,4194304,256,0,0,12,24,99584,0x7fc8d4b91b80,0x7fc8d42253c0,162454,162454,15664,1299640,65536,95675469,1195184,0,384430776,17834294938784,17834294888843,17834295197484,17834295199077
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,236725,236725,4194304,256,0,0,12,24,101312,0x7fc8d4b91a00,0x7fc8d4225400,298352,298352,22850,2386824,65536,218183439,2281773,0,874465752,17834295239986,17834295197484,17834295591724,17834295593397
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,236725,236725,4194304,256,0,0,12,24,102784,0x7fc8d4b91880,0x7fc8d4225440,299448,299448,22428,2395592,65536,208003050,2290833,0,833743560,17834295635696,17834295591724,17834295985005,17834295986638
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,236725,236725,4194304,256,0,0,12,24,104256,0x7fc8d4b91700,0x7fc8d4225480,161836,161836,15933,1294696,65536,98449694,1189411,0,395538516,17834296029047,17834295985005,17834296289485,17834296291350
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,236725,236725,4194304,256,0,0,12,24,106240,0x7fc8d71bf580,0x7fc8d42254c0,220777,220777,19935,1766224,65536,126795673,1647432,0,508938936,17834296332469,17834296289485,17834296633806,17834296635512
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,236725,236725,4194304,256,0,0,12,24,107712,0x7fc8d71bf400,0x7fc8d4225500,161888,161888,15580,1295112,65536,89962750,1188814,0,361583932,17834296685250,17834296633806,17834296943246,17834296945044
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,236725,236725,4194304,256,0,0,16,24,109440,0x7fc8d71bf280,0x7fc8d4225540,297291,297291,21409,2378336,65536,206695233,2272110,0,828513140,17834296991243,17834296943246,17834297338286,17834297340024
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,236725,236725,4194304,256,0,0,16,24,111168,0x7fc8d71bf100,0x7fc8d4225580,301879,301879,23718,2415040,65536,215905745,2301239,0,865353032,17834297383633,17834297338286,17834297732367,17834297734054
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,236725,236725,4194304,256,0,0,8,24,112896,0x7fc8d4b91f80,0x7fc8d42255c0,164601,164601,16231,1316816,65536,99833361,1209593,0,401091668,17834297775473,17834297732367,17834298041807,17834298043577
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,236725,236725,4194304,256,0,0,12,24,115136,0x7fc8d4b91e00,0x7fc8d4225600,229723,229723,19773,1837792,65536,149136492,1730381,0,598297608,17834298092205,17834298041807,17834298404048,17834298405698
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,236725,236725,4194304,256,0,0,12,24,116608,0x7fc8d4b91c80,0x7fc8d4225640,161402,161402,15123,1291224,65536,90921050,1187708,0,365422976,17834298454706,17834298404048,17834298712048,17834298713750
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,236725,236725,4194304,256,0,0,16,24,118336,0x7fc8d4b91b00,0x7fc8d4225680,298204,298204,20792,2385640,65536,197986138,2276652,0,793685384,17834298760439,17834298712048,17834299105809,17834299107450
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,236725,236725,4194304,256,0,0,16,24,120064,0x7fc8d4b91980,0x7fc8d42256c0,300595,300595,22494,2404768,65536,215379737,2301175,0,863254268,17834299150079,17834299105809,17834299496689,17834299498340
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,236725,236725,4194304,256,0,0,12,24,121792,0x7fc8d4b91800,0x7fc8d4225700,164958,164958,16370,1319672,65536,101616331,1214016,0,408212144,17834299539319,17834299496689,17834299801810,17834299803813
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,236725,236725,4194304,256,0,0,12,24,124032,0x7fc8d4b91680,0x7fc8d4225740,240645,240645,20516,1925168,65536,157732556,1813466,0,632674640,17834299844102,17834299801810,17834300163570,17834300165174
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,236725,236725,4194304,256,0,0,12,24,125504,0x7fc8d71bf500,0x7fc8d4225780,162126,162126,15768,1297016,65536,98187098,1194453,0,394504012,17834300214413,17834300163570,17834300475571,17834300477146
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,236725,236725,4194304,256,0,0,12,24,127488,0x7fc8d71bf380,0x7fc8d42257c0,302955,302955,20938,2423648,65536,205734897,2308541,0,824672836,17834300523855,17834300475571,17834300872531,17834300874236
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,236725,236725,4194304,256,0,0,12,24,129216,0x7fc8d71bf200,0x7fc8d4225800,298432,298432,20729,2387464,65536,202637622,2282225,0,812285600,17834300916045,17834300872531,17834301262772,17834301264587
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,236725,236725,4194304,256,0,0,12,24,130944,0x7fc8d71bf080,0x7fc8d4225840,171091,171091,16030,1368736,65536,100852134,1263541,0,405154688,17834301305746,17834301262772,17834301573972,17834301575609
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,236725,236725,4194304,256,0,0,12,24,133440,0x7fc8d4b91f00,0x7fc8d4225880,259655,259655,21249,2077248,65536,166745550,1964412,0,668732852,17834301617628,17834301573972,17834301938933,17834301940650
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,236725,236725,4194304,256,0,0,12,24,134912,0x7fc8d4b91d80,0x7fc8d42258c0,161815,161815,15866,1294528,65536,95893855,1188755,0,385320516,17834301990029,17834301938933,17834302259413,17834302260992
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,236725,236725,4194304,256,0,0,12,24,136896,0x7fc8d4b91c00,0x7fc8d4225900,296539,296539,20914,2372320,65536,202649671,2263614,0,812338056,17834302302771,17834302259413,17834302655254,17834302657002
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,236725,236725,4194304,256,0,0,12,24,138880,0x7fc8d4b91a80,0x7fc8d4225940,297031,297031,21172,2376256,65536,205901482,2265136,0,825344388,17834302698781,17834302655254,17834303044374,17834303046012
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,236725,236725,4194304,256,0,0,12,24,140864,0x7fc8d4b91900,0x7fc8d4225980,178771,178771,16738,1430176,65536,106947525,1324370,0,429537856,17834303087531,17834303044374,17834303357495,17834303359055
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,236725,236725,4194304,256,0,0,12,24,143616,0x7fc8d4b91780,0x7fc8d42259c0,280909,280909,23093,2247280,65536,190802329,2129530,0,764957064,17834303400584,17834303357495,17834303734775,17834303736465
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,236725,236725,4194304,256,0,0,12,24,145344,0x7fc8d4b91600,0x7fc8d4225a00,163019,163019,16590,1304160,65536,102331826,1195152,0,411073356,17834303785814,17834303734775,17834304045176,17834304046747
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,236725,236725,4194304,256,0,0,12,24,147584,0x7fc8d71bf480,0x7fc8d4225a40,296769,296769,21322,2374160,65536,203778534,2261266,0,816877520,17834304088806,17834304045176,17834304437496,17834304439028
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,236725,236725,4194304,256,0,0,12,24,149568,0x7fc8d71bf300,0x7fc8d4225a80,296072,296072,20953,2368584,65536,206833922,2259877,0,829074876,17834304479807,17834304437496,17834304828857,17834304830788
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,236725,236725,4194304,256,0,0,12,24,151552,0x7fc8d71bf180,0x7fc8d4225ac0,186912,186912,17450,1495304,65536,103138691,1380354,0,414306260,17834304870297,17834304828857,17834305160377,17834305162140
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,236725,236725,4194304,256,0,0,12,24,154304,0x7fc8d71bf000,0x7fc8d4225b00,300476,300476,23558,2403816,65536,195767935,2289652,0,784828060,17834305202979,17834305160377,17834305553338,17834305555040
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,236725,236725,4194304,256,0,0,12,24,156288,0x7fc8d4b91e80,0x7fc8d4225b40,171069,171069,16766,1368560,65536,101300694,1266522,0,406947060,17834305604099,17834305553338,17834305872538,17834305874242
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,236725,236725,4194304,256,0,0,12,24,158784,0x7fc8d4b91d00,0x7fc8d4225b80,299366,299366,19246,2394936,65536,164222368,2269854,0,658639616,17834305915891,17834305872538,17834306266619,17834306268682
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,236725,236725,4194304,256,0,0,12,24,161024,0x7fc8d4b91b80,0x7fc8d4225bc0,297382,297382,20708,2379064,65536,191601847,2264334,0,768152064,17834306309591,17834306266619,17834306661499,17834306663382
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,236725,236725,4194304,256,0,0,12,24,163264,0x7fc8d4b91a00,0x7fc8d4225c00,207412,207412,19074,1659304,65536,123377617,1541710,0,495275328,17834306703341,17834306661499,17834306993019,17834306994584
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,236725,236725,4194304,256,0,0,12,24,166528,0x7fc8d4b91880,0x7fc8d4225c40,341044,341044,25539,2728360,65536,230738852,2613176,0,924716048,17834307035523,17834306993019,17834307411260,17834307459113
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,236725,236725,4194304,256,0,0,12,24,168512,0x7fc8d4b91700,0x7fc8d4225c80,184919,184919,18033,1479360,65536,115675289,1368223,0,464448212,17834307478252,17834307411260,17834307767581,17834307769255
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,236725,236725,4194304,256,0,0,12,24,171264,0x7fc8d71bf580,0x7fc8d4225cc0,298024,298024,21863,2384200,65536,158606979,2238111,0,636177212,17834307811134,17834307767581,17834308161181,17834308162815
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,236725,236725,4194304,256,0,0,12,24,173760,0x7fc8d71bf400,0x7fc8d4225d00,297180,297180,20530,2377448,65536,184505727,2259504,0,739772484,17834308205604,17834308161181,17834308556062,17834308557885
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,236725,236725,4194304,256,0,0,12,24,176256,0x7fc8d71bf280,0x7fc8d4225d40,224815,224815,19630,1798528,65536,145776401,1689205,0,584851028,17834308598954,17834308556062,17834308900702,17834308902377
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,236725,236725,4194304,256,0,0,12,24,179776,0x7fc8d71bf100,0x7fc8d4225d80,381869,381869,27926,3054960,65536,257070858,2936653,0,1030042636,17834308943066,17834308900702,17834309347263,17834309366235
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,236725,236725,4194304,256,0,0,12,24,182272,0x7fc8d4b91f80,0x7fc8d4225dc0,212815,212815,19513,1702528,65536,122464861,1583033,0,491617708,17834309397585,17834309347263,17834309686303,17834309687957
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,236725,236725,4194304,256,0,0,12,24,185536,0x7fc8d4b91e00,0x7fc8d4225e00,310102,310102,24097,2480824,65536,185464783,2345934,0,743628116,17834309728316,17834309686303,17834310090304,17834310096947
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,236725,236725,4194304,256,0,0,12,24,188544,0x7fc8d4b91c80,0x7fc8d4225e40,311821,311821,20978,2494576,65536,179673646,2366407,0,720457404,17834310132456,17834310090304,17834310509824,17834310531006
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,236725,236725,4194304,256,0,0,12,24,191552,0x7fc8d4b91b00,0x7fc8d4225e80,266016,266016,21765,2128136,65536,177645979,2018546,0,712343952,17834310551946,17834310509824,17834310879745,17834310881678
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,236725,236725,4194304,256,0,0,12,24,195840,0x7fc8d4b91980,0x7fc8d4225ec0,462230,462230,31445,3697848,65536,327814997,3582185,0,1313021200,17834310921557,17834310879745,17834311373345,17834311392615
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,236725,236725,4194304,256,0,0,12,24,198592,0x7fc8d4b91800,0x7fc8d4225f00,243299,243299,20537,1946400,65536,168632596,1836482,0,676289424,17834311423864,17834311373345,17834311732706,17834311734556
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,236725,236725,4194304,256,0,0,12,24,202368,0x7fc8d4b91680,0x7fc8d4225f40,334675,334675,23818,2677408,65536,199877609,2554723,0,801277260,17834311774095,17834311732706,17834312160866,17834312179645
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,236725,236725,4194304,256,0,0,12,24,205888,0x7fc8d71bf500,0x7fc8d4225f80,333944,333944,23247,2671560,65536,207389401,2543268,0,831339332,17834312203145,17834312160866,17834312584067,17834312601845
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,236725,236725,4194304,256,0,0,12,24,209408,0x7fc8d71bf380,0x7fc8d4225fc0,307785,307785,23645,2462288,65536,204659723,2351204,0,820405932,17834312625324,17834312584067,17834312985508,17834312987395
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,236725,236725,4194304,256,0,0,12,24,214464,0x7fc8d71bf200,0x7fc8d4226000,543831,543831,36446,4350656,65536,400108703,4228041,0,1602203616,17834313028704,17834312985508,17834313528868,17834313545371
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,236725,236725,4194304,256,0,0,12,24,217728,0x7fc8d71bf080,0x7fc8d4226040,272076,272076,22079,2176616,65536,195969289,2069235,0,785630088,17834313580611,17834313528868,17834313907589,17834313909332
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,236725,236725,4194304,256,0,0,12,24,222016,0x7fc8d4b91f00,0x7fc8d4226080,366676,366676,27448,2933416,65536,245183051,2817157,0,982512760,17834313950611,17834313907589,17834314357029,17834314375181
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,236725,236725,4194304,256,0,0,12,24,226048,0x7fc8d4b91d80,0x7fc8d42260c0,364698,364698,28121,2917592,65536,255642502,2806900,0,1024333444,17834314399810,17834314357029,17834314802630,17834314845409
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,236725,236725,4194304,256,0,0,12,24,230080,0x7fc8d4b91c00,0x7fc8d4226100,347899,347899,25794,2783200,65536,242487603,2672104,0,971720320,17834314855839,17834314802630,17834315245191,17834315287608
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,236725,236725,4194304,256,0,0,12,24,235904,0x7fc8d4b91a80,0x7fc8d4226140,625481,625481,40686,5003856,65536,460031137,4879068,0,1841894612,17834315298628,17834315245191,17834315876071,17834315918383
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,236725,236725,4194304,256,0,0,12,24,239424,0x7fc8d4b91900,0x7fc8d4226180,302927,302927,23596,2423424,65536,213261601,2312174,0,854813768,17834315937612,17834315876071,17834316297832,17834316299403
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,236725,236725,4194304,256,0,0,12,24,244224,0x7fc8d4b91780,0x7fc8d42261c0,399075,399075,27608,3192608,65536,264195773,3080075,0,1058569392,17834316340782,17834316297832,17834316759753,17834316801851
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,236725,236725,4194304,256,0,0,12,24,248768,0x7fc8d4b91600,0x7fc8d4226200,392130,392130,27681,3137048,65536,289347031,3022706,0,1159165792,17834316812020,17834316759753,17834317239753,17834317281259
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,236725,236725,4194304,256,0,0,12,24,253312,0x7fc8d71bf480,0x7fc8d4226240,387952,387952,27807,3103624,65536,280753329,2989110,0,1124778064,17834317291418,17834317239753,17834317709354,17834317727518
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,236725,236725,4194304,256,0,0,8,24,255552,0x7fc8d71bf300,0x7fc8d4226280,719930,719930,44876,5759448,65536,543357386,5636111,0,2175169880,17834317752167,17834317709354,17834318374795,17834318418700
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,236725,236725,4194304,256,0,0,12,24,259840,0x7fc8d71bf180,0x7fc8d42262c0,364824,364824,27411,2918600,65536,263017562,2801039,0,1053835448,17834318438150,17834318374795,17834318836235,17834318879929
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,236725,236725,4194304,256,0,0,12,24,265664,0x7fc8d71bf000,0x7fc8d4226300,471292,471292,32403,3770344,65536,351197243,3653322,0,1406578836,17834318891029,17834318836235,17834319369036,17834319411026
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,236725,236725,4194304,256,0,0,12,24,271232,0x7fc8d4b91e80,0x7fc8d4226340,474138,474138,32968,3793112,65536,349572599,3680200,0,1400078536,17834319421405,17834319369036,17834319910157,17834319951892
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,236725,236725,4194304,256,0,0,8,24,273216,0x7fc8d4b91d00,0x7fc8d4226380,483314,483314,33001,3866520,65536,352783080,3753336,0,1412873680,17834319962552,17834319910157,17834320437198,17834320479809
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,236725,236725,4194304,256,0,0,8,24,275712,0x7fc8d4b91b80,0x7fc8d42263c0,880138,880138,52986,7041112,65536,675410808,6929733,0,2703384488,17834320490389,17834320437198,17834321229839,17834321272819
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,236725,236725,4194304,256,0,0,12,24,280768,0x7fc8d4b91a00,0x7fc8d4226400,425881,425881,29669,3407056,65536,318126163,3299396,0,1274275000,17834321292269,17834321229839,17834321724559,17834321742908
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,236725,236725,4194304,256,0,0,12,24,287616,0x7fc8d4b91880,0x7fc8d4226440,552000,552000,35408,4416008,65536,405168085,4305890,0,1622465864,17834321767237,17834321724559,17834322289360,17834322335643
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,236725,236725,4194304,256,0,0,12,24,294208,0x7fc8d4b91700,0x7fc8d4226480,551581,551581,36057,4412656,65536,409721582,4298465,0,1640670012,17834322347203,17834322289360,17834322879601,17834322924048
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,236725,236725,4194304,256,0,0,8,24,296960,0x7fc8d71bf580,0x7fc8d42264c0,563270,563270,36733,4506168,65536,422198219,4392694,0,1690538260,17834322935358,17834322879601,17834323460242,17834323501854
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,236725,236725,4194304,256,0,0,8,24,299968,0x7fc8d71bf400,0x7fc8d4226500,1041630,1041630,61508,8333048,65536,797586758,8218915,0,3192089132,17834323512054,17834323460072,17834324354792,17834324401882
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,236725,236725,4194304,256,0,0,8,24,302720,0x7fc8d71bf280,0x7fc8d4226540,721638,721638,44565,5773112,65536,538243078,5659185,0,2154714336,17834324420811,17834324354792,17834325038312,17834325080545
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,236725,236725,4194304,256,0,0,12,24,305472,0x7fc8d71bf100,0x7fc8d4226580,723659,723659,45227,5789280,65536,541683722,5671557,0,2168477180,17834325091305,17834325038312,17834325732233,17834325775538
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,236725,236725,4194304,256,0,0,12,24,308224,0x7fc8d4b91f80,0x7fc8d42265c0,724066,724066,45236,5792536,65536,554432325,5665808,0,2219470204,17834325786137,17834325732233,17834326425354,17834326470040
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,236725,236725,4194304,256,0,0,8,24,310976,0x7fc8d4b91e00,0x7fc8d4226600,727528,727528,45271,5820232,65536,542132432,5700957,0,2170273016,17834326481840,17834326425354,17834327121354,17834327165433
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,236725,236725,4194304,256,0,0,8,24,313216,0x7fc8d4b91c80,0x7fc8d4226640,1368716,1368716,77974,10949736,65536,1066748922,10813154,0,4268737600,17834327175473,17834327121354,17834328226315,17834328269906
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,236725,236725,4194304,256,0,0,8,24,315968,0x7fc8d4b91b00,0x7fc8d4226680,1369824,1369824,77831,10958600,65536,1076782474,10843115,0,4308871668,17834328288855,17834328226315,17834329311116,17834329374338
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,236725,236725,4194304,256,0,0,12,24,318720,0x7fc8d4b91980,0x7fc8d42266c0,1375124,1375124,78065,11001000,65536,1071881202,10865494,0,4289266868,17834329385588,17834329311116,17834330454158,17834330521830
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,236725,236725,4194304,256,0,0,12,24,321472,0x7fc8d4b91800,0x7fc8d4226700,1371238,1371238,77436,10969912,65536,1077779295,10853697,0,4312857984,17834330533269,17834330454158,17834331595599,17834331662981
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,236725,236725,4194304,256,0,0,8,24,324224,0x7fc8d4b91680,0x7fc8d4226740,1376130,1376130,77713,11009048,65536,1084688254,10886966,0,4340495408,17834331673821,17834331595599,17834332731920,17834332799413
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,236725,236725,4194304,256,0,0,8,24,326464,0x7fc8d71bf500,0x7fc8d4226780,2662336,2662336,142424,21298696,65536,2131580032,21184514,0,8528061380,17834332810773,17834332731920,17834334704242,17834334776354
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,236725,236725,4194304,256,0,0,8,24,329216,0x7fc8d71bf380,0x7fc8d42267c0,2670852,2670852,143342,21366824,65536,2131999864,21233521,0,8529740752,17834334795274,17834334704242,17834336653524,17834336720826
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,236725,236725,4194304,256,0,0,12,24,331968,0x7fc8d71bf200,0x7fc8d4226800,2670556,2670556,142721,21364456,65536,2122324716,21238623,0,8491039852,17834336731875,17834336653524,17834338654006,17834338725046
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,236725,236725,4194304,256,0,0,12,24,334720,0x7fc8d71bf080,0x7fc8d4226840,2669612,2669612,143666,21356904,65536,2113520736,21229473,0,8455823144,17834338736746,17834338654006,17834340663928,17834340732916
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,236725,236725,4194304,256,0,0,8,24,337472,0x7fc8d4b91f00,0x7fc8d4226880,2674293,2674293,143290,21394352,65536,2122181246,21263814,0,8490468052,17834340744566,17834340663928,17834342616730,17834342688017
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,236725,236725,4194304,256,0,0,8,24,0,0x7fc8d4b91d80,0x7fc8d42268c0,5256862,5256862,273842,42054904,65536,4229210368,41928959,0,16918583340,17834342699137,17834342616730,17834346261054,17834346333537
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 236725 236725 33554432 256 0 0 4 32 4160 0x0 0x7fc8d4204280 388118 388118 8813 3104952 524288 245379700 3015215 0 997822932 17834114824366 17833406340767 17834261594719 17834261709089
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 236725 236725 32768 256 0 0 12 24 13888 0x0 0x7fc8d4223f80 34226 34226 30380 273816 512 1732870 162674 0 6944808 17834266862991 17834261594719 17834267004326 17834267009117
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 5 236725 236725 4194304 256 0 0 12 24 14336 0x7fc8d71bf380 0x7fc8d4223fc0 166068 166068 13553 1328552 65536 78338107 1221027 0 315083700 17834267052826 17834267004326 17834267413606 17834267416207
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 236725 236725 4194304 256 0 0 16 24 15040 0x7fc8d71bf200 0x7fc8d4224000 309075 309075 24040 2472608 65536 207974461 2361927 0 833627480 17834267463736 17834267413606 17834267844007 17834267846456
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 11 236725 236725 4194304 256 0 0 16 24 15488 0x7fc8d71bf080 0x7fc8d4224040 312717 312717 25835 2501744 65536 225690218 2387810 0 904488700 17834267887865 17834267844007 17834268268807 17834268271026
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 14 236725 236725 4194304 256 0 0 12 24 15936 0x7fc8d4b91f00 0x7fc8d4224080 165971 165971 14858 1327776 65536 88194064 1222047 0 354501948 17834268313195 17834268268807 17834268603048 17834268605407
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 17 236725 236725 4194304 256 0 0 12 24 16384 0x7fc8d4b91d80 0x7fc8d42240c0 165219 165219 14018 1321760 65536 79047699 1212215 0 317927864 17834268645846 17834268603048 17834268930728 17834268933069
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 20 236725 236725 4194304 256 0 0 12 24 17088 0x7fc8d4b91c00 0x7fc8d4224100 164375 164375 14488 1315008 65536 91462162 1207066 0 367580624 17834268987318 17834268930728 17834269259369 17834269261561
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 236725 236725 4194304 256 0 0 16 24 17792 0x7fc8d4b91a80 0x7fc8d4224140 309703 309703 24852 2477632 65536 219777215 2368747 0 880840144 17834269301450 17834269259369 17834269686569 17834269688940
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 26 236725 236725 4194304 256 0 0 16 24 18496 0x7fc8d4b91900 0x7fc8d4224180 310809 310809 22257 2486480 65536 225212276 2380921 0 902579640 17834269729219 17834269686569 17834270108970 17834270111340
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 29 236725 236725 4194304 256 0 0 16 24 19200 0x7fc8d4b91780 0x7fc8d42241c0 165404 165404 14552 1323240 65536 80450116 1211697 0 323537692 17834270152509 17834270108970 17834270450890 17834270453171
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 32 236725 236725 4194304 256 0 0 16 24 19904 0x7fc8d4b91600 0x7fc8d4224200 165585 165585 14733 1324688 65536 89465853 1214515 0 359591852 17834270494250 17834270450890 17834270782411 17834270784683
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 35 236725 236725 4194304 256 0 0 12 24 20608 0x7fc8d71bf480 0x7fc8d4224240 166366 166366 14862 1330936 65536 91499648 1220000 0 367728464 17834270836062 17834270782411 17834271116011 17834271118425
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 236725 236725 4194304 256 0 0 16 24 21312 0x7fc8d71bf300 0x7fc8d4224280 312319 312319 24507 2498560 65536 233250131 2390649 0 934730296 17834271160384 17834271116011 17834271555532 17834271557414
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 41 236725 236725 4194304 256 0 0 16 24 22016 0x7fc8d71bf180 0x7fc8d42242c0 308649 308649 21619 2469200 65536 224851158 2359776 0 901134076 17834271600213 17834271555532 17834271944652 17834271946314
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 44 236725 236725 4194304 256 0 0 16 24 22720 0x7fc8d71bf000 0x7fc8d4224300 163725 163725 14889 1309808 65536 91154035 1208364 0 366346432 17834271989503 17834271944652 17834272252333 17834272254047
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 47 236725 236725 4194304 256 0 0 12 24 23424 0x7fc8d4b91e80 0x7fc8d4224340 163463 163463 14910 1307712 65536 95401874 1206350 0 383341996 17834272296706 17834272252333 17834272551373 17834272553179
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 50 236725 236725 4194304 256 0 0 12 24 24128 0x7fc8d4b91d00 0x7fc8d4224380 165174 165174 15006 1321400 65536 93783281 1212963 0 376860444 17834272601598 17834272551373 17834272857294 17834272859102
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 236725 236725 4194304 256 0 0 16 24 24832 0x7fc8d4b91b80 0x7fc8d42243c0 308899 308899 24067 2471200 65536 231007192 2364827 0 925758852 17834272905440 17834272857294 17834273249934 17834273251682
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 56 236725 236725 4194304 256 0 0 16 24 25536 0x7fc8d4b91a00 0x7fc8d4224400 309717 309717 24064 2477744 65536 223804023 2368967 0 896947924 17834273293911 17834273249934 17834273638895 17834273640612
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 59 236725 236725 4194304 256 0 0 12 24 26240 0x7fc8d4b91880 0x7fc8d4224440 164390 164390 15085 1315128 65536 93431898 1207629 0 375461760 17834273682421 17834273638895 17834273938095 17834273939705
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 62 236725 236725 4194304 256 0 0 12 24 26944 0x7fc8d4b91700 0x7fc8d4224480 164938 164938 14955 1319512 65536 107825297 1214954 0 433026808 17834273982454 17834273938095 17834274250575 17834274252317
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 65 236725 236725 4194304 256 0 0 12 24 27648 0x7fc8d71bf580 0x7fc8d42244c0 163684 163684 15364 1309480 65536 98572989 1202351 0 396025084 17834274303036 17834274250575 17834274560336 17834274561989
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 236725 236725 4194304 256 0 0 16 24 28608 0x7fc8d71bf400 0x7fc8d4224500 309216 309216 24259 2473736 65536 229456145 2366399 0 919555808 17834274608288 17834274560336 17834274967056 17834274968889
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 71 236725 236725 4194304 256 0 0 16 24 29312 0x7fc8d71bf280 0x7fc8d4224540 306859 306859 22328 2454880 65536 211370468 2340855 0 847210304 17834275011958 17834274967056 17834275359377 17834275361219
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 74 236725 236725 4194304 256 0 0 12 24 30016 0x7fc8d71bf100 0x7fc8d4224580 162796 162796 14816 1302376 65536 90130881 1195582 0 362264460 17834275404238 17834275359377 17834275659857 17834275661632
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 77 236725 236725 4194304 256 0 0 8 24 30976 0x7fc8d4b91f80 0x7fc8d42245c0 164176 164176 15291 1313416 65536 94637530 1203733 0 380286336 17834275703781 17834275659857 17834275964978 17834275966724
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 80 236725 236725 4194304 256 0 0 12 24 31680 0x7fc8d4b91e00 0x7fc8d4224600 164486 164486 15106 1315896 65536 98263113 1206137 0 394774388 17834276016083 17834275964978 17834276271378 17834276273017
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 236725 236725 4194304 256 0 0 16 24 32640 0x7fc8d4b91c80 0x7fc8d4224640 308147 308147 24483 2465184 65536 225461106 2358920 0 903576612 17834276314886 17834276271378 17834276663219 17834276665107
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 86 236725 236725 4194304 256 0 0 12 24 33600 0x7fc8d4b91b00 0x7fc8d4224680 306784 306784 21822 2454280 65536 212758018 2344118 0 852761708 17834276707936 17834276663219 17834277052179 17834277053737
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 89 236725 236725 4194304 256 0 0 12 24 34560 0x7fc8d4b91980 0x7fc8d42246c0 164291 164291 15379 1314336 65536 89768986 1209049 0 360811080 17834277096186 17834277052179 17834277355220 17834277357100
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 92 236725 236725 4194304 256 0 0 8 24 35520 0x7fc8d4b91800 0x7fc8d4224700 166338 166338 16385 1330712 65536 95949531 1221575 0 385529096 17834277398619 17834277355220 17834277660660 17834277662272
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 95 236725 236725 4194304 256 0 0 12 24 36224 0x7fc8d4b91680 0x7fc8d4224740 162847 162847 15060 1302784 65536 97505447 1200686 0 391750292 17834277710811 17834277660660 17834277967700 17834277969325
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 236725 236725 4194304 256 0 0 12 24 37184 0x7fc8d71bf500 0x7fc8d4224780 306864 306864 24043 2454920 65536 228596035 2350247 0 916117520 17834278011794 17834277967700 17834278362581 17834278364495
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 101 236725 236725 4194304 256 0 0 12 24 38144 0x7fc8d71bf380 0x7fc8d42247c0 307280 307280 22874 2458248 65536 219189165 2355632 0 878486864 17834278407854 17834278362581 17834278758901 17834278760595
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 104 236725 236725 4194304 256 0 0 12 24 39104 0x7fc8d71bf200 0x7fc8d4224800 163646 163646 15305 1309176 65536 92738259 1205867 0 372683892 17834278802324 17834278758901 17834279065622 17834279067307
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 107 236725 236725 4194304 256 0 0 8 24 40320 0x7fc8d71bf080 0x7fc8d4224840 162812 162812 15305 1302504 65536 91513072 1197944 0 367781628 17834279109276 17834279065622 17834279368342 17834279369940
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 110 236725 236725 4194304 256 0 0 12 24 41280 0x7fc8d4b91f00 0x7fc8d4224880 163697 163697 14743 1309584 65536 97528475 1204580 0 391844768 17834279418069 17834279368342 17834279676023 17834279677612
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 236725 236725 4194304 256 0 0 12 24 42240 0x7fc8d4b91d80 0x7fc8d42248c0 306817 306817 23855 2454544 65536 224074796 2348571 0 898027912 17834279723881 17834279676023 17834280077463 17834280079182
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 116 236725 236725 4194304 256 0 0 12 24 43200 0x7fc8d4b91c00 0x7fc8d4224900 303088 303088 21848 2424712 65536 215098226 2320002 0 862124472 17834280121761 17834280077463 17834280466424 17834280468003
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 119 236725 236725 4194304 256 0 0 8 24 44160 0x7fc8d4b91a80 0x7fc8d4224940 162715 162715 14617 1301728 65536 100141673 1199730 0 402297404 17834280509402 17834280466424 17834280770264 17834280771805
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 122 236725 236725 4194304 256 0 0 12 24 45376 0x7fc8d4b91900 0x7fc8d4224980 163608 163608 15486 1308872 65536 91950043 1202769 0 369547032 17834280813514 17834280770264 17834281073305 17834281075087
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 125 236725 236725 4194304 256 0 0 12 24 46336 0x7fc8d4b91780 0x7fc8d42249c0 162297 162297 14425 1298384 65536 94382812 1195314 0 379256192 17834281124096 17834281073305 17834281384345 17834281386110
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 236725 236725 4194304 256 0 0 12 24 47552 0x7fc8d4b91600 0x7fc8d4224a00 306664 306664 24786 2453320 65536 225485821 2347896 0 903674356 17834281432619 17834281384345 17834281788666 17834281790470
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 131 236725 236725 4194304 256 0 0 12 24 48512 0x7fc8d71bf480 0x7fc8d4224a40 304669 304669 22899 2437360 65536 214318449 2330625 0 859002420 17834281832979 17834281788666 17834282182906 17834282184770
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 134 236725 236725 4194304 256 0 0 8 24 49472 0x7fc8d71bf300 0x7fc8d4224a80 164032 164032 14631 1312264 65536 88858198 1205412 0 357162416 17834282227459 17834282182906 17834282489146 17834282490792
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 137 236725 236725 4194304 256 0 0 12 24 50688 0x7fc8d71bf180 0x7fc8d4224ac0 163201 163201 15807 1305616 65536 96721866 1200217 0 388622312 17834282533281 17834282489146 17834282793627 17834282795345
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 140 236725 236725 4194304 256 0 0 12 24 51648 0x7fc8d71bf000 0x7fc8d4224b00 161463 161463 14952 1291712 65536 88740842 1187214 0 356698560 17834282844754 17834282793627 17834283100827 17834283102377
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 236725 236725 4194304 256 0 0 12 24 52864 0x7fc8d4b91e80 0x7fc8d4224b40 303745 303745 22710 2429968 65536 201836625 2316360 0 809078756 17834283144876 17834283100827 17834283496508 17834283498217
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 146 236725 236725 4194304 256 0 0 12 24 54080 0x7fc8d4b91d00 0x7fc8d4224b80 301047 301047 21601 2408384 65536 210437020 2303682 0 843478572 17834283539956 17834283496508 17834283892508 17834283894117
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 149 236725 236725 4194304 256 0 0 8 24 55296 0x7fc8d4b91b80 0x7fc8d4224bc0 162428 162428 14903 1299432 65536 88474318 1194758 0 355627208 17834283936316 17834283892508 17834284193629 17834284195250
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 152 236725 236725 4194304 256 0 0 12 24 56768 0x7fc8d4b91a00 0x7fc8d4224c00 163629 163629 16950 1309040 65536 101217691 1198725 0 406601800 17834284237269 17834284193629 17834284495869 17834284497512
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 155 236725 236725 4194304 256 0 0 12 24 57728 0x7fc8d4b91880 0x7fc8d4224c40 163391 163391 14597 1307136 65536 91714320 1200360 0 368585112 17834284546191 17834284495869 17834284805790 17834284807455
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 236725 236725 4194304 256 0 0 12 24 58944 0x7fc8d4b91700 0x7fc8d4224c80 300221 300221 21845 2401776 65536 212739892 2297136 0 852693288 17834284848824 17834284805790 17834285192510 17834285194135
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 161 236725 236725 4194304 256 0 0 12 24 60160 0x7fc8d71bf580 0x7fc8d4224cc0 301545 301545 20283 2412368 65536 205629479 2301410 0 824246612 17834285238724 17834285192510 17834285579871 17834285581566
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 164 236725 236725 4194304 256 0 0 8 24 61376 0x7fc8d71bf400 0x7fc8d4224d00 163132 163132 15667 1305064 65536 95210655 1200481 0 382572852 17834285623274 17834285579871 17834285881151 17834285882808
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 167 236725 236725 4194304 256 0 0 12 24 62848 0x7fc8d71bf280 0x7fc8d4224d40 169065 169065 16375 1352528 65536 97879669 1245323 0 393262852 17834285924347 17834285881151 17834286199391 17834286201270
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 170 236725 236725 4194304 256 0 0 12 24 63808 0x7fc8d71bf100 0x7fc8d4224d80 162702 162702 15058 1301624 65536 92605328 1194089 0 372151888 17834286252129 17834286199391 17834286509952 17834286511732
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 236725 236725 4194304 256 0 0 12 24 65024 0x7fc8d4b91f80 0x7fc8d4224dc0 302903 302903 22609 2423232 65536 215042701 2319421 0 861904624 17834286559221 17834286509952 17834286905152 17834286906793
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 176 236725 236725 4194304 256 0 0 12 24 66240 0x7fc8d4b91e00 0x7fc8d4224e00 299934 299934 20991 2399480 65536 211568934 2288440 0 848010412 17834286949312 17834286905152 17834287299553 17834287301333
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 179 236725 236725 4194304 256 0 0 8 24 67456 0x7fc8d4b91c80 0x7fc8d4224e40 164917 164917 15176 1319344 65536 92895653 1215543 0 373328368 17834287342372 17834287299553 17834287601473 17834287603155
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 182 236725 236725 4194304 256 0 0 12 24 68928 0x7fc8d4b91b00 0x7fc8d4224e80 177796 177796 16578 1422376 65536 104994509 1313234 0 421714412 17834287645334 17834287601473 17834287915234 17834287916868
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 185 236725 236725 4194304 256 0 0 12 24 70144 0x7fc8d4b91980 0x7fc8d4224ec0 160811 160811 14705 1286496 65536 89629786 1181277 0 360258064 17834287965816 17834287915234 17834288223074 17834288224820
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 236725 236725 4194304 256 0 0 12 24 71616 0x7fc8d4b91800 0x7fc8d4224f00 302087 302087 23294 2416704 65536 219851616 2309099 0 881138856 17834288266549 17834288223074 17834288616835 17834288618460
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 191 236725 236725 4194304 256 0 0 12 24 72832 0x7fc8d4b91680 0x7fc8d4224f40 303611 303611 23005 2428896 65536 222137973 2319977 0 890282592 17834288661129 17834288616835 17834289007715 17834289009390
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 194 236725 236725 4194304 256 0 0 8 24 74048 0x7fc8d71bf500 0x7fc8d4224f80 163161 163161 15630 1305296 65536 91235959 1194973 0 366677940 17834289050369 17834289007715 17834289310436 17834289312333
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 197 236725 236725 4194304 256 0 0 12 24 75776 0x7fc8d71bf380 0x7fc8d4224fc0 183219 183219 17101 1465760 65536 109826885 1356619 0 441057852 17834289355122 17834289310436 17834289625796 17834289627395
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 200 236725 236725 4194304 256 0 0 12 24 76992 0x7fc8d71bf200 0x7fc8d4225000 162997 162997 15184 1303984 65536 88666144 1192526 0 356405896 17834289690813 17834289625796 17834289938917 17834289940647
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 236725 236725 4194304 256 0 0 12 24 78464 0x7fc8d71bf080 0x7fc8d4225040 301969 301969 22124 2415760 65536 214738349 2310781 0 860686468 17834289987216 17834289938917 17834290365157 17834290367057
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 206 236725 236725 4194304 256 0 0 12 24 79936 0x7fc8d4b91f00 0x7fc8d4225080 302753 302753 23164 2422032 65536 210241017 2311664 0 842698468 17834290408876 17834290365157 17834290767398 17834290769027
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 209 236725 236725 4194304 256 0 0 8 24 81408 0x7fc8d4b91d80 0x7fc8d42250c0 162581 162581 15730 1300656 65536 93338046 1195432 0 375088052 17834290811296 17834290767398 17834291075238 17834291077019
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 212 236725 236725 4194304 256 0 0 12 24 83136 0x7fc8d4b91c00 0x7fc8d4225100 192516 192516 18259 1540136 65536 115988784 1429576 0 465701400 17834291118798 17834291075238 17834291400198 17834291402111
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 215 236725 236725 4194304 256 0 0 12 24 84352 0x7fc8d4b91a80 0x7fc8d4225140 162889 162889 15404 1303120 65536 96009514 1198118 0 385765176 17834291450040 17834291400198 17834291712679 17834291714363
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 236725 236725 4194304 256 0 0 12 24 85824 0x7fc8d4b91900 0x7fc8d4225180 303894 303894 22975 2431160 65536 220298015 2321393 0 882931436 17834291756322 17834291712679 17834292106279 17834292108014
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 221 236725 236725 4194304 256 0 0 12 24 87296 0x7fc8d4b91780 0x7fc8d42251c0 299823 299823 22016 2398592 65536 213726362 2293812 0 856641476 17834292152253 17834292106279 17834292497480 17834292499214
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 224 236725 236725 4194304 256 0 0 12 24 88768 0x7fc8d4b91600 0x7fc8d4225200 162456 162456 15936 1299656 65536 96275564 1197182 0 386834488 17834292541063 17834292497480 17834292804840 17834292806386
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 227 236725 236725 4194304 256 0 0 12 24 90752 0x7fc8d71bf480 0x7fc8d4225240 203471 203471 18200 1627776 65536 117796929 1513037 0 472938496 17834292847715 17834292804840 17834293142121 17834293143698
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 230 236725 236725 4194304 256 0 0 12 24 91968 0x7fc8d71bf300 0x7fc8d4225280 162292 162292 15476 1298344 65536 93981779 1192840 0 377663004 17834293192997 17834293142121 17834293452041 17834293453861
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 236725 236725 4194304 256 0 0 12 24 93440 0x7fc8d71bf180 0x7fc8d42252c0 301740 301740 23035 2413928 65536 223216311 2308970 0 894601568 17834293501559 17834293452041 17834293849802 17834293851431
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 236 236725 236725 4194304 256 0 0 12 24 94912 0x7fc8d71bf000 0x7fc8d4225300 299586 299586 21971 2396696 65536 212866702 2295181 0 853196760 17834293895900 17834293849802 17834294243242 17834294245081
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 239 236725 236725 4194304 256 0 0 12 24 96384 0x7fc8d4b91e80 0x7fc8d4225340 162618 162618 15249 1300952 65536 98466108 1197652 0 395598028 17834294286870 17834294243242 17834294553963 17834294555623
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 242 236725 236725 4194304 256 0 0 12 24 98368 0x7fc8d4b91d00 0x7fc8d4225380 211130 211130 19059 1689048 65536 139997082 1578277 0 561732788 17834294597952 17834294553963 17834294888843 17834294890575
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 245 236725 236725 4194304 256 0 0 12 24 99584 0x7fc8d4b91b80 0x7fc8d42253c0 162454 162454 15664 1299640 65536 95675469 1195184 0 384430776 17834294938784 17834294888843 17834295197484 17834295199077
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 236725 236725 4194304 256 0 0 12 24 101312 0x7fc8d4b91a00 0x7fc8d4225400 298352 298352 22850 2386824 65536 218183439 2281773 0 874465752 17834295239986 17834295197484 17834295591724 17834295593397
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 251 236725 236725 4194304 256 0 0 12 24 102784 0x7fc8d4b91880 0x7fc8d4225440 299448 299448 22428 2395592 65536 208003050 2290833 0 833743560 17834295635696 17834295591724 17834295985005 17834295986638
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 254 236725 236725 4194304 256 0 0 12 24 104256 0x7fc8d4b91700 0x7fc8d4225480 161836 161836 15933 1294696 65536 98449694 1189411 0 395538516 17834296029047 17834295985005 17834296289485 17834296291350
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 257 236725 236725 4194304 256 0 0 12 24 106240 0x7fc8d71bf580 0x7fc8d42254c0 220777 220777 19935 1766224 65536 126795673 1647432 0 508938936 17834296332469 17834296289485 17834296633806 17834296635512
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 260 236725 236725 4194304 256 0 0 12 24 107712 0x7fc8d71bf400 0x7fc8d4225500 161888 161888 15580 1295112 65536 89962750 1188814 0 361583932 17834296685250 17834296633806 17834296943246 17834296945044
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 236725 236725 4194304 256 0 0 16 24 109440 0x7fc8d71bf280 0x7fc8d4225540 297291 297291 21409 2378336 65536 206695233 2272110 0 828513140 17834296991243 17834296943246 17834297338286 17834297340024
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 266 236725 236725 4194304 256 0 0 16 24 111168 0x7fc8d71bf100 0x7fc8d4225580 301879 301879 23718 2415040 65536 215905745 2301239 0 865353032 17834297383633 17834297338286 17834297732367 17834297734054
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 269 236725 236725 4194304 256 0 0 8 24 112896 0x7fc8d4b91f80 0x7fc8d42255c0 164601 164601 16231 1316816 65536 99833361 1209593 0 401091668 17834297775473 17834297732367 17834298041807 17834298043577
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 272 236725 236725 4194304 256 0 0 12 24 115136 0x7fc8d4b91e00 0x7fc8d4225600 229723 229723 19773 1837792 65536 149136492 1730381 0 598297608 17834298092205 17834298041807 17834298404048 17834298405698
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 275 236725 236725 4194304 256 0 0 12 24 116608 0x7fc8d4b91c80 0x7fc8d4225640 161402 161402 15123 1291224 65536 90921050 1187708 0 365422976 17834298454706 17834298404048 17834298712048 17834298713750
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 236725 236725 4194304 256 0 0 16 24 118336 0x7fc8d4b91b00 0x7fc8d4225680 298204 298204 20792 2385640 65536 197986138 2276652 0 793685384 17834298760439 17834298712048 17834299105809 17834299107450
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 281 236725 236725 4194304 256 0 0 16 24 120064 0x7fc8d4b91980 0x7fc8d42256c0 300595 300595 22494 2404768 65536 215379737 2301175 0 863254268 17834299150079 17834299105809 17834299496689 17834299498340
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 284 236725 236725 4194304 256 0 0 12 24 121792 0x7fc8d4b91800 0x7fc8d4225700 164958 164958 16370 1319672 65536 101616331 1214016 0 408212144 17834299539319 17834299496689 17834299801810 17834299803813
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 287 236725 236725 4194304 256 0 0 12 24 124032 0x7fc8d4b91680 0x7fc8d4225740 240645 240645 20516 1925168 65536 157732556 1813466 0 632674640 17834299844102 17834299801810 17834300163570 17834300165174
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 290 236725 236725 4194304 256 0 0 12 24 125504 0x7fc8d71bf500 0x7fc8d4225780 162126 162126 15768 1297016 65536 98187098 1194453 0 394504012 17834300214413 17834300163570 17834300475571 17834300477146
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 236725 236725 4194304 256 0 0 12 24 127488 0x7fc8d71bf380 0x7fc8d42257c0 302955 302955 20938 2423648 65536 205734897 2308541 0 824672836 17834300523855 17834300475571 17834300872531 17834300874236
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 296 236725 236725 4194304 256 0 0 12 24 129216 0x7fc8d71bf200 0x7fc8d4225800 298432 298432 20729 2387464 65536 202637622 2282225 0 812285600 17834300916045 17834300872531 17834301262772 17834301264587
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 299 236725 236725 4194304 256 0 0 12 24 130944 0x7fc8d71bf080 0x7fc8d4225840 171091 171091 16030 1368736 65536 100852134 1263541 0 405154688 17834301305746 17834301262772 17834301573972 17834301575609
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 302 236725 236725 4194304 256 0 0 12 24 133440 0x7fc8d4b91f00 0x7fc8d4225880 259655 259655 21249 2077248 65536 166745550 1964412 0 668732852 17834301617628 17834301573972 17834301938933 17834301940650
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 305 236725 236725 4194304 256 0 0 12 24 134912 0x7fc8d4b91d80 0x7fc8d42258c0 161815 161815 15866 1294528 65536 95893855 1188755 0 385320516 17834301990029 17834301938933 17834302259413 17834302260992
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 236725 236725 4194304 256 0 0 12 24 136896 0x7fc8d4b91c00 0x7fc8d4225900 296539 296539 20914 2372320 65536 202649671 2263614 0 812338056 17834302302771 17834302259413 17834302655254 17834302657002
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 311 236725 236725 4194304 256 0 0 12 24 138880 0x7fc8d4b91a80 0x7fc8d4225940 297031 297031 21172 2376256 65536 205901482 2265136 0 825344388 17834302698781 17834302655254 17834303044374 17834303046012
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 314 236725 236725 4194304 256 0 0 12 24 140864 0x7fc8d4b91900 0x7fc8d4225980 178771 178771 16738 1430176 65536 106947525 1324370 0 429537856 17834303087531 17834303044374 17834303357495 17834303359055
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 317 236725 236725 4194304 256 0 0 12 24 143616 0x7fc8d4b91780 0x7fc8d42259c0 280909 280909 23093 2247280 65536 190802329 2129530 0 764957064 17834303400584 17834303357495 17834303734775 17834303736465
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 320 236725 236725 4194304 256 0 0 12 24 145344 0x7fc8d4b91600 0x7fc8d4225a00 163019 163019 16590 1304160 65536 102331826 1195152 0 411073356 17834303785814 17834303734775 17834304045176 17834304046747
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 236725 236725 4194304 256 0 0 12 24 147584 0x7fc8d71bf480 0x7fc8d4225a40 296769 296769 21322 2374160 65536 203778534 2261266 0 816877520 17834304088806 17834304045176 17834304437496 17834304439028
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 326 236725 236725 4194304 256 0 0 12 24 149568 0x7fc8d71bf300 0x7fc8d4225a80 296072 296072 20953 2368584 65536 206833922 2259877 0 829074876 17834304479807 17834304437496 17834304828857 17834304830788
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 329 236725 236725 4194304 256 0 0 12 24 151552 0x7fc8d71bf180 0x7fc8d4225ac0 186912 186912 17450 1495304 65536 103138691 1380354 0 414306260 17834304870297 17834304828857 17834305160377 17834305162140
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 332 236725 236725 4194304 256 0 0 12 24 154304 0x7fc8d71bf000 0x7fc8d4225b00 300476 300476 23558 2403816 65536 195767935 2289652 0 784828060 17834305202979 17834305160377 17834305553338 17834305555040
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 335 236725 236725 4194304 256 0 0 12 24 156288 0x7fc8d4b91e80 0x7fc8d4225b40 171069 171069 16766 1368560 65536 101300694 1266522 0 406947060 17834305604099 17834305553338 17834305872538 17834305874242
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 236725 236725 4194304 256 0 0 12 24 158784 0x7fc8d4b91d00 0x7fc8d4225b80 299366 299366 19246 2394936 65536 164222368 2269854 0 658639616 17834305915891 17834305872538 17834306266619 17834306268682
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 341 236725 236725 4194304 256 0 0 12 24 161024 0x7fc8d4b91b80 0x7fc8d4225bc0 297382 297382 20708 2379064 65536 191601847 2264334 0 768152064 17834306309591 17834306266619 17834306661499 17834306663382
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 344 236725 236725 4194304 256 0 0 12 24 163264 0x7fc8d4b91a00 0x7fc8d4225c00 207412 207412 19074 1659304 65536 123377617 1541710 0 495275328 17834306703341 17834306661499 17834306993019 17834306994584
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 347 236725 236725 4194304 256 0 0 12 24 166528 0x7fc8d4b91880 0x7fc8d4225c40 341044 341044 25539 2728360 65536 230738852 2613176 0 924716048 17834307035523 17834306993019 17834307411260 17834307459113
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 350 236725 236725 4194304 256 0 0 12 24 168512 0x7fc8d4b91700 0x7fc8d4225c80 184919 184919 18033 1479360 65536 115675289 1368223 0 464448212 17834307478252 17834307411260 17834307767581 17834307769255
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 236725 236725 4194304 256 0 0 12 24 171264 0x7fc8d71bf580 0x7fc8d4225cc0 298024 298024 21863 2384200 65536 158606979 2238111 0 636177212 17834307811134 17834307767581 17834308161181 17834308162815
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 356 236725 236725 4194304 256 0 0 12 24 173760 0x7fc8d71bf400 0x7fc8d4225d00 297180 297180 20530 2377448 65536 184505727 2259504 0 739772484 17834308205604 17834308161181 17834308556062 17834308557885
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 359 236725 236725 4194304 256 0 0 12 24 176256 0x7fc8d71bf280 0x7fc8d4225d40 224815 224815 19630 1798528 65536 145776401 1689205 0 584851028 17834308598954 17834308556062 17834308900702 17834308902377
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 362 236725 236725 4194304 256 0 0 12 24 179776 0x7fc8d71bf100 0x7fc8d4225d80 381869 381869 27926 3054960 65536 257070858 2936653 0 1030042636 17834308943066 17834308900702 17834309347263 17834309366235
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 365 236725 236725 4194304 256 0 0 12 24 182272 0x7fc8d4b91f80 0x7fc8d4225dc0 212815 212815 19513 1702528 65536 122464861 1583033 0 491617708 17834309397585 17834309347263 17834309686303 17834309687957
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 236725 236725 4194304 256 0 0 12 24 185536 0x7fc8d4b91e00 0x7fc8d4225e00 310102 310102 24097 2480824 65536 185464783 2345934 0 743628116 17834309728316 17834309686303 17834310090304 17834310096947
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 371 236725 236725 4194304 256 0 0 12 24 188544 0x7fc8d4b91c80 0x7fc8d4225e40 311821 311821 20978 2494576 65536 179673646 2366407 0 720457404 17834310132456 17834310090304 17834310509824 17834310531006
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 374 236725 236725 4194304 256 0 0 12 24 191552 0x7fc8d4b91b00 0x7fc8d4225e80 266016 266016 21765 2128136 65536 177645979 2018546 0 712343952 17834310551946 17834310509824 17834310879745 17834310881678
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 377 236725 236725 4194304 256 0 0 12 24 195840 0x7fc8d4b91980 0x7fc8d4225ec0 462230 462230 31445 3697848 65536 327814997 3582185 0 1313021200 17834310921557 17834310879745 17834311373345 17834311392615
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 380 236725 236725 4194304 256 0 0 12 24 198592 0x7fc8d4b91800 0x7fc8d4225f00 243299 243299 20537 1946400 65536 168632596 1836482 0 676289424 17834311423864 17834311373345 17834311732706 17834311734556
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 236725 236725 4194304 256 0 0 12 24 202368 0x7fc8d4b91680 0x7fc8d4225f40 334675 334675 23818 2677408 65536 199877609 2554723 0 801277260 17834311774095 17834311732706 17834312160866 17834312179645
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 386 236725 236725 4194304 256 0 0 12 24 205888 0x7fc8d71bf500 0x7fc8d4225f80 333944 333944 23247 2671560 65536 207389401 2543268 0 831339332 17834312203145 17834312160866 17834312584067 17834312601845
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 389 236725 236725 4194304 256 0 0 12 24 209408 0x7fc8d71bf380 0x7fc8d4225fc0 307785 307785 23645 2462288 65536 204659723 2351204 0 820405932 17834312625324 17834312584067 17834312985508 17834312987395
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 392 236725 236725 4194304 256 0 0 12 24 214464 0x7fc8d71bf200 0x7fc8d4226000 543831 543831 36446 4350656 65536 400108703 4228041 0 1602203616 17834313028704 17834312985508 17834313528868 17834313545371
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 395 236725 236725 4194304 256 0 0 12 24 217728 0x7fc8d71bf080 0x7fc8d4226040 272076 272076 22079 2176616 65536 195969289 2069235 0 785630088 17834313580611 17834313528868 17834313907589 17834313909332
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 236725 236725 4194304 256 0 0 12 24 222016 0x7fc8d4b91f00 0x7fc8d4226080 366676 366676 27448 2933416 65536 245183051 2817157 0 982512760 17834313950611 17834313907589 17834314357029 17834314375181
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 401 236725 236725 4194304 256 0 0 12 24 226048 0x7fc8d4b91d80 0x7fc8d42260c0 364698 364698 28121 2917592 65536 255642502 2806900 0 1024333444 17834314399810 17834314357029 17834314802630 17834314845409
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 404 236725 236725 4194304 256 0 0 12 24 230080 0x7fc8d4b91c00 0x7fc8d4226100 347899 347899 25794 2783200 65536 242487603 2672104 0 971720320 17834314855839 17834314802630 17834315245191 17834315287608
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 407 236725 236725 4194304 256 0 0 12 24 235904 0x7fc8d4b91a80 0x7fc8d4226140 625481 625481 40686 5003856 65536 460031137 4879068 0 1841894612 17834315298628 17834315245191 17834315876071 17834315918383
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 410 236725 236725 4194304 256 0 0 12 24 239424 0x7fc8d4b91900 0x7fc8d4226180 302927 302927 23596 2423424 65536 213261601 2312174 0 854813768 17834315937612 17834315876071 17834316297832 17834316299403
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 236725 236725 4194304 256 0 0 12 24 244224 0x7fc8d4b91780 0x7fc8d42261c0 399075 399075 27608 3192608 65536 264195773 3080075 0 1058569392 17834316340782 17834316297832 17834316759753 17834316801851
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 416 236725 236725 4194304 256 0 0 12 24 248768 0x7fc8d4b91600 0x7fc8d4226200 392130 392130 27681 3137048 65536 289347031 3022706 0 1159165792 17834316812020 17834316759753 17834317239753 17834317281259
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 419 236725 236725 4194304 256 0 0 12 24 253312 0x7fc8d71bf480 0x7fc8d4226240 387952 387952 27807 3103624 65536 280753329 2989110 0 1124778064 17834317291418 17834317239753 17834317709354 17834317727518
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 422 236725 236725 4194304 256 0 0 8 24 255552 0x7fc8d71bf300 0x7fc8d4226280 719930 719930 44876 5759448 65536 543357386 5636111 0 2175169880 17834317752167 17834317709354 17834318374795 17834318418700
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 425 236725 236725 4194304 256 0 0 12 24 259840 0x7fc8d71bf180 0x7fc8d42262c0 364824 364824 27411 2918600 65536 263017562 2801039 0 1053835448 17834318438150 17834318374795 17834318836235 17834318879929
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 236725 236725 4194304 256 0 0 12 24 265664 0x7fc8d71bf000 0x7fc8d4226300 471292 471292 32403 3770344 65536 351197243 3653322 0 1406578836 17834318891029 17834318836235 17834319369036 17834319411026
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 431 236725 236725 4194304 256 0 0 12 24 271232 0x7fc8d4b91e80 0x7fc8d4226340 474138 474138 32968 3793112 65536 349572599 3680200 0 1400078536 17834319421405 17834319369036 17834319910157 17834319951892
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 434 236725 236725 4194304 256 0 0 8 24 273216 0x7fc8d4b91d00 0x7fc8d4226380 483314 483314 33001 3866520 65536 352783080 3753336 0 1412873680 17834319962552 17834319910157 17834320437198 17834320479809
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 437 236725 236725 4194304 256 0 0 8 24 275712 0x7fc8d4b91b80 0x7fc8d42263c0 880138 880138 52986 7041112 65536 675410808 6929733 0 2703384488 17834320490389 17834320437198 17834321229839 17834321272819
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 440 236725 236725 4194304 256 0 0 12 24 280768 0x7fc8d4b91a00 0x7fc8d4226400 425881 425881 29669 3407056 65536 318126163 3299396 0 1274275000 17834321292269 17834321229839 17834321724559 17834321742908
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 236725 236725 4194304 256 0 0 12 24 287616 0x7fc8d4b91880 0x7fc8d4226440 552000 552000 35408 4416008 65536 405168085 4305890 0 1622465864 17834321767237 17834321724559 17834322289360 17834322335643
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 446 236725 236725 4194304 256 0 0 12 24 294208 0x7fc8d4b91700 0x7fc8d4226480 551581 551581 36057 4412656 65536 409721582 4298465 0 1640670012 17834322347203 17834322289360 17834322879601 17834322924048
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 449 236725 236725 4194304 256 0 0 8 24 296960 0x7fc8d71bf580 0x7fc8d42264c0 563270 563270 36733 4506168 65536 422198219 4392694 0 1690538260 17834322935358 17834322879601 17834323460242 17834323501854
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 452 236725 236725 4194304 256 0 0 8 24 299968 0x7fc8d71bf400 0x7fc8d4226500 1041630 1041630 61508 8333048 65536 797586758 8218915 0 3192089132 17834323512054 17834323460072 17834324354792 17834324401882
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 455 236725 236725 4194304 256 0 0 8 24 302720 0x7fc8d71bf280 0x7fc8d4226540 721638 721638 44565 5773112 65536 538243078 5659185 0 2154714336 17834324420811 17834324354792 17834325038312 17834325080545
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 236725 236725 4194304 256 0 0 12 24 305472 0x7fc8d71bf100 0x7fc8d4226580 723659 723659 45227 5789280 65536 541683722 5671557 0 2168477180 17834325091305 17834325038312 17834325732233 17834325775538
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 461 236725 236725 4194304 256 0 0 12 24 308224 0x7fc8d4b91f80 0x7fc8d42265c0 724066 724066 45236 5792536 65536 554432325 5665808 0 2219470204 17834325786137 17834325732233 17834326425354 17834326470040
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 464 236725 236725 4194304 256 0 0 8 24 310976 0x7fc8d4b91e00 0x7fc8d4226600 727528 727528 45271 5820232 65536 542132432 5700957 0 2170273016 17834326481840 17834326425354 17834327121354 17834327165433
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 467 236725 236725 4194304 256 0 0 8 24 313216 0x7fc8d4b91c80 0x7fc8d4226640 1368716 1368716 77974 10949736 65536 1066748922 10813154 0 4268737600 17834327175473 17834327121354 17834328226315 17834328269906
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 470 236725 236725 4194304 256 0 0 8 24 315968 0x7fc8d4b91b00 0x7fc8d4226680 1369824 1369824 77831 10958600 65536 1076782474 10843115 0 4308871668 17834328288855 17834328226315 17834329311116 17834329374338
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 236725 236725 4194304 256 0 0 12 24 318720 0x7fc8d4b91980 0x7fc8d42266c0 1375124 1375124 78065 11001000 65536 1071881202 10865494 0 4289266868 17834329385588 17834329311116 17834330454158 17834330521830
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 476 236725 236725 4194304 256 0 0 12 24 321472 0x7fc8d4b91800 0x7fc8d4226700 1371238 1371238 77436 10969912 65536 1077779295 10853697 0 4312857984 17834330533269 17834330454158 17834331595599 17834331662981
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 479 236725 236725 4194304 256 0 0 8 24 324224 0x7fc8d4b91680 0x7fc8d4226740 1376130 1376130 77713 11009048 65536 1084688254 10886966 0 4340495408 17834331673821 17834331595599 17834332731920 17834332799413
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 482 236725 236725 4194304 256 0 0 8 24 326464 0x7fc8d71bf500 0x7fc8d4226780 2662336 2662336 142424 21298696 65536 2131580032 21184514 0 8528061380 17834332810773 17834332731920 17834334704242 17834334776354
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 485 236725 236725 4194304 256 0 0 8 24 329216 0x7fc8d71bf380 0x7fc8d42267c0 2670852 2670852 143342 21366824 65536 2131999864 21233521 0 8529740752 17834334795274 17834334704242 17834336653524 17834336720826
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 236725 236725 4194304 256 0 0 12 24 331968 0x7fc8d71bf200 0x7fc8d4226800 2670556 2670556 142721 21364456 65536 2122324716 21238623 0 8491039852 17834336731875 17834336653524 17834338654006 17834338725046
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 491 236725 236725 4194304 256 0 0 12 24 334720 0x7fc8d71bf080 0x7fc8d4226840 2669612 2669612 143666 21356904 65536 2113520736 21229473 0 8455823144 17834338736746 17834338654006 17834340663928 17834340732916
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 494 236725 236725 4194304 256 0 0 8 24 337472 0x7fc8d4b91f00 0x7fc8d4226880 2674293 2674293 143290 21394352 65536 2122181246 21263814 0 8490468052 17834340744566 17834340663928 17834342616730 17834342688017
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 497 236725 236725 4194304 256 0 0 8 24 0 0x7fc8d4b91d80 0x7fc8d42268c0 5256862 5256862 273842 42054904 65536 4229210368 41928959 0 16918583340 17834342699137 17834342616730 17834346261054 17834346333537
@@ -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]",1,3357122.0,3357122.0,3357122.0,7.840630919671416
"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",1,1724001.0,1724001.0,1724001.0,4.026441560999106
"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",1,1714881.0,1714881.0,1714881.0,4.005141604075466
"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",1,1696801.0,1696801.0,1696801.0,3.9629153736829874
"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",1,1672801.0,1672801.0,1672801.0,3.906862855462883
"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",1,1664801.0,1664801.0,1664801.0,3.888178682722848
"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",1,885601.0,885601.0,885601.0,2.0683402578434524
"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",1,879680.0,879680.0,879680.0,2.0545116344942342
"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",1,868961.0,868961.0,868961.0,2.02947717854418
"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",1,859681.0,859681.0,859681.0,2.0078035381657395
1 Kernel_Name Count Sum(ns) Mean(ns) Median(ns) Pct
2 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 1 3357122.0 3357122.0 3357122.0 7.840630919671416
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 1724001.0 1724001.0 1724001.0 4.026441560999106
4 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 1 1714881.0 1714881.0 1714881.0 4.005141604075466
5 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 1 1696801.0 1696801.0 1696801.0 3.9629153736829874
6 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 1 1672801.0 1672801.0 1672801.0 3.906862855462883
7 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 1 1664801.0 1664801.0 1664801.0 3.888178682722848
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 885601.0 885601.0 885601.0 2.0683402578434524
9 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 1 879680.0 879680.0 879680.0 2.0545116344942342
10 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 1 868961.0 868961.0 868961.0 2.02947717854418
11 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 1 859681.0 859681.0 859681.0 2.0078035381657395
@@ -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
invdev
06fa5f860366
AMD EPYC 7282 16-Core Processor
Ubuntu 20.04.5 LTS
5.11.0-27-generic
5.1.3-66
Wed Sep 28 20:50:32 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 invdev
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 20:50:32 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,32.86522814467785
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 32.86522814467785
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),0.7041533174396638,0.02534724389619167,1.15944860531231,Instr/cycle
IPC (Issue),1.0,1.0,1.0,Instr/cycle
SALU Util,2.625564540636618,0.029705405919730424,27.217319335633324,Pct
VALU Util,58.3677767471036,0.7574878509531259,98.94796544288582,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) 0.7041533174396638 0.02534724389619167 1.15944860531231 Instr/cycle
3 IPC (Issue) 1.0 1.0 1.0 Instr/cycle
4 SALU Util 2.625564540636618 0.029705405919730424 27.217319335633324 Pct
5 VALU Util 58.3677767471036 0.7574878509531259 98.94796544288582 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,18296.269474052384,1894.2776184082031,258229.23516845703,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 18296.269474052384 1894.2776184082031 258229.23516845703 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,27.441870036596768
Cache Hit,99.56538959749767
1 Metric Value
2 Bandwidth 27.441870036596768
3 Cache Hit 99.56538959749767
@@ -0,0 +1,6 @@
Metric,Mean,Min,Max,Unit
Req,127.76646706586827,9.0,1835.0,Req per wave
Hits,127.5332046782899,8.993011474609375,1834.9175720214844,Hits per wave
Misses - Non Duplicated,0.0017574104720247006,0.0,0.109375,Misses per wave
Misses - Duplicated,0.23150497710633422,0.00677490234375,3.79296875,Misses per wave
Cache Hit,99.56538959749767,75.6103515625,99.99550801206999,Pct
1 Metric Mean Min Max Unit
2 Req 127.76646706586827 9.0 1835.0 Req per wave
3 Hits 127.5332046782899 8.993011474609375 1834.9175720214844 Hits per wave
4 Misses - Non Duplicated 0.0017574104720247006 0.0 0.109375 Misses per wave
5 Misses - Duplicated 0.23150497710633422 0.00677490234375 3.79296875 Misses per wave
6 Cache Hit 99.56538959749767 75.6103515625 99.99550801206999 Pct
@@ -0,0 +1,3 @@
Metric,Value
Bandwidth,0.9345053588728524
Cache Hit,97.79806879466166
1 Metric Value
2 Bandwidth 0.9345053588728524
3 Cache Hit 97.79806879466166
@@ -0,0 +1,13 @@
Metric,Mean,Min,Max,Unit
Req,1.8023952095808384,1.0,7.0,Req per wave
Hits,1.770159293077663,0.0,6.987329483032227,Req per wave
Misses - Non Duplicated,0.001501757227732036,0.00042724609375,0.109375,Req per wave
Misses- Duplicated,0.030734159275443255,0.012243270874023438,0.890625,Req per wave
Cache Hit,97.79806879466166,0.0,99.8189926147461,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 1.770159293077663 0.0 6.987329483032227 Req per wave
4 Misses - Non Duplicated 0.001501757227732036 0.00042724609375 0.109375 Req per wave
5 Misses- Duplicated 0.030734159275443255 0.012243270874023438 0.890625 Req per wave
6 Cache Hit 97.79806879466166 0.0 99.8189926147461 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,60.05179215393539,0.9559106795575751,91.38774974744675,Pct
TC2TA Addr Stall,39.00120735349709,0.018892582078970366,71.91598141411671,Pct
TC2TA Data Stall,0.3245565066341392,0.0,54.20093660790125,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 60.05179215393539 0.9559106795575751 91.38774974744675 Pct
3 TC2TA Addr Stall 39.00120735349709 0.018892582078970366 71.91598141411671 Pct
4 TC2TA Data Stall 0.3245565066341392 0.0 54.20093660790125 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,79.08056398970129,4.481455007913706,95.2557378605352,Pct
TC2TD Stall,63.61922366802417,3.9358792568078758,93.87501248382047,Pct
SPI2TD Stall,0.007817740810349489,0.0,0.01905204047427641,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 79.08056398970129 4.481455007913706 95.2557378605352 Pct
3 TC2TD Stall 63.61922366802417 3.9358792568078758 93.87501248382047 Pct
4 SPI2TD Stall 0.007817740810349489 0.0 0.01905204047427641 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,83.77291675765915
Cache BW,3.789330348599962
Cache Hit,20.35928143712575
1 Metric Value
2 Buffer Coalescing 69.91017964071857
3 Cache Util 83.77291675765915
4 Cache BW 3.789330348599962
5 Cache Hit 20.35928143712575
@@ -0,0 +1,6 @@
Metric,Mean,Min,Max,unit
Stalled on L2 Data,65.78450692680276,4.608646068082825,90.71647990838945,Pct
Stalled on L2 Req,2.003597890399542,0.0,10.79597118002572,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 65.78450692680276 4.608646068082825 90.71647990838945 Pct
3 Stalled on L2 Req 2.003597890399542 0.0 10.79597118002572 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,1267.9031301258567,437.29411125183105,1929.5430164337158,Cycles
L1-L2 Read Latency,780.3639466432204,375.36071968078613,1135.0321774482727,Cycles
L1-L2 Write Latency,354.663063287735,354.663063287735,354.663063287735,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 1267.9031301258567 437.29411125183105 1929.5430164337158 Cycles
14 L1-L2 Read Latency 780.3639466432204 375.36071968078613 1135.0321774482727 Cycles
15 L1-L2 Write Latency 354.663063287735 354.663063287735 354.663063287735 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,97.72526118569745,93.017578125,98.4992504119873,Pct
Hits,68.48541632098352,15.721416473388672,125.9581298828125, per wave
Misses (Translation),0.1391296158293764,0.025325775146484375,0.203125, 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 97.72526118569745 93.017578125 98.4992504119873 Pct
4 Hits 68.48541632098352 15.721416473388672 125.9581298828125 per wave
5 Misses (Translation) 0.1391296158293764 0.025325775146484375 0.203125 per wave
6 Misses (Permission) 0.0 0.0 0.0 per wave
@@ -0,0 +1,5 @@
Metric,Value,Unit
L2 Util,91.00959571640085,Pct
Cache Hit,3.855530631367665,Pct
L2-EA Rd BW,1157.2645255860773,Gb/s
L2-EA Wr BW,6.60164530751581,Gb/s
1 Metric Value Unit
2 L2 Util 91.00959571640085 Pct
3 Cache Hit 3.855530631367665 Pct
4 L2-EA Rd BW 1157.2645255860773 Gb/s
5 L2-EA Wr BW 6.60164530751581 Gb/s
@@ -0,0 +1,16 @@
Metric,Avg,Min,Max,Unit
Read BW,2839.266489725627,0.0379638671875,4096.3310546875,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),0.007365129664986434,0.001155853271484375,0.23046875,Req per wave
Read (64B),44.36353890196292,0.0005931854248046875,64.00517272949219,Req per wave
HBM Read,44.362073224461724,0.000270843505859375,64.00436401367188,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,529.4951240521125,254.47494514318083,2069.379421221865,Cycles
Write Latency,411.7537543887184,411.7537543887184,411.7537543887184,Cycles
Atomic Latency,,,,Cycles
Read Stall,5.662330760293383,0.0,13.131874935902374,Pct
Write Stall,0.09703262601202511,0.0,16.204448544008194,Pct
1 Metric Avg Min Max Unit
2 Read BW 2839.266489725627 0.0379638671875 4096.3310546875 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) 0.007365129664986434 0.001155853271484375 0.23046875 Req per wave
6 Read (64B) 44.36353890196292 0.0005931854248046875 64.00517272949219 Req per wave
7 HBM Read 44.362073224461724 0.000270843505859375 64.00436401367188 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 529.4951240521125 254.47494514318083 2069.379421221865 Cycles
13 Write Latency 411.7537543887184 411.7537543887184 411.7537543887184 Cycles
14 Atomic Latency Cycles
15 Read Stall 5.662330760293383 0.0 13.131874935902374 Pct
16 Write Stall 0.09703262601202511 0.0 16.204448544008194 Pct
@@ -0,0 +1,19 @@
Metric,Avg,Min,Max,Unit
Req,23.467293173967008,8.00143051147461,36.25372314453125,Req per wave
Streaming Req,0.0,0.0,0.0,Req per wave
Read Req,23.444925399597533,0.0014400482177734375,36.297088623046875,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,1.2596518008294935,0.00592041015625,4.2498321533203125,Hits per wave
Misses,22.207641373137513,4.000587463378906,32.0050048828125,Misses per wave
Cache Hit,3.855530631367665,0.03698228377040102,50.00159711889287,Pct
Writeback,0.024407792234135244,0.0004730224609375,3.9375057220458984, per wave
NC Req,6.395899607035928e-07,0.0,0.0001068115234375,Req per wave
UC Req,0.0036939632392928986,0.0005741119384765625,0.1171875,Req per wave
CC Req,0.0,0.0,0.0,Req per wave
RW Req,23.475410233000794,8.000747680664062,36.41102600097656,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),21.16718569772686,0.0,31.000839233398438, per wave
Evict (TC Req),0.0,0.0,0.0, per wave
1 Metric Avg Min Max Unit
2 Req 23.467293173967008 8.00143051147461 36.25372314453125 Req per wave
3 Streaming Req 0.0 0.0 0.0 Req per wave
4 Read Req 23.444925399597533 0.0014400482177734375 36.297088623046875 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 1.2596518008294935 0.00592041015625 4.2498321533203125 Hits per wave
9 Misses 22.207641373137513 4.000587463378906 32.0050048828125 Misses per wave
10 Cache Hit 3.855530631367665 0.03698228377040102 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 0.0036939632392928986 0.0005741119384765625 0.1171875 Req per wave
14 CC Req 0.0 0.0 0.0 Req per wave
15 RW Req 23.475410233000794 8.000747680664062 36.41102600097656 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) 21.16718569772686 0.0 31.000839233398438 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,5.598615634941055,0.0,14.219879150390625,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,0.01764870832066336,0.0,2.9473342895507812,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 5.598615634941055 0.0 14.219879150390625 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 0.01764870832066336 0.0 2.9473342895507812 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
0,3.7895718616332856,0.7330604598907653,0.7315634539027414,0.0014970059880239522,0.0,1.3862423468492702,0.0014736152694610778,0.0,512.4759314846668,402.3611111111111,,0.0,0.0,0.15983362254982222,0.0,0.0,0.0005222480454130801,0.0
1,3.81309749410961,0.7335050662834487,0.7320080602954248,0.0014970059880239522,0.0,1.3862426209592533,0.0014736152694610778,0.0,505.7891423239866,401.80970207093253,,0.0,0.0,0.15946805120228294,0.0,0.0,0.0005297746487006456,0.0
2,3.8014206311458385,0.7331581458360136,0.7316611398479895,0.0014970059880239522,0.0,1.3862421641092815,0.0014736152694610778,0.0,524.8110042761184,402.74786861359127,,0.0,0.0,0.14608993073423465,0.0,0.0,0.0005343659909185536,0.0
3,3.813668343492799,0.7336020212687419,0.7321050152807178,0.0014970059880239522,0.0,1.3865635466432857,0.0014736152694610778,0.0,531.9793122279001,414.2158668154762,,0.0,0.0,0.1706504593352358,0.0,0.0,0.0005589787831563436,0.0
4,3.80242128057692,0.7330687745602545,0.7315717685722305,0.0014970059880239522,0.0,1.3862425524317576,0.0014736152694610778,0.0,523.8541553060674,406.70176866319446,,0.0,0.0,0.1592140426178892,0.0,0.0,0.0005319332648180202,0.0
5,4.174952053188192,0.7357135704177582,0.7342165644297343,0.0014970059880239522,0.0,1.386288854176413,0.0014736152694610778,0.0,539.4153477299254,409.1932353670635,,0.0,0.0,0.2536792869339446,0.0,0.0,0.0005435029903571762,0.0
6,3.8050667150346706,0.7332251999906437,0.7317281940026198,0.0014970059880239522,0.0,1.3862421641092815,0.0014736152694610778,0.0,540.790908896914,403.5860150049603,,0.0,0.0,0.238656689306933,0.0,0.0,0.0005261426914237931,0.0
7,3.799478881192864,0.7332007128321482,0.7317037068441242,0.0014970059880239522,0.0,1.386242072739287,0.0014736152694610778,0.0,564.8097274030364,421.11803230406747,,0.0,0.0,0.28763977781741207,0.0,0.0,0.0005697490212446201,0.0
8,3.8189147898613123,0.7333427931734188,0.7318457871853948,0.0014970059880239522,0.0,1.386242255479276,0.0014736152694610778,0.0,511.34685887259985,406.9412047371032,,0.0,0.0,0.171766178336686,0.0,0.0,0.0005339205621959207,0.0
9,3.788496118174839,0.7330019830943582,0.7315049771063342,0.0014970059880239522,0.0,1.3862418899992983,0.0014736152694610778,0.0,492.4154965185424,406.613040984623,,0.0,0.0,0.1216218685675524,0.0,0.0,0.0005479344350849083,0.0
10,3.8071823933979556,0.7334333408378555,0.7319363348498316,0.0014970059880239522,0.0,1.3862573315283495,0.0014736152694610778,0.0,487.53574152873574,400.2972392733135,,0.0,0.0,0.12753506049424587,0.0,0.0,0.0005264739076534431,0.0
11,3.795518808413885,0.7346767950914577,0.7331797891034337,0.0014970059880239522,0.0,1.3862417986293039,0.0014736152694610778,0.0,506.9065761802826,416.8939732142857,,0.0,0.0,0.15344229144250562,0.0,0.0,0.0005722616960902413,0.0
12,3.8146943763722967,0.733625503357299,0.7321284973692751,0.0014970059880239522,0.0,1.3865326293214353,0.0014736152694610778,0.0,512.3877719039374,412.91038876488096,,0.0,0.0,0.14086557719521894,0.0,0.0,0.0005470664201382391,0.0
13,3.8015251432193624,0.7331317284863866,0.7316347224983627,0.0014970059880239522,0.0,1.3862694037888579,0.0014736152694610778,0.0,3737.876065351138,410.3890128968254,,0.0,0.0,0.128666129654753,0.0,0.0,0.0005516806048547437,0.0
14,4.1865798778999785,0.7358360975802302,0.7343390915922062,0.0014970059880239522,0.0,1.386288854176413,0.0014736152694610778,0.0,492.74812678677654,407.633052765377,,0.0,0.0,0.1674625602311003,0.0,0.0,0.0005461527201943768,0.0
15,3.8143081588416488,0.7332943670763941,0.7317973610883701,0.0014970059880239522,0.0,1.3862430778092254,0.0014736152694610778,0.0,534.0008449829592,422.1587146577381,,0.0,0.0,0.21530324970176834,0.0,0.0,0.0005728441798044536,0.0
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 3.7895718616332856 0.7330604598907653 0.7315634539027414 0.0014970059880239522 0.0 1.3862423468492702 0.0014736152694610778 0.0 512.4759314846668 402.3611111111111 0.0 0.0 0.15983362254982222 0.0 0.0 0.0005222480454130801 0.0
3 1 3.81309749410961 0.7335050662834487 0.7320080602954248 0.0014970059880239522 0.0 1.3862426209592533 0.0014736152694610778 0.0 505.7891423239866 401.80970207093253 0.0 0.0 0.15946805120228294 0.0 0.0 0.0005297746487006456 0.0
4 2 3.8014206311458385 0.7331581458360136 0.7316611398479895 0.0014970059880239522 0.0 1.3862421641092815 0.0014736152694610778 0.0 524.8110042761184 402.74786861359127 0.0 0.0 0.14608993073423465 0.0 0.0 0.0005343659909185536 0.0
5 3 3.813668343492799 0.7336020212687419 0.7321050152807178 0.0014970059880239522 0.0 1.3865635466432857 0.0014736152694610778 0.0 531.9793122279001 414.2158668154762 0.0 0.0 0.1706504593352358 0.0 0.0 0.0005589787831563436 0.0
6 4 3.80242128057692 0.7330687745602545 0.7315717685722305 0.0014970059880239522 0.0 1.3862425524317576 0.0014736152694610778 0.0 523.8541553060674 406.70176866319446 0.0 0.0 0.1592140426178892 0.0 0.0 0.0005319332648180202 0.0
7 5 4.174952053188192 0.7357135704177582 0.7342165644297343 0.0014970059880239522 0.0 1.386288854176413 0.0014736152694610778 0.0 539.4153477299254 409.1932353670635 0.0 0.0 0.2536792869339446 0.0 0.0 0.0005435029903571762 0.0
8 6 3.8050667150346706 0.7332251999906437 0.7317281940026198 0.0014970059880239522 0.0 1.3862421641092815 0.0014736152694610778 0.0 540.790908896914 403.5860150049603 0.0 0.0 0.238656689306933 0.0 0.0 0.0005261426914237931 0.0
9 7 3.799478881192864 0.7332007128321482 0.7317037068441242 0.0014970059880239522 0.0 1.386242072739287 0.0014736152694610778 0.0 564.8097274030364 421.11803230406747 0.0 0.0 0.28763977781741207 0.0 0.0 0.0005697490212446201 0.0
10 8 3.8189147898613123 0.7333427931734188 0.7318457871853948 0.0014970059880239522 0.0 1.386242255479276 0.0014736152694610778 0.0 511.34685887259985 406.9412047371032 0.0 0.0 0.171766178336686 0.0 0.0 0.0005339205621959207 0.0
11 9 3.788496118174839 0.7330019830943582 0.7315049771063342 0.0014970059880239522 0.0 1.3862418899992983 0.0014736152694610778 0.0 492.4154965185424 406.613040984623 0.0 0.0 0.1216218685675524 0.0 0.0 0.0005479344350849083 0.0
12 10 3.8071823933979556 0.7334333408378555 0.7319363348498316 0.0014970059880239522 0.0 1.3862573315283495 0.0014736152694610778 0.0 487.53574152873574 400.2972392733135 0.0 0.0 0.12753506049424587 0.0 0.0 0.0005264739076534431 0.0
13 11 3.795518808413885 0.7346767950914577 0.7331797891034337 0.0014970059880239522 0.0 1.3862417986293039 0.0014736152694610778 0.0 506.9065761802826 416.8939732142857 0.0 0.0 0.15344229144250562 0.0 0.0 0.0005722616960902413 0.0
14 12 3.8146943763722967 0.733625503357299 0.7321284973692751 0.0014970059880239522 0.0 1.3865326293214353 0.0014736152694610778 0.0 512.3877719039374 412.91038876488096 0.0 0.0 0.14086557719521894 0.0 0.0 0.0005470664201382391 0.0
15 13 3.8015251432193624 0.7331317284863866 0.7316347224983627 0.0014970059880239522 0.0 1.3862694037888579 0.0014736152694610778 0.0 3737.876065351138 410.3890128968254 0.0 0.0 0.128666129654753 0.0 0.0 0.0005516806048547437 0.0
16 14 4.1865798778999785 0.7358360975802302 0.7343390915922062 0.0014970059880239522 0.0 1.386288854176413 0.0014736152694610778 0.0 492.74812678677654 407.633052765377 0.0 0.0 0.1674625602311003 0.0 0.0 0.0005461527201943768 0.0
17 15 3.8143081588416488 0.7332943670763941 0.7317973610883701 0.0014970059880239522 0.0 1.3862430778092254 0.0014736152694610778 0.0 534.0008449829592 422.1587146577381 0.0 0.0 0.21530324970176834 0.0 0.0 0.0005728441798044536 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
16,3.779048839080373,0.7329206637993544,0.7314236578113305,0.0014970059880239522,0.0,1.3877529669664577,0.0014736152694610778,0.0,530.4836472166746,402.0967571924603,,0.0,0.0,0.17332613825084206,0.0,0.0,0.00051707421948096,0.0
17,3.81250192565867,0.7333050687869865,0.7318080627989626,0.0014970059880239522,0.0,1.386269221048869,0.0014736152694610778,0.0,526.6401697563895,402.4264400421627,,0.0,0.0,0.18236866111526945,0.0,0.0,0.0005284040987848522,0.0
18,3.791114411268259,0.7330928962387725,0.7315958902507484,0.0014970059880239522,0.0,1.386242072739287,0.0014736152694610778,0.0,520.4840500997606,398.65807136656747,,0.0,0.0,0.18284817084580837,0.0,0.0,0.0005149498671114802,0.0
19,3.773896974831362,0.732896907600814,0.73139990161279,0.0014970059880239522,0.0,1.3862421641092815,0.0014736152694610778,0.0,532.5629319239533,412.99733382936506,,0.0,0.0,0.19374203253648953,0.0,0.0,0.0005571628045179173,0.0
20,3.793954865480005,0.7329970491146613,0.7315000431266373,0.0014970059880239522,0.0,1.386242529589259,0.0014736152694610778,0.0,538.0362658018178,406.76612878224205,,0.0,0.0,0.20529978860638098,0.0,0.0,0.0005269536001239708,0.0
21,3.805516637979221,0.7339424772890742,0.7324454713010502,0.0014970059880239522,0.0,1.387014274825593,0.0014736152694610778,0.0,519.1033097582226,406.85870070684524,,0.0,0.0,0.1407541971720621,0.0,0.0,0.0005328469647618825,0.0
22,3.8106426601128236,0.7331944083025356,0.7316974023145116,0.0014970059880239522,0.0,1.3862422097942786,0.0014736152694610778,0.0,528.2219582086902,402.28794642857144,,0.0,0.0,0.16057938444400263,0.0,0.0,0.0005204434880239521,0.0
23,3.982729248808964,0.7338425870427114,0.7323455810546875,0.0014970059880239522,0.0,1.3862543163185348,0.0014736152694610778,0.0,551.2163861917193,417.9811197916667,,0.0,0.0,0.2803750409337575,0.0,0.0,0.0005604635455651198,0.0
24,3.819108733002833,0.7333260724644461,0.7318290664764222,0.0014970059880239522,0.0,1.3862428036992422,0.0014736152694610778,0.0,510.88124138464656,403.9800502232143,,0.0,0.0,0.19807808699008234,0.0,0.0,0.0005232873790992235,0.0
25,3.7834396266167216,0.7329739325060816,0.7314769265180576,0.0014970059880239522,0.0,1.386242255479276,0.0014736152694610778,0.0,511.42809354420575,406.13596695188494,,0.0,0.0,0.1400604248046875,0.0,0.0,0.0005433202503684038,0.0
26,3.8144076235217534,0.7333539403127339,0.73185693432471,0.0014970059880239522,0.0,1.3862419813692928,0.0014736152694610778,0.0,503.38833792023655,399.1180013020833,,0.0,0.0,0.18065245851071296,0.0,0.0,0.0005220995691722025,0.0
27,3.784694874508206,0.7330117596837575,0.7315147536957335,0.0014970059880239522,0.0,1.386242072739287,0.0014736152694610778,0.0,515.3725696800907,419.3984840029762,,0.0,0.0,0.1545203660062687,0.0,0.0,0.0005763505033390251,0.0
28,3.7725108245216425,0.7328964507508421,0.7313994447628182,0.0014970059880239522,0.0,1.386242072739287,0.0014736152694610778,0.0,516.0649215192589,409.70965091765873,,0.0,0.0,0.166656494140625,0.0,0.0,0.0005382035306827751,0.0
29,3.7965732109831842,0.7330519624812875,0.7315549564932635,0.0014970059880239522,0.0,1.3862424382192646,0.0014736152694610778,0.0,518.5381618368095,412.92992001488096,,0.0,0.0,0.16276669073961453,0.0,0.0,0.0005627592166740738,0.0
30,3.795675756580328,0.7338621402215101,0.7323651342334861,0.0014970059880239522,0.0,1.387037094481691,0.0014736152694610778,0.0,523.190477661644,406.03724888392856,,0.0,0.0,0.1582224040688155,0.0,0.0,0.0005382720581785647,0.0
31,3.8213811798589417,0.7333387728936658,0.7318417669056418,0.0014970059880239522,0.0,1.3862425410105084,0.0014736152694610778,0.0,537.6031362360802,420.5706845238095,,0.0,0.0,0.2330806526595247,0.0,0.0,0.0005717705823704154,0.0
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 3.779048839080373 0.7329206637993544 0.7314236578113305 0.0014970059880239522 0.0 1.3877529669664577 0.0014736152694610778 0.0 530.4836472166746 402.0967571924603 0.0 0.0 0.17332613825084206 0.0 0.0 0.00051707421948096 0.0
3 17 3.81250192565867 0.7333050687869865 0.7318080627989626 0.0014970059880239522 0.0 1.386269221048869 0.0014736152694610778 0.0 526.6401697563895 402.4264400421627 0.0 0.0 0.18236866111526945 0.0 0.0 0.0005284040987848522 0.0
4 18 3.791114411268259 0.7330928962387725 0.7315958902507484 0.0014970059880239522 0.0 1.386242072739287 0.0014736152694610778 0.0 520.4840500997606 398.65807136656747 0.0 0.0 0.18284817084580837 0.0 0.0 0.0005149498671114802 0.0
5 19 3.773896974831362 0.732896907600814 0.73139990161279 0.0014970059880239522 0.0 1.3862421641092815 0.0014736152694610778 0.0 532.5629319239533 412.99733382936506 0.0 0.0 0.19374203253648953 0.0 0.0 0.0005571628045179173 0.0
6 20 3.793954865480005 0.7329970491146613 0.7315000431266373 0.0014970059880239522 0.0 1.386242529589259 0.0014736152694610778 0.0 538.0362658018178 406.76612878224205 0.0 0.0 0.20529978860638098 0.0 0.0 0.0005269536001239708 0.0
7 21 3.805516637979221 0.7339424772890742 0.7324454713010502 0.0014970059880239522 0.0 1.387014274825593 0.0014736152694610778 0.0 519.1033097582226 406.85870070684524 0.0 0.0 0.1407541971720621 0.0 0.0 0.0005328469647618825 0.0
8 22 3.8106426601128236 0.7331944083025356 0.7316974023145116 0.0014970059880239522 0.0 1.3862422097942786 0.0014736152694610778 0.0 528.2219582086902 402.28794642857144 0.0 0.0 0.16057938444400263 0.0 0.0 0.0005204434880239521 0.0
9 23 3.982729248808964 0.7338425870427114 0.7323455810546875 0.0014970059880239522 0.0 1.3862543163185348 0.0014736152694610778 0.0 551.2163861917193 417.9811197916667 0.0 0.0 0.2803750409337575 0.0 0.0 0.0005604635455651198 0.0
10 24 3.819108733002833 0.7333260724644461 0.7318290664764222 0.0014970059880239522 0.0 1.3862428036992422 0.0014736152694610778 0.0 510.88124138464656 403.9800502232143 0.0 0.0 0.19807808699008234 0.0 0.0 0.0005232873790992235 0.0
11 25 3.7834396266167216 0.7329739325060816 0.7314769265180576 0.0014970059880239522 0.0 1.386242255479276 0.0014736152694610778 0.0 511.42809354420575 406.13596695188494 0.0 0.0 0.1400604248046875 0.0 0.0 0.0005433202503684038 0.0
12 26 3.8144076235217534 0.7333539403127339 0.73185693432471 0.0014970059880239522 0.0 1.3862419813692928 0.0014736152694610778 0.0 503.38833792023655 399.1180013020833 0.0 0.0 0.18065245851071296 0.0 0.0 0.0005220995691722025 0.0
13 27 3.784694874508206 0.7330117596837575 0.7315147536957335 0.0014970059880239522 0.0 1.386242072739287 0.0014736152694610778 0.0 515.3725696800907 419.3984840029762 0.0 0.0 0.1545203660062687 0.0 0.0 0.0005763505033390251 0.0
14 28 3.7725108245216425 0.7328964507508421 0.7313994447628182 0.0014970059880239522 0.0 1.386242072739287 0.0014736152694610778 0.0 516.0649215192589 409.70965091765873 0.0 0.0 0.166656494140625 0.0 0.0 0.0005382035306827751 0.0
15 29 3.7965732109831842 0.7330519624812875 0.7315549564932635 0.0014970059880239522 0.0 1.3862424382192646 0.0014736152694610778 0.0 518.5381618368095 412.92992001488096 0.0 0.0 0.16276669073961453 0.0 0.0 0.0005627592166740738 0.0
16 30 3.795675756580328 0.7338621402215101 0.7323651342334861 0.0014970059880239522 0.0 1.387037094481691 0.0014736152694610778 0.0 523.190477661644 406.03724888392856 0.0 0.0 0.1582224040688155 0.0 0.0 0.0005382720581785647 0.0
17 31 3.8213811798589417 0.7333387728936658 0.7318417669056418 0.0014970059880239522 0.0 1.3862425410105084 0.0014736152694610778 0.0 537.6031362360802 420.5706845238095 0.0 0.0 0.2330806526595247 0.0 0.0 0.0005717705823704154 0.0
@@ -0,0 +1,55 @@
Metric,Value,Alias
Wave Life,18296.0,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,1268.0,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,780.0,l2_rd_lat_
L2 Wr Lat,355.0,l2_wr_lat_
Fabric Rd Lat,529.0,fabric_rd_lat_
Fabric Wr Lat,412.0,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,25.0,wave_occ_
1 Metric Value Alias
2 Wave Life 18296.0 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 1268.0 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 780.0 l2_rd_lat_
40 L2 Wr Lat 355.0 l2_wr_lat_
41 Fabric Rd Lat 529.0 fabric_rd_lat_
42 Fabric Wr Lat 412.0 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 25.0 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,7437.532590053177,Gflop,22630.4,32.86522814467785
VALU IOPs,2297.2282209316063,Giop,22630.4,10.15107210182589
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,2.6255645406366175,Pct,100,2.6255645406366175
VALU Util,58.3677767471036,Pct,100,58.3677767471036
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,99.99259859947313,Pct,100,99.99259859947313
Instr Cache BW,1671.978257589768,Gb/s,6092.8,27.441870036596768
Scalar L1D Cache Hit Rate,99.3485588612334,Pct,100,99.3485588612334
Scalar L1D Cache BW,56.93754250540514,Gb/s,6092.8,0.9345053588728522
Vector L1D Cache Hit Rate,20.35928143712575,Pct,100,20.35928143712575
Vector L1D Cache BW,1690.5441090458708,Gb/s,11315.199999999999,14.940470420724962
L2 Cache Hit Rate,3.855530631367665,Pct,100,3.855530631367665
L2-Fabric Read BW,1157.2645255860773,Gb/s,1638.4,70.63382114172835
L2-Fabric Write BW,6.60164530751581,Gb/s,1638.4,0.40293245285130674
L2-Fabric Read Latency,529.4951240521125,Cycles,,
L2-Fabric Write Latency,411.7537543887184,Cycles,,
Wave Occupancy,2621.069420561901,Wavefronts,3328,78.75809556976866
Instr Fetch BW,404.9210622988756,Gb/s,3046.4,13.291789072310781
Instr Fetch Latency,17.174407318683716,Cycles,,
1 Metric Value Unit Peak PoP
2 VALU FLOPs 7437.532590053177 Gflop 22630.4 32.86522814467785
3 VALU IOPs 2297.2282209316063 Giop 22630.4 10.15107210182589
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 2.6255645406366175 Pct 100 2.6255645406366175
11 VALU Util 58.3677767471036 Pct 100 58.3677767471036
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 99.99259859947313 Pct 100 99.99259859947313
18 Instr Cache BW 1671.978257589768 Gb/s 6092.8 27.441870036596768
19 Scalar L1D Cache Hit Rate 99.3485588612334 Pct 100 99.3485588612334
20 Scalar L1D Cache BW 56.93754250540514 Gb/s 6092.8 0.9345053588728522
21 Vector L1D Cache Hit Rate 20.35928143712575 Pct 100 20.35928143712575
22 Vector L1D Cache BW 1690.5441090458708 Gb/s 11315.199999999999 14.940470420724962
23 L2 Cache Hit Rate 3.855530631367665 Pct 100 3.855530631367665
24 L2-Fabric Read BW 1157.2645255860773 Gb/s 1638.4 70.63382114172835
25 L2-Fabric Write BW 6.60164530751581 Gb/s 1638.4 0.40293245285130674
26 L2-Fabric Read Latency 529.4951240521125 Cycles
27 L2-Fabric Write Latency 411.7537543887184 Cycles
28 Wave Occupancy 2621.069420561901 Wavefronts 3328 78.75809556976866
29 Instr Fetch BW 404.9210622988756 Gb/s 3046.4 13.291789072310781
30 Instr Fetch Latency 17.174407318683716 Cycles
@@ -0,0 +1,9 @@
Metric,Avg,Min,Max,Unit
GPU Busy Cycles,416564.371257485,33146,5256591,Cycles/kernel
CPF Busy,416564.371257485,33146,5256591,Cycles/kernel
CPF Util,100.0,100.0,100.0,Pct
CPF Stall,0.0,0.0,0.0,Cycles/kernel
L2Cache Intf Busy,2289.5209580838323,2215,2620,Cycles/kernel
L2Cache Intf Util,0.9447317604196492,0.049094377952175,6.7370153728579405,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 416564.371257485 33146 5256591 Cycles/kernel
3 CPF Busy 416564.371257485 33146 5256591 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 2289.5209580838323 2215 2620 Cycles/kernel
7 L2Cache Intf Util 0.9447317604196492 0.049094377952175 6.7370153728579405 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,416564.371257485,33146,5256591,Cycles
CPC Busy Cycles,416564.371257485,33146,5256591,Cycles
CPC Util,100.0,100.0,100.0,Pct
CPC Stall Cycles,12034.862275449103,8608,45046,Cycles
CPC Stall Rate,4.529452267109492,0.85694321662081,34.854884450612445,Pct
CPC Packet Decoding,28739.94610778443,8834,273884,Cycles
SPI Intf Busy Cycles,385525.7964071856,499,4979307,Cycles
SPI Intf Util,90.56276836329359,1.505460689072588,97.00898538428908,Pct
L2Cache Intf Util,0.12531703421706647,0.005744097416848959,0.8967810903907828,Pct
UTCL1 Stall Cycles,2611.8323353293413,920,3303,Cycles
UTCL2 Intf Busy Cycles,2866.2694610778444,1179,3630,Cycles
UTCL2 Intf Util,1.1625714386293555,0.05326591012200729,3.980326077056198,Pct
1 Metric Avg Min Max Unit
2 GPU Busy Cycles 416564.371257485 33146 5256591 Cycles
3 CPC Busy Cycles 416564.371257485 33146 5256591 Cycles
4 CPC Util 100.0 100.0 100.0 Pct
5 CPC Stall Cycles 12034.862275449103 8608 45046 Cycles
6 CPC Stall Rate 4.529452267109492 0.85694321662081 34.854884450612445 Pct
7 CPC Packet Decoding 28739.94610778443 8834 273884 Cycles
8 SPI Intf Busy Cycles 385525.7964071856 499 4979307 Cycles
9 SPI Intf Util 90.56276836329359 1.505460689072588 97.00898538428908 Pct
10 L2Cache Intf Util 0.12531703421706647 0.005744097416848959 0.8967810903907828 Pct
11 UTCL1 Stall Cycles 2611.8323353293413 920 3303 Cycles
12 UTCL2 Intf Busy Cycles 2866.2694610778444 1179 3630 Cycles
13 UTCL2 Intf Util 1.1625714386293555 0.05326591012200729 3.980326077056198 Pct

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