Remove old workloads

Signed-off-by: coleramos425 <colramos@amd.com>


[ROCm/rocprofiler-compute commit: 73f18d20f5]
This commit is contained in:
coleramos425
2024-05-31 17:29:38 +00:00
committed by Cole Ramos
parent ebad309264
commit b046f69ce4
8758 changed files with 0 additions and 242259 deletions
@@ -1,168 +0,0 @@
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",0,0,0,899514,899519,33554432,256,0,0,8,32,6464,0x0,0x7f1fa6004180,503617,503617,524288,6291456,791394,101370956,12075916066690965,12075916308968012,12075916309291690,12075916309401692
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,899514,899519,32768,256,0,0,24,24,12480,0x0,0x7f1fa6035100,28476,28476,512,8192,8822,1126348,12075916323842971,12075916324149848,12075916324156728,12075916324169417
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,899514,899519,4194304,256,0,0,24,24,12928,0x7f20b1c5c900,0x7f1fa6035140,219068,219068,65536,917504,139994,17933088,12075916324227495,12075916324447606,12075916324581365,12075916324585631
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,899514,899519,4194304,256,0,0,36,24,13632,0x7f20b1c5c800,0x7f1fa6035180,393105,393105,65536,1245184,181426,23255396,12075916324658817,12075916324838964,12075916325089203,12075916325159598
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,899514,899519,4194304,256,0,0,28,24,14080,0x7f20b1c5c700,0x7f1fa60351c0,402548,402548,65536,983040,136384,17499772,12075916325193911,12075916325394161,12075916325650160,12075916325717745
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,899514,899519,4194304,256,0,0,24,24,14528,0x7f20b1c5c600,0x7f1fa6035200,219289,219289,65536,1048576,158095,20172564,12075916325738864,12075916325933198,12075916326067437,12075916326071522
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,899514,899519,4194304,256,0,0,24,24,14976,0x7f20b1c5c500,0x7f1fa6035240,225531,225531,65536,983040,148759,19074732,12075916326124531,12075916326304716,12075916326442795,12075916326446630
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,899514,899519,4194304,256,0,0,24,24,15424,0x7f20b1c5c400,0x7f1fa6035280,211873,211873,65536,1048576,146763,18827604,12075916326531487,12075916326699754,12075916326828713,12075916326832587
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,899514,899519,4194304,256,0,0,28,24,16128,0x7f20b1c5c300,0x7f1fa60352c0,403459,403459,65536,1572864,229538,29378076,12075916326884834,12075916327065192,12075916327322151,12075916327363393
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,899514,899519,4194304,256,0,0,28,24,16832,0x7f20b1c5ca00,0x7f1fa6035300,396817,396817,65536,1179648,158588,20275688,12075916327396525,12075916327583269,12075916327836228,12075916327901603
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,899514,899519,4194304,256,0,0,24,24,17536,0x7f20b1c5c900,0x7f1fa6035340,216604,216604,65536,1114112,161450,20628652,12075916327926390,12075916328115746,12075916328247745,12075916328251784
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,899514,899519,4194304,256,0,0,24,24,18240,0x7f20b1c5c800,0x7f1fa6035380,212169,212169,65536,1114112,158126,20294324,12075916328298631,12075916328484384,12075916328613823,12075916328617795
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,899514,899519,4194304,256,0,0,24,24,18944,0x7f20b1c5c700,0x7f1fa60353c0,222876,222876,65536,1179648,165753,21211448,12075916328683236,12075916328851102,12075916328987741,12075916328991229
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,899514,899519,4194304,256,0,0,28,24,19904,0x7f20b1c5c600,0x7f1fa6035400,396625,396625,65536,1835008,252662,32368796,12075916329044267,12075916329223420,12075916329475099,12075916329541932
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,899514,899519,4194304,256,0,0,28,24,20608,0x7f20b1c5c500,0x7f1fa6035440,396515,396515,65536,1310720,177666,22805040,12075916329568361,12075916329750137,12075916330002936,12075916330069873
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,899514,899519,4194304,256,0,0,24,24,21312,0x7f20b1c5c400,0x7f1fa6035480,212081,212081,65536,1245184,176381,22530196,12075916330094689,12075916330281814,12075916330411414,12075916330415365
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,899514,899519,4194304,256,0,0,24,24,22016,0x7f20b1c5c300,0x7f1fa60354c0,215763,215763,65536,1310720,184051,23580376,12075916330466941,12075916330652532,12075916330783892,12075916330787747
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,899514,899519,4194304,256,0,0,24,24,22720,0x7f20b1c5ca00,0x7f1fa6035500,208889,208889,65536,1310720,180006,23109804,12075916330853309,12075916331023730,12075916331151090,12075916331155330
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,899514,899519,4194304,256,0,0,28,24,23680,0x7f20b1c5c900,0x7f1fa6035540,410787,410787,65536,2097152,313279,40098956,12075916331206976,12075916331390768,12075916331653327,12075916331719870
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,899514,899519,4194304,256,0,0,28,24,24384,0x7f20b1c5c800,0x7f1fa6035580,405705,405705,65536,1441792,197013,25126000,12075916331745708,12075916331929165,12075916332188044,12075916332258360
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,899514,899519,4194304,256,0,0,24,24,25088,0x7f20b1c5c700,0x7f1fa60355c0,224787,224787,65536,1376256,189538,24301748,12075916332283006,12075916332470922,12075916332609002,12075916332612529
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,899514,899519,4194304,256,0,0,24,24,25792,0x7f20b1c5c600,0x7f1fa6035600,207521,207521,65536,1507328,211473,27130856,12075916332665467,12075916332845000,12075916332971400,12075916332975363
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,899514,899519,4194304,256,0,0,24,24,26496,0x7f20b1c5c500,0x7f1fa6035640,210652,210652,65536,1441792,202685,26001552,12075916333041967,12075916333211398,12075916333339878,12075916333343918
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,899514,899519,4194304,256,0,0,28,24,27712,0x7f20b1c5c400,0x7f1fa6035680,402289,402289,65536,2359296,323765,41628452,12075916333395634,12075916333571396,12075916333828355,12075916333896094
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,899514,899519,4194304,256,0,0,28,24,28416,0x7f20b1c5c300,0x7f1fa60356c0,395244,395244,65536,1572864,212217,27072792,12075916333919007,12075916334108673,12075916334360832,12075916334427902
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,899514,899519,4194304,256,0,0,24,24,29120,0x7f20b1c5ca00,0x7f1fa6035700,215849,215849,65536,1507328,209407,26785052,12075916334452218,12075916334645630,12075916334777630,12075916334781209
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,899514,899519,4194304,256,0,0,24,24,30080,0x7f20b1c5c900,0x7f1fa6035740,220868,220868,65536,1703936,235510,30184856,12075916334832665,12075916335007388,12075916335142908,12075916335147049
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,899514,899519,4194304,256,0,0,24,24,30784,0x7f20b1c5c800,0x7f1fa6035780,216849,216849,65536,1572864,213596,27241740,12075916335212480,12075916335380986,12075916335514106,12075916335517958
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,899514,899519,4194304,256,0,0,28,24,32000,0x7f20b1c5c700,0x7f1fa60357c0,398444,398444,65536,2621440,358249,45757280,12075916335569694,12075916335742424,12075916335997623,12075916336064955
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,899514,899519,4194304,256,0,0,28,24,32960,0x7f20b1c5c600,0x7f1fa6035800,389257,389257,65536,1703936,229529,29392720,12075916336090693,12075916336280022,12075916336528340,12075916336594900
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,899514,899519,4194304,256,0,0,24,24,33920,0x7f20b1c5c500,0x7f1fa6035840,207531,207531,65536,1638400,227467,29171912,12075916336619165,12075916336802899,12075916336928978,12075916336933038
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,899514,899519,4194304,256,0,0,24,24,34880,0x7f20b1c5c400,0x7f1fa6035880,218153,218153,65536,1900544,270751,34514900,12075916336984864,12075916337163537,12075916337298096,12075916337301974
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,899514,899519,4194304,256,0,0,24,24,35840,0x7f20b1c5c300,0x7f1fa60358c0,210963,210963,65536,1703936,230379,29483712,12075916337366153,12075916337540175,12075916337668494,12075916337672693
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,899514,899519,4194304,256,0,0,28,24,37312,0x7f20b1c5ca00,0x7f1fa6035900,406273,406273,65536,2883584,388422,49723928,12075916337723217,12075916337902893,12075916338163211,12075916338230710
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,899514,899519,4194304,256,0,0,28,24,38272,0x7f20b1c5c900,0x7f1fa6035940,409180,409180,65536,1835008,243988,31231160,12075916338255426,12075916338441770,12075916338703208,12075916338769852
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,899514,899519,4194304,256,0,0,24,24,39232,0x7f20b1c5c800,0x7f1fa6035980,283945,283945,65536,1769472,276244,35365832,12075916338793385,12075916338977607,12075916339155526,12075916339159556
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,899514,899519,4194304,256,0,0,24,24,40192,0x7f20b1c5c700,0x7f1fa60359c0,216156,216156,65536,2097152,327033,41843432,12075916339217283,12075916339382725,12075916339514884,12075916339518764
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,899514,899519,4194304,256,0,0,24,24,41152,0x7f20b1c5c600,0x7f1fa6035a00,217529,217529,65536,1835008,248404,31855532,12075916339583895,12075916339750563,12075916339883842,12075916339887890
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,899514,899519,4194304,256,0,0,28,24,42624,0x7f20b1c5c500,0x7f1fa6035a40,403555,403555,65536,3145728,431394,55216548,12075916339940207,12075916340115361,12075916340374719,12075916340443452
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,899514,899519,4194304,256,0,0,28,24,43584,0x7f20b1c5c400,0x7f1fa6035a80,396929,396929,65536,1966080,262065,33520048,12075916340467156,12075916340654078,12075916340908316,12075916340975170
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,899514,899519,4194304,256,0,0,24,24,44544,0x7f20b1c5c300,0x7f1fa6035ac0,217732,217732,65536,1900544,285400,36495776,12075916340998463,12075916341193435,12075916341327034,12075916341331102
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,899514,899519,4194304,256,0,0,24,24,45760,0x7f20b1c5ca00,0x7f1fa6035b00,219881,219881,65536,2293760,307023,39409272,12075916341384240,12075916341557913,12075916341693752,12075916341697713
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,899514,899519,4194304,256,0,0,24,24,46720,0x7f20b1c5c900,0x7f1fa6035b40,220396,220396,65536,1966080,296839,37962360,12075916341761812,12075916341928471,12075916342062710,12075916342067059
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,899514,899519,4194304,256,0,0,28,24,48448,0x7f20b1c5c800,0x7f1fa6035b80,417121,417121,65536,3407872,458924,58644720,12075916342119357,12075916342297909,12075916342566067,12075916342632350
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,899514,899519,4194304,256,0,0,28,24,49408,0x7f20b1c5c700,0x7f1fa6035bc0,399452,399452,65536,2097152,276846,35433256,12075916342658749,12075916342843186,12075916343098864,12075916343140284
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,899514,899519,4194304,256,0,0,24,24,50368,0x7f20b1c5c600,0x7f1fa6035c00,217073,217073,65536,2031616,276387,35380428,12075916343176561,12075916343349743,12075916343482542,12075916343486537
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,899514,899519,4194304,256,0,0,24,24,51584,0x7f20b1c5c500,0x7f1fa6035c40,229820,229820,65536,2490368,338179,43217084,12075916343538614,12075916343711181,12075916343853260,12075916343857096
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,899514,899519,4194304,256,0,0,24,24,52544,0x7f20b1c5c400,0x7f1fa6035c80,218857,218857,65536,2097152,309395,39738332,12075916343921656,12075916344091499,12075916344225898,12075916344229969
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,899514,899519,4194304,256,0,0,28,24,54272,0x7f20b1c5c300,0x7f1fa6035cc0,414612,414612,65536,3670016,491598,62976380,12075916344282547,12075916344457417,12075916344723655,12075916344790401
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,899514,899519,4194304,256,0,0,28,24,55488,0x7f20b1c5ca00,0x7f1fa6035d00,409409,409409,65536,2228224,298402,38266784,12075916344813273,12075916344995654,12075916345258052,12075916345326727
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,899514,899519,4194304,256,0,0,24,24,56704,0x7f20b1c5c900,0x7f1fa6035d40,218947,218947,65536,2162688,291271,37281260,12075916345349600,12075916345533411,12075916345668130,12075916345671849
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,899514,899519,4194304,256,0,0,24,24,58176,0x7f20b1c5c800,0x7f1fa6035d80,224089,224089,65536,2686976,383606,49022056,12075916345725518,12075916345888449,12075916346027648,12075916346031547
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,899514,899519,4194304,256,0,0,24,24,59392,0x7f20b1c5c700,0x7f1fa6035dc0,217428,217428,65536,2228224,311071,39831812,12075916346095666,12075916346262207,12075916346395486,12075916346399721
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,899514,899519,4194304,256,0,0,28,24,61376,0x7f20b1c5c600,0x7f1fa6035e00,416393,416393,65536,3932160,535483,68615452,12075916346452680,12075916346625245,12075916346893243,12075916346934004
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,899514,899519,4194304,256,0,0,28,24,62592,0x7f20b1c5c500,0x7f1fa6035e40,410899,410899,65536,2359296,310836,39774492,12075916346962778,12075916347145722,12075916347407161,12075916347473908
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,899514,899519,4194304,256,0,0,24,24,63808,0x7f20b1c5c400,0x7f1fa6035e80,217097,217097,65536,2293760,325336,41670612,12075916347500006,12075916347681079,12075916347814998,12075916347818628
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,899514,899519,4194304,256,0,0,24,24,65280,0x7f20b1c5c300,0x7f1fa6035ec0,228019,228019,65536,2883584,414191,53132544,12075916347870034,12075916348053237,12075916348194356,12075916348198695
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,899514,899519,4194304,256,0,0,24,24,66496,0x7f20b1c5ca00,0x7f1fa6035f00,220449,220449,65536,2359296,347267,44467248,12075916348264477,12075916348429395,12075916348564754,12075916348569023
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,899514,899519,4194304,256,0,0,28,24,68480,0x7f20b1c5c900,0x7f1fa6035f40,417772,417772,65536,4194304,600677,76644864,12075916348621430,12075916348793073,12075916349062352,12075916349131538
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,899514,899519,4194304,256,0,0,28,24,69696,0x7f20b1c5c800,0x7f1fa6035f80,394937,394937,65536,2490368,341347,43644740,12075916349159190,12075916349342510,12075916349596269,12075916349661864
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,899514,899519,4194304,256,0,0,24,24,70912,0x7f20b1c5c700,0x7f1fa6035fc0,218124,218124,65536,2424832,354887,45366088,12075916349687321,12075916349868747,12075916350002986,12075916350006655
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,899514,899519,4194304,256,0,0,24,24,72384,0x7f20b1c5c600,0x7f1fa6036000,224289,224289,65536,3080192,505287,64783864,12075916350059423,12075916350231305,12075916350370504,12075916350374488
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,899514,899519,4194304,256,0,0,24,24,73600,0x7f20b1c5c500,0x7f1fa6036040,227747,227747,65536,2490368,398926,51106732,12075916350438668,12075916350606023,12075916350746342,12075916350750227
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,899514,899519,4194304,256,0,0,28,24,75840,0x7f20b1c5c400,0x7f1fa6036080,421793,421793,65536,4456448,591942,75761828,12075916350803536,12075916350976581,12075916351249220,12075916351316078
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,899514,899519,4194304,256,0,0,28,24,77056,0x7f20b1c5c300,0x7f1fa60360c0,401779,401779,65536,2621440,343098,43913092,12075916351340935,12075916351528578,12075916351786817,12075916351853547
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,899514,899519,4194304,256,0,0,24,24,78272,0x7f20b1c5ca00,0x7f1fa6036100,218513,218513,65536,2555904,375219,48022984,12075916351877131,12075916352066655,12075916352201214,12075916352205381
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,899514,899519,4194304,256,0,0,24,24,80000,0x7f20b1c5c900,0x7f1fa6036140,232340,232340,65536,3276800,483003,61965428,12075916352260013,12075916352427933,12075916352572412,12075916352576360
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,899514,899519,4194304,256,0,0,24,24,81216,0x7f20b1c5c800,0x7f1fa6036180,215697,215697,65536,2621440,375485,47982220,12075916352641121,12075916352801851,12075916352934810,12075916352938784
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,899514,899519,4194304,256,0,0,28,24,83456,0x7f20b1c5c700,0x7f1fa60361c0,416587,416587,65536,4718592,630971,80728640,12075916352991662,12075916353168889,12075916353437848,12075916353488115
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,899514,899519,4194304,256,0,0,28,24,84928,0x7f20b1c5c600,0x7f1fa6036200,401097,401097,65536,2752512,362820,46292548,12075916353512510,12075916353691286,12075916353949525,12075916353971203
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,899514,899519,4194304,256,0,0,24,24,86400,0x7f20b1c5c500,0x7f1fa6036240,223236,223236,65536,2686976,406088,51970384,12075916354022758,12075916354185044,12075916354322163,12075916354326333
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,899514,899519,4194304,256,0,0,24,24,88128,0x7f20b1c5c400,0x7f1fa6036280,243425,243425,65536,3473408,515020,65892028,12075916354379361,12075916354551442,12075916354703441,12075916354707411
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,899514,899519,4194304,256,0,0,24,24,89600,0x7f20b1c5c300,0x7f1fa60362c0,220131,220131,65536,2752512,393213,50328156,12075916354788622,12075916354949839,12075916355085519,12075916355089731
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,899514,899519,4194304,256,0,0,28,24,92096,0x7f20b1c5ca00,0x7f1fa6036300,424113,424113,65536,4980736,666222,85273704,12075916355142480,12075916355319917,12075916355593996,12075916355641527
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,899514,899519,4194304,256,0,0,28,24,93568,0x7f20b1c5c900,0x7f1fa6036340,399571,399571,65536,2883584,396081,50495908,12075916355667686,12075916355848875,12075916356105833,12075916356155041
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,899514,899519,4194304,256,0,0,24,24,95040,0x7f20b1c5c800,0x7f1fa6036380,211953,211953,65536,2818048,407583,52215332,12075916356179557,12075916356363432,12075916356494151,12075916356498179
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,899514,899519,4194304,256,0,0,24,24,96768,0x7f20b1c5c700,0x7f1fa60363c0,251524,251524,65536,3670016,556013,70963600,12075916356550055,12075916356722950,12075916356880069,12075916356884116
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,899514,899519,4194304,256,0,0,24,24,98240,0x7f20b1c5c600,0x7f1fa6036400,225697,225697,65536,2883584,399863,51233460,12075916356948596,12075916357118148,12075916357257187,12075916357261397
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,899514,899519,4194304,256,0,0,28,24,100736,0x7f20b1c5c500,0x7f1fa6036440,417012,417012,65536,5177344,690166,88328624,12075916357308264,12075916357489986,12075916357760064,12075916357807973
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,899514,899519,4194304,256,0,0,28,24,102208,0x7f20b1c5c400,0x7f1fa6036480,393913,393913,65536,3014656,397746,50807912,12075916357830896,12075916358014463,12075916358268061,12075916358316218
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,899514,899519,4194304,256,0,0,24,24,103680,0x7f20b1c5c300,0x7f1fa60364c0,222411,222411,65536,2949120,432036,55230596,12075916358339571,12075916358528380,12075916358665499,12075916358669625
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,899514,899519,4194304,256,0,0,24,24,105664,0x7f20b1c5ca00,0x7f1fa6036500,263417,263417,65536,3866624,557609,71371148,12075916358723445,12075916358893178,12075916359058937,12075916359062785
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,899514,899519,4194304,256,0,0,24,24,107136,0x7f20b1c5c900,0x7f1fa6036540,222891,222891,65536,3014656,426756,54661620,12075916359128307,12075916359293176,12075916359430455,12075916359434766
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,899514,899519,4194304,256,0,0,28,24,109888,0x7f20b1c5c800,0x7f1fa6036580,413465,413465,65536,5439488,721005,92538604,12075916359486382,12075916359658774,12075916359926932,12075916359974830
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,899514,899519,4194304,256,0,0,28,24,111360,0x7f20b1c5c700,0x7f1fa60365c0,401308,401308,65536,3145728,411924,52895648,12075916359997071,12075916360188211,12075916360446449,12075916360496169
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,899514,899519,4194304,256,0,0,24,24,112832,0x7f20b1c5c600,0x7f1fa6036600,218537,218537,65536,3080192,436231,55846648,12075916360518360,12075916360699408,12075916360833967,12075916360838265
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,899514,899519,4194304,256,0,0,24,24,114816,0x7f20b1c5c500,0x7f1fa6036640,275436,275436,65536,4063232,569621,73117460,12075916360890452,12075916361058766,12075916361232045,12075916361235844
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,899514,899519,4194304,256,0,0,24,24,116288,0x7f20b1c5c400,0x7f1fa6036680,220889,220889,65536,3145728,423661,54219680,12075916361301466,12075916361466924,12075916361602923,12075916361607014
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,899514,899519,4194304,256,0,0,28,24,119040,0x7f20b1c5c300,0x7f1fa60366c0,408524,408524,65536,5701632,831172,106683448,12075916361659040,12075916361841322,12075916362105480,12075916362153900
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,899514,899519,4194304,256,0,0,28,24,120768,0x7f20b1c5ca00,0x7f1fa6036700,403265,403265,65536,3276800,430198,54924244,12075916362181231,12075916362364039,12075916362624197,12075916362670981
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,899514,899519,4194304,256,0,0,24,24,122496,0x7f20b1c5c900,0x7f1fa6036740,226364,226364,65536,3211264,475725,60910476,12075916362693403,12075916362875876,12075916363015395,12075916363019559
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,899514,899519,4194304,256,0,0,24,24,124736,0x7f20b1c5c800,0x7f1fa6036780,290337,290337,65536,4259840,638866,80999604,12075916363072146,12075916363250914,12075916363434913,12075916363439128
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,899514,899519,4194304,256,0,0,24,24,126464,0x7f20b1c5c700,0x7f1fa60367c0,224467,224467,65536,3276800,548438,70065800,12075916363503859,12075916363668192,12075916363806751,12075916363811060
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,899514,899519,4194304,256,0,0,20,24,127936,0x7f20b1c5c600,0x7f1fa6036800,410025,410025,65536,7733248,974585,124904944,12075916363864038,12075916364041470,12075916364308028,12075916364357645
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,899514,899519,4194304,256,0,0,28,24,129664,0x7f20b1c5c500,0x7f1fa6036840,407540,407540,65536,3407872,450450,57806308,12075916364381871,12075916364564987,12075916364827065,12075916364874115
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,899514,899519,4194304,256,0,0,24,24,131392,0x7f20b1c5c400,0x7f1fa6036880,218681,218681,65536,3342336,456403,58401020,12075916364897338,12075916365091704,12075916365226743,12075916365231129
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,899514,899519,4194304,256,0,0,24,24,133632,0x7f20b1c5c300,0x7f1fa60368c0,301932,301932,65536,4456448,613290,78155728,12075916365286161,12075916365452662,12075916365644821,12075916365691244
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,899514,899519,4194304,256,0,0,24,24,135360,0x7f20b1c5ca00,0x7f1fa6036900,226121,226121,65536,3538944,554775,71032664,12075916365729225,12075916365891220,12075916366029139,12075916366033450
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,899514,899519,4194304,256,0,0,20,24,136832,0x7f20b1c5c900,0x7f1fa6036940,435307,435307,65536,8978432,1134433,145548104,12075916366088382,12075916366264658,12075916366547856,12075916366595254
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,899514,899519,4194304,256,0,0,28,24,138560,0x7f20b1c5c800,0x7f1fa6036980,398129,398129,65536,3670016,478937,61116896,12075916366617826,12075916366798895,12075916367056333,12075916367104070
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,899514,899519,4194304,256,0,0,24,24,140288,0x7f20b1c5c700,0x7f1fa60369c0,224723,224723,65536,3604480,514050,65858700,12075916367127804,12075916367313292,12075916367451691,12075916367456194
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,899514,899519,4194304,256,0,0,24,24,142784,0x7f20b1c5c600,0x7f1fa6036a00,329409,329409,65536,4849664,739653,94492548,12075916367508020,12075916367679690,12075916367889769,12075916367935926
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,899514,899519,4194304,256,0,0,24,24,144768,0x7f20b1c5c500,0x7f1fa6036a40,220740,220740,65536,3801088,586063,74921436,12075916367973545,12075916368144487,12075916368281127,12075916368285265
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,899514,899519,4194304,256,0,0,20,24,145728,0x7f20b1c5c400,0x7f1fa6036a80,469473,469473,65536,14548992,1827760,234072720,12075916368337582,12075916368513765,12075916368820644,12075916368867587
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,899514,899519,4194304,256,0,0,28,24,147712,0x7f20b1c5c300,0x7f1fa6036ac0,402460,402460,65536,3932160,510983,65618032,12075916368895589,12075916369080322,12075916369340961,12075916369389928
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,899514,899519,4194304,256,0,0,24,24,149696,0x7f20b1c5ca00,0x7f1fa6036b00,220473,220473,65536,3866624,588987,75447212,12075916369414543,12075916369600959,12075916369737119,12075916369741181
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,899514,899519,4194304,256,0,0,24,24,152192,0x7f20b1c5c900,0x7f1fa6036b40,357355,357355,65536,5242880,803092,103036472,12075916369792366,12075916369963677,12075916370191996,12075916370218007
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,899514,899519,4194304,256,0,0,24,24,154176,0x7f20b1c5c800,0x7f1fa6036b80,224977,224977,65536,4063232,601835,77039816,12075916370277167,12075916370444155,12075916370583674,12075916370587674
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,899514,899519,4194304,256,0,0,20,24,155648,0x7f20b1c5c700,0x7f1fa6036bc0,503548,503548,65536,10027008,1260119,161382664,12075916370638478,12075916370810073,12075916371139191,12075916371168062
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,899514,899519,4194304,256,0,0,28,24,157632,0x7f20b1c5c600,0x7f1fa6036c00,389329,389329,65536,4194304,572949,73193228,12075916371211974,12075916371377110,12075916371629428,12075916371654166
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,899514,899519,4194304,256,0,0,24,24,159616,0x7f20b1c5c500,0x7f1fa6036c40,228187,228187,65536,4128768,677745,86778556,12075916371702265,12075916371866166,12075916372007606,12075916372015096
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,899514,899519,4194304,256,0,0,24,24,162368,0x7f20b1c5c400,0x7f1fa6036c80,431697,431697,65536,5636096,770561,98522144,12075916372066873,12075916372242484,12075916372520562,12075916372545332
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,899514,899519,4194304,256,0,0,24,24,164608,0x7f20b1c5c300,0x7f1fa6036cc0,232531,232531,65536,4587520,724524,92754808,12075916372604722,12075916372770801,12075916372914481,12075916372917764
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,899514,899519,4194304,256,0,0,20,24,166336,0x7f20b1c5ca00,0x7f1fa6036d00,573017,573017,65536,11075584,1393059,178236652,12075916372968749,12075916373148240,12075916373524398,12075916373551682
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,899514,899519,4194304,256,0,0,28,24,168576,0x7f20b1c5c900,0x7f1fa6036d40,404451,404451,65536,4718592,648555,83005264,12075916373595504,12075916373756877,12075916374018956,12075916374043586
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,899514,899519,4194304,256,0,0,24,24,170816,0x7f20b1c5c800,0x7f1fa6036d80,228281,228281,65536,4653056,670879,85872492,12075916374095403,12075916374265355,12075916374407274,12075916374410649
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,899514,899519,4194304,256,0,0,24,24,174080,0x7f20b1c5c700,0x7f1fa6036dc0,435292,435292,65536,6422528,921264,116635016,12075916374462375,12075916374637673,12075916374917832,12075916374941215
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,899514,899519,4194304,256,0,0,24,24,176576,0x7f20b1c5c600,0x7f1fa6036e00,224185,224185,65536,5111808,808241,103462896,12075916374999783,12075916375170151,12075916375309670,12075916375313376
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,899514,899519,4194304,256,0,0,20,24,177792,0x7f20b1c5c500,0x7f1fa6036e40,645316,645316,65536,15007744,1879968,240859716,12075916375364301,12075916375536069,12075916375960707,12075916375984564
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,899514,899519,4194304,256,0,0,28,24,180288,0x7f20b1c5c400,0x7f1fa6036e80,411345,411345,65536,5242880,684436,87871116,12075916376038193,12075916376200866,12075916376467745,12075916376494892
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,899514,899519,4194304,256,0,0,24,24,182784,0x7f20b1c5c300,0x7f1fa6036ec0,228868,228868,65536,5177344,885780,113427572,12075916376536910,12075916376699424,12075916376841664,12075916376845253
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,899514,899519,4194304,256,0,0,24,24,186304,0x7f20b1c5ca00,0x7f1fa6036f00,488977,488977,65536,7208960,1047607,134585948,12075916376896759,12075916377070623,12075916377386941,12075916377413920
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,899514,899519,4194304,256,0,0,24,24,189312,0x7f20b1c5c900,0x7f1fa6036f40,242588,242588,65536,6160384,894601,114542844,12075916377475705,12075916377644060,12075916377795899,12075916377799116
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,899514,899519,4194304,256,0,0,20,24,190784,0x7f20b1c5c800,0x7f1fa6036f80,810337,810337,65536,17104896,2144975,274667468,12075916377850722,12075916378033498,12075916378568056,12075916378593131
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,899514,899519,4194304,256,0,0,28,24,193792,0x7f20b1c5c700,0x7f1fa6036fc0,457587,457587,65536,6291456,917521,117681912,12075916378645349,12075916378811735,12075916379111734,12075916379136381
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,899514,899519,4194304,256,0,0,24,24,196800,0x7f20b1c5c600,0x7f1fa6037000,246273,246273,65536,6225920,924668,118345764,12075916379186294,12075916379355093,12075916379510132,12075916379513512
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,899514,899519,4194304,256,0,0,24,24,201088,0x7f20b1c5c500,0x7f1fa6037040,592363,592363,65536,8781824,1257827,160039500,12075916379567963,12075916379742131,12075916380127089,12075916380151898
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,899514,899519,4194304,256,0,0,24,24,204608,0x7f20b1c5c400,0x7f1fa6037080,278569,278569,65536,7208960,1059382,135576048,12075916380213864,12075916380379728,12075916380556368,12075916380559806
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,899514,899519,4194304,256,0,0,20,24,206080,0x7f20b1c5c300,0x7f1fa60370c0,924339,924339,65536,19202048,2416609,308033820,12075916380610761,12075916380783727,12075916381394444,12075916381445052
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,899514,899519,4194304,256,0,0,28,24,209600,0x7f20b1c5ca00,0x7f1fa6037100,502401,502401,65536,7340032,1092262,139528472,12075916381468175,12075916381658603,12075916381987241,12075916382033595
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,899514,899519,4194304,256,0,0,24,24,213120,0x7f20b1c5c900,0x7f1fa6037140,284868,284868,65536,7274496,1166887,149196352,12075916382058121,12075916382242440,12075916382422919,12075916382426285
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,899514,899519,4194304,256,0,0,24,24,218176,0x7f20b1c5c800,0x7f1fa6037180,697161,697161,65536,10354688,1496224,192182000,12075916382480276,12075916382644358,12075916383100037,12075916383124853
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,899514,899519,4194304,256,0,0,24,24,222208,0x7f20b1c5c700,0x7f1fa60371c0,313692,313692,65536,8257536,1256226,160834988,12075916383184855,12075916383352675,12075916383552835,12075916383598444
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,899514,899519,4194304,256,0,0,20,24,223936,0x7f20b1c5c600,0x7f1fa6037200,1065745,1065745,65536,21299200,2676507,342650552,12075916383624302,12075916383803393,12075916384506750,12075916384555372
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,899514,899519,4194304,256,0,0,28,24,227968,0x7f20b1c5c500,0x7f1fa6037240,568275,568275,65536,8388608,1209059,154519352,12075916384580839,12075916384768189,12075916385142108,12075916385188889
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,899514,899519,4194304,256,0,0,24,24,232000,0x7f20b1c5c400,0x7f1fa6037280,317801,317801,65536,8323072,1213847,155305920,12075916385215539,12075916385403067,12075916385606746,12075916385653152
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,899514,899519,4194304,256,0,0,24,24,237824,0x7f20b1c5c300,0x7f1fa60372c0,802763,802763,65536,11927552,1650931,211195876,12075916385682407,12075916385860345,12075916386386262,12075916386436278
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,899514,899519,4194304,256,0,0,24,24,242368,0x7f20b1c5ca00,0x7f1fa6037300,349249,349249,65536,9306112,1426365,182564060,12075916386473487,12075916386641781,12075916386866580,12075916386912723
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,899514,899519,4194304,256,0,0,20,24,243584,0x7f20b1c5c900,0x7f1fa6037340,1211204,1211204,65536,29163520,3652164,467442080,12075916386938621,12075916387123219,12075916387922096,12075916387974236
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,899514,899519,4194304,256,0,0,28,24,248128,0x7f20b1c5c800,0x7f1fa6037380,636153,636153,65536,9437184,1289940,165570996,12075916388000084,12075916388191054,12075916388610893,12075916388658588
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,899514,899519,4194304,256,0,0,24,24,252672,0x7f20b1c5c700,0x7f1fa60373c0,353804,353804,65536,9371648,1427926,182691504,12075916388681610,12075916388864012,12075916389091211,12075916389141826
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,899514,899519,4194304,256,0,0,24,24,259264,0x7f20b1c5c600,0x7f1fa6037400,909129,909129,65536,13500416,1933190,246812968,12075916389169437,12075916389352009,12075916389949447,12075916389997566
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,899514,899519,4194304,256,0,0,24,24,264832,0x7f20b1c5c500,0x7f1fa6037440,418915,418915,65536,11403264,1766415,226224532,12075916390039163,12075916390216166,12075916390485285,12075916390534574
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,899514,899519,4194304,256,0,0,20,24,266304,0x7f20b1c5c400,0x7f1fa6037480,1488113,1488113,65536,33357824,4178219,534567304,12075916390560973,12075916390740163,12075916391726239,12075916391792792
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,899514,899519,4194304,256,0,0,28,24,271872,0x7f20b1c5c300,0x7f1fa60374c0,777739,777739,65536,11534336,1607694,205776828,12075916391817589,12075916392009918,12075916392525116,12075916392593390
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,899514,899519,4194304,256,0,0,24,24,277440,0x7f20b1c5ca00,0x7f1fa6037500,468681,468681,65536,11534336,1720877,220265624,12075916392617265,12075916392807675,12075916393110873,12075916393179229
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,899514,899519,4194304,256,0,0,12,24,279936,0x7f20b1c5c900,0x7f1fa6037540,1128459,1128459,65536,19267584,2434702,311637172,12075916393203033,12075916393390392,12075916394129909,12075916394196049
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,899514,899519,4194304,256,0,0,24,24,286528,0x7f20b1c5c800,0x7f1fa6037580,487425,487425,65536,13500416,2042692,261428708,12075916394232206,12075916394403828,12075916394719666,12075916394786316
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,899514,899519,4194304,256,0,0,20,24,288000,0x7f20b1c5c700,0x7f1fa60375c0,1768524,1768524,65536,37552128,4704085,601614640,12075916394816352,12075916394999185,12075916396168940,12075916396237533
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,899514,899519,4194304,256,0,0,32,24,294592,0x7f20b1c5c600,0x7f1fa6037600,916817,916817,65536,13631488,1865178,238996804,12075916396268741,12075916396453099,12075916397061576,12075916397128328
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,899514,899519,4194304,256,0,0,24,24,301184,0x7f20b1c5c500,0x7f1fa6037640,493787,493787,65536,13631488,2158423,276223040,12075916397152313,12075916397350535,12075916397670693,12075916397737140
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,899514,899519,4194304,256,0,0,12,24,304960,0x7f20b1c5c400,0x7f1fa6037680,1336265,1336265,65536,21692416,2742898,350582172,12075916397763318,12075916397949572,12075916398827648,12075916398896134
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,899514,899519,4194304,256,0,0,24,24,313600,0x7f20b1c5c300,0x7f1fa60376c0,630548,630548,65536,17694720,2751825,352308480,12075916398934595,12075916399101727,12075916399513245,12075916399581057
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,899514,899519,4194304,256,0,0,20,24,314816,0x7f20b1c5ca00,0x7f1fa6037700,2332625,2332625,65536,57475072,7194961,920860004,12075916399606804,12075916399794204,12075916401341718,12075916401409044
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,899514,899519,4194304,256,0,0,20,24,317568,0x7f20b1c5c900,0x7f1fa6037740,1203068,1203068,65536,19660800,2468602,316318244,12075916401439140,12075916401627316,12075916402422193,12075916402490414
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,899514,899519,4194304,256,0,0,12,24,320320,0x7f20b1c5c800,0x7f1fa6037780,640609,640609,65536,20381696,2573004,329097856,12075916402519578,12075916402705552,12075916403120430,12075916403187379
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,899514,899519,4194304,256,0,0,12,24,324096,0x7f20b1c5c700,0x7f1fa60377c0,1758556,1758556,65536,28704768,3611724,462042368,12075916403218897,12075916403402509,12075916404561064,12075916404628437
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,899514,899519,4194304,256,0,0,12,24,328896,0x7f20b1c5c600,0x7f1fa6037800,1197081,1197081,65536,36634624,4631196,592792088,12075916404671397,12075916404840102,12075916405625379,12075916405695219
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,899514,899519,4194304,256,0,0,20,24,330112,0x7f20b1c5c500,0x7f1fa6037840,4584724,4584724,65536,105840640,13235155,1694947128,12075916405727089,12075916405915778,12075916408964085,12075916409033504
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,899514,899519,4194304,256,0,0,20,24,332864,0x7f20b1c5c400,0x7f1fa6037880,2323497,2323497,65536,38535168,4838840,619436944,12075916409063920,12075916409243923,12075916410786957,12075916410854147
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,899514,899519,4194304,256,0,0,12,24,335616,0x7f20b1c5c300,0x7f1fa60378c0,1202979,1202979,65536,39124992,4913770,628880100,12075916410878032,12075916411073195,12075916411862472,12075916411931059
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,899514,899519,4194304,256,0,0,12,24,339392,0x7f20b1c5ca00,0x7f1fa6037900,3442833,3442833,65536,55771136,7015754,897399764,12075916411955534,12075916412150631,12075916414432541,12075916414500544
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,899514,899519,4194304,256,0,0,12,24,344192,0x7f20b1c5c900,0x7f1fa6037940,2322483,2322483,65536,72548352,9109474,1166235308,12075916414543323,12075916414713500,12075916416248853,12075916416316799
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,899514,899519,4194304,256,0,0,20,24,345408,0x7f20b1c5c800,0x7f1fa6037980,9087337,9087337,65536,210698240,26345530,3372659472,12075916416346655,12075916416529652,12075916422582586,12075916422650290
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,899514,899519,4194304,256,0,0,20,24,348160,0x7f20b1c5c700,0x7f1fa60379c0,4573948,4573948,65536,76283904,9535244,1222007488,12075916422682720,12075916422859704,12075916425901771,12075916425974247
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,899514,899519,4194304,256,0,0,12,24,350912,0x7f20b1c5c600,0x7f1fa6037a00,2328153,2328153,65536,77398016,9701948,1242243220,12075916425998983,12075916426203050,12075916427742403,12075916427811642
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,899514,899519,4194304,256,0,0,12,24,0,0x7f20b1c5c500,0x7f1fa6037a40,6811515,6811515,65536,110821376,13883505,1777296880,12075916427841417,12075916428034082,12075916432560622,12075916432633032
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 899514 899519 33554432 256 0 0 8 32 6464 0x0 0x7f1fa6004180 503617 503617 524288 6291456 791394 101370956 12075916066690965 12075916308968012 12075916309291690 12075916309401692
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 899514 899519 32768 256 0 0 24 24 12480 0x0 0x7f1fa6035100 28476 28476 512 8192 8822 1126348 12075916323842971 12075916324149848 12075916324156728 12075916324169417
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 4 899514 899519 4194304 256 0 0 24 24 12928 0x7f20b1c5c900 0x7f1fa6035140 219068 219068 65536 917504 139994 17933088 12075916324227495 12075916324447606 12075916324581365 12075916324585631
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 899514 899519 4194304 256 0 0 36 24 13632 0x7f20b1c5c800 0x7f1fa6035180 393105 393105 65536 1245184 181426 23255396 12075916324658817 12075916324838964 12075916325089203 12075916325159598
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 8 899514 899519 4194304 256 0 0 28 24 14080 0x7f20b1c5c700 0x7f1fa60351c0 402548 402548 65536 983040 136384 17499772 12075916325193911 12075916325394161 12075916325650160 12075916325717745
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 10 899514 899519 4194304 256 0 0 24 24 14528 0x7f20b1c5c600 0x7f1fa6035200 219289 219289 65536 1048576 158095 20172564 12075916325738864 12075916325933198 12075916326067437 12075916326071522
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 12 899514 899519 4194304 256 0 0 24 24 14976 0x7f20b1c5c500 0x7f1fa6035240 225531 225531 65536 983040 148759 19074732 12075916326124531 12075916326304716 12075916326442795 12075916326446630
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 14 899514 899519 4194304 256 0 0 24 24 15424 0x7f20b1c5c400 0x7f1fa6035280 211873 211873 65536 1048576 146763 18827604 12075916326531487 12075916326699754 12075916326828713 12075916326832587
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 899514 899519 4194304 256 0 0 28 24 16128 0x7f20b1c5c300 0x7f1fa60352c0 403459 403459 65536 1572864 229538 29378076 12075916326884834 12075916327065192 12075916327322151 12075916327363393
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 18 899514 899519 4194304 256 0 0 28 24 16832 0x7f20b1c5ca00 0x7f1fa6035300 396817 396817 65536 1179648 158588 20275688 12075916327396525 12075916327583269 12075916327836228 12075916327901603
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 20 899514 899519 4194304 256 0 0 24 24 17536 0x7f20b1c5c900 0x7f1fa6035340 216604 216604 65536 1114112 161450 20628652 12075916327926390 12075916328115746 12075916328247745 12075916328251784
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 22 899514 899519 4194304 256 0 0 24 24 18240 0x7f20b1c5c800 0x7f1fa6035380 212169 212169 65536 1114112 158126 20294324 12075916328298631 12075916328484384 12075916328613823 12075916328617795
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 24 899514 899519 4194304 256 0 0 24 24 18944 0x7f20b1c5c700 0x7f1fa60353c0 222876 222876 65536 1179648 165753 21211448 12075916328683236 12075916328851102 12075916328987741 12075916328991229
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 899514 899519 4194304 256 0 0 28 24 19904 0x7f20b1c5c600 0x7f1fa6035400 396625 396625 65536 1835008 252662 32368796 12075916329044267 12075916329223420 12075916329475099 12075916329541932
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 28 899514 899519 4194304 256 0 0 28 24 20608 0x7f20b1c5c500 0x7f1fa6035440 396515 396515 65536 1310720 177666 22805040 12075916329568361 12075916329750137 12075916330002936 12075916330069873
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 30 899514 899519 4194304 256 0 0 24 24 21312 0x7f20b1c5c400 0x7f1fa6035480 212081 212081 65536 1245184 176381 22530196 12075916330094689 12075916330281814 12075916330411414 12075916330415365
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 32 899514 899519 4194304 256 0 0 24 24 22016 0x7f20b1c5c300 0x7f1fa60354c0 215763 215763 65536 1310720 184051 23580376 12075916330466941 12075916330652532 12075916330783892 12075916330787747
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 34 899514 899519 4194304 256 0 0 24 24 22720 0x7f20b1c5ca00 0x7f1fa6035500 208889 208889 65536 1310720 180006 23109804 12075916330853309 12075916331023730 12075916331151090 12075916331155330
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 899514 899519 4194304 256 0 0 28 24 23680 0x7f20b1c5c900 0x7f1fa6035540 410787 410787 65536 2097152 313279 40098956 12075916331206976 12075916331390768 12075916331653327 12075916331719870
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 38 899514 899519 4194304 256 0 0 28 24 24384 0x7f20b1c5c800 0x7f1fa6035580 405705 405705 65536 1441792 197013 25126000 12075916331745708 12075916331929165 12075916332188044 12075916332258360
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 40 899514 899519 4194304 256 0 0 24 24 25088 0x7f20b1c5c700 0x7f1fa60355c0 224787 224787 65536 1376256 189538 24301748 12075916332283006 12075916332470922 12075916332609002 12075916332612529
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 42 899514 899519 4194304 256 0 0 24 24 25792 0x7f20b1c5c600 0x7f1fa6035600 207521 207521 65536 1507328 211473 27130856 12075916332665467 12075916332845000 12075916332971400 12075916332975363
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 44 899514 899519 4194304 256 0 0 24 24 26496 0x7f20b1c5c500 0x7f1fa6035640 210652 210652 65536 1441792 202685 26001552 12075916333041967 12075916333211398 12075916333339878 12075916333343918
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 899514 899519 4194304 256 0 0 28 24 27712 0x7f20b1c5c400 0x7f1fa6035680 402289 402289 65536 2359296 323765 41628452 12075916333395634 12075916333571396 12075916333828355 12075916333896094
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 48 899514 899519 4194304 256 0 0 28 24 28416 0x7f20b1c5c300 0x7f1fa60356c0 395244 395244 65536 1572864 212217 27072792 12075916333919007 12075916334108673 12075916334360832 12075916334427902
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 50 899514 899519 4194304 256 0 0 24 24 29120 0x7f20b1c5ca00 0x7f1fa6035700 215849 215849 65536 1507328 209407 26785052 12075916334452218 12075916334645630 12075916334777630 12075916334781209
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 52 899514 899519 4194304 256 0 0 24 24 30080 0x7f20b1c5c900 0x7f1fa6035740 220868 220868 65536 1703936 235510 30184856 12075916334832665 12075916335007388 12075916335142908 12075916335147049
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 54 899514 899519 4194304 256 0 0 24 24 30784 0x7f20b1c5c800 0x7f1fa6035780 216849 216849 65536 1572864 213596 27241740 12075916335212480 12075916335380986 12075916335514106 12075916335517958
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 899514 899519 4194304 256 0 0 28 24 32000 0x7f20b1c5c700 0x7f1fa60357c0 398444 398444 65536 2621440 358249 45757280 12075916335569694 12075916335742424 12075916335997623 12075916336064955
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 58 899514 899519 4194304 256 0 0 28 24 32960 0x7f20b1c5c600 0x7f1fa6035800 389257 389257 65536 1703936 229529 29392720 12075916336090693 12075916336280022 12075916336528340 12075916336594900
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 60 899514 899519 4194304 256 0 0 24 24 33920 0x7f20b1c5c500 0x7f1fa6035840 207531 207531 65536 1638400 227467 29171912 12075916336619165 12075916336802899 12075916336928978 12075916336933038
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 62 899514 899519 4194304 256 0 0 24 24 34880 0x7f20b1c5c400 0x7f1fa6035880 218153 218153 65536 1900544 270751 34514900 12075916336984864 12075916337163537 12075916337298096 12075916337301974
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 64 899514 899519 4194304 256 0 0 24 24 35840 0x7f20b1c5c300 0x7f1fa60358c0 210963 210963 65536 1703936 230379 29483712 12075916337366153 12075916337540175 12075916337668494 12075916337672693
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 899514 899519 4194304 256 0 0 28 24 37312 0x7f20b1c5ca00 0x7f1fa6035900 406273 406273 65536 2883584 388422 49723928 12075916337723217 12075916337902893 12075916338163211 12075916338230710
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 68 899514 899519 4194304 256 0 0 28 24 38272 0x7f20b1c5c900 0x7f1fa6035940 409180 409180 65536 1835008 243988 31231160 12075916338255426 12075916338441770 12075916338703208 12075916338769852
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 70 899514 899519 4194304 256 0 0 24 24 39232 0x7f20b1c5c800 0x7f1fa6035980 283945 283945 65536 1769472 276244 35365832 12075916338793385 12075916338977607 12075916339155526 12075916339159556
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 72 899514 899519 4194304 256 0 0 24 24 40192 0x7f20b1c5c700 0x7f1fa60359c0 216156 216156 65536 2097152 327033 41843432 12075916339217283 12075916339382725 12075916339514884 12075916339518764
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 74 899514 899519 4194304 256 0 0 24 24 41152 0x7f20b1c5c600 0x7f1fa6035a00 217529 217529 65536 1835008 248404 31855532 12075916339583895 12075916339750563 12075916339883842 12075916339887890
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 899514 899519 4194304 256 0 0 28 24 42624 0x7f20b1c5c500 0x7f1fa6035a40 403555 403555 65536 3145728 431394 55216548 12075916339940207 12075916340115361 12075916340374719 12075916340443452
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 78 899514 899519 4194304 256 0 0 28 24 43584 0x7f20b1c5c400 0x7f1fa6035a80 396929 396929 65536 1966080 262065 33520048 12075916340467156 12075916340654078 12075916340908316 12075916340975170
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 80 899514 899519 4194304 256 0 0 24 24 44544 0x7f20b1c5c300 0x7f1fa6035ac0 217732 217732 65536 1900544 285400 36495776 12075916340998463 12075916341193435 12075916341327034 12075916341331102
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 82 899514 899519 4194304 256 0 0 24 24 45760 0x7f20b1c5ca00 0x7f1fa6035b00 219881 219881 65536 2293760 307023 39409272 12075916341384240 12075916341557913 12075916341693752 12075916341697713
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 84 899514 899519 4194304 256 0 0 24 24 46720 0x7f20b1c5c900 0x7f1fa6035b40 220396 220396 65536 1966080 296839 37962360 12075916341761812 12075916341928471 12075916342062710 12075916342067059
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 899514 899519 4194304 256 0 0 28 24 48448 0x7f20b1c5c800 0x7f1fa6035b80 417121 417121 65536 3407872 458924 58644720 12075916342119357 12075916342297909 12075916342566067 12075916342632350
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 88 899514 899519 4194304 256 0 0 28 24 49408 0x7f20b1c5c700 0x7f1fa6035bc0 399452 399452 65536 2097152 276846 35433256 12075916342658749 12075916342843186 12075916343098864 12075916343140284
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 90 899514 899519 4194304 256 0 0 24 24 50368 0x7f20b1c5c600 0x7f1fa6035c00 217073 217073 65536 2031616 276387 35380428 12075916343176561 12075916343349743 12075916343482542 12075916343486537
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 92 899514 899519 4194304 256 0 0 24 24 51584 0x7f20b1c5c500 0x7f1fa6035c40 229820 229820 65536 2490368 338179 43217084 12075916343538614 12075916343711181 12075916343853260 12075916343857096
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 94 899514 899519 4194304 256 0 0 24 24 52544 0x7f20b1c5c400 0x7f1fa6035c80 218857 218857 65536 2097152 309395 39738332 12075916343921656 12075916344091499 12075916344225898 12075916344229969
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 899514 899519 4194304 256 0 0 28 24 54272 0x7f20b1c5c300 0x7f1fa6035cc0 414612 414612 65536 3670016 491598 62976380 12075916344282547 12075916344457417 12075916344723655 12075916344790401
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 98 899514 899519 4194304 256 0 0 28 24 55488 0x7f20b1c5ca00 0x7f1fa6035d00 409409 409409 65536 2228224 298402 38266784 12075916344813273 12075916344995654 12075916345258052 12075916345326727
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 100 899514 899519 4194304 256 0 0 24 24 56704 0x7f20b1c5c900 0x7f1fa6035d40 218947 218947 65536 2162688 291271 37281260 12075916345349600 12075916345533411 12075916345668130 12075916345671849
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 102 899514 899519 4194304 256 0 0 24 24 58176 0x7f20b1c5c800 0x7f1fa6035d80 224089 224089 65536 2686976 383606 49022056 12075916345725518 12075916345888449 12075916346027648 12075916346031547
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 104 899514 899519 4194304 256 0 0 24 24 59392 0x7f20b1c5c700 0x7f1fa6035dc0 217428 217428 65536 2228224 311071 39831812 12075916346095666 12075916346262207 12075916346395486 12075916346399721
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 899514 899519 4194304 256 0 0 28 24 61376 0x7f20b1c5c600 0x7f1fa6035e00 416393 416393 65536 3932160 535483 68615452 12075916346452680 12075916346625245 12075916346893243 12075916346934004
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 108 899514 899519 4194304 256 0 0 28 24 62592 0x7f20b1c5c500 0x7f1fa6035e40 410899 410899 65536 2359296 310836 39774492 12075916346962778 12075916347145722 12075916347407161 12075916347473908
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 110 899514 899519 4194304 256 0 0 24 24 63808 0x7f20b1c5c400 0x7f1fa6035e80 217097 217097 65536 2293760 325336 41670612 12075916347500006 12075916347681079 12075916347814998 12075916347818628
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 112 899514 899519 4194304 256 0 0 24 24 65280 0x7f20b1c5c300 0x7f1fa6035ec0 228019 228019 65536 2883584 414191 53132544 12075916347870034 12075916348053237 12075916348194356 12075916348198695
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 114 899514 899519 4194304 256 0 0 24 24 66496 0x7f20b1c5ca00 0x7f1fa6035f00 220449 220449 65536 2359296 347267 44467248 12075916348264477 12075916348429395 12075916348564754 12075916348569023
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 899514 899519 4194304 256 0 0 28 24 68480 0x7f20b1c5c900 0x7f1fa6035f40 417772 417772 65536 4194304 600677 76644864 12075916348621430 12075916348793073 12075916349062352 12075916349131538
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 118 899514 899519 4194304 256 0 0 28 24 69696 0x7f20b1c5c800 0x7f1fa6035f80 394937 394937 65536 2490368 341347 43644740 12075916349159190 12075916349342510 12075916349596269 12075916349661864
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 120 899514 899519 4194304 256 0 0 24 24 70912 0x7f20b1c5c700 0x7f1fa6035fc0 218124 218124 65536 2424832 354887 45366088 12075916349687321 12075916349868747 12075916350002986 12075916350006655
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 122 899514 899519 4194304 256 0 0 24 24 72384 0x7f20b1c5c600 0x7f1fa6036000 224289 224289 65536 3080192 505287 64783864 12075916350059423 12075916350231305 12075916350370504 12075916350374488
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 124 899514 899519 4194304 256 0 0 24 24 73600 0x7f20b1c5c500 0x7f1fa6036040 227747 227747 65536 2490368 398926 51106732 12075916350438668 12075916350606023 12075916350746342 12075916350750227
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 899514 899519 4194304 256 0 0 28 24 75840 0x7f20b1c5c400 0x7f1fa6036080 421793 421793 65536 4456448 591942 75761828 12075916350803536 12075916350976581 12075916351249220 12075916351316078
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 128 899514 899519 4194304 256 0 0 28 24 77056 0x7f20b1c5c300 0x7f1fa60360c0 401779 401779 65536 2621440 343098 43913092 12075916351340935 12075916351528578 12075916351786817 12075916351853547
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 130 899514 899519 4194304 256 0 0 24 24 78272 0x7f20b1c5ca00 0x7f1fa6036100 218513 218513 65536 2555904 375219 48022984 12075916351877131 12075916352066655 12075916352201214 12075916352205381
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 132 899514 899519 4194304 256 0 0 24 24 80000 0x7f20b1c5c900 0x7f1fa6036140 232340 232340 65536 3276800 483003 61965428 12075916352260013 12075916352427933 12075916352572412 12075916352576360
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 134 899514 899519 4194304 256 0 0 24 24 81216 0x7f20b1c5c800 0x7f1fa6036180 215697 215697 65536 2621440 375485 47982220 12075916352641121 12075916352801851 12075916352934810 12075916352938784
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 899514 899519 4194304 256 0 0 28 24 83456 0x7f20b1c5c700 0x7f1fa60361c0 416587 416587 65536 4718592 630971 80728640 12075916352991662 12075916353168889 12075916353437848 12075916353488115
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 138 899514 899519 4194304 256 0 0 28 24 84928 0x7f20b1c5c600 0x7f1fa6036200 401097 401097 65536 2752512 362820 46292548 12075916353512510 12075916353691286 12075916353949525 12075916353971203
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 140 899514 899519 4194304 256 0 0 24 24 86400 0x7f20b1c5c500 0x7f1fa6036240 223236 223236 65536 2686976 406088 51970384 12075916354022758 12075916354185044 12075916354322163 12075916354326333
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 142 899514 899519 4194304 256 0 0 24 24 88128 0x7f20b1c5c400 0x7f1fa6036280 243425 243425 65536 3473408 515020 65892028 12075916354379361 12075916354551442 12075916354703441 12075916354707411
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 144 899514 899519 4194304 256 0 0 24 24 89600 0x7f20b1c5c300 0x7f1fa60362c0 220131 220131 65536 2752512 393213 50328156 12075916354788622 12075916354949839 12075916355085519 12075916355089731
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 899514 899519 4194304 256 0 0 28 24 92096 0x7f20b1c5ca00 0x7f1fa6036300 424113 424113 65536 4980736 666222 85273704 12075916355142480 12075916355319917 12075916355593996 12075916355641527
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 148 899514 899519 4194304 256 0 0 28 24 93568 0x7f20b1c5c900 0x7f1fa6036340 399571 399571 65536 2883584 396081 50495908 12075916355667686 12075916355848875 12075916356105833 12075916356155041
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 150 899514 899519 4194304 256 0 0 24 24 95040 0x7f20b1c5c800 0x7f1fa6036380 211953 211953 65536 2818048 407583 52215332 12075916356179557 12075916356363432 12075916356494151 12075916356498179
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 152 899514 899519 4194304 256 0 0 24 24 96768 0x7f20b1c5c700 0x7f1fa60363c0 251524 251524 65536 3670016 556013 70963600 12075916356550055 12075916356722950 12075916356880069 12075916356884116
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 154 899514 899519 4194304 256 0 0 24 24 98240 0x7f20b1c5c600 0x7f1fa6036400 225697 225697 65536 2883584 399863 51233460 12075916356948596 12075916357118148 12075916357257187 12075916357261397
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 899514 899519 4194304 256 0 0 28 24 100736 0x7f20b1c5c500 0x7f1fa6036440 417012 417012 65536 5177344 690166 88328624 12075916357308264 12075916357489986 12075916357760064 12075916357807973
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 158 899514 899519 4194304 256 0 0 28 24 102208 0x7f20b1c5c400 0x7f1fa6036480 393913 393913 65536 3014656 397746 50807912 12075916357830896 12075916358014463 12075916358268061 12075916358316218
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 160 899514 899519 4194304 256 0 0 24 24 103680 0x7f20b1c5c300 0x7f1fa60364c0 222411 222411 65536 2949120 432036 55230596 12075916358339571 12075916358528380 12075916358665499 12075916358669625
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 162 899514 899519 4194304 256 0 0 24 24 105664 0x7f20b1c5ca00 0x7f1fa6036500 263417 263417 65536 3866624 557609 71371148 12075916358723445 12075916358893178 12075916359058937 12075916359062785
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 164 899514 899519 4194304 256 0 0 24 24 107136 0x7f20b1c5c900 0x7f1fa6036540 222891 222891 65536 3014656 426756 54661620 12075916359128307 12075916359293176 12075916359430455 12075916359434766
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 899514 899519 4194304 256 0 0 28 24 109888 0x7f20b1c5c800 0x7f1fa6036580 413465 413465 65536 5439488 721005 92538604 12075916359486382 12075916359658774 12075916359926932 12075916359974830
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 168 899514 899519 4194304 256 0 0 28 24 111360 0x7f20b1c5c700 0x7f1fa60365c0 401308 401308 65536 3145728 411924 52895648 12075916359997071 12075916360188211 12075916360446449 12075916360496169
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 170 899514 899519 4194304 256 0 0 24 24 112832 0x7f20b1c5c600 0x7f1fa6036600 218537 218537 65536 3080192 436231 55846648 12075916360518360 12075916360699408 12075916360833967 12075916360838265
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 172 899514 899519 4194304 256 0 0 24 24 114816 0x7f20b1c5c500 0x7f1fa6036640 275436 275436 65536 4063232 569621 73117460 12075916360890452 12075916361058766 12075916361232045 12075916361235844
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 174 899514 899519 4194304 256 0 0 24 24 116288 0x7f20b1c5c400 0x7f1fa6036680 220889 220889 65536 3145728 423661 54219680 12075916361301466 12075916361466924 12075916361602923 12075916361607014
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 899514 899519 4194304 256 0 0 28 24 119040 0x7f20b1c5c300 0x7f1fa60366c0 408524 408524 65536 5701632 831172 106683448 12075916361659040 12075916361841322 12075916362105480 12075916362153900
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 178 899514 899519 4194304 256 0 0 28 24 120768 0x7f20b1c5ca00 0x7f1fa6036700 403265 403265 65536 3276800 430198 54924244 12075916362181231 12075916362364039 12075916362624197 12075916362670981
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 180 899514 899519 4194304 256 0 0 24 24 122496 0x7f20b1c5c900 0x7f1fa6036740 226364 226364 65536 3211264 475725 60910476 12075916362693403 12075916362875876 12075916363015395 12075916363019559
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 182 899514 899519 4194304 256 0 0 24 24 124736 0x7f20b1c5c800 0x7f1fa6036780 290337 290337 65536 4259840 638866 80999604 12075916363072146 12075916363250914 12075916363434913 12075916363439128
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 184 899514 899519 4194304 256 0 0 24 24 126464 0x7f20b1c5c700 0x7f1fa60367c0 224467 224467 65536 3276800 548438 70065800 12075916363503859 12075916363668192 12075916363806751 12075916363811060
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 899514 899519 4194304 256 0 0 20 24 127936 0x7f20b1c5c600 0x7f1fa6036800 410025 410025 65536 7733248 974585 124904944 12075916363864038 12075916364041470 12075916364308028 12075916364357645
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 188 899514 899519 4194304 256 0 0 28 24 129664 0x7f20b1c5c500 0x7f1fa6036840 407540 407540 65536 3407872 450450 57806308 12075916364381871 12075916364564987 12075916364827065 12075916364874115
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 190 899514 899519 4194304 256 0 0 24 24 131392 0x7f20b1c5c400 0x7f1fa6036880 218681 218681 65536 3342336 456403 58401020 12075916364897338 12075916365091704 12075916365226743 12075916365231129
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 192 899514 899519 4194304 256 0 0 24 24 133632 0x7f20b1c5c300 0x7f1fa60368c0 301932 301932 65536 4456448 613290 78155728 12075916365286161 12075916365452662 12075916365644821 12075916365691244
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 194 899514 899519 4194304 256 0 0 24 24 135360 0x7f20b1c5ca00 0x7f1fa6036900 226121 226121 65536 3538944 554775 71032664 12075916365729225 12075916365891220 12075916366029139 12075916366033450
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 899514 899519 4194304 256 0 0 20 24 136832 0x7f20b1c5c900 0x7f1fa6036940 435307 435307 65536 8978432 1134433 145548104 12075916366088382 12075916366264658 12075916366547856 12075916366595254
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 198 899514 899519 4194304 256 0 0 28 24 138560 0x7f20b1c5c800 0x7f1fa6036980 398129 398129 65536 3670016 478937 61116896 12075916366617826 12075916366798895 12075916367056333 12075916367104070
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 200 899514 899519 4194304 256 0 0 24 24 140288 0x7f20b1c5c700 0x7f1fa60369c0 224723 224723 65536 3604480 514050 65858700 12075916367127804 12075916367313292 12075916367451691 12075916367456194
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 202 899514 899519 4194304 256 0 0 24 24 142784 0x7f20b1c5c600 0x7f1fa6036a00 329409 329409 65536 4849664 739653 94492548 12075916367508020 12075916367679690 12075916367889769 12075916367935926
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 204 899514 899519 4194304 256 0 0 24 24 144768 0x7f20b1c5c500 0x7f1fa6036a40 220740 220740 65536 3801088 586063 74921436 12075916367973545 12075916368144487 12075916368281127 12075916368285265
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 899514 899519 4194304 256 0 0 20 24 145728 0x7f20b1c5c400 0x7f1fa6036a80 469473 469473 65536 14548992 1827760 234072720 12075916368337582 12075916368513765 12075916368820644 12075916368867587
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 208 899514 899519 4194304 256 0 0 28 24 147712 0x7f20b1c5c300 0x7f1fa6036ac0 402460 402460 65536 3932160 510983 65618032 12075916368895589 12075916369080322 12075916369340961 12075916369389928
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 210 899514 899519 4194304 256 0 0 24 24 149696 0x7f20b1c5ca00 0x7f1fa6036b00 220473 220473 65536 3866624 588987 75447212 12075916369414543 12075916369600959 12075916369737119 12075916369741181
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 212 899514 899519 4194304 256 0 0 24 24 152192 0x7f20b1c5c900 0x7f1fa6036b40 357355 357355 65536 5242880 803092 103036472 12075916369792366 12075916369963677 12075916370191996 12075916370218007
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 214 899514 899519 4194304 256 0 0 24 24 154176 0x7f20b1c5c800 0x7f1fa6036b80 224977 224977 65536 4063232 601835 77039816 12075916370277167 12075916370444155 12075916370583674 12075916370587674
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 899514 899519 4194304 256 0 0 20 24 155648 0x7f20b1c5c700 0x7f1fa6036bc0 503548 503548 65536 10027008 1260119 161382664 12075916370638478 12075916370810073 12075916371139191 12075916371168062
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 218 899514 899519 4194304 256 0 0 28 24 157632 0x7f20b1c5c600 0x7f1fa6036c00 389329 389329 65536 4194304 572949 73193228 12075916371211974 12075916371377110 12075916371629428 12075916371654166
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 220 899514 899519 4194304 256 0 0 24 24 159616 0x7f20b1c5c500 0x7f1fa6036c40 228187 228187 65536 4128768 677745 86778556 12075916371702265 12075916371866166 12075916372007606 12075916372015096
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 222 899514 899519 4194304 256 0 0 24 24 162368 0x7f20b1c5c400 0x7f1fa6036c80 431697 431697 65536 5636096 770561 98522144 12075916372066873 12075916372242484 12075916372520562 12075916372545332
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 224 899514 899519 4194304 256 0 0 24 24 164608 0x7f20b1c5c300 0x7f1fa6036cc0 232531 232531 65536 4587520 724524 92754808 12075916372604722 12075916372770801 12075916372914481 12075916372917764
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 899514 899519 4194304 256 0 0 20 24 166336 0x7f20b1c5ca00 0x7f1fa6036d00 573017 573017 65536 11075584 1393059 178236652 12075916372968749 12075916373148240 12075916373524398 12075916373551682
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 228 899514 899519 4194304 256 0 0 28 24 168576 0x7f20b1c5c900 0x7f1fa6036d40 404451 404451 65536 4718592 648555 83005264 12075916373595504 12075916373756877 12075916374018956 12075916374043586
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 230 899514 899519 4194304 256 0 0 24 24 170816 0x7f20b1c5c800 0x7f1fa6036d80 228281 228281 65536 4653056 670879 85872492 12075916374095403 12075916374265355 12075916374407274 12075916374410649
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 232 899514 899519 4194304 256 0 0 24 24 174080 0x7f20b1c5c700 0x7f1fa6036dc0 435292 435292 65536 6422528 921264 116635016 12075916374462375 12075916374637673 12075916374917832 12075916374941215
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 234 899514 899519 4194304 256 0 0 24 24 176576 0x7f20b1c5c600 0x7f1fa6036e00 224185 224185 65536 5111808 808241 103462896 12075916374999783 12075916375170151 12075916375309670 12075916375313376
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 899514 899519 4194304 256 0 0 20 24 177792 0x7f20b1c5c500 0x7f1fa6036e40 645316 645316 65536 15007744 1879968 240859716 12075916375364301 12075916375536069 12075916375960707 12075916375984564
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 238 899514 899519 4194304 256 0 0 28 24 180288 0x7f20b1c5c400 0x7f1fa6036e80 411345 411345 65536 5242880 684436 87871116 12075916376038193 12075916376200866 12075916376467745 12075916376494892
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 240 899514 899519 4194304 256 0 0 24 24 182784 0x7f20b1c5c300 0x7f1fa6036ec0 228868 228868 65536 5177344 885780 113427572 12075916376536910 12075916376699424 12075916376841664 12075916376845253
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 242 899514 899519 4194304 256 0 0 24 24 186304 0x7f20b1c5ca00 0x7f1fa6036f00 488977 488977 65536 7208960 1047607 134585948 12075916376896759 12075916377070623 12075916377386941 12075916377413920
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 244 899514 899519 4194304 256 0 0 24 24 189312 0x7f20b1c5c900 0x7f1fa6036f40 242588 242588 65536 6160384 894601 114542844 12075916377475705 12075916377644060 12075916377795899 12075916377799116
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 899514 899519 4194304 256 0 0 20 24 190784 0x7f20b1c5c800 0x7f1fa6036f80 810337 810337 65536 17104896 2144975 274667468 12075916377850722 12075916378033498 12075916378568056 12075916378593131
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 248 899514 899519 4194304 256 0 0 28 24 193792 0x7f20b1c5c700 0x7f1fa6036fc0 457587 457587 65536 6291456 917521 117681912 12075916378645349 12075916378811735 12075916379111734 12075916379136381
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 250 899514 899519 4194304 256 0 0 24 24 196800 0x7f20b1c5c600 0x7f1fa6037000 246273 246273 65536 6225920 924668 118345764 12075916379186294 12075916379355093 12075916379510132 12075916379513512
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 252 899514 899519 4194304 256 0 0 24 24 201088 0x7f20b1c5c500 0x7f1fa6037040 592363 592363 65536 8781824 1257827 160039500 12075916379567963 12075916379742131 12075916380127089 12075916380151898
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 254 899514 899519 4194304 256 0 0 24 24 204608 0x7f20b1c5c400 0x7f1fa6037080 278569 278569 65536 7208960 1059382 135576048 12075916380213864 12075916380379728 12075916380556368 12075916380559806
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 899514 899519 4194304 256 0 0 20 24 206080 0x7f20b1c5c300 0x7f1fa60370c0 924339 924339 65536 19202048 2416609 308033820 12075916380610761 12075916380783727 12075916381394444 12075916381445052
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 258 899514 899519 4194304 256 0 0 28 24 209600 0x7f20b1c5ca00 0x7f1fa6037100 502401 502401 65536 7340032 1092262 139528472 12075916381468175 12075916381658603 12075916381987241 12075916382033595
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 260 899514 899519 4194304 256 0 0 24 24 213120 0x7f20b1c5c900 0x7f1fa6037140 284868 284868 65536 7274496 1166887 149196352 12075916382058121 12075916382242440 12075916382422919 12075916382426285
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 262 899514 899519 4194304 256 0 0 24 24 218176 0x7f20b1c5c800 0x7f1fa6037180 697161 697161 65536 10354688 1496224 192182000 12075916382480276 12075916382644358 12075916383100037 12075916383124853
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 264 899514 899519 4194304 256 0 0 24 24 222208 0x7f20b1c5c700 0x7f1fa60371c0 313692 313692 65536 8257536 1256226 160834988 12075916383184855 12075916383352675 12075916383552835 12075916383598444
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 899514 899519 4194304 256 0 0 20 24 223936 0x7f20b1c5c600 0x7f1fa6037200 1065745 1065745 65536 21299200 2676507 342650552 12075916383624302 12075916383803393 12075916384506750 12075916384555372
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 268 899514 899519 4194304 256 0 0 28 24 227968 0x7f20b1c5c500 0x7f1fa6037240 568275 568275 65536 8388608 1209059 154519352 12075916384580839 12075916384768189 12075916385142108 12075916385188889
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 270 899514 899519 4194304 256 0 0 24 24 232000 0x7f20b1c5c400 0x7f1fa6037280 317801 317801 65536 8323072 1213847 155305920 12075916385215539 12075916385403067 12075916385606746 12075916385653152
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 272 899514 899519 4194304 256 0 0 24 24 237824 0x7f20b1c5c300 0x7f1fa60372c0 802763 802763 65536 11927552 1650931 211195876 12075916385682407 12075916385860345 12075916386386262 12075916386436278
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 274 899514 899519 4194304 256 0 0 24 24 242368 0x7f20b1c5ca00 0x7f1fa6037300 349249 349249 65536 9306112 1426365 182564060 12075916386473487 12075916386641781 12075916386866580 12075916386912723
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 899514 899519 4194304 256 0 0 20 24 243584 0x7f20b1c5c900 0x7f1fa6037340 1211204 1211204 65536 29163520 3652164 467442080 12075916386938621 12075916387123219 12075916387922096 12075916387974236
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 278 899514 899519 4194304 256 0 0 28 24 248128 0x7f20b1c5c800 0x7f1fa6037380 636153 636153 65536 9437184 1289940 165570996 12075916388000084 12075916388191054 12075916388610893 12075916388658588
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 280 899514 899519 4194304 256 0 0 24 24 252672 0x7f20b1c5c700 0x7f1fa60373c0 353804 353804 65536 9371648 1427926 182691504 12075916388681610 12075916388864012 12075916389091211 12075916389141826
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 282 899514 899519 4194304 256 0 0 24 24 259264 0x7f20b1c5c600 0x7f1fa6037400 909129 909129 65536 13500416 1933190 246812968 12075916389169437 12075916389352009 12075916389949447 12075916389997566
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 284 899514 899519 4194304 256 0 0 24 24 264832 0x7f20b1c5c500 0x7f1fa6037440 418915 418915 65536 11403264 1766415 226224532 12075916390039163 12075916390216166 12075916390485285 12075916390534574
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 899514 899519 4194304 256 0 0 20 24 266304 0x7f20b1c5c400 0x7f1fa6037480 1488113 1488113 65536 33357824 4178219 534567304 12075916390560973 12075916390740163 12075916391726239 12075916391792792
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 288 899514 899519 4194304 256 0 0 28 24 271872 0x7f20b1c5c300 0x7f1fa60374c0 777739 777739 65536 11534336 1607694 205776828 12075916391817589 12075916392009918 12075916392525116 12075916392593390
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 290 899514 899519 4194304 256 0 0 24 24 277440 0x7f20b1c5ca00 0x7f1fa6037500 468681 468681 65536 11534336 1720877 220265624 12075916392617265 12075916392807675 12075916393110873 12075916393179229
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 292 899514 899519 4194304 256 0 0 12 24 279936 0x7f20b1c5c900 0x7f1fa6037540 1128459 1128459 65536 19267584 2434702 311637172 12075916393203033 12075916393390392 12075916394129909 12075916394196049
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 294 899514 899519 4194304 256 0 0 24 24 286528 0x7f20b1c5c800 0x7f1fa6037580 487425 487425 65536 13500416 2042692 261428708 12075916394232206 12075916394403828 12075916394719666 12075916394786316
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 899514 899519 4194304 256 0 0 20 24 288000 0x7f20b1c5c700 0x7f1fa60375c0 1768524 1768524 65536 37552128 4704085 601614640 12075916394816352 12075916394999185 12075916396168940 12075916396237533
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 298 899514 899519 4194304 256 0 0 32 24 294592 0x7f20b1c5c600 0x7f1fa6037600 916817 916817 65536 13631488 1865178 238996804 12075916396268741 12075916396453099 12075916397061576 12075916397128328
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 300 899514 899519 4194304 256 0 0 24 24 301184 0x7f20b1c5c500 0x7f1fa6037640 493787 493787 65536 13631488 2158423 276223040 12075916397152313 12075916397350535 12075916397670693 12075916397737140
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 302 899514 899519 4194304 256 0 0 12 24 304960 0x7f20b1c5c400 0x7f1fa6037680 1336265 1336265 65536 21692416 2742898 350582172 12075916397763318 12075916397949572 12075916398827648 12075916398896134
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 304 899514 899519 4194304 256 0 0 24 24 313600 0x7f20b1c5c300 0x7f1fa60376c0 630548 630548 65536 17694720 2751825 352308480 12075916398934595 12075916399101727 12075916399513245 12075916399581057
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 899514 899519 4194304 256 0 0 20 24 314816 0x7f20b1c5ca00 0x7f1fa6037700 2332625 2332625 65536 57475072 7194961 920860004 12075916399606804 12075916399794204 12075916401341718 12075916401409044
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 308 899514 899519 4194304 256 0 0 20 24 317568 0x7f20b1c5c900 0x7f1fa6037740 1203068 1203068 65536 19660800 2468602 316318244 12075916401439140 12075916401627316 12075916402422193 12075916402490414
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 310 899514 899519 4194304 256 0 0 12 24 320320 0x7f20b1c5c800 0x7f1fa6037780 640609 640609 65536 20381696 2573004 329097856 12075916402519578 12075916402705552 12075916403120430 12075916403187379
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 312 899514 899519 4194304 256 0 0 12 24 324096 0x7f20b1c5c700 0x7f1fa60377c0 1758556 1758556 65536 28704768 3611724 462042368 12075916403218897 12075916403402509 12075916404561064 12075916404628437
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 314 899514 899519 4194304 256 0 0 12 24 328896 0x7f20b1c5c600 0x7f1fa6037800 1197081 1197081 65536 36634624 4631196 592792088 12075916404671397 12075916404840102 12075916405625379 12075916405695219
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 899514 899519 4194304 256 0 0 20 24 330112 0x7f20b1c5c500 0x7f1fa6037840 4584724 4584724 65536 105840640 13235155 1694947128 12075916405727089 12075916405915778 12075916408964085 12075916409033504
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 318 899514 899519 4194304 256 0 0 20 24 332864 0x7f20b1c5c400 0x7f1fa6037880 2323497 2323497 65536 38535168 4838840 619436944 12075916409063920 12075916409243923 12075916410786957 12075916410854147
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 320 899514 899519 4194304 256 0 0 12 24 335616 0x7f20b1c5c300 0x7f1fa60378c0 1202979 1202979 65536 39124992 4913770 628880100 12075916410878032 12075916411073195 12075916411862472 12075916411931059
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 322 899514 899519 4194304 256 0 0 12 24 339392 0x7f20b1c5ca00 0x7f1fa6037900 3442833 3442833 65536 55771136 7015754 897399764 12075916411955534 12075916412150631 12075916414432541 12075916414500544
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 324 899514 899519 4194304 256 0 0 12 24 344192 0x7f20b1c5c900 0x7f1fa6037940 2322483 2322483 65536 72548352 9109474 1166235308 12075916414543323 12075916414713500 12075916416248853 12075916416316799
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 899514 899519 4194304 256 0 0 20 24 345408 0x7f20b1c5c800 0x7f1fa6037980 9087337 9087337 65536 210698240 26345530 3372659472 12075916416346655 12075916416529652 12075916422582586 12075916422650290
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 328 899514 899519 4194304 256 0 0 20 24 348160 0x7f20b1c5c700 0x7f1fa60379c0 4573948 4573948 65536 76283904 9535244 1222007488 12075916422682720 12075916422859704 12075916425901771 12075916425974247
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 330 899514 899519 4194304 256 0 0 12 24 350912 0x7f20b1c5c600 0x7f1fa6037a00 2328153 2328153 65536 77398016 9701948 1242243220 12075916425998983 12075916426203050 12075916427742403 12075916427811642
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 332 899514 899519 4194304 256 0 0 12 24 0 0x7f20b1c5c500 0x7f1fa6037a40 6811515 6811515 65536 110821376 13883505 1777296880 12075916427841417 12075916428034082 12075916432560622 12075916432633032
@@ -1,168 +0,0 @@
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",0,0,0,901311,901316,33554432,256,0,0,8,32,6464,0x0,0x7f8ba1604180,0,0,0,12075942327036344,12075942571037950,12075942571360189,12075942571463912
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,901311,901316,32768,256,0,0,24,24,12480,0x0,0x7f8ba1635100,0,0,0,12075942586056261,12075942586355119,12075942586361839,12075942586377678
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,901311,901316,4194304,256,0,0,24,24,12928,0x7f8cad17c900,0x7f8ba1635140,0,0,0,12075942586430637,12075942586646478,12075942586779597,12075942586783532
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,901311,901316,4194304,256,0,0,36,24,13632,0x7f8cad17c800,0x7f8ba1635180,0,0,0,12075942586848583,12075942587013836,12075942587261995,12075942587313227
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,901311,901316,4194304,256,0,0,28,24,14080,0x7f8cad17c700,0x7f8ba16351c0,0,0,0,12075942587346699,12075942587530953,12075942587787272,12075942587833313
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,901311,901316,4194304,256,0,0,24,24,14528,0x7f8cad17c600,0x7f8ba1635200,0,0,0,12075942587859883,12075942588052711,12075942588186790,12075942588190577
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,901311,901316,4194304,256,0,0,24,24,14976,0x7f8cad17c500,0x7f8ba1635240,0,0,0,12075942588231564,12075942588424869,12075942588555589,12075942588558702
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,901311,901316,4194304,256,0,0,24,24,15424,0x7f8cad17c400,0x7f8ba1635280,0,0,0,12075942588636646,12075942588802948,12075942588934787,12075942588938247
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,901311,901316,4194304,256,0,0,28,24,16128,0x7f8cad17c300,0x7f8ba16352c0,0,0,0,12075942588985825,12075942589173346,12075942589432705,12075942589454366
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,901311,901316,4194304,256,0,0,28,24,16832,0x7f8cad17ca00,0x7f8ba1635300,0,0,0,12075942589503047,12075942589665824,12075942589921342,12075942589968021
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,901311,901316,4194304,256,0,0,24,24,17536,0x7f8cad17c900,0x7f8ba1635340,0,0,0,12075942589995662,12075942590194141,12075942590327741,12075942590331386
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,901311,901316,4194304,256,0,0,24,24,18240,0x7f8cad17c800,0x7f8ba1635380,0,0,0,12075942590377532,12075942590570779,12075942590707099,12075942590710370
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,901311,901316,4194304,256,0,0,24,24,18944,0x7f8cad17c700,0x7f8ba16353c0,0,0,0,12075942590769590,12075942590933498,12075942591061977,12075942591066142
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,901311,901316,4194304,256,0,0,28,24,19904,0x7f8cad17c600,0x7f8ba1635400,0,0,0,12075942591114481,12075942591298136,12075942591547415,12075942591593802
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,901311,901316,4194304,256,0,0,28,24,20608,0x7f8cad17c500,0x7f8ba1635440,0,0,0,12075942591620161,12075942591797174,12075942592049173,12075942592097428
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,901311,901316,4194304,256,0,0,24,24,21312,0x7f8cad17c400,0x7f8ba1635480,0,0,0,12075942592120701,12075942592301011,12075942592432691,12075942592436248
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,901311,901316,4194304,256,0,0,24,24,22016,0x7f8cad17c300,0x7f8ba16354c0,0,0,0,12075942592486060,12075942592663250,12075942592796209,12075942592799663
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,901311,901316,4194304,256,0,0,24,24,22720,0x7f8cad17ca00,0x7f8ba1635500,0,0,0,12075942592862871,12075942593057968,12075942593188047,12075942593191772
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,901311,901316,4194304,256,0,0,28,24,23680,0x7f8cad17c900,0x7f8ba1635540,0,0,0,12075942593239971,12075942593426446,12075942593679405,12075942593724281
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,901311,901316,4194304,256,0,0,28,24,24384,0x7f8cad17c800,0x7f8ba1635580,0,0,0,12075942593750039,12075942593930124,12075942594184203,12075942594229420
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,901311,901316,4194304,256,0,0,24,24,25088,0x7f8cad17c700,0x7f8ba16355c0,0,0,0,12075942594267321,12075942594441962,12075942594573801,12075942594577147
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,901311,901316,4194304,256,0,0,24,24,25792,0x7f8cad17c600,0x7f8ba1635600,0,0,0,12075942594625136,12075942594810920,12075942594939239,12075942594942656
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,901311,901316,4194304,256,0,0,24,24,26496,0x7f8cad17c500,0x7f8ba1635640,0,0,0,12075942595011694,12075942595183078,12075942595311078,12075942595314357
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,901311,901316,4194304,256,0,0,28,24,27712,0x7f8cad17c400,0x7f8ba1635680,0,0,0,12075942595364370,12075942595541797,12075942595797795,12075942595842067
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,901311,901316,4194304,256,0,0,28,24,28416,0x7f8cad17c300,0x7f8ba16356c0,0,0,0,12075942595869318,12075942596058914,12075942596312993,12075942596358818
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,901311,901316,4194304,256,0,0,24,24,29120,0x7f8cad17ca00,0x7f8ba1635700,0,0,0,12075942596387411,12075942596554272,12075942596687711,12075942596690865
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,901311,901316,4194304,256,0,0,24,24,30080,0x7f8cad17c900,0x7f8ba1635740,0,0,0,12075942596740076,12075942596914430,12075942597045950,12075942597049521
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,901311,901316,4194304,256,0,0,24,24,30784,0x7f8cad17c800,0x7f8ba1635780,0,0,0,12075942597110254,12075942597280029,12075942597415548,12075942597419288
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,901311,901316,4194304,256,0,0,28,24,32000,0x7f8cad17c700,0x7f8ba16357c0,0,0,0,12075942597467829,12075942597647067,12075942597903066,12075942597947660
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,901311,901316,4194304,256,0,0,28,24,32960,0x7f8cad17c600,0x7f8ba1635800,0,0,0,12075942597972797,12075942598158905,12075942598412663,12075942598458229
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,901311,901316,4194304,256,0,0,24,24,33920,0x7f8cad17c500,0x7f8ba1635840,0,0,0,12075942598484628,12075942598661462,12075942598793622,12075942598797039
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,901311,901316,4194304,256,0,0,24,24,34880,0x7f8cad17c400,0x7f8ba1635880,0,0,0,12075942598845699,12075942599028660,12075942599163540,12075942599167267
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,901311,901316,4194304,256,0,0,24,24,35840,0x7f8cad17c300,0x7f8ba16358c0,0,0,0,12075942599228821,12075942599397459,12075942599528498,12075942599531815
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,901311,901316,4194304,256,0,0,28,24,37312,0x7f8cad17ca00,0x7f8ba1635900,0,0,0,12075942599583170,12075942599757137,12075942600013776,12075942600058614
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,901311,901316,4194304,256,0,0,28,24,38272,0x7f8cad17c900,0x7f8ba1635940,0,0,0,12075942600085854,12075942600263055,12075942600512014,12075942600555387
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,901311,901316,4194304,256,0,0,24,24,39232,0x7f8cad17c800,0x7f8ba1635980,0,0,0,12075942600583229,12075942600751853,12075942600886412,12075942600889888
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,901311,901316,4194304,256,0,0,24,24,40192,0x7f8cad17c700,0x7f8ba16359c0,0,0,0,12075942600937036,12075942601128171,12075942601266090,12075942601269664
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,901311,901316,4194304,256,0,0,24,24,41152,0x7f8cad17c600,0x7f8ba1635a00,0,0,0,12075942601330177,12075942601497609,12075942601629929,12075942601633280
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,901311,901316,4194304,256,0,0,28,24,42624,0x7f8cad17c500,0x7f8ba1635a40,0,0,0,12075942601675198,12075942601863047,12075942602124326,12075942602169687
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,901311,901316,4194304,256,0,0,28,24,43584,0x7f8cad17c400,0x7f8ba1635a80,0,0,0,12075942602195936,12075942602372485,12075942602624644,12075942602668374
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,901311,901316,4194304,256,0,0,24,24,44544,0x7f8cad17c300,0x7f8ba1635ac0,0,0,0,12075942602694512,12075942602874243,12075942603005762,12075942603009227
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,901311,901316,4194304,256,0,0,24,24,45760,0x7f8cad17ca00,0x7f8ba1635b00,0,0,0,12075942603060793,12075942603230721,12075942603362241,12075942603365720
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,901311,901316,4194304,256,0,0,24,24,46720,0x7f8cad17c900,0x7f8ba1635b40,0,0,0,12075942603425681,12075942603591039,12075942603724479,12075942603727963
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,901311,901316,4194304,256,0,0,28,24,48448,0x7f8cad17c800,0x7f8ba1635b80,0,0,0,12075942603775391,12075942603949758,12075942604212637,12075942604258439
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,901311,901316,4194304,256,0,0,28,24,49408,0x7f8cad17c700,0x7f8ba1635bc0,0,0,0,12075942604284407,12075942604460635,12075942604716474,12075942604761293
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,901311,901316,4194304,256,0,0,24,24,50368,0x7f8cad17c600,0x7f8ba1635c00,0,0,0,12075942604785869,12075942604961593,12075942605092153,12075942605095965
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,901311,901316,4194304,256,0,0,24,24,51584,0x7f8cad17c500,0x7f8ba1635c40,0,0,0,12075942605145908,12075942605325271,12075942605457591,12075942605461094
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,901311,901316,4194304,256,0,0,24,24,52544,0x7f8cad17c400,0x7f8ba1635c80,0,0,0,12075942605521306,12075942605686390,12075942605816629,12075942605820041
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,901311,901316,4194304,256,0,0,28,24,54272,0x7f8cad17c300,0x7f8ba1635cc0,0,0,0,12075942605869733,12075942606053428,12075942606322867,12075942606368140
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,901311,901316,4194304,256,0,0,28,24,55488,0x7f8cad17ca00,0x7f8ba1635d00,0,0,0,12075942606396122,12075942606566866,12075942606826225,12075942606869091
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,901311,901316,4194304,256,0,0,24,24,56704,0x7f8cad17c900,0x7f8ba1635d40,0,0,0,12075942606894167,12075942607075663,12075942607203023,12075942607206538
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,901311,901316,4194304,256,0,0,24,24,58176,0x7f8cad17c800,0x7f8ba1635d80,0,0,0,12075942607255388,12075942607430702,12075942607572301,12075942607575604
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,901311,901316,4194304,256,0,0,24,24,59392,0x7f8cad17c700,0x7f8ba1635dc0,0,0,0,12075942607636477,12075942607800940,12075942607933739,12075942607937045
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,901311,901316,4194304,256,0,0,28,24,61376,0x7f8cad17c600,0x7f8ba1635e00,0,0,0,12075942607976970,12075942608171178,12075942608436617,12075942608481527
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,901311,901316,4194304,256,0,0,28,24,62592,0x7f8cad17c500,0x7f8ba1635e40,0,0,0,12075942608507375,12075942608687816,12075942608939495,12075942608983480
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,901311,901316,4194304,256,0,0,24,24,63808,0x7f8cad17c400,0x7f8ba1635e80,0,0,0,12075942609016051,12075942609186534,12075942609317253,12075942609320607
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,901311,901316,4194304,256,0,0,24,24,65280,0x7f8cad17c300,0x7f8ba1635ec0,0,0,0,12075942609372904,12075942609545892,12075942609687331,12075942609690754
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,901311,901316,4194304,256,0,0,24,24,66496,0x7f8cad17ca00,0x7f8ba1635f00,0,0,0,12075942609749434,12075942609915650,12075942610044130,12075942610047808
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,901311,901316,4194304,256,0,0,28,24,68480,0x7f8cad17c900,0x7f8ba1635f40,0,0,0,12075942610098222,12075942610272609,12075942610534847,12075942610579206
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,901311,901316,4194304,256,0,0,28,24,69696,0x7f8cad17c800,0x7f8ba1635f80,0,0,0,12075942610604553,12075942610777726,12075942611029405,12075942611073855
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,901311,901316,4194304,256,0,0,24,24,70912,0x7f8cad17c700,0x7f8ba1635fc0,0,0,0,12075942611101055,12075942611271004,12075942611403483,12075942611406844
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,901311,901316,4194304,256,0,0,24,24,72384,0x7f8cad17c600,0x7f8ba1636000,0,0,0,12075942611457077,12075942611628442,12075942611767642,12075942611771181
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,901311,901316,4194304,256,0,0,24,24,73600,0x7f8cad17c500,0x7f8ba1636040,0,0,0,12075942611835530,12075942612003801,12075942612136600,12075942612140317
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,901311,901316,4194304,256,0,0,28,24,75840,0x7f8cad17c400,0x7f8ba1636080,0,0,0,12075942612188106,12075942612380919,12075942612649878,12075942612694417
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,901311,901316,4194304,256,0,0,28,24,77056,0x7f8cad17c300,0x7f8ba16360c0,0,0,0,12075942612724062,12075942612886197,12075942613139955,12075942613186120
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,901311,901316,4194304,256,0,0,24,24,78272,0x7f8cad17ca00,0x7f8ba1636100,0,0,0,12075942613220675,12075942613391314,12075942613519794,12075942613523548
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,901311,901316,4194304,256,0,0,24,24,80000,0x7f8cad17c900,0x7f8ba1636140,0,0,0,12075942613571396,12075942613754033,12075942613897552,12075942613900999
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,901311,901316,4194304,256,0,0,24,24,81216,0x7f8cad17c800,0x7f8ba1636180,0,0,0,12075942613962273,12075942614134191,12075942614263790,12075942614267721
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,901311,901316,4194304,256,0,0,28,24,83456,0x7f8cad17c700,0x7f8ba16361c0,0,0,0,12075942614315850,12075942614490509,12075942614757228,12075942614801933
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,901311,901316,4194304,256,0,0,28,24,84928,0x7f8cad17c600,0x7f8ba1636200,0,0,0,12075942614828934,12075942614997547,12075942615246986,12075942615293387
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,901311,901316,4194304,256,0,0,24,24,86400,0x7f8cad17c500,0x7f8ba1636240,0,0,0,12075942615317942,12075942615495305,12075942615630504,12075942615633890
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,901311,901316,4194304,256,0,0,24,24,88128,0x7f8cad17c400,0x7f8ba1636280,0,0,0,12075942615684423,12075942615856743,12075942616006342,12075942616010249
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,901311,901316,4194304,256,0,0,24,24,89600,0x7f8cad17c300,0x7f8ba16362c0,0,0,0,12075942616096099,12075942616265061,12075942616399620,12075942616403079
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,901311,901316,4194304,256,0,0,28,24,92096,0x7f8cad17ca00,0x7f8ba1636300,0,0,0,12075942616445438,12075942616626499,12075942616895138,12075942616939095
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,901311,901316,4194304,256,0,0,28,24,93568,0x7f8cad17c900,0x7f8ba1636340,0,0,0,12075942616967929,12075942617141537,12075942617393216,12075942617439355
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,901311,901316,4194304,256,0,0,24,24,95040,0x7f8cad17c800,0x7f8ba1636380,0,0,0,12075942617470483,12075942617645535,12075942617778174,12075942617781641
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,901311,901316,4194304,256,0,0,24,24,96768,0x7f8cad17c700,0x7f8ba16363c0,0,0,0,12075942617829159,12075942618011933,12075942618170172,12075942618173680
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,901311,901316,4194304,256,0,0,24,24,98240,0x7f8cad17c600,0x7f8ba1636400,0,0,0,12075942618237007,12075942618404891,12075942618533851,12075942618537155
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,901311,901316,4194304,256,0,0,28,24,100736,0x7f8cad17c500,0x7f8ba1636440,0,0,0,12075942618588220,12075942618756090,12075942619021368,12075942619066609
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,901311,901316,4194304,256,0,0,28,24,102208,0x7f8cad17c400,0x7f8ba1636480,0,0,0,12075942619094461,12075942619263287,12075942619517686,12075942619561409
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,901311,901316,4194304,256,0,0,24,24,103680,0x7f8cad17c300,0x7f8ba16364c0,0,0,0,12075942619586505,12075942619758325,12075942619891764,12075942619895309
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,901311,901316,4194304,256,0,0,24,24,105664,0x7f8cad17ca00,0x7f8ba1636500,0,0,0,12075942619941675,12075942620136883,12075942620302962,12075942620306584
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,901311,901316,4194304,256,0,0,24,24,107136,0x7f8cad17c900,0x7f8ba1636540,0,0,0,12075942620368639,12075942620537361,12075942620673841,12075942620677313
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,901311,901316,4194304,256,0,0,28,24,109888,0x7f8cad17c800,0x7f8ba1636580,0,0,0,12075942620725061,12075942620897840,12075942621162799,12075942621208850
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,901311,901316,4194304,256,0,0,28,24,111360,0x7f8cad17c700,0x7f8ba16365c0,0,0,0,12075942621238055,12075942621404077,12075942621696076,12075942621715061
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,901311,901316,4194304,256,0,0,24,24,112832,0x7f8cad17c600,0x7f8ba1636600,0,0,0,12075942621770905,12075942621937195,12075942622073034,12075942622077004
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,901311,901316,4194304,256,0,0,24,24,114816,0x7f8cad17c500,0x7f8ba1636640,0,0,0,12075942622127538,12075942622312393,12075942622486472,12075942622489821
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,901311,901316,4194304,256,0,0,24,24,116288,0x7f8cad17c400,0x7f8ba1636680,0,0,0,12075942622553249,12075942622720231,12075942622855271,12075942622858646
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,901311,901316,4194304,256,0,0,28,24,119040,0x7f8cad17c300,0x7f8ba16366c0,0,0,0,12075942622906395,12075942623096550,12075942623356708,12075942623402237
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,901311,901316,4194304,256,0,0,28,24,120768,0x7f8cad17ca00,0x7f8ba1636700,0,0,0,12075942623428826,12075942623597187,12075942623849666,12075942623893690
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,901311,901316,4194304,256,0,0,24,24,122496,0x7f8cad17c900,0x7f8ba1636740,0,0,0,12075942623918797,12075942624098145,12075942624231904,12075942624235595
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,901311,901316,4194304,256,0,0,24,24,124736,0x7f8cad17c800,0x7f8ba1636780,0,0,0,12075942624285268,12075942624458303,12075942624640862,12075942624644375
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,901311,901316,4194304,256,0,0,24,24,126464,0x7f8cad17c700,0x7f8ba16367c0,0,0,0,12075942624704677,12075942624869661,12075942625005661,12075942625009504
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,901311,901316,4194304,256,0,0,20,24,127936,0x7f8cad17c600,0x7f8ba1636800,0,0,0,12075942625056140,12075942625235100,12075942625502459,12075942625540070
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,901311,901316,4194304,256,0,0,28,24,129664,0x7f8cad17c500,0x7f8ba1636840,0,0,0,12075942625572360,12075942625733337,12075942625981496,12075942626017106
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,901311,901316,4194304,256,0,0,24,24,131392,0x7f8cad17c400,0x7f8ba1636880,0,0,0,12075942626050198,12075942626218135,12075942626351895,12075942626355515
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,901311,901316,4194304,256,0,0,24,24,133632,0x7f8cad17c300,0x7f8ba16368c0,0,0,0,12075942626400799,12075942626577814,12075942626769813,12075942626787839
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,901311,901316,4194304,256,0,0,24,24,135360,0x7f8cad17ca00,0x7f8ba1636900,0,0,0,12075942626851036,12075942627021812,12075942627160851,12075942627164449
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,901311,901316,4194304,256,0,0,20,24,136832,0x7f8cad17c900,0x7f8ba1636940,0,0,0,12075942627209392,12075942627390610,12075942627673489,12075942627696187
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,901311,901316,4194304,256,0,0,28,24,138560,0x7f8cad17c800,0x7f8ba1636980,0,0,0,12075942627734047,12075942627895407,12075942628150286,12075942628186198
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,901311,901316,4194304,256,0,0,24,24,140288,0x7f8cad17c700,0x7f8ba16369c0,0,0,0,12075942628218668,12075942628388365,12075942628519405,12075942628523174
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,901311,901316,4194304,256,0,0,24,24,142784,0x7f8cad17c600,0x7f8ba1636a00,0,0,0,12075942628571944,12075942628748044,12075942628957803,12075942628979913
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,901311,901316,4194304,256,0,0,24,24,144768,0x7f8cad17c500,0x7f8ba1636a40,0,0,0,12075942629043992,12075942629210761,12075942629353001,12075942629356793
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,901311,901316,4194304,256,0,0,20,24,145728,0x7f8cad17c400,0x7f8ba1636a80,0,0,0,12075942629403530,12075942629584360,12075942629891398,12075942629914509
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,901311,901316,4194304,256,0,0,28,24,147712,0x7f8cad17c300,0x7f8ba1636ac0,0,0,0,12075942629959453,12075942630134117,12075942630393956,12075942630418186
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,901311,901316,4194304,256,0,0,24,24,149696,0x7f8cad17ca00,0x7f8ba1636b00,0,0,0,12075942630466756,12075942630633315,12075942630768674,12075942630772414
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,901311,901316,4194304,256,0,0,24,24,152192,0x7f8cad17c900,0x7f8ba1636b40,0,0,0,12075942630818900,12075942631005153,12075942631233632,12075942631258728
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,901311,901316,4194304,256,0,0,24,24,154176,0x7f8cad17c800,0x7f8ba1636b80,0,0,0,12075942631314101,12075942631481631,12075942631619710,12075942631623375
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,901311,901316,4194304,256,0,0,20,24,155648,0x7f8cad17c700,0x7f8ba1636bc0,0,0,0,12075942631671465,12075942631851709,12075942632181468,12075942632218351
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,901311,901316,4194304,256,0,0,28,24,157632,0x7f8cad17c600,0x7f8ba1636c00,0,0,0,12075942632252875,12075942632421787,12075942632677945,12075942632699756
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,901311,901316,4194304,256,0,0,24,24,159616,0x7f8cad17c500,0x7f8ba1636c40,0,0,0,12075942632744429,12075942632908664,12075942633050424,12075942633054365
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,901311,901316,4194304,256,0,0,24,24,162368,0x7f8cad17c400,0x7f8ba1636c80,0,0,0,12075942633100911,12075942633281303,12075942633525942,12075942633547882
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,901311,901316,4194304,256,0,0,24,24,164608,0x7f8cad17c300,0x7f8ba1636cc0,0,0,0,12075942633602213,12075942633768980,12075942633909300,12075942633912930
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,901311,901316,4194304,256,0,0,20,24,166336,0x7f8cad17ca00,0x7f8ba1636d00,0,0,0,12075942633960158,12075942634153792,12075942634530271,12075942634569991
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,901311,901316,4194304,256,0,0,28,24,168576,0x7f8cad17c900,0x7f8ba1636d40,0,0,0,12075942634597913,12075942634763869,12075942635028827,12075942635051647
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,901311,901316,4194304,256,0,0,24,24,170816,0x7f8cad17c800,0x7f8ba1636d80,0,0,0,12075942635102681,12075942635268666,12075942635407866,12075942635411505
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,901311,901316,4194304,256,0,0,24,24,174080,0x7f8cad17c700,0x7f8ba1636dc0,0,0,0,12075942635460416,12075942635634425,12075942635944983,12075942635966767
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,901311,901316,4194304,256,0,0,24,24,176576,0x7f8cad17c600,0x7f8ba1636e00,0,0,0,12075942636032640,12075942636204182,12075942636341942,12075942636345621
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,901311,901316,4194304,256,0,0,20,24,177792,0x7f8cad17c500,0x7f8ba1636e40,0,0,0,12075942636391436,12075942636577141,12075942637024499,12075942637047305
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,901311,901316,4194304,256,0,0,28,24,180288,0x7f8cad17c400,0x7f8ba1636e80,0,0,0,12075942637096286,12075942637263858,12075942637529137,12075942637550561
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,901311,901316,4194304,256,0,0,24,24,182784,0x7f8cad17c300,0x7f8ba1636ec0,0,0,0,12075942637598470,12075942637762255,12075942637900495,12075942637904348
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,901311,901316,4194304,256,0,0,24,24,186304,0x7f8cad17ca00,0x7f8ba1636f00,0,0,0,12075942637950484,12075942638142894,12075942638457132,12075942638493824
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,901311,901316,4194304,256,0,0,24,24,189312,0x7f8cad17c900,0x7f8ba1636f40,0,0,0,12075942638537826,12075942638703851,12075942638856331,12075942638859944
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,901311,901316,4194304,256,0,0,20,24,190784,0x7f8cad17c800,0x7f8ba1636f80,0,0,0,12075942638906952,12075942639091850,12075942639609767,12075942639644893
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,901311,901316,4194304,256,0,0,28,24,193792,0x7f8cad17c700,0x7f8ba1636fc0,0,0,0,12075942639680359,12075942639846886,12075942640143845,12075942640166282
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,901311,901316,4194304,256,0,0,24,24,196800,0x7f8cad17c600,0x7f8ba1637000,0,0,0,12075942640215043,12075942640384004,12075942640539683,12075942640543172
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,901311,901316,4194304,256,0,0,24,24,201088,0x7f8cad17c500,0x7f8ba1637040,0,0,0,12075942640591162,12075942640765762,12075942641153121,12075942641175748
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,901311,901316,4194304,256,0,0,24,24,204608,0x7f8cad17c400,0x7f8ba1637080,0,0,0,12075942641238164,12075942641407039,12075942641583359,12075942641586922
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,901311,901316,4194304,256,0,0,20,24,206080,0x7f8cad17c300,0x7f8ba16370c0,0,0,0,12075942641634050,12075942641818398,12075942642440955,12075942642476886
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,901311,901316,4194304,256,0,0,28,24,209600,0x7f8cad17ca00,0x7f8ba1637100,0,0,0,12075942642510799,12075942642678234,12075942643007672,12075942643029964
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,901311,901316,4194304,256,0,0,24,24,213120,0x7f8cad17c900,0x7f8ba1637140,0,0,0,12075942643079486,12075942643242231,12075942643421591,12075942643425098
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,901311,901316,4194304,256,0,0,24,24,218176,0x7f8cad17c800,0x7f8ba1637180,0,0,0,12075942643473719,12075942643656150,12075942644133588,12075942644156778
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,901311,901316,4194304,256,0,0,24,24,222208,0x7f8cad17c700,0x7f8ba16371c0,0,0,0,12075942644218383,12075942644388146,12075942644589426,12075942644611022
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,901311,901316,4194304,256,0,0,20,24,223936,0x7f8cad17c600,0x7f8ba1637200,0,0,0,12075942644662959,12075942644829744,12075942645539501,12075942645580304
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,901311,901316,4194304,256,0,0,28,24,227968,0x7f8cad17c500,0x7f8ba1637240,0,0,0,12075942645604989,12075942645781900,12075942646154699,12075942646202690
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,901311,901316,4194304,256,0,0,24,24,232000,0x7f8cad17c400,0x7f8ba1637280,0,0,0,12075942646230452,12075942646397418,12075942646600457,12075942646645203
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,901311,901316,4194304,256,0,0,24,24,237824,0x7f8cad17c300,0x7f8ba16372c0,0,0,0,12075942646679246,12075942646845736,12075942647371813,12075942647417688
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,901311,901316,4194304,256,0,0,24,24,242368,0x7f8cad17ca00,0x7f8ba1637300,0,0,0,12075942647455809,12075942647628132,12075942647851651,12075942647896388
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,901311,901316,4194304,256,0,0,20,24,243584,0x7f8cad17c900,0x7f8ba1637340,0,0,0,12075942647930111,12075942648100450,12075942648900607,12075942648945428
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,901311,901316,4194304,256,0,0,28,24,248128,0x7f8cad17c800,0x7f8ba1637380,0,0,0,12075942648973880,12075942649142366,12075942649564444,12075942649610193
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,901311,901316,4194304,256,0,0,24,24,252672,0x7f8cad17c700,0x7f8ba16373c0,0,0,0,12075942649637033,12075942649815003,12075942650041882,12075942650087961
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,901311,901316,4194304,256,0,0,24,24,259264,0x7f8cad17c600,0x7f8ba1637400,0,0,0,12075942650114811,12075942650285561,12075942650883478,12075942650927822
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,901311,901316,4194304,256,0,0,24,24,264832,0x7f8cad17c500,0x7f8ba1637440,0,0,0,12075942650965622,12075942651140917,12075942651410516,12075942651456434
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,901311,901316,4194304,256,0,0,20,24,266304,0x7f8cad17c400,0x7f8ba1637480,0,0,0,12075942651483795,12075942651650515,12075942652637070,12075942652682503
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,901311,901316,4194304,256,0,0,28,24,271872,0x7f8cad17c300,0x7f8ba16374c0,0,0,0,12075942652716917,12075942652888429,12075942653402507,12075942653447484
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,901311,901316,4194304,256,0,0,24,24,277440,0x7f8cad17ca00,0x7f8ba1637500,0,0,0,12075942653480205,12075942653648746,12075942653921545,12075942653940391
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,901311,901316,4194304,256,0,0,12,24,279936,0x7f8cad17c900,0x7f8ba1637540,0,0,0,12075942653997196,12075942654171943,12075942654910180,12075942654956098
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,901311,901316,4194304,256,0,0,24,24,286528,0x7f8cad17c800,0x7f8ba1637580,0,0,0,12075942655006211,12075942655173219,12075942655490978,12075942655537188
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,901311,901316,4194304,256,0,0,20,24,288000,0x7f8cad17c700,0x7f8ba16375c0,0,0,0,12075942655563377,12075942655737537,12075942656908411,12075942656954803
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,901311,901316,4194304,256,0,0,32,24,294592,0x7f8cad17c600,0x7f8ba1637600,0,0,0,12075942656985460,12075942657172250,12075942657783288,12075942657828116
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,901311,901316,4194304,256,0,0,24,24,301184,0x7f8cad17c500,0x7f8ba1637640,0,0,0,12075942657860576,12075942658036247,12075942658356885,12075942658403515
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,901311,901316,4194304,256,0,0,12,24,304960,0x7f8cad17c400,0x7f8ba1637680,0,0,0,12075942658436627,12075942658605684,12075942659484560,12075942659530540
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,901311,901316,4194304,256,0,0,24,24,313600,0x7f8cad17c300,0x7f8ba16376c0,0,0,0,12075942659575934,12075942659741839,12075942660153997,12075942660200495
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,901311,901316,4194304,256,0,0,20,24,314816,0x7f8cad17ca00,0x7f8ba1637700,0,0,0,12075942660230140,12075942660394156,12075942661943589,12075942661989640
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,901311,901316,4194304,256,0,0,20,24,317568,0x7f8cad17c900,0x7f8ba1637740,0,0,0,12075942662020527,12075942662189188,12075942662985185,12075942663031947
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,901311,901316,4194304,256,0,0,12,24,320320,0x7f8cad17c800,0x7f8ba1637780,0,0,0,12075942663064217,12075942663231904,12075942663647262,12075942663692524
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,901311,901316,4194304,256,0,0,12,24,324096,0x7f8cad17c700,0x7f8ba16377c0,0,0,0,12075942663725806,12075942663891901,12075942665051096,12075942665097435
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,901311,901316,4194304,256,0,0,12,24,328896,0x7f8cad17c600,0x7f8ba1637800,0,0,0,12075942665142760,12075942665313335,12075942666098931,12075942666144461
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,901311,901316,4194304,256,0,0,20,24,330112,0x7f8cad17c500,0x7f8ba1637840,0,0,0,12075942666178565,12075942666345490,12075942669397317,12075942669443643
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,901311,901316,4194304,256,0,0,20,24,332864,0x7f8cad17c400,0x7f8ba1637880,0,0,0,12075942669475031,12075942669645316,12075942671188989,12075942671235262
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,901311,901316,4194304,256,0,0,12,24,335616,0x7f8cad17c300,0x7f8ba16378c0,0,0,0,12075942671269526,12075942671438428,12075942672228344,12075942672274363
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,901311,901316,4194304,256,0,0,12,24,339392,0x7f8cad17ca00,0x7f8ba1637900,0,0,0,12075942672308807,12075942672476823,12075942674759053,12075942674804786
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,901311,901316,4194304,256,0,0,12,24,344192,0x7f8cad17c900,0x7f8ba1637940,0,0,0,12075942674847535,12075942675013452,12075942676549125,12075942676595995
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,901311,901316,4194304,256,0,0,20,24,345408,0x7f8cad17c800,0x7f8ba1637980,0,0,0,12075942676629688,12075942676800164,12075942682854698,12075942682901904
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,901311,901316,4194304,256,0,0,20,24,348160,0x7f8cad17c700,0x7f8ba16379c0,0,0,0,12075942682936198,12075942683115656,12075942686156763,12075942686204051
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,901311,901316,4194304,256,0,0,12,24,350912,0x7f8cad17c600,0x7f8ba1637a00,0,0,0,12075942686233836,12075942686396762,12075942687935475,12075942687982366
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,901311,901316,4194304,256,0,0,12,24,0,0x7f8cad17c500,0x7f8ba1637a40,0,0,0,12075942688024494,12075942688190674,12075942692717534,12075942692765686
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 901311 901316 33554432 256 0 0 8 32 6464 0x0 0x7f8ba1604180 0 0 0 12075942327036344 12075942571037950 12075942571360189 12075942571463912
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 901311 901316 32768 256 0 0 24 24 12480 0x0 0x7f8ba1635100 0 0 0 12075942586056261 12075942586355119 12075942586361839 12075942586377678
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 4 901311 901316 4194304 256 0 0 24 24 12928 0x7f8cad17c900 0x7f8ba1635140 0 0 0 12075942586430637 12075942586646478 12075942586779597 12075942586783532
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 901311 901316 4194304 256 0 0 36 24 13632 0x7f8cad17c800 0x7f8ba1635180 0 0 0 12075942586848583 12075942587013836 12075942587261995 12075942587313227
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 8 901311 901316 4194304 256 0 0 28 24 14080 0x7f8cad17c700 0x7f8ba16351c0 0 0 0 12075942587346699 12075942587530953 12075942587787272 12075942587833313
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 10 901311 901316 4194304 256 0 0 24 24 14528 0x7f8cad17c600 0x7f8ba1635200 0 0 0 12075942587859883 12075942588052711 12075942588186790 12075942588190577
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 12 901311 901316 4194304 256 0 0 24 24 14976 0x7f8cad17c500 0x7f8ba1635240 0 0 0 12075942588231564 12075942588424869 12075942588555589 12075942588558702
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 14 901311 901316 4194304 256 0 0 24 24 15424 0x7f8cad17c400 0x7f8ba1635280 0 0 0 12075942588636646 12075942588802948 12075942588934787 12075942588938247
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 901311 901316 4194304 256 0 0 28 24 16128 0x7f8cad17c300 0x7f8ba16352c0 0 0 0 12075942588985825 12075942589173346 12075942589432705 12075942589454366
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 18 901311 901316 4194304 256 0 0 28 24 16832 0x7f8cad17ca00 0x7f8ba1635300 0 0 0 12075942589503047 12075942589665824 12075942589921342 12075942589968021
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 20 901311 901316 4194304 256 0 0 24 24 17536 0x7f8cad17c900 0x7f8ba1635340 0 0 0 12075942589995662 12075942590194141 12075942590327741 12075942590331386
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 22 901311 901316 4194304 256 0 0 24 24 18240 0x7f8cad17c800 0x7f8ba1635380 0 0 0 12075942590377532 12075942590570779 12075942590707099 12075942590710370
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 24 901311 901316 4194304 256 0 0 24 24 18944 0x7f8cad17c700 0x7f8ba16353c0 0 0 0 12075942590769590 12075942590933498 12075942591061977 12075942591066142
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 901311 901316 4194304 256 0 0 28 24 19904 0x7f8cad17c600 0x7f8ba1635400 0 0 0 12075942591114481 12075942591298136 12075942591547415 12075942591593802
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 28 901311 901316 4194304 256 0 0 28 24 20608 0x7f8cad17c500 0x7f8ba1635440 0 0 0 12075942591620161 12075942591797174 12075942592049173 12075942592097428
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 30 901311 901316 4194304 256 0 0 24 24 21312 0x7f8cad17c400 0x7f8ba1635480 0 0 0 12075942592120701 12075942592301011 12075942592432691 12075942592436248
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 32 901311 901316 4194304 256 0 0 24 24 22016 0x7f8cad17c300 0x7f8ba16354c0 0 0 0 12075942592486060 12075942592663250 12075942592796209 12075942592799663
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 34 901311 901316 4194304 256 0 0 24 24 22720 0x7f8cad17ca00 0x7f8ba1635500 0 0 0 12075942592862871 12075942593057968 12075942593188047 12075942593191772
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 901311 901316 4194304 256 0 0 28 24 23680 0x7f8cad17c900 0x7f8ba1635540 0 0 0 12075942593239971 12075942593426446 12075942593679405 12075942593724281
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 38 901311 901316 4194304 256 0 0 28 24 24384 0x7f8cad17c800 0x7f8ba1635580 0 0 0 12075942593750039 12075942593930124 12075942594184203 12075942594229420
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 40 901311 901316 4194304 256 0 0 24 24 25088 0x7f8cad17c700 0x7f8ba16355c0 0 0 0 12075942594267321 12075942594441962 12075942594573801 12075942594577147
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 42 901311 901316 4194304 256 0 0 24 24 25792 0x7f8cad17c600 0x7f8ba1635600 0 0 0 12075942594625136 12075942594810920 12075942594939239 12075942594942656
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 44 901311 901316 4194304 256 0 0 24 24 26496 0x7f8cad17c500 0x7f8ba1635640 0 0 0 12075942595011694 12075942595183078 12075942595311078 12075942595314357
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 901311 901316 4194304 256 0 0 28 24 27712 0x7f8cad17c400 0x7f8ba1635680 0 0 0 12075942595364370 12075942595541797 12075942595797795 12075942595842067
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 48 901311 901316 4194304 256 0 0 28 24 28416 0x7f8cad17c300 0x7f8ba16356c0 0 0 0 12075942595869318 12075942596058914 12075942596312993 12075942596358818
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 50 901311 901316 4194304 256 0 0 24 24 29120 0x7f8cad17ca00 0x7f8ba1635700 0 0 0 12075942596387411 12075942596554272 12075942596687711 12075942596690865
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 52 901311 901316 4194304 256 0 0 24 24 30080 0x7f8cad17c900 0x7f8ba1635740 0 0 0 12075942596740076 12075942596914430 12075942597045950 12075942597049521
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 54 901311 901316 4194304 256 0 0 24 24 30784 0x7f8cad17c800 0x7f8ba1635780 0 0 0 12075942597110254 12075942597280029 12075942597415548 12075942597419288
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 901311 901316 4194304 256 0 0 28 24 32000 0x7f8cad17c700 0x7f8ba16357c0 0 0 0 12075942597467829 12075942597647067 12075942597903066 12075942597947660
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 58 901311 901316 4194304 256 0 0 28 24 32960 0x7f8cad17c600 0x7f8ba1635800 0 0 0 12075942597972797 12075942598158905 12075942598412663 12075942598458229
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 60 901311 901316 4194304 256 0 0 24 24 33920 0x7f8cad17c500 0x7f8ba1635840 0 0 0 12075942598484628 12075942598661462 12075942598793622 12075942598797039
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 62 901311 901316 4194304 256 0 0 24 24 34880 0x7f8cad17c400 0x7f8ba1635880 0 0 0 12075942598845699 12075942599028660 12075942599163540 12075942599167267
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 64 901311 901316 4194304 256 0 0 24 24 35840 0x7f8cad17c300 0x7f8ba16358c0 0 0 0 12075942599228821 12075942599397459 12075942599528498 12075942599531815
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 901311 901316 4194304 256 0 0 28 24 37312 0x7f8cad17ca00 0x7f8ba1635900 0 0 0 12075942599583170 12075942599757137 12075942600013776 12075942600058614
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 68 901311 901316 4194304 256 0 0 28 24 38272 0x7f8cad17c900 0x7f8ba1635940 0 0 0 12075942600085854 12075942600263055 12075942600512014 12075942600555387
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 70 901311 901316 4194304 256 0 0 24 24 39232 0x7f8cad17c800 0x7f8ba1635980 0 0 0 12075942600583229 12075942600751853 12075942600886412 12075942600889888
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 72 901311 901316 4194304 256 0 0 24 24 40192 0x7f8cad17c700 0x7f8ba16359c0 0 0 0 12075942600937036 12075942601128171 12075942601266090 12075942601269664
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 74 901311 901316 4194304 256 0 0 24 24 41152 0x7f8cad17c600 0x7f8ba1635a00 0 0 0 12075942601330177 12075942601497609 12075942601629929 12075942601633280
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 901311 901316 4194304 256 0 0 28 24 42624 0x7f8cad17c500 0x7f8ba1635a40 0 0 0 12075942601675198 12075942601863047 12075942602124326 12075942602169687
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 78 901311 901316 4194304 256 0 0 28 24 43584 0x7f8cad17c400 0x7f8ba1635a80 0 0 0 12075942602195936 12075942602372485 12075942602624644 12075942602668374
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 80 901311 901316 4194304 256 0 0 24 24 44544 0x7f8cad17c300 0x7f8ba1635ac0 0 0 0 12075942602694512 12075942602874243 12075942603005762 12075942603009227
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 82 901311 901316 4194304 256 0 0 24 24 45760 0x7f8cad17ca00 0x7f8ba1635b00 0 0 0 12075942603060793 12075942603230721 12075942603362241 12075942603365720
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 84 901311 901316 4194304 256 0 0 24 24 46720 0x7f8cad17c900 0x7f8ba1635b40 0 0 0 12075942603425681 12075942603591039 12075942603724479 12075942603727963
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 901311 901316 4194304 256 0 0 28 24 48448 0x7f8cad17c800 0x7f8ba1635b80 0 0 0 12075942603775391 12075942603949758 12075942604212637 12075942604258439
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 88 901311 901316 4194304 256 0 0 28 24 49408 0x7f8cad17c700 0x7f8ba1635bc0 0 0 0 12075942604284407 12075942604460635 12075942604716474 12075942604761293
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 90 901311 901316 4194304 256 0 0 24 24 50368 0x7f8cad17c600 0x7f8ba1635c00 0 0 0 12075942604785869 12075942604961593 12075942605092153 12075942605095965
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 92 901311 901316 4194304 256 0 0 24 24 51584 0x7f8cad17c500 0x7f8ba1635c40 0 0 0 12075942605145908 12075942605325271 12075942605457591 12075942605461094
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 94 901311 901316 4194304 256 0 0 24 24 52544 0x7f8cad17c400 0x7f8ba1635c80 0 0 0 12075942605521306 12075942605686390 12075942605816629 12075942605820041
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 901311 901316 4194304 256 0 0 28 24 54272 0x7f8cad17c300 0x7f8ba1635cc0 0 0 0 12075942605869733 12075942606053428 12075942606322867 12075942606368140
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 98 901311 901316 4194304 256 0 0 28 24 55488 0x7f8cad17ca00 0x7f8ba1635d00 0 0 0 12075942606396122 12075942606566866 12075942606826225 12075942606869091
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 100 901311 901316 4194304 256 0 0 24 24 56704 0x7f8cad17c900 0x7f8ba1635d40 0 0 0 12075942606894167 12075942607075663 12075942607203023 12075942607206538
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 102 901311 901316 4194304 256 0 0 24 24 58176 0x7f8cad17c800 0x7f8ba1635d80 0 0 0 12075942607255388 12075942607430702 12075942607572301 12075942607575604
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 104 901311 901316 4194304 256 0 0 24 24 59392 0x7f8cad17c700 0x7f8ba1635dc0 0 0 0 12075942607636477 12075942607800940 12075942607933739 12075942607937045
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 901311 901316 4194304 256 0 0 28 24 61376 0x7f8cad17c600 0x7f8ba1635e00 0 0 0 12075942607976970 12075942608171178 12075942608436617 12075942608481527
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 108 901311 901316 4194304 256 0 0 28 24 62592 0x7f8cad17c500 0x7f8ba1635e40 0 0 0 12075942608507375 12075942608687816 12075942608939495 12075942608983480
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 110 901311 901316 4194304 256 0 0 24 24 63808 0x7f8cad17c400 0x7f8ba1635e80 0 0 0 12075942609016051 12075942609186534 12075942609317253 12075942609320607
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 112 901311 901316 4194304 256 0 0 24 24 65280 0x7f8cad17c300 0x7f8ba1635ec0 0 0 0 12075942609372904 12075942609545892 12075942609687331 12075942609690754
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 114 901311 901316 4194304 256 0 0 24 24 66496 0x7f8cad17ca00 0x7f8ba1635f00 0 0 0 12075942609749434 12075942609915650 12075942610044130 12075942610047808
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 901311 901316 4194304 256 0 0 28 24 68480 0x7f8cad17c900 0x7f8ba1635f40 0 0 0 12075942610098222 12075942610272609 12075942610534847 12075942610579206
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 118 901311 901316 4194304 256 0 0 28 24 69696 0x7f8cad17c800 0x7f8ba1635f80 0 0 0 12075942610604553 12075942610777726 12075942611029405 12075942611073855
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 120 901311 901316 4194304 256 0 0 24 24 70912 0x7f8cad17c700 0x7f8ba1635fc0 0 0 0 12075942611101055 12075942611271004 12075942611403483 12075942611406844
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 122 901311 901316 4194304 256 0 0 24 24 72384 0x7f8cad17c600 0x7f8ba1636000 0 0 0 12075942611457077 12075942611628442 12075942611767642 12075942611771181
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 124 901311 901316 4194304 256 0 0 24 24 73600 0x7f8cad17c500 0x7f8ba1636040 0 0 0 12075942611835530 12075942612003801 12075942612136600 12075942612140317
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 901311 901316 4194304 256 0 0 28 24 75840 0x7f8cad17c400 0x7f8ba1636080 0 0 0 12075942612188106 12075942612380919 12075942612649878 12075942612694417
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 128 901311 901316 4194304 256 0 0 28 24 77056 0x7f8cad17c300 0x7f8ba16360c0 0 0 0 12075942612724062 12075942612886197 12075942613139955 12075942613186120
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 130 901311 901316 4194304 256 0 0 24 24 78272 0x7f8cad17ca00 0x7f8ba1636100 0 0 0 12075942613220675 12075942613391314 12075942613519794 12075942613523548
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 132 901311 901316 4194304 256 0 0 24 24 80000 0x7f8cad17c900 0x7f8ba1636140 0 0 0 12075942613571396 12075942613754033 12075942613897552 12075942613900999
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 134 901311 901316 4194304 256 0 0 24 24 81216 0x7f8cad17c800 0x7f8ba1636180 0 0 0 12075942613962273 12075942614134191 12075942614263790 12075942614267721
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 901311 901316 4194304 256 0 0 28 24 83456 0x7f8cad17c700 0x7f8ba16361c0 0 0 0 12075942614315850 12075942614490509 12075942614757228 12075942614801933
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 138 901311 901316 4194304 256 0 0 28 24 84928 0x7f8cad17c600 0x7f8ba1636200 0 0 0 12075942614828934 12075942614997547 12075942615246986 12075942615293387
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 140 901311 901316 4194304 256 0 0 24 24 86400 0x7f8cad17c500 0x7f8ba1636240 0 0 0 12075942615317942 12075942615495305 12075942615630504 12075942615633890
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 142 901311 901316 4194304 256 0 0 24 24 88128 0x7f8cad17c400 0x7f8ba1636280 0 0 0 12075942615684423 12075942615856743 12075942616006342 12075942616010249
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 144 901311 901316 4194304 256 0 0 24 24 89600 0x7f8cad17c300 0x7f8ba16362c0 0 0 0 12075942616096099 12075942616265061 12075942616399620 12075942616403079
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 901311 901316 4194304 256 0 0 28 24 92096 0x7f8cad17ca00 0x7f8ba1636300 0 0 0 12075942616445438 12075942616626499 12075942616895138 12075942616939095
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 148 901311 901316 4194304 256 0 0 28 24 93568 0x7f8cad17c900 0x7f8ba1636340 0 0 0 12075942616967929 12075942617141537 12075942617393216 12075942617439355
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 150 901311 901316 4194304 256 0 0 24 24 95040 0x7f8cad17c800 0x7f8ba1636380 0 0 0 12075942617470483 12075942617645535 12075942617778174 12075942617781641
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 152 901311 901316 4194304 256 0 0 24 24 96768 0x7f8cad17c700 0x7f8ba16363c0 0 0 0 12075942617829159 12075942618011933 12075942618170172 12075942618173680
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 154 901311 901316 4194304 256 0 0 24 24 98240 0x7f8cad17c600 0x7f8ba1636400 0 0 0 12075942618237007 12075942618404891 12075942618533851 12075942618537155
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 901311 901316 4194304 256 0 0 28 24 100736 0x7f8cad17c500 0x7f8ba1636440 0 0 0 12075942618588220 12075942618756090 12075942619021368 12075942619066609
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 158 901311 901316 4194304 256 0 0 28 24 102208 0x7f8cad17c400 0x7f8ba1636480 0 0 0 12075942619094461 12075942619263287 12075942619517686 12075942619561409
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 160 901311 901316 4194304 256 0 0 24 24 103680 0x7f8cad17c300 0x7f8ba16364c0 0 0 0 12075942619586505 12075942619758325 12075942619891764 12075942619895309
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 162 901311 901316 4194304 256 0 0 24 24 105664 0x7f8cad17ca00 0x7f8ba1636500 0 0 0 12075942619941675 12075942620136883 12075942620302962 12075942620306584
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 164 901311 901316 4194304 256 0 0 24 24 107136 0x7f8cad17c900 0x7f8ba1636540 0 0 0 12075942620368639 12075942620537361 12075942620673841 12075942620677313
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 901311 901316 4194304 256 0 0 28 24 109888 0x7f8cad17c800 0x7f8ba1636580 0 0 0 12075942620725061 12075942620897840 12075942621162799 12075942621208850
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 168 901311 901316 4194304 256 0 0 28 24 111360 0x7f8cad17c700 0x7f8ba16365c0 0 0 0 12075942621238055 12075942621404077 12075942621696076 12075942621715061
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 170 901311 901316 4194304 256 0 0 24 24 112832 0x7f8cad17c600 0x7f8ba1636600 0 0 0 12075942621770905 12075942621937195 12075942622073034 12075942622077004
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 172 901311 901316 4194304 256 0 0 24 24 114816 0x7f8cad17c500 0x7f8ba1636640 0 0 0 12075942622127538 12075942622312393 12075942622486472 12075942622489821
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 174 901311 901316 4194304 256 0 0 24 24 116288 0x7f8cad17c400 0x7f8ba1636680 0 0 0 12075942622553249 12075942622720231 12075942622855271 12075942622858646
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 901311 901316 4194304 256 0 0 28 24 119040 0x7f8cad17c300 0x7f8ba16366c0 0 0 0 12075942622906395 12075942623096550 12075942623356708 12075942623402237
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 178 901311 901316 4194304 256 0 0 28 24 120768 0x7f8cad17ca00 0x7f8ba1636700 0 0 0 12075942623428826 12075942623597187 12075942623849666 12075942623893690
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 180 901311 901316 4194304 256 0 0 24 24 122496 0x7f8cad17c900 0x7f8ba1636740 0 0 0 12075942623918797 12075942624098145 12075942624231904 12075942624235595
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 182 901311 901316 4194304 256 0 0 24 24 124736 0x7f8cad17c800 0x7f8ba1636780 0 0 0 12075942624285268 12075942624458303 12075942624640862 12075942624644375
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 184 901311 901316 4194304 256 0 0 24 24 126464 0x7f8cad17c700 0x7f8ba16367c0 0 0 0 12075942624704677 12075942624869661 12075942625005661 12075942625009504
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 901311 901316 4194304 256 0 0 20 24 127936 0x7f8cad17c600 0x7f8ba1636800 0 0 0 12075942625056140 12075942625235100 12075942625502459 12075942625540070
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 188 901311 901316 4194304 256 0 0 28 24 129664 0x7f8cad17c500 0x7f8ba1636840 0 0 0 12075942625572360 12075942625733337 12075942625981496 12075942626017106
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 190 901311 901316 4194304 256 0 0 24 24 131392 0x7f8cad17c400 0x7f8ba1636880 0 0 0 12075942626050198 12075942626218135 12075942626351895 12075942626355515
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 192 901311 901316 4194304 256 0 0 24 24 133632 0x7f8cad17c300 0x7f8ba16368c0 0 0 0 12075942626400799 12075942626577814 12075942626769813 12075942626787839
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 194 901311 901316 4194304 256 0 0 24 24 135360 0x7f8cad17ca00 0x7f8ba1636900 0 0 0 12075942626851036 12075942627021812 12075942627160851 12075942627164449
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 901311 901316 4194304 256 0 0 20 24 136832 0x7f8cad17c900 0x7f8ba1636940 0 0 0 12075942627209392 12075942627390610 12075942627673489 12075942627696187
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 198 901311 901316 4194304 256 0 0 28 24 138560 0x7f8cad17c800 0x7f8ba1636980 0 0 0 12075942627734047 12075942627895407 12075942628150286 12075942628186198
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 200 901311 901316 4194304 256 0 0 24 24 140288 0x7f8cad17c700 0x7f8ba16369c0 0 0 0 12075942628218668 12075942628388365 12075942628519405 12075942628523174
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 202 901311 901316 4194304 256 0 0 24 24 142784 0x7f8cad17c600 0x7f8ba1636a00 0 0 0 12075942628571944 12075942628748044 12075942628957803 12075942628979913
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 204 901311 901316 4194304 256 0 0 24 24 144768 0x7f8cad17c500 0x7f8ba1636a40 0 0 0 12075942629043992 12075942629210761 12075942629353001 12075942629356793
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 901311 901316 4194304 256 0 0 20 24 145728 0x7f8cad17c400 0x7f8ba1636a80 0 0 0 12075942629403530 12075942629584360 12075942629891398 12075942629914509
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 208 901311 901316 4194304 256 0 0 28 24 147712 0x7f8cad17c300 0x7f8ba1636ac0 0 0 0 12075942629959453 12075942630134117 12075942630393956 12075942630418186
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 210 901311 901316 4194304 256 0 0 24 24 149696 0x7f8cad17ca00 0x7f8ba1636b00 0 0 0 12075942630466756 12075942630633315 12075942630768674 12075942630772414
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 212 901311 901316 4194304 256 0 0 24 24 152192 0x7f8cad17c900 0x7f8ba1636b40 0 0 0 12075942630818900 12075942631005153 12075942631233632 12075942631258728
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 214 901311 901316 4194304 256 0 0 24 24 154176 0x7f8cad17c800 0x7f8ba1636b80 0 0 0 12075942631314101 12075942631481631 12075942631619710 12075942631623375
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 901311 901316 4194304 256 0 0 20 24 155648 0x7f8cad17c700 0x7f8ba1636bc0 0 0 0 12075942631671465 12075942631851709 12075942632181468 12075942632218351
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 218 901311 901316 4194304 256 0 0 28 24 157632 0x7f8cad17c600 0x7f8ba1636c00 0 0 0 12075942632252875 12075942632421787 12075942632677945 12075942632699756
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 220 901311 901316 4194304 256 0 0 24 24 159616 0x7f8cad17c500 0x7f8ba1636c40 0 0 0 12075942632744429 12075942632908664 12075942633050424 12075942633054365
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 222 901311 901316 4194304 256 0 0 24 24 162368 0x7f8cad17c400 0x7f8ba1636c80 0 0 0 12075942633100911 12075942633281303 12075942633525942 12075942633547882
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 224 901311 901316 4194304 256 0 0 24 24 164608 0x7f8cad17c300 0x7f8ba1636cc0 0 0 0 12075942633602213 12075942633768980 12075942633909300 12075942633912930
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 901311 901316 4194304 256 0 0 20 24 166336 0x7f8cad17ca00 0x7f8ba1636d00 0 0 0 12075942633960158 12075942634153792 12075942634530271 12075942634569991
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 228 901311 901316 4194304 256 0 0 28 24 168576 0x7f8cad17c900 0x7f8ba1636d40 0 0 0 12075942634597913 12075942634763869 12075942635028827 12075942635051647
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 230 901311 901316 4194304 256 0 0 24 24 170816 0x7f8cad17c800 0x7f8ba1636d80 0 0 0 12075942635102681 12075942635268666 12075942635407866 12075942635411505
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 232 901311 901316 4194304 256 0 0 24 24 174080 0x7f8cad17c700 0x7f8ba1636dc0 0 0 0 12075942635460416 12075942635634425 12075942635944983 12075942635966767
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 234 901311 901316 4194304 256 0 0 24 24 176576 0x7f8cad17c600 0x7f8ba1636e00 0 0 0 12075942636032640 12075942636204182 12075942636341942 12075942636345621
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 901311 901316 4194304 256 0 0 20 24 177792 0x7f8cad17c500 0x7f8ba1636e40 0 0 0 12075942636391436 12075942636577141 12075942637024499 12075942637047305
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 238 901311 901316 4194304 256 0 0 28 24 180288 0x7f8cad17c400 0x7f8ba1636e80 0 0 0 12075942637096286 12075942637263858 12075942637529137 12075942637550561
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 240 901311 901316 4194304 256 0 0 24 24 182784 0x7f8cad17c300 0x7f8ba1636ec0 0 0 0 12075942637598470 12075942637762255 12075942637900495 12075942637904348
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 242 901311 901316 4194304 256 0 0 24 24 186304 0x7f8cad17ca00 0x7f8ba1636f00 0 0 0 12075942637950484 12075942638142894 12075942638457132 12075942638493824
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 244 901311 901316 4194304 256 0 0 24 24 189312 0x7f8cad17c900 0x7f8ba1636f40 0 0 0 12075942638537826 12075942638703851 12075942638856331 12075942638859944
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 901311 901316 4194304 256 0 0 20 24 190784 0x7f8cad17c800 0x7f8ba1636f80 0 0 0 12075942638906952 12075942639091850 12075942639609767 12075942639644893
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 248 901311 901316 4194304 256 0 0 28 24 193792 0x7f8cad17c700 0x7f8ba1636fc0 0 0 0 12075942639680359 12075942639846886 12075942640143845 12075942640166282
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 250 901311 901316 4194304 256 0 0 24 24 196800 0x7f8cad17c600 0x7f8ba1637000 0 0 0 12075942640215043 12075942640384004 12075942640539683 12075942640543172
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 252 901311 901316 4194304 256 0 0 24 24 201088 0x7f8cad17c500 0x7f8ba1637040 0 0 0 12075942640591162 12075942640765762 12075942641153121 12075942641175748
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 254 901311 901316 4194304 256 0 0 24 24 204608 0x7f8cad17c400 0x7f8ba1637080 0 0 0 12075942641238164 12075942641407039 12075942641583359 12075942641586922
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 901311 901316 4194304 256 0 0 20 24 206080 0x7f8cad17c300 0x7f8ba16370c0 0 0 0 12075942641634050 12075942641818398 12075942642440955 12075942642476886
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 258 901311 901316 4194304 256 0 0 28 24 209600 0x7f8cad17ca00 0x7f8ba1637100 0 0 0 12075942642510799 12075942642678234 12075942643007672 12075942643029964
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 260 901311 901316 4194304 256 0 0 24 24 213120 0x7f8cad17c900 0x7f8ba1637140 0 0 0 12075942643079486 12075942643242231 12075942643421591 12075942643425098
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 262 901311 901316 4194304 256 0 0 24 24 218176 0x7f8cad17c800 0x7f8ba1637180 0 0 0 12075942643473719 12075942643656150 12075942644133588 12075942644156778
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 264 901311 901316 4194304 256 0 0 24 24 222208 0x7f8cad17c700 0x7f8ba16371c0 0 0 0 12075942644218383 12075942644388146 12075942644589426 12075942644611022
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 901311 901316 4194304 256 0 0 20 24 223936 0x7f8cad17c600 0x7f8ba1637200 0 0 0 12075942644662959 12075942644829744 12075942645539501 12075942645580304
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 268 901311 901316 4194304 256 0 0 28 24 227968 0x7f8cad17c500 0x7f8ba1637240 0 0 0 12075942645604989 12075942645781900 12075942646154699 12075942646202690
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 270 901311 901316 4194304 256 0 0 24 24 232000 0x7f8cad17c400 0x7f8ba1637280 0 0 0 12075942646230452 12075942646397418 12075942646600457 12075942646645203
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 272 901311 901316 4194304 256 0 0 24 24 237824 0x7f8cad17c300 0x7f8ba16372c0 0 0 0 12075942646679246 12075942646845736 12075942647371813 12075942647417688
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 274 901311 901316 4194304 256 0 0 24 24 242368 0x7f8cad17ca00 0x7f8ba1637300 0 0 0 12075942647455809 12075942647628132 12075942647851651 12075942647896388
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 901311 901316 4194304 256 0 0 20 24 243584 0x7f8cad17c900 0x7f8ba1637340 0 0 0 12075942647930111 12075942648100450 12075942648900607 12075942648945428
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 278 901311 901316 4194304 256 0 0 28 24 248128 0x7f8cad17c800 0x7f8ba1637380 0 0 0 12075942648973880 12075942649142366 12075942649564444 12075942649610193
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 280 901311 901316 4194304 256 0 0 24 24 252672 0x7f8cad17c700 0x7f8ba16373c0 0 0 0 12075942649637033 12075942649815003 12075942650041882 12075942650087961
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 282 901311 901316 4194304 256 0 0 24 24 259264 0x7f8cad17c600 0x7f8ba1637400 0 0 0 12075942650114811 12075942650285561 12075942650883478 12075942650927822
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 284 901311 901316 4194304 256 0 0 24 24 264832 0x7f8cad17c500 0x7f8ba1637440 0 0 0 12075942650965622 12075942651140917 12075942651410516 12075942651456434
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 901311 901316 4194304 256 0 0 20 24 266304 0x7f8cad17c400 0x7f8ba1637480 0 0 0 12075942651483795 12075942651650515 12075942652637070 12075942652682503
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 288 901311 901316 4194304 256 0 0 28 24 271872 0x7f8cad17c300 0x7f8ba16374c0 0 0 0 12075942652716917 12075942652888429 12075942653402507 12075942653447484
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 290 901311 901316 4194304 256 0 0 24 24 277440 0x7f8cad17ca00 0x7f8ba1637500 0 0 0 12075942653480205 12075942653648746 12075942653921545 12075942653940391
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 292 901311 901316 4194304 256 0 0 12 24 279936 0x7f8cad17c900 0x7f8ba1637540 0 0 0 12075942653997196 12075942654171943 12075942654910180 12075942654956098
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 294 901311 901316 4194304 256 0 0 24 24 286528 0x7f8cad17c800 0x7f8ba1637580 0 0 0 12075942655006211 12075942655173219 12075942655490978 12075942655537188
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 901311 901316 4194304 256 0 0 20 24 288000 0x7f8cad17c700 0x7f8ba16375c0 0 0 0 12075942655563377 12075942655737537 12075942656908411 12075942656954803
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 298 901311 901316 4194304 256 0 0 32 24 294592 0x7f8cad17c600 0x7f8ba1637600 0 0 0 12075942656985460 12075942657172250 12075942657783288 12075942657828116
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 300 901311 901316 4194304 256 0 0 24 24 301184 0x7f8cad17c500 0x7f8ba1637640 0 0 0 12075942657860576 12075942658036247 12075942658356885 12075942658403515
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 302 901311 901316 4194304 256 0 0 12 24 304960 0x7f8cad17c400 0x7f8ba1637680 0 0 0 12075942658436627 12075942658605684 12075942659484560 12075942659530540
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 304 901311 901316 4194304 256 0 0 24 24 313600 0x7f8cad17c300 0x7f8ba16376c0 0 0 0 12075942659575934 12075942659741839 12075942660153997 12075942660200495
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 901311 901316 4194304 256 0 0 20 24 314816 0x7f8cad17ca00 0x7f8ba1637700 0 0 0 12075942660230140 12075942660394156 12075942661943589 12075942661989640
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 308 901311 901316 4194304 256 0 0 20 24 317568 0x7f8cad17c900 0x7f8ba1637740 0 0 0 12075942662020527 12075942662189188 12075942662985185 12075942663031947
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 310 901311 901316 4194304 256 0 0 12 24 320320 0x7f8cad17c800 0x7f8ba1637780 0 0 0 12075942663064217 12075942663231904 12075942663647262 12075942663692524
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 312 901311 901316 4194304 256 0 0 12 24 324096 0x7f8cad17c700 0x7f8ba16377c0 0 0 0 12075942663725806 12075942663891901 12075942665051096 12075942665097435
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 314 901311 901316 4194304 256 0 0 12 24 328896 0x7f8cad17c600 0x7f8ba1637800 0 0 0 12075942665142760 12075942665313335 12075942666098931 12075942666144461
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 901311 901316 4194304 256 0 0 20 24 330112 0x7f8cad17c500 0x7f8ba1637840 0 0 0 12075942666178565 12075942666345490 12075942669397317 12075942669443643
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 318 901311 901316 4194304 256 0 0 20 24 332864 0x7f8cad17c400 0x7f8ba1637880 0 0 0 12075942669475031 12075942669645316 12075942671188989 12075942671235262
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 320 901311 901316 4194304 256 0 0 12 24 335616 0x7f8cad17c300 0x7f8ba16378c0 0 0 0 12075942671269526 12075942671438428 12075942672228344 12075942672274363
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 322 901311 901316 4194304 256 0 0 12 24 339392 0x7f8cad17ca00 0x7f8ba1637900 0 0 0 12075942672308807 12075942672476823 12075942674759053 12075942674804786
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 324 901311 901316 4194304 256 0 0 12 24 344192 0x7f8cad17c900 0x7f8ba1637940 0 0 0 12075942674847535 12075942675013452 12075942676549125 12075942676595995
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 901311 901316 4194304 256 0 0 20 24 345408 0x7f8cad17c800 0x7f8ba1637980 0 0 0 12075942676629688 12075942676800164 12075942682854698 12075942682901904
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 328 901311 901316 4194304 256 0 0 20 24 348160 0x7f8cad17c700 0x7f8ba16379c0 0 0 0 12075942682936198 12075942683115656 12075942686156763 12075942686204051
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 330 901311 901316 4194304 256 0 0 12 24 350912 0x7f8cad17c600 0x7f8ba1637a00 0 0 0 12075942686233836 12075942686396762 12075942687935475 12075942687982366
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 332 901311 901316 4194304 256 0 0 12 24 0 0x7f8cad17c500 0x7f8ba1637a40 0 0 0 12075942688024494 12075942688190674 12075942692717534 12075942692765686
@@ -1,168 +0,0 @@
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",0,0,0,900933,900938,33554432,256,0,0,8,32,6464,0x0,0x7fde4da04180,4194304,3099050,396455528,12075939814530162,12075940060541623,12075940060866101,12075940060977444
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,900933,900938,32768,256,0,0,24,24,12480,0x0,0x7fde4da35100,512,21834,2778040,12075940075409134,12075940075710667,12075940075716907,12075940075730201
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,900933,900938,4194304,256,0,0,24,24,12928,0x7fdf5971c900,0x7fde4da35140,65536,170266,21950512,12075940075787127,12075940075998985,12075940076129225,12075940076133521
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,900933,900938,4194304,256,0,0,36,24,13632,0x7fdf5971c800,0x7fde4da35180,65536,153214,19573408,12075940076205134,12075940076381383,12075940076630822,12075940076699242
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,900933,900938,4194304,256,0,0,28,24,14080,0x7fdf5971c700,0x7fde4da351c0,65536,179042,22917000,12075940076732634,12075940076913541,12075940077168259,12075940077239356
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,900933,900938,4194304,256,0,0,24,24,14528,0x7fdf5971c600,0x7fde4da35200,65536,175090,22474192,12075940077270443,12075940077450818,12075940077586817,12075940077590588
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,900933,900938,4194304,256,0,0,24,24,14976,0x7fdf5971c500,0x7fde4da35240,65536,168222,21624176,12075940077643407,12075940077800576,12075940077933216,12075940077936922
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,900933,900938,4194304,256,0,0,24,24,15424,0x7fdf5971c400,0x7fde4da35280,131072,240138,30897664,12075940078023202,12075940078192574,12075940078324414,12075940078328059
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,900933,900938,4194304,256,0,0,28,24,16128,0x7fdf5971c300,0x7fde4da352c0,131072,196376,25118896,12075940078378643,12075940078554653,12075940078814011,12075940078856651
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,900933,900938,4194304,256,0,0,28,24,16832,0x7fdf5971ca00,0x7fde4da35300,65536,164504,21064144,12075940078890104,12075940079076730,12075940079329369,12075940079426791
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,900933,900938,4194304,256,0,0,24,24,17536,0x7fdf5971c900,0x7fde4da35340,131072,241400,30883224,12075940079494336,12075940079767127,12075940079896406,12075940079900311
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,900933,900938,4194304,256,0,0,24,24,18240,0x7fdf5971c800,0x7fde4da35380,131072,243336,31081624,12075940079969680,12075940080187125,12075940080322484,12075940080326243
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,900933,900938,4194304,256,0,0,24,24,18944,0x7fdf5971c700,0x7fde4da353c0,131072,246818,31644296,12075940080429645,12075940080595923,12075940080728242,12075940080731926
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,900933,900938,4194304,256,0,0,28,24,19904,0x7fdf5971c600,0x7fde4da35400,131072,196906,25213968,12075940080785476,12075940080949041,12075940081203600,12075940081273914
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,900933,900938,4194304,256,0,0,28,24,20608,0x7fdf5971c500,0x7fde4da35440,65536,171562,21926720,12075940081336490,12075940081557518,12075940081810317,12075940081877355
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,900933,900938,4194304,256,0,0,24,24,21312,0x7fdf5971c400,0x7fde4da35480,131072,242542,31038520,12075940081938679,12075940082165515,12075940082295434,12075940082299470
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,900933,900938,4194304,256,0,0,24,24,22016,0x7fdf5971c300,0x7fde4da354c0,131072,253412,32463424,12075940082357908,12075940082530793,12075940082664232,12075940082668476
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,900933,900938,4194304,256,0,0,24,24,22720,0x7fdf5971ca00,0x7fde4da35500,131072,240942,30868544,12075940082734398,12075940082897031,12075940083026470,12075940083030418
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,900933,900938,4194304,256,0,0,28,24,23680,0x7fdf5971c900,0x7fde4da35540,131072,212370,27206360,12075940083080822,12075940083257669,12075940083509028,12075940083551346
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,900933,900938,4194304,256,0,0,28,24,24384,0x7fdf5971c800,0x7fde4da35580,65536,183140,23391472,12075940083613221,12075940083828227,12075940084088705,12075940084155990
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,900933,900938,4194304,256,0,0,24,24,25088,0x7fdf5971c700,0x7fde4da355c0,131072,263730,33849176,12075940084194291,12075940084366304,12075940084494623,12075940084498316
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,900933,900938,4194304,256,0,0,24,24,25792,0x7fdf5971c600,0x7fde4da35600,131072,242660,30716560,12075940084550603,12075940084714622,12075940084844062,12075940084848036
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,900933,900938,4194304,256,0,0,24,24,26496,0x7fdf5971c500,0x7fde4da35640,131072,250068,31969472,12075940084914860,12075940085090460,12075940085219580,12075940085223564
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,900933,900938,4194304,256,0,0,28,24,27712,0x7fdf5971c400,0x7fde4da35680,131072,202606,25727152,12075940085272545,12075940085448379,12075940085701817,12075940085768777
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,900933,900938,4194304,256,0,0,28,24,28416,0x7fdf5971c300,0x7fde4da356c0,65536,182366,23360984,12075940085795327,12075940085977976,12075940086231415,12075940086300696
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,900933,900938,4194304,256,0,0,24,24,29120,0x7fdf5971ca00,0x7fde4da35700,131072,243906,31261504,12075940086329539,12075940086508693,12075940086639573,12075940086643273
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,900933,900938,4194304,256,0,0,24,24,30080,0x7fdf5971c900,0x7fde4da35740,131072,258810,33101664,12075940086694388,12075940086855572,12075940086987571,12075940086991389
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,900933,900938,4194304,256,0,0,24,24,30784,0x7fdf5971c800,0x7fde4da35780,131072,268706,34447536,12075940087054266,12075940087216210,12075940087348849,12075940087352671
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,900933,900938,4194304,256,0,0,28,24,32000,0x7fdf5971c700,0x7fde4da357c0,131072,215504,27560480,12075940087400239,12075940087557808,12075940087809807,12075940087852370
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,900933,900938,4194304,256,0,0,28,24,32960,0x7fdf5971c600,0x7fde4da35800,65536,167196,21317520,12075940087874992,12075940088042286,12075940088297004,12075940088363880
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,900933,900938,4194304,256,0,0,24,24,33920,0x7fdf5971c500,0x7fde4da35840,131072,246388,31484296,12075940088387133,12075940088551083,12075940088678603,12075940088682462
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,900933,900938,4194304,256,0,0,24,24,34880,0x7fdf5971c400,0x7fde4da35880,131072,261208,33416552,12075940088729530,12075940088879722,12075940089009161,12075940089013457
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,900933,900938,4194304,256,0,0,24,24,35840,0x7fdf5971c300,0x7fde4da358c0,131072,252244,32419800,12075940089073609,12075940089218120,12075940089347399,12075940089351365
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,900933,900938,4194304,256,0,0,28,24,37312,0x7fdf5971ca00,0x7fde4da35900,131072,201812,25831312,12075940089398032,12075940089550278,12075940089851397,12075940089917928
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,900933,900938,4194304,256,0,0,28,24,38272,0x7fdf5971c900,0x7fde4da35940,65536,167022,21458664,12075940089939488,12075940090105475,12075940090352514,12075940090421674
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,900933,900938,4194304,256,0,0,24,24,39232,0x7fdf5971c800,0x7fde4da35980,131072,248808,31770344,12075940090444978,12075940090606913,12075940090735552,12075940090739445
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,900933,900938,4194304,256,0,0,24,24,40192,0x7fdf5971c700,0x7fde4da359c0,131072,246468,31433240,12075940090787314,12075940090940991,12075940091068991,12075940091073566
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,900933,900938,4194304,256,0,0,24,24,41152,0x7fdf5971c600,0x7fde4da35a00,131072,240090,30815120,12075940091132245,12075940091278270,12075940091409789,12075940091413698
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,900933,900938,4194304,256,0,0,28,24,42624,0x7fdf5971c500,0x7fde4da35a40,131072,223360,28577552,12075940091460475,12075940091613148,12075940091864987,12075940091931701
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,900933,900938,4194304,256,0,0,28,24,43584,0x7fdf5971c400,0x7fde4da35a80,65536,168482,21546808,12075940091951467,12075940092126746,12075940092378904,12075940092446497
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,900933,900938,4194304,256,0,0,24,24,44544,0x7fdf5971c300,0x7fde4da35ac0,131072,237220,30615720,12075940092470823,12075940092631383,12075940092760502,12075940092764348
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,900933,900938,4194304,256,0,0,24,24,45760,0x7fdf5971ca00,0x7fde4da35b00,131072,237506,30404264,12075940092810544,12075940092962101,12075940093099861,12075940093104090
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,900933,900938,4194304,256,0,0,24,24,46720,0x7fdf5971c900,0x7fde4da35b40,131072,237996,30445864,12075940093163500,12075940093308660,12075940093445139,12075940093449231
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,900933,900938,4194304,256,0,0,28,24,48448,0x7fdf5971c800,0x7fde4da35b80,131072,194720,24988208,12075940093495197,12075940093646098,12075940093908337,12075940093975129
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,900933,900938,4194304,256,0,0,28,24,49408,0x7fdf5971c700,0x7fde4da35bc0,65536,190000,24292064,12075940093995066,12075940094169615,12075940094426094,12075940094495055
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,900933,900938,4194304,256,0,0,24,24,50368,0x7fdf5971c600,0x7fde4da35c00,131072,234644,29994208,12075940094516124,12075940094690413,12075940094822092,12075940094826070
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,900933,900938,4194304,256,0,0,24,24,51584,0x7fdf5971c500,0x7fde4da35c40,131072,240236,30650128,12075940094875842,12075940095033931,12075940095169130,12075940095173245
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,900933,900938,4194304,256,0,0,24,24,52544,0x7fdf5971c400,0x7fde4da35c80,131072,238718,30592480,12075940095233968,12075940095371849,12075940095500489,12075940095504501
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,900933,900938,4194304,256,0,0,28,24,54272,0x7fdf5971c300,0x7fde4da35cc0,131072,205164,26219968,12075940095551358,12075940095700488,12075940095966887,12075940096033915
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,900933,900938,4194304,256,0,0,28,24,55488,0x7fdf5971ca00,0x7fde4da35d00,65536,179670,23011328,12075940096056196,12075940096221445,12075940096478244,12075940096544774
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,900933,900938,4194304,256,0,0,24,24,56704,0x7fdf5971c900,0x7fde4da35d40,131072,247184,31545984,12075940096567556,12075940096727523,12075940096862882,12075940096866903
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,900933,900938,4194304,256,0,0,24,24,58176,0x7fdf5971c800,0x7fde4da35d80,131072,238298,30600256,12075940096913820,12075940097063201,12075940097204000,12075940097207906
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,900933,900938,4194304,256,0,0,24,24,59392,0x7fdf5971c700,0x7fde4da35dc0,131072,240282,30706832,12075940097267708,12075940097412799,12075940097545919,12075940097549832
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,900933,900938,4194304,256,0,0,28,24,61376,0x7fdf5971c600,0x7fde4da35e00,131072,247142,31648000,12075940097596198,12075940097749278,12075940098006876,12075940098075198
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,900933,900938,4194304,256,0,0,28,24,62592,0x7fdf5971c500,0x7fde4da35e40,65536,168820,21617368,12075940098097359,12075940098262555,12075940098517114,12075940098584054
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,900933,900938,4194304,256,0,0,24,24,63808,0x7fdf5971c400,0x7fde4da35e80,131072,238760,30504352,12075940098608149,12075940098777113,12075940098906232,12075940098910140
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,900933,900938,4194304,256,0,0,24,24,65280,0x7fdf5971c300,0x7fde4da35ec0,131072,255712,32670848,12075940098957448,12075940099115831,12075940099258550,12075940099262755
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,900933,900938,4194304,256,0,0,24,24,66496,0x7fdf5971ca00,0x7fde4da35f00,131072,239132,30558648,12075940099324179,12075940099463989,12075940099598229,12075940099602126
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,900933,900938,4194304,256,0,0,28,24,68480,0x7fdf5971c900,0x7fde4da35f40,131072,240610,31068928,12075940099648973,12075940099800308,12075940100066866,12075940100116091
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,900933,900938,4194304,256,0,0,28,24,69696,0x7fdf5971c800,0x7fde4da35f80,65536,180632,23173592,12075940100138843,12075940100301905,12075940100592304,12075940100641788
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,900933,900938,4194304,256,0,0,24,24,70912,0x7fdf5971c700,0x7fde4da35fc0,131072,252166,32390936,12075940100664090,12075940100825103,12075940100955662,12075940100959519
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,900933,900938,4194304,256,0,0,24,24,72384,0x7fdf5971c600,0x7fde4da36000,131072,240100,30730728,12075940101012808,12075940101163021,12075940101304300,12075940101308537
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,900933,900938,4194304,256,0,0,24,24,73600,0x7fdf5971c500,0x7fde4da36040,131072,248786,31944680,12075940101369230,12075940101510219,12075940101642858,12075940101646806
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,900933,900938,4194304,256,0,0,28,24,75840,0x7fdf5971c400,0x7fde4da36080,131072,201370,25715584,12075940101692160,12075940101856137,12075940102116776,12075940102166171
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,900933,900938,4194304,256,0,0,28,24,77056,0x7fdf5971c300,0x7fde4da360c0,65536,175566,22377376,12075940102188242,12075940102355495,12075940102612774,12075940102660870
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,900933,900938,4194304,256,0,0,24,24,78272,0x7fdf5971ca00,0x7fde4da36100,131072,239208,30756896,12075940102682260,12075940102843493,12075940102975332,12075940102979372
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,900933,900938,4194304,256,0,0,24,24,80000,0x7fdf5971c900,0x7fde4da36140,131072,203748,26217128,12075940103026410,12075940103189411,12075940103333570,12075940103337568
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,900933,900938,4194304,256,0,0,24,24,81216,0x7fdf5971c800,0x7fde4da36180,131072,236616,30282656,12075940103395566,12075940103535009,12075940103671328,12075940103675406
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,900933,900938,4194304,256,0,0,28,24,83456,0x7fdf5971c700,0x7fde4da361c0,131072,206280,26469216,12075940103722203,12075940103871487,12075940104138366,12075940104187007
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,900933,900938,4194304,256,0,0,28,24,84928,0x7fdf5971c600,0x7fde4da36200,65536,164074,21007432,12075940104209529,12075940104373405,12075940104630364,12075940104652432
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,900933,900938,4194304,256,0,0,24,24,86400,0x7fdf5971c500,0x7fde4da36240,131072,240534,30644192,12075940104694941,12075940104835483,12075940104968922,12075940104973007
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,900933,900938,4194304,256,0,0,24,24,88128,0x7fdf5971c400,0x7fde4da36280,131072,197370,25279192,12075940105023932,12075940105181081,12075940105331320,12075940105335661
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,900933,900938,4194304,256,0,0,24,24,89600,0x7fdf5971c300,0x7fde4da362c0,131072,248490,31936912,12075940105408096,12075940105549399,12075940105677559,12075940105681454
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,900933,900938,4194304,256,0,0,28,24,92096,0x7fdf5971ca00,0x7fde4da36300,131072,205282,26397080,12075940105728061,12075940105880598,12075940106144596,12075940106198615
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,900933,900938,4194304,256,0,0,28,24,93568,0x7fdf5971c900,0x7fde4da36340,65536,172128,22176200,12075940106223131,12075940106395155,12075940106645394,12075940106692804
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,900933,900938,4194304,256,0,0,24,24,95040,0x7fdf5971c800,0x7fde4da36380,131072,242878,30960912,12075940106715155,12075940106872593,12075940107012112,12075940107016044
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,900933,900938,4194304,256,0,0,24,24,96768,0x7fdf5971c700,0x7fde4da363c0,131072,256046,32890016,12075940107064054,12075940107216431,12075940107373550,12075940107377486
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,900933,900938,4194304,256,0,0,24,24,98240,0x7fdf5971c600,0x7fde4da36400,131072,242574,31072608,12075940107437307,12075940107575949,12075940107704108,12075940107708151
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,900933,900938,4194304,256,0,0,28,24,100736,0x7fdf5971c500,0x7fde4da36440,131072,207714,26542336,12075940107755659,12075940107902988,12075940108168266,12075940108216946
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,900933,900938,4194304,256,0,0,28,24,102208,0x7fdf5971c400,0x7fde4da36480,65536,172678,22106528,12075940108238957,12075940108400105,12075940108657544,12075940108704212
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,900933,900938,4194304,256,0,0,24,24,103680,0x7fdf5971c300,0x7fde4da364c0,131072,243214,31210912,12075940108726253,12075940108887943,12075940109020902,12075940109025058
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,900933,900938,4194304,256,0,0,24,24,105664,0x7fdf5971ca00,0x7fde4da36500,131072,259010,33034888,12075940109070422,12075940109234181,12075940109400100,12075940109404183
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,900933,900938,4194304,256,0,0,24,24,107136,0x7fdf5971c900,0x7fde4da36540,131072,244884,31316312,12075940109462381,12075940109605379,12075940109738498,12075940109742201
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,900933,900938,4194304,256,0,0,28,24,109888,0x7fdf5971c800,0x7fde4da36580,131072,197884,25417576,12075940109787786,12075940109939137,12075940110199616,12075940110249003
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,900933,900938,4194304,256,0,0,28,24,111360,0x7fdf5971c700,0x7fde4da365c0,65536,182048,23200776,12075940110272106,12075940110436095,12075940110685694,12075940110733042
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,900933,900938,4194304,256,0,0,24,24,112832,0x7fdf5971c600,0x7fde4da36600,131072,247244,31717200,12075940110757087,12075940110915613,12075940111050812,12075940111055441
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,900933,900938,4194304,256,0,0,24,24,114816,0x7fdf5971c500,0x7fde4da36640,131072,248180,31730560,12075940111103371,12075940111256411,12075940111430650,12075940111434596
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,900933,900938,4194304,256,0,0,24,24,116288,0x7fdf5971c400,0x7fde4da36680,131072,237582,30499072,12075940111492975,12075940111631449,12075940111764888,12075940111768767
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,900933,900938,4194304,256,0,0,28,24,119040,0x7fdf5971c300,0x7fde4da366c0,131072,210898,26911232,12075940111814642,12075940111967927,12075940112223126,12075940112271391
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,900933,900938,4194304,256,0,0,28,24,120768,0x7fdf5971ca00,0x7fde4da36700,65536,175310,22505488,12075940112293763,12075940112457365,12075940112710164,12075940112756803
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,900933,900938,4194304,256,0,0,24,24,122496,0x7fdf5971c900,0x7fde4da36740,131072,245806,31459680,12075940112777933,12075940112945523,12075940113083282,12075940113087538
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,900933,900938,4194304,256,0,0,24,24,124736,0x7fdf5971c800,0x7fde4da36780,131072,256766,32837736,12075940113135918,12075940113291121,12075940113474000,12075940113477984
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,900933,900938,4194304,256,0,0,24,24,126464,0x7fdf5971c700,0x7fde4da367c0,131072,258182,32871184,12075940113538025,12075940113677519,12075940113809038,12075940113812906
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,900933,900938,4194304,256,0,0,20,24,127936,0x7fdf5971c600,0x7fde4da36800,131072,243222,31147776,12075940113861627,12075940114010957,12075940114277196,12075940114325749
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,900933,900938,4194304,256,0,0,28,24,129664,0x7fdf5971c500,0x7fde4da36840,65536,170312,21827104,12075940114348742,12075940114511595,12075940114769674,12075940114790623
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,900933,900938,4194304,256,0,0,24,24,131392,0x7fdf5971c400,0x7fde4da36880,131072,243572,31109192,12075940114832060,12075940114970313,12075940115106312,12075940115110227
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,900933,900938,4194304,256,0,0,24,24,133632,0x7fdf5971c300,0x7fde4da368c0,131072,249078,31764776,12075940115158397,12075940115314791,12075940115505990,12075940115553451
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,900933,900938,4194304,256,0,0,24,24,135360,0x7fdf5971ca00,0x7fde4da36900,131072,238562,30480264,12075940115585861,12075940115734789,12075940115873988,12075940115877854
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,900933,900938,4194304,256,0,0,20,24,136832,0x7fdf5971c900,0x7fde4da36940,131072,238364,30420216,12075940115924039,12075940116077027,12075940116361186,12075940116409742
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,900933,900938,4194304,256,0,0,28,24,138560,0x7fdf5971c800,0x7fde4da36980,65536,168436,21650736,12075940116431382,12075940116597185,12075940116857183,12075940116904512
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,900933,900938,4194304,256,0,0,24,24,140288,0x7fdf5971c700,0x7fde4da369c0,131072,244776,31218152,12075940116928887,12075940117100382,12075940117233181,12075940117237601
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,900933,900938,4194304,256,0,0,24,24,142784,0x7fdf5971c600,0x7fde4da36a00,131072,241062,30995944,12075940117285920,12075940117435900,12075940117646139,12075940117693758
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,900933,900938,4194304,256,0,0,24,24,144768,0x7fdf5971c500,0x7fde4da36a40,131072,268098,34172264,12075940117727231,12075940117877178,12075940118013018,12075940118017330
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,900933,900938,4194304,256,0,0,20,24,145728,0x7fdf5971c400,0x7fde4da36a80,131072,241030,30789088,12075940118064357,12075940118216057,12075940118523735,12075940118570999
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,900933,900938,4194304,256,0,0,28,24,147712,0x7fdf5971c300,0x7fde4da36ac0,65536,169176,21544168,12075940118592148,12075940118757494,12075940119017173,12075940119066129
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,900933,900938,4194304,256,0,0,24,24,149696,0x7fdf5971ca00,0x7fde4da36b00,131072,239168,30681616,12075940119094542,12075940119256531,12075940119391411,12075940119395501
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,900933,900938,4194304,256,0,0,24,24,152192,0x7fdf5971c900,0x7fde4da36b40,131072,262992,33677984,12075940119442789,12075940119592210,12075940119820689,12075940119867649
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,900933,900938,4194304,256,0,0,24,24,154176,0x7fdf5971c800,0x7fde4da36b80,131072,267360,34489600,12075940119903916,12075940120066287,12075940120201647,12075940120205947
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,900933,900938,4194304,256,0,0,20,24,155648,0x7fdf5971c700,0x7fde4da36bc0,131072,270860,34754936,12075940120253876,12075940120410286,12075940120739244,12075940120761530
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,900933,900938,4194304,256,0,0,28,24,157632,0x7fdf5971c600,0x7fde4da36c00,65536,169364,21684544,12075940120802606,12075940120941643,12075940121198602,12075940121248956
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,900933,900938,4194304,256,0,0,24,24,159616,0x7fdf5971c500,0x7fde4da36c40,131072,263658,33732512,12075940121271117,12075940121436361,12075940121576520,12075940121580572
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,900933,900938,4194304,256,0,0,24,24,162368,0x7fdf5971c400,0x7fde4da36c80,131072,236470,30244656,12075940121627720,12075940121777479,12075940122023238,12075940122073067
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,900933,900938,4194304,256,0,0,24,24,164608,0x7fdf5971c300,0x7fde4da36cc0,131072,245820,31650312,12075940122106039,12075940122256837,12075940122397316,12075940122401367
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,900933,900938,4194304,256,0,0,20,24,166336,0x7fdf5971ca00,0x7fde4da36d00,131072,243472,30828256,12075940122449677,12075940122596675,12075940122972833,12075940123021730
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,900933,900938,4194304,256,0,0,28,24,168576,0x7fdf5971c900,0x7fde4da36d40,65536,173984,22249888,12075940123044132,12075940123207712,12075940123471711,12075940123520307
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,900933,900938,4194304,256,0,0,24,24,170816,0x7fdf5971c800,0x7fde4da36d80,131072,242078,31027840,12075940123544893,12075940123700761,12075940123843801,12075940123851152
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,900933,900938,4194304,256,0,0,24,24,174080,0x7fdf5971c700,0x7fde4da36dc0,131072,246382,31548104,12075940123894502,12075940124064439,12075940124343798,12075940124372811
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,900933,900938,4194304,256,0,0,24,24,176576,0x7fdf5971c600,0x7fde4da36e00,131072,237556,30666096,12075940124417544,12075940124558517,12075940124693876,12075940124697024
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,900933,900938,4194304,256,0,0,20,24,177792,0x7fdf5971c500,0x7fde4da36e40,131072,267186,33957256,12075940124744081,12075940124897236,12075940125320914,12075940125349116
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,900933,900938,4194304,256,0,0,28,24,180288,0x7fdf5971c400,0x7fde4da36e80,65536,177724,22686256,12075940125387767,12075940125534833,12075940125795792,12075940125819029
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,900933,900938,4194304,256,0,0,24,24,182784,0x7fdf5971c300,0x7fde4da36ec0,131072,251324,32194656,12075940125862329,12075940126000111,12075940126140431,12075940126144293
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,900933,900938,4194304,256,0,0,24,24,186304,0x7fdf5971ca00,0x7fde4da36f00,131072,241586,31023488,12075940126193325,12075940126345390,12075940126661389,12075940126684818
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,900933,900938,4194304,256,0,0,24,24,189312,0x7fdf5971c900,0x7fde4da36f40,131072,240604,30897328,12075940126742926,12075940126884748,12075940127037067,12075940127040499
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,900933,900938,4194304,256,0,0,20,24,190784,0x7fdf5971c800,0x7fde4da36f80,131072,231834,29812952,12075940127087176,12075940127240747,12075940127757705,12075940127781005
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,900933,900938,4194304,256,0,0,28,24,193792,0x7fdf5971c700,0x7fde4da36fc0,65536,173250,22195936,12075940127822683,12075940127961864,12075940128261383,12075940128287587
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,900933,900938,4194304,256,0,0,24,24,196800,0x7fdf5971c600,0x7fde4da37000,131072,231440,29607928,12075940128327090,12075940128465702,12075940128621221,12075940128624352
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,900933,900938,4194304,256,0,0,24,24,201088,0x7fdf5971c500,0x7fde4da37040,131072,244712,31258992,12075940128671089,12075940128826500,12075940129211619,12075940129240928
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,900933,900938,4194304,256,0,0,24,24,204608,0x7fdf5971c400,0x7fde4da37080,131072,243636,30988368,12075940129289479,12075940129430818,12075940129606498,12075940129609684
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,900933,900938,4194304,256,0,0,20,24,206080,0x7fdf5971c300,0x7fde4da370c0,131072,236554,30417224,12075940129655308,12075940129806177,12075940130428414,12075940130453983
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,900933,900938,4194304,256,0,0,28,24,209600,0x7fdf5971ca00,0x7fde4da37100,65536,171290,21817528,12075940130493146,12075940130638814,12075940130967612,12075940130991061
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,900933,900938,4194304,256,0,0,24,24,213120,0x7fdf5971c900,0x7fde4da37140,131072,239242,30602952,12075940131038068,12075940131180252,12075940131359291,12075940131362461
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,900933,900938,4194304,256,0,0,24,24,218176,0x7fdf5971c800,0x7fde4da37180,131072,249190,32122816,12075940131408647,12075940131562810,12075940132018808,12075940132043226
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,900933,900938,4194304,256,0,0,24,24,222208,0x7fdf5971c700,0x7fde4da371c0,131072,240356,30768632,12075940132097066,12075940132238807,12075940132440247,12075940132463648
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,900933,900938,4194304,256,0,0,20,24,223936,0x7fdf5971c600,0x7fde4da37200,131072,251500,32278976,12075940132505976,12075940132646806,12075940133350643,12075940133376023
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,900933,900938,4194304,256,0,0,28,24,227968,0x7fdf5971c500,0x7fde4da37240,65536,169878,21716776,12075940133413313,12075940133570322,12075940133944241,12075940133990565
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,900933,900938,4194304,256,0,0,24,24,232000,0x7fdf5971c400,0x7fde4da37280,131072,248026,31717072,12075940134020180,12075940134193040,12075940134395759,12075940134444489
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,900933,900938,4194304,256,0,0,24,24,237824,0x7fdf5971c300,0x7fde4da372c0,131072,242116,31026816,12075940134470477,12075940134631438,12075940135158476,12075940135208469
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,900933,900938,4194304,256,0,0,24,24,242368,0x7fdf5971ca00,0x7fde4da37300,131072,240096,30622160,12075940135242602,12075940135400875,12075940135624715,12075940135672211
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,900933,900938,4194304,256,0,0,20,24,243584,0x7fdf5971c900,0x7fde4da37340,131072,237952,30442592,12075940135693701,12075940135857674,12075940136656871,12075940136707515
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,900933,900938,4194304,256,0,0,28,24,248128,0x7fdf5971c800,0x7fde4da37380,65536,191548,24463368,12075940136729516,12075940136894790,12075940137315908,12075940137368373
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,900933,900938,4194304,256,0,0,24,24,252672,0x7fdf5971c700,0x7fde4da373c0,131072,247516,31710640,12075940137392237,12075940137555107,12075940137780226,12075940137828809
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,900933,900938,4194304,256,0,0,24,24,259264,0x7fdf5971c600,0x7fde4da37400,131072,247198,31707512,12075940137850238,12075940138012225,12075940138609823,12075940138658070
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,900933,900938,4194304,256,0,0,24,24,264832,0x7fdf5971c500,0x7fde4da37440,131072,245668,31272984,12075940138690270,12075940138842782,12075940139113501,12075940139160163
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,900933,900938,4194304,256,0,0,20,24,266304,0x7fdf5971c400,0x7fde4da37480,131072,261060,33357928,12075940139183276,12075940139353660,12075940140339257,12075940140390429
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,900933,900938,4194304,256,0,0,28,24,271872,0x7fdf5971c300,0x7fde4da374c0,65536,176780,22602688,12075940140413141,12075940140582936,12075940141098294,12075940141139862
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,900933,900938,4194304,256,0,0,24,24,277440,0x7fdf5971ca00,0x7fde4da37500,131072,240100,30875440,12075940141168706,12075940141329493,12075940141602452,12075940141642947
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,900933,900938,4194304,256,0,0,12,24,279936,0x7fdf5971c900,0x7fde4da37540,131072,266672,34188936,12075940141664667,12075940141828531,12075940142567728,12075940142611637
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,900933,900938,4194304,256,0,0,24,24,286528,0x7fdf5971c800,0x7fde4da37580,131072,238776,30600664,12075940142652243,12075940142792687,12075940143137646,12075940143206082
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,900933,900938,4194304,256,0,0,20,24,288000,0x7fdf5971c700,0x7fde4da375c0,131072,250258,31826752,12075940143227341,12075940143397165,12075940144569480,12075940144636801
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,900933,900938,4194304,256,0,0,32,24,294592,0x7fdf5971c600,0x7fde4da37600,65536,168102,21452784,12075940144665594,12075940144830759,12075940145441317,12075940145509863
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,900933,900938,4194304,256,0,0,24,24,301184,0x7fdf5971c500,0x7fde4da37640,131072,252494,32409400,12075940145533067,12075940145699396,12075940146046755,12075940146115309
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,900933,900938,4194304,256,0,0,12,24,304960,0x7fdf5971c400,0x7fde4da37680,131072,246326,31504880,12075940146142279,12075940146301314,12075940147179710,12075940147247042
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,900933,900938,4194304,256,0,0,24,24,313600,0x7fdf5971c300,0x7fde4da376c0,131072,242918,30955672,12075940147287437,12075940147441949,12075940147874908,12075940147941442
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,900933,900938,4194304,256,0,0,20,24,314816,0x7fdf5971ca00,0x7fde4da37700,131072,246048,31498344,12075940147963544,12075940148138907,12075940149688821,12075940149757097
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,900933,900938,4194304,256,0,0,20,24,317568,0x7fdf5971c900,0x7fde4da37740,65536,165966,21306576,12075940149779879,12075940149950900,12075940150748497,12075940150817247
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,900933,900938,4194304,256,0,0,12,24,320320,0x7fdf5971c800,0x7fde4da37780,131072,269980,34844488,12075940150839909,12075940151009296,12075940151447694,12075940151514833
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,900933,900938,4194304,256,0,0,12,24,324096,0x7fdf5971c700,0x7fde4da377c0,131072,259410,33177320,12075940151537966,12075940151699693,12075940152858729,12075940152927469
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,900933,900938,4194304,256,0,0,12,24,328896,0x7fdf5971c600,0x7fde4da37800,131072,240332,30866976,12075940152968355,12075940153116488,12075940153902085,12075940153970988
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,900933,900938,4194304,256,0,0,20,24,330112,0x7fdf5971c500,0x7fde4da37840,131072,238710,30684320,12075940153997948,12075940154168324,12075940157222072,12075940157295286
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,900933,900938,4194304,256,0,0,20,24,332864,0x7fdf5971c400,0x7fde4da37880,65536,170586,21812872,12075940157318489,12075940157481271,12075940159027505,12075940159095542
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,900933,900938,4194304,256,0,0,12,24,335616,0x7fdf5971c300,0x7fde4da378c0,131072,239240,30698104,12075940159125478,12075940159287664,12075940160078701,12075940160146435
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,900933,900938,4194304,256,0,0,12,24,339392,0x7fdf5971ca00,0x7fde4da37900,131072,258544,33154864,12075940160169418,12075940160343980,12075940162626211,12075940162693829
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,900933,900938,4194304,256,0,0,12,24,344192,0x7fdf5971c900,0x7fde4da37940,131072,237262,30425144,12075940162732251,12075940162883490,12075940164419165,12075940164488975
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,900933,900938,4194304,256,0,0,20,24,345408,0x7fdf5971c800,0x7fde4da37980,131072,247440,31774800,12075940164517939,12075940164682044,12075940170739620,12075940170809462
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,900933,900938,4194304,256,0,0,20,24,348160,0x7fdf5971c700,0x7fde4da379c0,65536,184318,23535632,12075940170837233,12075940171002019,12075940174046968,12075940174120465
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,900933,900938,4194304,256,0,0,12,24,350912,0x7fdf5971c600,0x7fde4da37a00,131072,251480,32263840,12075940174143087,12075940174314007,12075940175852881,12075940175920520
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,900933,900938,4194304,256,0,0,12,24,0,0x7fdf5971c500,0x7fde4da37a40,131072,233574,30067768,12075940175949013,12075940176116880,12075940180645663,12075940180715712
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 900933 900938 33554432 256 0 0 8 32 6464 0x0 0x7fde4da04180 4194304 3099050 396455528 12075939814530162 12075940060541623 12075940060866101 12075940060977444
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 900933 900938 32768 256 0 0 24 24 12480 0x0 0x7fde4da35100 512 21834 2778040 12075940075409134 12075940075710667 12075940075716907 12075940075730201
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 4 900933 900938 4194304 256 0 0 24 24 12928 0x7fdf5971c900 0x7fde4da35140 65536 170266 21950512 12075940075787127 12075940075998985 12075940076129225 12075940076133521
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 900933 900938 4194304 256 0 0 36 24 13632 0x7fdf5971c800 0x7fde4da35180 65536 153214 19573408 12075940076205134 12075940076381383 12075940076630822 12075940076699242
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 8 900933 900938 4194304 256 0 0 28 24 14080 0x7fdf5971c700 0x7fde4da351c0 65536 179042 22917000 12075940076732634 12075940076913541 12075940077168259 12075940077239356
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 10 900933 900938 4194304 256 0 0 24 24 14528 0x7fdf5971c600 0x7fde4da35200 65536 175090 22474192 12075940077270443 12075940077450818 12075940077586817 12075940077590588
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 12 900933 900938 4194304 256 0 0 24 24 14976 0x7fdf5971c500 0x7fde4da35240 65536 168222 21624176 12075940077643407 12075940077800576 12075940077933216 12075940077936922
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 14 900933 900938 4194304 256 0 0 24 24 15424 0x7fdf5971c400 0x7fde4da35280 131072 240138 30897664 12075940078023202 12075940078192574 12075940078324414 12075940078328059
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 900933 900938 4194304 256 0 0 28 24 16128 0x7fdf5971c300 0x7fde4da352c0 131072 196376 25118896 12075940078378643 12075940078554653 12075940078814011 12075940078856651
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 18 900933 900938 4194304 256 0 0 28 24 16832 0x7fdf5971ca00 0x7fde4da35300 65536 164504 21064144 12075940078890104 12075940079076730 12075940079329369 12075940079426791
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 20 900933 900938 4194304 256 0 0 24 24 17536 0x7fdf5971c900 0x7fde4da35340 131072 241400 30883224 12075940079494336 12075940079767127 12075940079896406 12075940079900311
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 22 900933 900938 4194304 256 0 0 24 24 18240 0x7fdf5971c800 0x7fde4da35380 131072 243336 31081624 12075940079969680 12075940080187125 12075940080322484 12075940080326243
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 24 900933 900938 4194304 256 0 0 24 24 18944 0x7fdf5971c700 0x7fde4da353c0 131072 246818 31644296 12075940080429645 12075940080595923 12075940080728242 12075940080731926
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 900933 900938 4194304 256 0 0 28 24 19904 0x7fdf5971c600 0x7fde4da35400 131072 196906 25213968 12075940080785476 12075940080949041 12075940081203600 12075940081273914
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 28 900933 900938 4194304 256 0 0 28 24 20608 0x7fdf5971c500 0x7fde4da35440 65536 171562 21926720 12075940081336490 12075940081557518 12075940081810317 12075940081877355
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 30 900933 900938 4194304 256 0 0 24 24 21312 0x7fdf5971c400 0x7fde4da35480 131072 242542 31038520 12075940081938679 12075940082165515 12075940082295434 12075940082299470
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 32 900933 900938 4194304 256 0 0 24 24 22016 0x7fdf5971c300 0x7fde4da354c0 131072 253412 32463424 12075940082357908 12075940082530793 12075940082664232 12075940082668476
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 34 900933 900938 4194304 256 0 0 24 24 22720 0x7fdf5971ca00 0x7fde4da35500 131072 240942 30868544 12075940082734398 12075940082897031 12075940083026470 12075940083030418
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 900933 900938 4194304 256 0 0 28 24 23680 0x7fdf5971c900 0x7fde4da35540 131072 212370 27206360 12075940083080822 12075940083257669 12075940083509028 12075940083551346
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 38 900933 900938 4194304 256 0 0 28 24 24384 0x7fdf5971c800 0x7fde4da35580 65536 183140 23391472 12075940083613221 12075940083828227 12075940084088705 12075940084155990
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 40 900933 900938 4194304 256 0 0 24 24 25088 0x7fdf5971c700 0x7fde4da355c0 131072 263730 33849176 12075940084194291 12075940084366304 12075940084494623 12075940084498316
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 42 900933 900938 4194304 256 0 0 24 24 25792 0x7fdf5971c600 0x7fde4da35600 131072 242660 30716560 12075940084550603 12075940084714622 12075940084844062 12075940084848036
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 44 900933 900938 4194304 256 0 0 24 24 26496 0x7fdf5971c500 0x7fde4da35640 131072 250068 31969472 12075940084914860 12075940085090460 12075940085219580 12075940085223564
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 900933 900938 4194304 256 0 0 28 24 27712 0x7fdf5971c400 0x7fde4da35680 131072 202606 25727152 12075940085272545 12075940085448379 12075940085701817 12075940085768777
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 48 900933 900938 4194304 256 0 0 28 24 28416 0x7fdf5971c300 0x7fde4da356c0 65536 182366 23360984 12075940085795327 12075940085977976 12075940086231415 12075940086300696
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 50 900933 900938 4194304 256 0 0 24 24 29120 0x7fdf5971ca00 0x7fde4da35700 131072 243906 31261504 12075940086329539 12075940086508693 12075940086639573 12075940086643273
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 52 900933 900938 4194304 256 0 0 24 24 30080 0x7fdf5971c900 0x7fde4da35740 131072 258810 33101664 12075940086694388 12075940086855572 12075940086987571 12075940086991389
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 54 900933 900938 4194304 256 0 0 24 24 30784 0x7fdf5971c800 0x7fde4da35780 131072 268706 34447536 12075940087054266 12075940087216210 12075940087348849 12075940087352671
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 900933 900938 4194304 256 0 0 28 24 32000 0x7fdf5971c700 0x7fde4da357c0 131072 215504 27560480 12075940087400239 12075940087557808 12075940087809807 12075940087852370
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 58 900933 900938 4194304 256 0 0 28 24 32960 0x7fdf5971c600 0x7fde4da35800 65536 167196 21317520 12075940087874992 12075940088042286 12075940088297004 12075940088363880
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 60 900933 900938 4194304 256 0 0 24 24 33920 0x7fdf5971c500 0x7fde4da35840 131072 246388 31484296 12075940088387133 12075940088551083 12075940088678603 12075940088682462
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 62 900933 900938 4194304 256 0 0 24 24 34880 0x7fdf5971c400 0x7fde4da35880 131072 261208 33416552 12075940088729530 12075940088879722 12075940089009161 12075940089013457
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 64 900933 900938 4194304 256 0 0 24 24 35840 0x7fdf5971c300 0x7fde4da358c0 131072 252244 32419800 12075940089073609 12075940089218120 12075940089347399 12075940089351365
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 900933 900938 4194304 256 0 0 28 24 37312 0x7fdf5971ca00 0x7fde4da35900 131072 201812 25831312 12075940089398032 12075940089550278 12075940089851397 12075940089917928
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 68 900933 900938 4194304 256 0 0 28 24 38272 0x7fdf5971c900 0x7fde4da35940 65536 167022 21458664 12075940089939488 12075940090105475 12075940090352514 12075940090421674
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 70 900933 900938 4194304 256 0 0 24 24 39232 0x7fdf5971c800 0x7fde4da35980 131072 248808 31770344 12075940090444978 12075940090606913 12075940090735552 12075940090739445
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 72 900933 900938 4194304 256 0 0 24 24 40192 0x7fdf5971c700 0x7fde4da359c0 131072 246468 31433240 12075940090787314 12075940090940991 12075940091068991 12075940091073566
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 74 900933 900938 4194304 256 0 0 24 24 41152 0x7fdf5971c600 0x7fde4da35a00 131072 240090 30815120 12075940091132245 12075940091278270 12075940091409789 12075940091413698
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 900933 900938 4194304 256 0 0 28 24 42624 0x7fdf5971c500 0x7fde4da35a40 131072 223360 28577552 12075940091460475 12075940091613148 12075940091864987 12075940091931701
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 78 900933 900938 4194304 256 0 0 28 24 43584 0x7fdf5971c400 0x7fde4da35a80 65536 168482 21546808 12075940091951467 12075940092126746 12075940092378904 12075940092446497
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 80 900933 900938 4194304 256 0 0 24 24 44544 0x7fdf5971c300 0x7fde4da35ac0 131072 237220 30615720 12075940092470823 12075940092631383 12075940092760502 12075940092764348
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 82 900933 900938 4194304 256 0 0 24 24 45760 0x7fdf5971ca00 0x7fde4da35b00 131072 237506 30404264 12075940092810544 12075940092962101 12075940093099861 12075940093104090
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 84 900933 900938 4194304 256 0 0 24 24 46720 0x7fdf5971c900 0x7fde4da35b40 131072 237996 30445864 12075940093163500 12075940093308660 12075940093445139 12075940093449231
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 900933 900938 4194304 256 0 0 28 24 48448 0x7fdf5971c800 0x7fde4da35b80 131072 194720 24988208 12075940093495197 12075940093646098 12075940093908337 12075940093975129
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 88 900933 900938 4194304 256 0 0 28 24 49408 0x7fdf5971c700 0x7fde4da35bc0 65536 190000 24292064 12075940093995066 12075940094169615 12075940094426094 12075940094495055
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 90 900933 900938 4194304 256 0 0 24 24 50368 0x7fdf5971c600 0x7fde4da35c00 131072 234644 29994208 12075940094516124 12075940094690413 12075940094822092 12075940094826070
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 92 900933 900938 4194304 256 0 0 24 24 51584 0x7fdf5971c500 0x7fde4da35c40 131072 240236 30650128 12075940094875842 12075940095033931 12075940095169130 12075940095173245
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 94 900933 900938 4194304 256 0 0 24 24 52544 0x7fdf5971c400 0x7fde4da35c80 131072 238718 30592480 12075940095233968 12075940095371849 12075940095500489 12075940095504501
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 900933 900938 4194304 256 0 0 28 24 54272 0x7fdf5971c300 0x7fde4da35cc0 131072 205164 26219968 12075940095551358 12075940095700488 12075940095966887 12075940096033915
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 98 900933 900938 4194304 256 0 0 28 24 55488 0x7fdf5971ca00 0x7fde4da35d00 65536 179670 23011328 12075940096056196 12075940096221445 12075940096478244 12075940096544774
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 100 900933 900938 4194304 256 0 0 24 24 56704 0x7fdf5971c900 0x7fde4da35d40 131072 247184 31545984 12075940096567556 12075940096727523 12075940096862882 12075940096866903
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 102 900933 900938 4194304 256 0 0 24 24 58176 0x7fdf5971c800 0x7fde4da35d80 131072 238298 30600256 12075940096913820 12075940097063201 12075940097204000 12075940097207906
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 104 900933 900938 4194304 256 0 0 24 24 59392 0x7fdf5971c700 0x7fde4da35dc0 131072 240282 30706832 12075940097267708 12075940097412799 12075940097545919 12075940097549832
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 900933 900938 4194304 256 0 0 28 24 61376 0x7fdf5971c600 0x7fde4da35e00 131072 247142 31648000 12075940097596198 12075940097749278 12075940098006876 12075940098075198
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 108 900933 900938 4194304 256 0 0 28 24 62592 0x7fdf5971c500 0x7fde4da35e40 65536 168820 21617368 12075940098097359 12075940098262555 12075940098517114 12075940098584054
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 110 900933 900938 4194304 256 0 0 24 24 63808 0x7fdf5971c400 0x7fde4da35e80 131072 238760 30504352 12075940098608149 12075940098777113 12075940098906232 12075940098910140
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 112 900933 900938 4194304 256 0 0 24 24 65280 0x7fdf5971c300 0x7fde4da35ec0 131072 255712 32670848 12075940098957448 12075940099115831 12075940099258550 12075940099262755
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 114 900933 900938 4194304 256 0 0 24 24 66496 0x7fdf5971ca00 0x7fde4da35f00 131072 239132 30558648 12075940099324179 12075940099463989 12075940099598229 12075940099602126
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 900933 900938 4194304 256 0 0 28 24 68480 0x7fdf5971c900 0x7fde4da35f40 131072 240610 31068928 12075940099648973 12075940099800308 12075940100066866 12075940100116091
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 118 900933 900938 4194304 256 0 0 28 24 69696 0x7fdf5971c800 0x7fde4da35f80 65536 180632 23173592 12075940100138843 12075940100301905 12075940100592304 12075940100641788
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 120 900933 900938 4194304 256 0 0 24 24 70912 0x7fdf5971c700 0x7fde4da35fc0 131072 252166 32390936 12075940100664090 12075940100825103 12075940100955662 12075940100959519
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 122 900933 900938 4194304 256 0 0 24 24 72384 0x7fdf5971c600 0x7fde4da36000 131072 240100 30730728 12075940101012808 12075940101163021 12075940101304300 12075940101308537
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 124 900933 900938 4194304 256 0 0 24 24 73600 0x7fdf5971c500 0x7fde4da36040 131072 248786 31944680 12075940101369230 12075940101510219 12075940101642858 12075940101646806
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 900933 900938 4194304 256 0 0 28 24 75840 0x7fdf5971c400 0x7fde4da36080 131072 201370 25715584 12075940101692160 12075940101856137 12075940102116776 12075940102166171
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 128 900933 900938 4194304 256 0 0 28 24 77056 0x7fdf5971c300 0x7fde4da360c0 65536 175566 22377376 12075940102188242 12075940102355495 12075940102612774 12075940102660870
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 130 900933 900938 4194304 256 0 0 24 24 78272 0x7fdf5971ca00 0x7fde4da36100 131072 239208 30756896 12075940102682260 12075940102843493 12075940102975332 12075940102979372
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 132 900933 900938 4194304 256 0 0 24 24 80000 0x7fdf5971c900 0x7fde4da36140 131072 203748 26217128 12075940103026410 12075940103189411 12075940103333570 12075940103337568
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 134 900933 900938 4194304 256 0 0 24 24 81216 0x7fdf5971c800 0x7fde4da36180 131072 236616 30282656 12075940103395566 12075940103535009 12075940103671328 12075940103675406
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 900933 900938 4194304 256 0 0 28 24 83456 0x7fdf5971c700 0x7fde4da361c0 131072 206280 26469216 12075940103722203 12075940103871487 12075940104138366 12075940104187007
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 138 900933 900938 4194304 256 0 0 28 24 84928 0x7fdf5971c600 0x7fde4da36200 65536 164074 21007432 12075940104209529 12075940104373405 12075940104630364 12075940104652432
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 140 900933 900938 4194304 256 0 0 24 24 86400 0x7fdf5971c500 0x7fde4da36240 131072 240534 30644192 12075940104694941 12075940104835483 12075940104968922 12075940104973007
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 142 900933 900938 4194304 256 0 0 24 24 88128 0x7fdf5971c400 0x7fde4da36280 131072 197370 25279192 12075940105023932 12075940105181081 12075940105331320 12075940105335661
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 144 900933 900938 4194304 256 0 0 24 24 89600 0x7fdf5971c300 0x7fde4da362c0 131072 248490 31936912 12075940105408096 12075940105549399 12075940105677559 12075940105681454
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 900933 900938 4194304 256 0 0 28 24 92096 0x7fdf5971ca00 0x7fde4da36300 131072 205282 26397080 12075940105728061 12075940105880598 12075940106144596 12075940106198615
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 148 900933 900938 4194304 256 0 0 28 24 93568 0x7fdf5971c900 0x7fde4da36340 65536 172128 22176200 12075940106223131 12075940106395155 12075940106645394 12075940106692804
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 150 900933 900938 4194304 256 0 0 24 24 95040 0x7fdf5971c800 0x7fde4da36380 131072 242878 30960912 12075940106715155 12075940106872593 12075940107012112 12075940107016044
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 152 900933 900938 4194304 256 0 0 24 24 96768 0x7fdf5971c700 0x7fde4da363c0 131072 256046 32890016 12075940107064054 12075940107216431 12075940107373550 12075940107377486
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 154 900933 900938 4194304 256 0 0 24 24 98240 0x7fdf5971c600 0x7fde4da36400 131072 242574 31072608 12075940107437307 12075940107575949 12075940107704108 12075940107708151
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 900933 900938 4194304 256 0 0 28 24 100736 0x7fdf5971c500 0x7fde4da36440 131072 207714 26542336 12075940107755659 12075940107902988 12075940108168266 12075940108216946
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 158 900933 900938 4194304 256 0 0 28 24 102208 0x7fdf5971c400 0x7fde4da36480 65536 172678 22106528 12075940108238957 12075940108400105 12075940108657544 12075940108704212
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 160 900933 900938 4194304 256 0 0 24 24 103680 0x7fdf5971c300 0x7fde4da364c0 131072 243214 31210912 12075940108726253 12075940108887943 12075940109020902 12075940109025058
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 162 900933 900938 4194304 256 0 0 24 24 105664 0x7fdf5971ca00 0x7fde4da36500 131072 259010 33034888 12075940109070422 12075940109234181 12075940109400100 12075940109404183
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 164 900933 900938 4194304 256 0 0 24 24 107136 0x7fdf5971c900 0x7fde4da36540 131072 244884 31316312 12075940109462381 12075940109605379 12075940109738498 12075940109742201
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 900933 900938 4194304 256 0 0 28 24 109888 0x7fdf5971c800 0x7fde4da36580 131072 197884 25417576 12075940109787786 12075940109939137 12075940110199616 12075940110249003
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 168 900933 900938 4194304 256 0 0 28 24 111360 0x7fdf5971c700 0x7fde4da365c0 65536 182048 23200776 12075940110272106 12075940110436095 12075940110685694 12075940110733042
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 170 900933 900938 4194304 256 0 0 24 24 112832 0x7fdf5971c600 0x7fde4da36600 131072 247244 31717200 12075940110757087 12075940110915613 12075940111050812 12075940111055441
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 172 900933 900938 4194304 256 0 0 24 24 114816 0x7fdf5971c500 0x7fde4da36640 131072 248180 31730560 12075940111103371 12075940111256411 12075940111430650 12075940111434596
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 174 900933 900938 4194304 256 0 0 24 24 116288 0x7fdf5971c400 0x7fde4da36680 131072 237582 30499072 12075940111492975 12075940111631449 12075940111764888 12075940111768767
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 900933 900938 4194304 256 0 0 28 24 119040 0x7fdf5971c300 0x7fde4da366c0 131072 210898 26911232 12075940111814642 12075940111967927 12075940112223126 12075940112271391
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 178 900933 900938 4194304 256 0 0 28 24 120768 0x7fdf5971ca00 0x7fde4da36700 65536 175310 22505488 12075940112293763 12075940112457365 12075940112710164 12075940112756803
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 180 900933 900938 4194304 256 0 0 24 24 122496 0x7fdf5971c900 0x7fde4da36740 131072 245806 31459680 12075940112777933 12075940112945523 12075940113083282 12075940113087538
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 182 900933 900938 4194304 256 0 0 24 24 124736 0x7fdf5971c800 0x7fde4da36780 131072 256766 32837736 12075940113135918 12075940113291121 12075940113474000 12075940113477984
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 184 900933 900938 4194304 256 0 0 24 24 126464 0x7fdf5971c700 0x7fde4da367c0 131072 258182 32871184 12075940113538025 12075940113677519 12075940113809038 12075940113812906
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 900933 900938 4194304 256 0 0 20 24 127936 0x7fdf5971c600 0x7fde4da36800 131072 243222 31147776 12075940113861627 12075940114010957 12075940114277196 12075940114325749
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 188 900933 900938 4194304 256 0 0 28 24 129664 0x7fdf5971c500 0x7fde4da36840 65536 170312 21827104 12075940114348742 12075940114511595 12075940114769674 12075940114790623
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 190 900933 900938 4194304 256 0 0 24 24 131392 0x7fdf5971c400 0x7fde4da36880 131072 243572 31109192 12075940114832060 12075940114970313 12075940115106312 12075940115110227
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 192 900933 900938 4194304 256 0 0 24 24 133632 0x7fdf5971c300 0x7fde4da368c0 131072 249078 31764776 12075940115158397 12075940115314791 12075940115505990 12075940115553451
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 194 900933 900938 4194304 256 0 0 24 24 135360 0x7fdf5971ca00 0x7fde4da36900 131072 238562 30480264 12075940115585861 12075940115734789 12075940115873988 12075940115877854
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 900933 900938 4194304 256 0 0 20 24 136832 0x7fdf5971c900 0x7fde4da36940 131072 238364 30420216 12075940115924039 12075940116077027 12075940116361186 12075940116409742
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 198 900933 900938 4194304 256 0 0 28 24 138560 0x7fdf5971c800 0x7fde4da36980 65536 168436 21650736 12075940116431382 12075940116597185 12075940116857183 12075940116904512
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 200 900933 900938 4194304 256 0 0 24 24 140288 0x7fdf5971c700 0x7fde4da369c0 131072 244776 31218152 12075940116928887 12075940117100382 12075940117233181 12075940117237601
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 202 900933 900938 4194304 256 0 0 24 24 142784 0x7fdf5971c600 0x7fde4da36a00 131072 241062 30995944 12075940117285920 12075940117435900 12075940117646139 12075940117693758
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 204 900933 900938 4194304 256 0 0 24 24 144768 0x7fdf5971c500 0x7fde4da36a40 131072 268098 34172264 12075940117727231 12075940117877178 12075940118013018 12075940118017330
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 900933 900938 4194304 256 0 0 20 24 145728 0x7fdf5971c400 0x7fde4da36a80 131072 241030 30789088 12075940118064357 12075940118216057 12075940118523735 12075940118570999
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 208 900933 900938 4194304 256 0 0 28 24 147712 0x7fdf5971c300 0x7fde4da36ac0 65536 169176 21544168 12075940118592148 12075940118757494 12075940119017173 12075940119066129
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 210 900933 900938 4194304 256 0 0 24 24 149696 0x7fdf5971ca00 0x7fde4da36b00 131072 239168 30681616 12075940119094542 12075940119256531 12075940119391411 12075940119395501
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 212 900933 900938 4194304 256 0 0 24 24 152192 0x7fdf5971c900 0x7fde4da36b40 131072 262992 33677984 12075940119442789 12075940119592210 12075940119820689 12075940119867649
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 214 900933 900938 4194304 256 0 0 24 24 154176 0x7fdf5971c800 0x7fde4da36b80 131072 267360 34489600 12075940119903916 12075940120066287 12075940120201647 12075940120205947
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 900933 900938 4194304 256 0 0 20 24 155648 0x7fdf5971c700 0x7fde4da36bc0 131072 270860 34754936 12075940120253876 12075940120410286 12075940120739244 12075940120761530
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 218 900933 900938 4194304 256 0 0 28 24 157632 0x7fdf5971c600 0x7fde4da36c00 65536 169364 21684544 12075940120802606 12075940120941643 12075940121198602 12075940121248956
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 220 900933 900938 4194304 256 0 0 24 24 159616 0x7fdf5971c500 0x7fde4da36c40 131072 263658 33732512 12075940121271117 12075940121436361 12075940121576520 12075940121580572
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 222 900933 900938 4194304 256 0 0 24 24 162368 0x7fdf5971c400 0x7fde4da36c80 131072 236470 30244656 12075940121627720 12075940121777479 12075940122023238 12075940122073067
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 224 900933 900938 4194304 256 0 0 24 24 164608 0x7fdf5971c300 0x7fde4da36cc0 131072 245820 31650312 12075940122106039 12075940122256837 12075940122397316 12075940122401367
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 900933 900938 4194304 256 0 0 20 24 166336 0x7fdf5971ca00 0x7fde4da36d00 131072 243472 30828256 12075940122449677 12075940122596675 12075940122972833 12075940123021730
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 228 900933 900938 4194304 256 0 0 28 24 168576 0x7fdf5971c900 0x7fde4da36d40 65536 173984 22249888 12075940123044132 12075940123207712 12075940123471711 12075940123520307
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 230 900933 900938 4194304 256 0 0 24 24 170816 0x7fdf5971c800 0x7fde4da36d80 131072 242078 31027840 12075940123544893 12075940123700761 12075940123843801 12075940123851152
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 232 900933 900938 4194304 256 0 0 24 24 174080 0x7fdf5971c700 0x7fde4da36dc0 131072 246382 31548104 12075940123894502 12075940124064439 12075940124343798 12075940124372811
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 234 900933 900938 4194304 256 0 0 24 24 176576 0x7fdf5971c600 0x7fde4da36e00 131072 237556 30666096 12075940124417544 12075940124558517 12075940124693876 12075940124697024
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 900933 900938 4194304 256 0 0 20 24 177792 0x7fdf5971c500 0x7fde4da36e40 131072 267186 33957256 12075940124744081 12075940124897236 12075940125320914 12075940125349116
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 238 900933 900938 4194304 256 0 0 28 24 180288 0x7fdf5971c400 0x7fde4da36e80 65536 177724 22686256 12075940125387767 12075940125534833 12075940125795792 12075940125819029
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 240 900933 900938 4194304 256 0 0 24 24 182784 0x7fdf5971c300 0x7fde4da36ec0 131072 251324 32194656 12075940125862329 12075940126000111 12075940126140431 12075940126144293
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 242 900933 900938 4194304 256 0 0 24 24 186304 0x7fdf5971ca00 0x7fde4da36f00 131072 241586 31023488 12075940126193325 12075940126345390 12075940126661389 12075940126684818
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 244 900933 900938 4194304 256 0 0 24 24 189312 0x7fdf5971c900 0x7fde4da36f40 131072 240604 30897328 12075940126742926 12075940126884748 12075940127037067 12075940127040499
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 900933 900938 4194304 256 0 0 20 24 190784 0x7fdf5971c800 0x7fde4da36f80 131072 231834 29812952 12075940127087176 12075940127240747 12075940127757705 12075940127781005
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 248 900933 900938 4194304 256 0 0 28 24 193792 0x7fdf5971c700 0x7fde4da36fc0 65536 173250 22195936 12075940127822683 12075940127961864 12075940128261383 12075940128287587
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 250 900933 900938 4194304 256 0 0 24 24 196800 0x7fdf5971c600 0x7fde4da37000 131072 231440 29607928 12075940128327090 12075940128465702 12075940128621221 12075940128624352
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 252 900933 900938 4194304 256 0 0 24 24 201088 0x7fdf5971c500 0x7fde4da37040 131072 244712 31258992 12075940128671089 12075940128826500 12075940129211619 12075940129240928
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 254 900933 900938 4194304 256 0 0 24 24 204608 0x7fdf5971c400 0x7fde4da37080 131072 243636 30988368 12075940129289479 12075940129430818 12075940129606498 12075940129609684
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 900933 900938 4194304 256 0 0 20 24 206080 0x7fdf5971c300 0x7fde4da370c0 131072 236554 30417224 12075940129655308 12075940129806177 12075940130428414 12075940130453983
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 258 900933 900938 4194304 256 0 0 28 24 209600 0x7fdf5971ca00 0x7fde4da37100 65536 171290 21817528 12075940130493146 12075940130638814 12075940130967612 12075940130991061
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 260 900933 900938 4194304 256 0 0 24 24 213120 0x7fdf5971c900 0x7fde4da37140 131072 239242 30602952 12075940131038068 12075940131180252 12075940131359291 12075940131362461
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 262 900933 900938 4194304 256 0 0 24 24 218176 0x7fdf5971c800 0x7fde4da37180 131072 249190 32122816 12075940131408647 12075940131562810 12075940132018808 12075940132043226
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 264 900933 900938 4194304 256 0 0 24 24 222208 0x7fdf5971c700 0x7fde4da371c0 131072 240356 30768632 12075940132097066 12075940132238807 12075940132440247 12075940132463648
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 900933 900938 4194304 256 0 0 20 24 223936 0x7fdf5971c600 0x7fde4da37200 131072 251500 32278976 12075940132505976 12075940132646806 12075940133350643 12075940133376023
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 268 900933 900938 4194304 256 0 0 28 24 227968 0x7fdf5971c500 0x7fde4da37240 65536 169878 21716776 12075940133413313 12075940133570322 12075940133944241 12075940133990565
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 270 900933 900938 4194304 256 0 0 24 24 232000 0x7fdf5971c400 0x7fde4da37280 131072 248026 31717072 12075940134020180 12075940134193040 12075940134395759 12075940134444489
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 272 900933 900938 4194304 256 0 0 24 24 237824 0x7fdf5971c300 0x7fde4da372c0 131072 242116 31026816 12075940134470477 12075940134631438 12075940135158476 12075940135208469
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 274 900933 900938 4194304 256 0 0 24 24 242368 0x7fdf5971ca00 0x7fde4da37300 131072 240096 30622160 12075940135242602 12075940135400875 12075940135624715 12075940135672211
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 900933 900938 4194304 256 0 0 20 24 243584 0x7fdf5971c900 0x7fde4da37340 131072 237952 30442592 12075940135693701 12075940135857674 12075940136656871 12075940136707515
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 278 900933 900938 4194304 256 0 0 28 24 248128 0x7fdf5971c800 0x7fde4da37380 65536 191548 24463368 12075940136729516 12075940136894790 12075940137315908 12075940137368373
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 280 900933 900938 4194304 256 0 0 24 24 252672 0x7fdf5971c700 0x7fde4da373c0 131072 247516 31710640 12075940137392237 12075940137555107 12075940137780226 12075940137828809
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 282 900933 900938 4194304 256 0 0 24 24 259264 0x7fdf5971c600 0x7fde4da37400 131072 247198 31707512 12075940137850238 12075940138012225 12075940138609823 12075940138658070
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 284 900933 900938 4194304 256 0 0 24 24 264832 0x7fdf5971c500 0x7fde4da37440 131072 245668 31272984 12075940138690270 12075940138842782 12075940139113501 12075940139160163
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 900933 900938 4194304 256 0 0 20 24 266304 0x7fdf5971c400 0x7fde4da37480 131072 261060 33357928 12075940139183276 12075940139353660 12075940140339257 12075940140390429
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 288 900933 900938 4194304 256 0 0 28 24 271872 0x7fdf5971c300 0x7fde4da374c0 65536 176780 22602688 12075940140413141 12075940140582936 12075940141098294 12075940141139862
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 290 900933 900938 4194304 256 0 0 24 24 277440 0x7fdf5971ca00 0x7fde4da37500 131072 240100 30875440 12075940141168706 12075940141329493 12075940141602452 12075940141642947
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 292 900933 900938 4194304 256 0 0 12 24 279936 0x7fdf5971c900 0x7fde4da37540 131072 266672 34188936 12075940141664667 12075940141828531 12075940142567728 12075940142611637
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 294 900933 900938 4194304 256 0 0 24 24 286528 0x7fdf5971c800 0x7fde4da37580 131072 238776 30600664 12075940142652243 12075940142792687 12075940143137646 12075940143206082
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 900933 900938 4194304 256 0 0 20 24 288000 0x7fdf5971c700 0x7fde4da375c0 131072 250258 31826752 12075940143227341 12075940143397165 12075940144569480 12075940144636801
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 298 900933 900938 4194304 256 0 0 32 24 294592 0x7fdf5971c600 0x7fde4da37600 65536 168102 21452784 12075940144665594 12075940144830759 12075940145441317 12075940145509863
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 300 900933 900938 4194304 256 0 0 24 24 301184 0x7fdf5971c500 0x7fde4da37640 131072 252494 32409400 12075940145533067 12075940145699396 12075940146046755 12075940146115309
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 302 900933 900938 4194304 256 0 0 12 24 304960 0x7fdf5971c400 0x7fde4da37680 131072 246326 31504880 12075940146142279 12075940146301314 12075940147179710 12075940147247042
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 304 900933 900938 4194304 256 0 0 24 24 313600 0x7fdf5971c300 0x7fde4da376c0 131072 242918 30955672 12075940147287437 12075940147441949 12075940147874908 12075940147941442
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 900933 900938 4194304 256 0 0 20 24 314816 0x7fdf5971ca00 0x7fde4da37700 131072 246048 31498344 12075940147963544 12075940148138907 12075940149688821 12075940149757097
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 308 900933 900938 4194304 256 0 0 20 24 317568 0x7fdf5971c900 0x7fde4da37740 65536 165966 21306576 12075940149779879 12075940149950900 12075940150748497 12075940150817247
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 310 900933 900938 4194304 256 0 0 12 24 320320 0x7fdf5971c800 0x7fde4da37780 131072 269980 34844488 12075940150839909 12075940151009296 12075940151447694 12075940151514833
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 312 900933 900938 4194304 256 0 0 12 24 324096 0x7fdf5971c700 0x7fde4da377c0 131072 259410 33177320 12075940151537966 12075940151699693 12075940152858729 12075940152927469
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 314 900933 900938 4194304 256 0 0 12 24 328896 0x7fdf5971c600 0x7fde4da37800 131072 240332 30866976 12075940152968355 12075940153116488 12075940153902085 12075940153970988
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 900933 900938 4194304 256 0 0 20 24 330112 0x7fdf5971c500 0x7fde4da37840 131072 238710 30684320 12075940153997948 12075940154168324 12075940157222072 12075940157295286
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 318 900933 900938 4194304 256 0 0 20 24 332864 0x7fdf5971c400 0x7fde4da37880 65536 170586 21812872 12075940157318489 12075940157481271 12075940159027505 12075940159095542
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 320 900933 900938 4194304 256 0 0 12 24 335616 0x7fdf5971c300 0x7fde4da378c0 131072 239240 30698104 12075940159125478 12075940159287664 12075940160078701 12075940160146435
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 322 900933 900938 4194304 256 0 0 12 24 339392 0x7fdf5971ca00 0x7fde4da37900 131072 258544 33154864 12075940160169418 12075940160343980 12075940162626211 12075940162693829
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 324 900933 900938 4194304 256 0 0 12 24 344192 0x7fdf5971c900 0x7fde4da37940 131072 237262 30425144 12075940162732251 12075940162883490 12075940164419165 12075940164488975
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 900933 900938 4194304 256 0 0 20 24 345408 0x7fdf5971c800 0x7fde4da37980 131072 247440 31774800 12075940164517939 12075940164682044 12075940170739620 12075940170809462
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 328 900933 900938 4194304 256 0 0 20 24 348160 0x7fdf5971c700 0x7fde4da379c0 65536 184318 23535632 12075940170837233 12075940171002019 12075940174046968 12075940174120465
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 330 900933 900938 4194304 256 0 0 12 24 350912 0x7fdf5971c600 0x7fde4da37a00 131072 251480 32263840 12075940174143087 12075940174314007 12075940175852881 12075940175920520
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 332 900933 900938 4194304 256 0 0 12 24 0 0x7fdf5971c500 0x7fde4da37a40 131072 233574 30067768 12075940175949013 12075940176116880 12075940180645663 12075940180715712
@@ -1,168 +0,0 @@
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",0,0,0,901123,901128,33554432,256,0,0,8,32,6464,0x0,0x7f34bac04180,1048576,11105144,1422096704,12075941073738305,12075941319842027,12075941320166985,12075941320278178
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,901123,901128,32768,256,0,0,24,24,12480,0x0,0x7f34bac35100,4096,114185,14602220,12075941334761004,12075941335062034,12075941335068594,12075941335073605
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,901123,901128,4194304,256,0,0,24,24,12928,0x7f35ead59900,0x7f34bac35140,524288,12413352,1588891204,12075941335135089,12075941335348753,12075941335481872,12075941335485801
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,901123,901128,4194304,256,0,0,36,24,13632,0x7f35ead59800,0x7f34bac35180,524288,13402692,1715511820,12075941335555170,12075941335724591,12075941335975470,12075941336049198
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,901123,901128,4194304,256,0,0,28,24,14080,0x7f35ead59700,0x7f34bac351c0,524288,13545990,1733904120,12075941336080867,12075941336269389,12075941336523788,12075941336590725
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,901123,901128,4194304,256,0,0,24,24,14528,0x7f35ead59600,0x7f34bac35200,524288,11846202,1516289108,12075941336618556,12075941336803946,12075941336938026,12075941336941276
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,901123,901128,4194304,256,0,0,24,24,14976,0x7f35ead59500,0x7f34bac35240,524288,12320378,1576894116,12075941336992060,12075941337166665,12075941337297384,12075941337300834
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,901123,901128,4194304,256,0,0,24,24,15424,0x7f35ead59400,0x7f34bac35280,524288,12661711,1620725488,12075941337380412,12075941337551623,12075941337681702,12075941337685018
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,901123,901128,4194304,256,0,0,28,24,16128,0x7f35ead59300,0x7f34bac352c0,524288,13923625,1782206516,12075941337740571,12075941337902021,12075941338156260,12075941338224401
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,901123,901128,4194304,256,0,0,28,24,16832,0x7f35ead59a00,0x7f34bac35300,524288,14364290,1838601808,12075941338250970,12075941338430339,12075941338681058,12075941338721194
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,901123,901128,4194304,256,0,0,24,24,17536,0x7f35ead59900,0x7f34bac35340,524288,12121934,1551545080,12075941338745309,12075941338934976,12075941339066496,12075941339070293
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,901123,901128,4194304,256,0,0,24,24,18240,0x7f35ead59800,0x7f34bac35380,524288,12295928,1573961776,12075941339121768,12075941339296575,12075941339429054,12075941339432706
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,901123,901128,4194304,256,0,0,24,24,18944,0x7f35ead59700,0x7f34bac353c0,524288,12754550,1632620856,12075941339495172,12075941339656733,12075941339786332,12075941339789439
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,901123,901128,4194304,256,0,0,28,24,19904,0x7f35ead59600,0x7f34bac35400,524288,13435440,1719754172,12075941339840194,12075941340002171,12075941340257370,12075941340324974
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,901123,901128,4194304,256,0,0,28,24,20608,0x7f35ead59500,0x7f34bac35440,524288,13925867,1782592428,12075941340349891,12075941340534169,12075941340786008,12075941340852705
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,901123,901128,4194304,256,0,0,24,24,21312,0x7f35ead59400,0x7f34bac35480,524288,12809035,1639523772,12075941340879635,12075941341068086,12075941341198006,12075941341201373
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,901123,901128,4194304,256,0,0,24,24,22016,0x7f35ead59300,0x7f34bac354c0,524288,12558038,1607355812,12075941341250775,12075941341416085,12075941341546484,12075941341549961
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,901123,901128,4194304,256,0,0,24,24,22720,0x7f35ead59a00,0x7f34bac35500,524288,13017882,1666221916,12075941341610984,12075941341772083,12075941341901202,12075941341904690
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,901123,901128,4194304,256,0,0,28,24,23680,0x7f35ead59900,0x7f34bac35540,524288,14287812,1828820564,12075941341953000,12075941342132081,12075941342385680,12075941342454352
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,901123,901128,4194304,256,0,0,28,24,24384,0x7f35ead59800,0x7f34bac35580,524288,13836888,1771164088,12075941342478867,12075941342666159,12075941342920238,12075941342961484
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,901123,901128,4194304,256,0,0,24,24,25088,0x7f35ead59700,0x7f34bac355c0,524288,12824198,1641489492,12075941342988815,12075941343179916,12075941343309516,12075941343313208
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,901123,901128,4194304,256,0,0,24,24,25792,0x7f35ead59600,0x7f34bac35600,524288,12501384,1600220792,12075941343358482,12075941343545195,12075941343677194,12075941343680671
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,901123,901128,4194304,256,0,0,24,24,26496,0x7f35ead59500,0x7f34bac35640,524288,13061932,1671874556,12075941343743187,12075941343905513,12075941344033032,12075941344036502
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,901123,901128,4194304,256,0,0,28,24,27712,0x7f35ead59400,0x7f34bac35680,524288,14229473,1821327376,12075941344086746,12075941344259751,12075941344513510,12075941344580523
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,901123,901128,4194304,256,0,0,28,24,28416,0x7f35ead59300,0x7f34bac356c0,524288,14281620,1828091580,12075941344606992,12075941344786789,12075941345039108,12075941345110338
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,901123,901128,4194304,256,0,0,24,24,29120,0x7f35ead59a00,0x7f34bac35700,524288,12216801,1563868688,12075941345135484,12075941345317506,12075941345448546,12075941345451953
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,901123,901128,4194304,256,0,0,24,24,30080,0x7f35ead59900,0x7f34bac35740,524288,11178209,1430796288,12075941345501034,12075941345663105,12075941345800384,12075941345803857
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,901123,901128,4194304,256,0,0,24,24,30784,0x7f35ead59800,0x7f34bac35780,524288,12957083,1658486552,12075941345867355,12075941346034303,12075941346164063,12075941346168144
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,901123,901128,4194304,256,0,0,28,24,32000,0x7f35ead59700,0x7f34bac357c0,524288,14211379,1819014236,12075941346218127,12075941346397021,12075941346652700,12075941346695053
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,901123,901128,4194304,256,0,0,28,24,32960,0x7f35ead59600,0x7f34bac35800,524288,14173967,1814269816,12075941346720981,12075941346896379,12075941347143258,12075941347212885
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,901123,901128,4194304,256,0,0,24,24,33920,0x7f35ead59500,0x7f34bac35840,524288,11387218,1457420568,12075941347239234,12075941347417817,12075941347553176,12075941347556664
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,901123,901128,4194304,256,0,0,24,24,34880,0x7f35ead59400,0x7f34bac35880,524288,13140501,1681986640,12075941347605104,12075941347773015,12075941347902134,12075941347905623
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,901123,901128,4194304,256,0,0,24,24,35840,0x7f35ead59300,0x7f34bac358c0,524288,12083419,1546626624,12075941347966917,12075941348131893,12075941348264853,12075941348268838
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,901123,901128,4194304,256,0,0,28,24,37312,0x7f35ead59a00,0x7f34bac35900,524288,13812879,1768101904,12075941348317608,12075941348489812,12075941348745010,12075941348812318
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,901123,901128,4194304,256,0,0,28,24,38272,0x7f35ead59900,0x7f34bac35940,524288,13663026,1748803952,12075941348838547,12075941349013329,12075941349271088,12075941349341632
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,901123,901128,4194304,256,0,0,24,24,39232,0x7f35ead59800,0x7f34bac35980,524288,11935524,1527683272,12075941349368131,12075941349545967,12075941349678766,12075941349682425
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,901123,901128,4194304,256,0,0,24,24,40192,0x7f35ead59700,0x7f34bac359c0,524288,11997706,1535696976,12075941349732328,12075941349901965,12075941350035884,12075941350039729
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,901123,901128,4194304,256,0,0,24,24,41152,0x7f35ead59600,0x7f34bac35a00,524288,12513785,1601718828,12075941350101924,12075941350265643,12075941350396683,12075941350400159
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,901123,901128,4194304,256,0,0,28,24,42624,0x7f35ead59500,0x7f34bac35a40,524288,13045409,1669837856,12075941350449450,12075941350612362,12075941350870761,12075941350912601
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,901123,901128,4194304,256,0,0,28,24,43584,0x7f35ead59400,0x7f34bac35a80,524288,13718177,1755951836,12075941350937588,12075941351116839,12075941351405798,12075941351474485
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,901123,901128,4194304,256,0,0,24,24,44544,0x7f35ead59300,0x7f34bac35ac0,524288,12607261,1613586480,12075941351501345,12075941351677157,12075941351809316,12075941351812824
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,901123,901128,4194304,256,0,0,24,24,45760,0x7f35ead59a00,0x7f34bac35b00,524288,12281335,1572113032,12075941351862026,12075941352036355,12075941352168834,12075941352172513
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,901123,901128,4194304,256,0,0,24,24,46720,0x7f35ead59900,0x7f34bac35b40,524288,12200786,1561792864,12075941352233295,12075941352393953,12075941352525953,12075941352529586
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,901123,901128,4194304,256,0,0,28,24,48448,0x7f35ead59800,0x7f34bac35b80,524288,14159216,1812328088,12075941352578637,12075941352737152,12075941352992191,12075941353060603
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,901123,901128,4194304,256,0,0,28,24,49408,0x7f35ead59700,0x7f34bac35bc0,524288,14265797,1826001812,12075941353084708,12075941353263389,12075941353514268,12075941353582122
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,901123,901128,4194304,256,0,0,24,24,50368,0x7f35ead59600,0x7f34bac35c00,524288,11014339,1409820884,12075941353600697,12075941353785147,12075941353921946,12075941353925510
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,901123,901128,4194304,256,0,0,24,24,51584,0x7f35ead59500,0x7f34bac35c40,524288,11574756,1481574580,12075941353974652,12075941354144185,12075941354280985,12075941354284748
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,901123,901128,4194304,256,0,0,24,24,52544,0x7f35ead59400,0x7f34bac35c80,524288,12231612,1565600244,12075941354347685,12075941354511064,12075941354643063,12075941354646540
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,901123,901128,4194304,256,0,0,28,24,54272,0x7f35ead59300,0x7f34bac35cc0,524288,13401925,1715406044,12075941354698657,12075941354858102,12075941355126261,12075941355195771
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,901123,901128,4194304,256,0,0,28,24,55488,0x7f35ead59a00,0x7f34bac35d00,524288,14241911,1822943244,12075941355220868,12075941355403219,12075941355656338,12075941355724794
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,901123,901128,4194304,256,0,0,24,24,56704,0x7f35ead59900,0x7f34bac35d40,524288,12877435,1648285668,12075941355750542,12075941355924337,12075941356053616,12075941356057392
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,901123,901128,4194304,256,0,0,24,24,58176,0x7f35ead59800,0x7f34bac35d80,524288,11153587,1427696540,12075941356099621,12075941356273615,12075941356407855,12075941356411521
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,901123,901128,4194304,256,0,0,24,24,59392,0x7f35ead59700,0x7f34bac35dc0,524288,11663651,1492993708,12075941356473666,12075941356631694,12075941356766413,12075941356769957
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,901123,901128,4194304,256,0,0,28,24,61376,0x7f35ead59600,0x7f34bac35e00,524288,13892877,1778318404,12075941356818317,12075941356984332,12075941357251371,12075941357320410
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,901123,901128,4194304,256,0,0,28,24,62592,0x7f35ead59500,0x7f34bac35e40,524288,14207833,1818629776,12075941357344054,12075941357531689,12075941357777768,12075941357845085
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,901123,901128,4194304,256,0,0,24,24,63808,0x7f35ead59400,0x7f34bac35e80,524288,12370766,1583575676,12075941357868378,12075941358049927,12075941358180646,12075941358184395
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,901123,901128,4194304,256,0,0,24,24,65280,0x7f35ead59300,0x7f34bac35ec0,524288,8879272,1136491052,12075941358232565,12075941358399845,12075941358535045,12075941358538463
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,901123,901128,4194304,256,0,0,24,24,66496,0x7f35ead59a00,0x7f34bac35f00,524288,11394146,1458491948,12075941358599867,12075941358757444,12075941358892963,12075941358896459
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,901123,901128,4194304,256,0,0,28,24,68480,0x7f35ead59900,0x7f34bac35f40,524288,12986316,1662175360,12075941358944428,12075941359112642,12075941359375521,12075941359427145
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,901123,901128,4194304,256,0,0,28,24,69696,0x7f35ead59800,0x7f34bac35f80,524288,14111739,1806299644,12075941359449336,12075941359626560,12075941359874718,12075941359924229
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,901123,901128,4194304,256,0,0,24,24,70912,0x7f35ead59700,0x7f34bac35fc0,524288,11823209,1513326296,12075941359950057,12075941360129757,12075941360263517,12075941360267226
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,901123,901128,4194304,256,0,0,24,24,72384,0x7f35ead59600,0x7f34bac36000,524288,7359701,942000352,12075941360316488,12075941360482396,12075941360620635,12075941360624270
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,901123,901128,4194304,256,0,0,24,24,73600,0x7f35ead59500,0x7f34bac36040,524288,11046478,1413963584,12075941360683881,12075941360843834,12075941360980953,12075941360984720
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,901123,901128,4194304,256,0,0,28,24,75840,0x7f35ead59400,0x7f34bac36080,524288,11790360,1509148136,12075941361031456,12075941361210072,12075941361476791,12075941361526426
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,901123,901128,4194304,256,0,0,28,24,77056,0x7f35ead59300,0x7f34bac360c0,524288,13937127,1783918532,12075941361549469,12075941361726710,12075941361981589,12075941362031685
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,901123,901128,4194304,256,0,0,24,24,78272,0x7f35ead59a00,0x7f34bac36100,524288,11716925,1499760940,12075941362057884,12075941362233107,12075941362365747,12075941362369323
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,901123,901128,4194304,256,0,0,24,24,80000,0x7f35ead59900,0x7f34bac36140,524288,7304085,935115064,12075941362423103,12075941362584306,12075941362729425,12075941362732838
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,901123,901128,4194304,256,0,0,24,24,81216,0x7f35ead59800,0x7f34bac36180,524288,11969279,1531964272,12075941362793601,12075941362953104,12075941363086063,12075941363089822
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,901123,901128,4194304,256,0,0,28,24,83456,0x7f35ead59700,0x7f34bac361c0,524288,14020291,1794568384,12075941363139394,12075941363308942,12075941363574861,12075941363626339
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,901123,901128,4194304,256,0,0,28,24,84928,0x7f35ead59600,0x7f34bac36200,524288,14135678,1809359296,12075941363656044,12075941363829100,12075941364077579,12075941364126238
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,901123,901128,4194304,256,0,0,24,24,86400,0x7f35ead59500,0x7f34bac36240,524288,12516572,1602146548,12075941364151946,12075941364333418,12075941364464297,12075941364467993
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,901123,901128,4194304,256,0,0,24,24,88128,0x7f35ead59400,0x7f34bac36280,524288,5999343,767927368,12075941364517275,12075941364680776,12075941364831015,12075941364834604
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,901123,901128,4194304,256,0,0,24,24,89600,0x7f35ead59300,0x7f34bac362c0,524288,13160509,1684571980,12075941364911708,12075941365079334,12075941365207334,12075941365211204
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,901123,901128,4194304,256,0,0,28,24,92096,0x7f35ead59a00,0x7f34bac36300,524288,12382816,1585020452,12075941365258943,12075941365427973,12075941365694051,12075941365741590
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,901123,901128,4194304,256,0,0,28,24,93568,0x7f35ead59900,0x7f34bac36340,524288,14119658,1807288388,12075941365765014,12075941365943010,12075941366226529,12075941366276825
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,901123,901128,4194304,256,0,0,24,24,95040,0x7f35ead59800,0x7f34bac36380,524288,11111074,1422209636,12075941366300308,12075941366480928,12075941366615327,12075941366619031
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,901123,901128,4194304,256,0,0,24,24,96768,0x7f35ead59700,0x7f34bac363c0,524288,4567073,584458584,12075941366667932,12075941366833246,12075941366990685,12075941366994198
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,901123,901128,4194304,256,0,0,24,24,98240,0x7f35ead59600,0x7f34bac36400,524288,11072032,1417247668,12075941367055732,12075941367216764,12075941367352764,12075941367356722
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,901123,901128,4194304,256,0,0,28,24,100736,0x7f35ead59500,0x7f34bac36440,524288,10940691,1400432356,12075941367400794,12075941367570043,12075941367836761,12075941367884002
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,901123,901128,4194304,256,0,0,28,24,102208,0x7f35ead59400,0x7f34bac36480,524288,14150327,1811202328,12075941367910451,12075941368090680,12075941368344759,12075941368395372
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,901123,901128,4194304,256,0,0,24,24,103680,0x7f35ead59300,0x7f34bac364c0,524288,12556595,1607181392,12075941368422262,12075941368597238,12075941368729237,12075941368733029
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,901123,901128,4194304,256,0,0,24,24,105664,0x7f35ead59a00,0x7f34bac36500,524288,3619555,463195720,12075941368781099,12075941368953716,12075941369120435,12075941369124347
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,901123,901128,4194304,256,0,0,24,24,107136,0x7f35ead59900,0x7f34bac36540,524288,11346463,1452246776,12075941369185841,12075941369344274,12075941369480594,12075941369484175
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,901123,901128,4194304,256,0,0,28,24,109888,0x7f35ead59800,0x7f34bac36580,524288,9861627,1262405588,12075941369533167,12075941369693073,12075941369957071,12075941370011806
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,901123,901128,4194304,256,0,0,28,24,111360,0x7f35ead59700,0x7f34bac365c0,524288,13578265,1737987808,12075941370039077,12075941370215630,12075941370470669,12075941370521183
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,901123,901128,4194304,256,0,0,24,24,112832,0x7f35ead59600,0x7f34bac36600,524288,10862889,1390332780,12075941370545758,12075941370719628,12075941370856747,12075941370860213
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,901123,901128,4194304,256,0,0,24,24,114816,0x7f35ead59500,0x7f34bac36640,524288,3768399,482466372,12075941370908963,12075941371068586,12075941371243625,12075941371247322
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,901123,901128,4194304,256,0,0,24,24,116288,0x7f35ead59400,0x7f34bac36680,524288,11125523,1424189248,12075941371310259,12075941371470184,12075941371606024,12075941371609836
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,901123,901128,4194304,256,0,0,28,24,119040,0x7f35ead59300,0x7f34bac366c0,524288,10166911,1301412412,12075941371658025,12075941371823783,12075941372092421,12075941372143728
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,901123,901128,4194304,256,0,0,28,24,120768,0x7f35ead59a00,0x7f34bac36700,524288,14193603,1816787272,12075941372162573,12075941372350340,12075941372604739,12075941372652243
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,901123,901128,4194304,256,0,0,24,24,122496,0x7f35ead59900,0x7f34bac36740,524288,11340321,1451512340,12075941372678592,12075941372850978,12075941372987297,12075941372990913
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,901123,901128,4194304,256,0,0,24,24,124736,0x7f35ead59800,0x7f34bac36780,524288,3504091,448482292,12075941373041597,12075941373209856,12075941373393055,12075941373396667
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,901123,901128,4194304,256,0,0,24,24,126464,0x7f35ead59700,0x7f34bac367c0,524288,10317857,1320505200,12075941373457229,12075941373614334,12075941373755614,12075941373759341
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,901123,901128,4194304,256,0,0,20,24,127936,0x7f35ead59600,0x7f34bac36800,524288,4101828,524956188,12075941373808222,12075941373971933,12075941374238011,12075941374285769
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,901123,901128,4194304,256,0,0,28,24,129664,0x7f35ead59500,0x7f34bac36840,524288,12508930,1601156888,12075941374312719,12075941374491930,12075941374748889,12075941374769799
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,901123,901128,4194304,256,0,0,24,24,131392,0x7f35ead59400,0x7f34bac36880,524288,11711559,1499006932,12075941374817227,12075941374974648,12075941375109687,12075941375113568
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,901123,901128,4194304,256,0,0,24,24,133632,0x7f35ead59300,0x7f34bac368c0,524288,3653621,467870008,12075941375153953,12075941375333206,12075941375525525,12075941375575596
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,901123,901128,4194304,256,0,0,24,24,135360,0x7f35ead59a00,0x7f34bac36900,524288,10432998,1335562824,12075941375611563,12075941375770644,12075941375909204,12075941375912863
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,901123,901128,4194304,256,0,0,20,24,136832,0x7f35ead59900,0x7f34bac36940,524288,2885035,369285468,12075941375962936,12075941376138162,12075941376423921,12075941376472032
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,901123,901128,4194304,256,0,0,28,24,138560,0x7f35ead59800,0x7f34bac36980,524288,13860509,1774178164,12075941376500756,12075941376672400,12075941376929839,12075941376977942
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,901123,901128,4194304,256,0,0,24,24,140288,0x7f35ead59700,0x7f34bac369c0,524288,11868610,1518994548,12075941377006776,12075941377180878,12075941377316397,12075941377319938
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,901123,901128,4194304,256,0,0,24,24,142784,0x7f35ead59600,0x7f34bac36a00,524288,3277846,419504484,12075941377362196,12075941377531596,12075941377742795,12075941377790993
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,901123,901128,4194304,256,0,0,24,24,144768,0x7f35ead59500,0x7f34bac36a40,524288,10948403,1401520460,12075941377828162,12075941377985034,12075941378122473,12075941378126647
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,901123,901128,4194304,256,0,0,20,24,145728,0x7f35ead59400,0x7f34bac36a80,524288,2539792,325196848,12075941378174306,12075941378342152,12075941378650791,12075941378675718
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,901123,901128,4194304,256,0,0,28,24,147712,0x7f35ead59300,0x7f34bac36ac0,524288,13250388,1696016800,12075941378718527,12075941378876550,12075941379136708,12075941379165287
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,901123,901128,4194304,256,0,0,24,24,149696,0x7f35ead59a00,0x7f34bac36b00,524288,10710142,1370961328,12075941379205863,12075941379363907,12075941379503427,12075941379507223
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,901123,901128,4194304,256,0,0,24,24,152192,0x7f35ead59900,0x7f34bac36b40,524288,3120835,399334568,12075941379554831,12075941379718466,12075941379945505,12075941379970494
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,901123,901128,4194304,256,0,0,24,24,154176,0x7f35ead59800,0x7f34bac36b80,524288,11216129,1435653884,12075941380032038,12075941380192384,12075941380328223,12075941380332046
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,901123,901128,4194304,256,0,0,20,24,155648,0x7f35ead59700,0x7f34bac36bc0,524288,2493114,319246408,12075941380380325,12075941380553182,12075941380883580,12075941380907776
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,901123,901128,4194304,256,0,0,28,24,157632,0x7f35ead59600,0x7f34bac36c00,524288,14094306,1804076396,12075941380954984,12075941381120699,12075941381379418,12075941381407685
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,901123,901128,4194304,256,0,0,24,24,159616,0x7f35ead59500,0x7f34bac36c40,524288,10111014,1294254764,12075941381449422,12075941381604697,12075941381746296,12075941381749951
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,901123,901128,4194304,256,0,0,24,24,162368,0x7f35ead59400,0x7f34bac36c80,524288,3436745,439760088,12075941381798130,12075941381960855,12075941382206134,12075941382231466
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,901123,901128,4194304,256,0,0,24,24,164608,0x7f35ead59300,0x7f34bac36cc0,524288,9693626,1240839820,12075941382288051,12075941382446933,12075941382589332,12075941382593068
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,901123,901128,4194304,256,0,0,20,24,166336,0x7f35ead59a00,0x7f34bac36d00,524288,2360670,302228600,12075941382641207,12075941382808702,12075941383184701,12075941383219211
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,901123,901128,4194304,256,0,0,28,24,168576,0x7f35ead59900,0x7f34bac36d40,524288,13997276,1791629420,12075941383254647,12075941383416379,12075941383676858,12075941383700696
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,901123,901128,4194304,256,0,0,24,24,170816,0x7f35ead59800,0x7f34bac36d80,524288,9437555,1207951892,12075941383744728,12075941383901337,12075941384046296,12075941384049735
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,901123,901128,4194304,256,0,0,24,24,174080,0x7f35ead59700,0x7f34bac36dc0,524288,3461187,443081552,12075941384099047,12075941384270615,12075941384581174,12075941384605047
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,901123,901128,4194304,256,0,0,24,24,176576,0x7f35ead59600,0x7f34bac36e00,524288,7941659,1016697620,12075941384662484,12075941384823253,12075941384964372,12075941384967761
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,901123,901128,4194304,256,0,0,20,24,177792,0x7f35ead59500,0x7f34bac36e40,524288,2340566,299456684,12075941385023475,12075941385184052,12075941385608050,12075941385635833
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,901123,901128,4194304,256,0,0,28,24,180288,0x7f35ead59400,0x7f34bac36e80,524288,12630735,1616795204,12075941385677660,12075941385834929,12075941386104208,12075941386133127
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,901123,901128,4194304,256,0,0,24,24,182784,0x7f35ead59300,0x7f34bac36ec0,524288,7344495,940088460,12075941386176097,12075941386339407,12075941386479566,12075941386482907
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,901123,901128,4194304,256,0,0,24,24,186304,0x7f35ead59a00,0x7f34bac36f00,524288,3462569,443232556,12075941386532158,12075941386691085,12075941387007724,12075941387032769
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,901123,901128,4194304,256,0,0,24,24,189312,0x7f35ead59900,0x7f34bac36f40,524288,3511513,449361624,12075941387092670,12075941387254763,12075941387406923,12075941387410230
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,901123,901128,4194304,256,0,0,20,24,190784,0x7f35ead59800,0x7f34bac36f80,524288,2304428,295010200,12075941387461906,12075941387619722,12075941388137320,12075941388162919
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,901123,901128,4194304,256,0,0,28,24,193792,0x7f35ead59700,0x7f34bac36fc0,524288,7922407,1014020540,12075941388205629,12075941388363239,12075941388660517,12075941388684398
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,901123,901128,4194304,256,0,0,24,24,196800,0x7f35ead59600,0x7f34bac37000,524288,3634989,465362128,12075941388732738,12075941388890277,12075941389046276,12075941389049647
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,901123,901128,4194304,256,0,0,24,24,201088,0x7f35ead59500,0x7f34bac37040,524288,3264320,417970424,12075941389101774,12075941389261315,12075941389646593,12075941389673356
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,901123,901128,4194304,256,0,0,24,24,204608,0x7f35ead59400,0x7f34bac37080,524288,3419795,437808280,12075941389730973,12075941389890432,12075941390068032,12075941390071316
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,901123,901128,4194304,256,0,0,20,24,206080,0x7f35ead59300,0x7f34bac370c0,524288,2342972,300028836,12075941390119265,12075941390299231,12075941390909788,12075941390934560
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,901123,901128,4194304,256,0,0,28,24,209600,0x7f35ead59a00,0x7f34bac37100,524288,4239022,542724156,12075941390978792,12075941391141467,12075941391469306,12075941391497476
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,901123,901128,4194304,256,0,0,24,24,213120,0x7f35ead59900,0x7f34bac37140,524288,3156831,404335252,12075941391537831,12075941391694265,12075941391874424,12075941391877753
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,901123,901128,4194304,256,0,0,24,24,218176,0x7f35ead59800,0x7f34bac37180,524288,3527636,451606824,12075941391926033,12075941392094584,12075941392551062,12075941392576111
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,901123,901128,4194304,256,0,0,24,24,222208,0x7f35ead59700,0x7f34bac371c0,524288,3123762,399628880,12075941392632325,12075941392793301,12075941392993300,12075941393018132
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,901123,901128,4194304,256,0,0,20,24,223936,0x7f35ead59600,0x7f34bac37200,524288,2318630,296929744,12075941393067013,12075941393225939,12075941393929616,12075941393979940
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,901123,901128,4194304,256,0,0,28,24,227968,0x7f35ead59500,0x7f34bac37240,524288,3723177,476514456,12075941394010046,12075941394187855,12075941394563374,12075941394611393
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,901123,901128,4194304,256,0,0,24,24,232000,0x7f35ead59400,0x7f34bac37280,524288,3027860,387429044,12075941394638474,12075941394813132,12075941395016492,12075941395064505
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,901123,901128,4194304,256,0,0,24,24,237824,0x7f35ead59300,0x7f34bac372c0,524288,3271517,418710948,12075941395091606,12075941395266091,12075941395792809,12075941395840247
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,901123,901128,4194304,256,0,0,24,24,242368,0x7f35ead59a00,0x7f34bac37300,524288,3191215,408404284,12075941395880592,12075941396046407,12075941396271687,12075941396319047
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,901123,901128,4194304,256,0,0,20,24,243584,0x7f35ead59900,0x7f34bac37340,524288,2296875,294173120,12075941396345706,12075941396521286,12075941397320162,12075941397369589
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,901123,901128,4194304,256,0,0,28,24,248128,0x7f35ead59800,0x7f34bac37380,524288,3684102,471608300,12075941397393574,12075941397572641,12075941398015680,12075941398041819
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,901123,901128,4194304,256,0,0,24,24,252672,0x7f35ead59700,0x7f34bac373c0,524288,3239223,414548536,12075941398090679,12075941398266878,12075941398528157,12075941398577294
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,901123,901128,4194304,256,0,0,24,24,259264,0x7f35ead59600,0x7f34bac37400,524288,3722152,476358204,12075941398606488,12075941398775836,12075941399373114,12075941399422695
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,901123,901128,4194304,256,0,0,24,24,264832,0x7f35ead59500,0x7f34bac37440,524288,3279408,419684984,12075941399458271,12075941399628153,12075941399896952,12075941399946949
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,901123,901128,4194304,256,0,0,20,24,266304,0x7f35ead59400,0x7f34bac37480,524288,2305992,295057208,12075941399968670,12075941400159991,12075941401144467,12075941401214194
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,901123,901128,4194304,256,0,0,28,24,271872,0x7f35ead59300,0x7f34bac374c0,524288,3454546,442318960,12075941401242968,12075941401423666,12075941401939344,12075941402013450
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,901123,901128,4194304,256,0,0,24,24,277440,0x7f35ead59a00,0x7f34bac37500,524288,3233069,413736316,12075941402046701,12075941402220302,12075941402492461,12075941402560186
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,901123,901128,4194304,256,0,0,12,24,279936,0x7f35ead59900,0x7f34bac37540,524288,2208117,282588208,12075941402585062,12075941402758060,12075941403496777,12075941403564622
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,901123,901128,4194304,256,0,0,24,24,286528,0x7f35ead59800,0x7f34bac37580,524288,3121979,399732712,12075941403601481,12075941403761896,12075941404078375,12075941404147235
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,901123,901128,4194304,256,0,0,20,24,288000,0x7f35ead59700,0x7f34bac375c0,524288,2276762,291266148,12075941404176329,12075941404353254,12075941405523809,12075941405593203
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,901123,901128,4194304,256,0,0,32,24,294592,0x7f35ead59600,0x7f34bac37600,524288,3470031,444046844,12075941405624671,12075941405805728,12075941406416285,12075941406487715
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,901123,901128,4194304,256,0,0,24,24,301184,0x7f35ead59500,0x7f34bac37640,524288,3216318,411644140,12075941406514144,12075941406689564,12075941407009083,12075941407076649
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,901123,901128,4194304,256,0,0,12,24,304960,0x7f35ead59400,0x7f34bac37680,524288,2210352,282859868,12075941407101796,12075941407292922,12075941408171318,12075941408240462
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,901123,901128,4194304,256,0,0,24,24,313600,0x7f35ead59300,0x7f34bac376c0,524288,3134829,401167460,12075941408285486,12075941408448917,12075941408880595,12075941408948408
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,901123,901128,4194304,256,0,0,20,24,314816,0x7f35ead59a00,0x7f34bac37700,524288,2304562,294814896,12075941408979766,12075941409160594,12075941410708908,12075941410778710
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,901123,901128,4194304,256,0,0,20,24,317568,0x7f35ead59900,0x7f34bac37740,524288,2256011,288722584,12075941410809577,12075941410988267,12075941411783944,12075941411854970
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,901123,901128,4194304,256,0,0,12,24,320320,0x7f35ead59800,0x7f34bac37780,524288,2165744,277297756,12075941411885597,12075941412060903,12075941412476101,12075941412543139
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,901123,901128,4194304,256,0,0,12,24,324096,0x7f35ead59700,0x7f34bac377c0,524288,2268843,290249632,12075941412569468,12075941412745060,12075941413905055,12075941413972776
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,901123,901128,4194304,256,0,0,12,24,328896,0x7f35ead59600,0x7f34bac37800,524288,2183015,279412272,12075941414017429,12075941414179294,12075941414965531,12075941415035310
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,901123,901128,4194304,256,0,0,20,24,330112,0x7f35ead59500,0x7f34bac37840,524288,2607429,333886484,12075941415065987,12075941415242650,12075941418292237,12075941418360760
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,901123,901128,4194304,256,0,0,20,24,332864,0x7f35ead59400,0x7f34bac37880,524288,2305239,295018316,12075941418397589,12075941418560716,12075941420102790,12075941420171956
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,901123,901128,4194304,256,0,0,12,24,335616,0x7f35ead59300,0x7f34bac378c0,524288,2212707,283063448,12075941420205950,12075941420385029,12075941421175426,12075941421243638
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,901123,901128,4194304,256,0,0,12,24,339392,0x7f35ead59a00,0x7f34bac37900,524288,2543016,325743776,12075941421275077,12075941421454465,12075941423737015,12075941423805660
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,901123,901128,4194304,256,0,0,12,24,344192,0x7f35ead59900,0x7f34bac37940,524288,2356147,301682824,12075941423852016,12075941424013654,12075941425549008,12075941425619971
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,901123,901128,4194304,256,0,0,20,24,345408,0x7f35ead59800,0x7f34bac37980,524288,2916112,373306396,12075941425649997,12075941425827567,12075941431883222,12075941431952370
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,901123,901128,4194304,256,0,0,20,24,348160,0x7f35ead59700,0x7f34bac379c0,524288,3345927,428390632,12075941431982816,12075941432162581,12075941435206089,12075941435276628
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,901123,901128,4194304,256,0,0,12,24,350912,0x7f35ead59600,0x7f34bac37a00,524288,2278656,291716872,12075941435308106,12075941435487208,12075941437026241,12075941437095168
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,901123,901128,4194304,256,0,0,12,24,0,0x7f35ead59500,0x7f34bac37a40,524288,2546903,326018512,12075941437125083,12075941437302400,12075941441829102,12075941441898384
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 901123 901128 33554432 256 0 0 8 32 6464 0x0 0x7f34bac04180 1048576 11105144 1422096704 12075941073738305 12075941319842027 12075941320166985 12075941320278178
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 901123 901128 32768 256 0 0 24 24 12480 0x0 0x7f34bac35100 4096 114185 14602220 12075941334761004 12075941335062034 12075941335068594 12075941335073605
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 4 901123 901128 4194304 256 0 0 24 24 12928 0x7f35ead59900 0x7f34bac35140 524288 12413352 1588891204 12075941335135089 12075941335348753 12075941335481872 12075941335485801
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 901123 901128 4194304 256 0 0 36 24 13632 0x7f35ead59800 0x7f34bac35180 524288 13402692 1715511820 12075941335555170 12075941335724591 12075941335975470 12075941336049198
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 8 901123 901128 4194304 256 0 0 28 24 14080 0x7f35ead59700 0x7f34bac351c0 524288 13545990 1733904120 12075941336080867 12075941336269389 12075941336523788 12075941336590725
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 10 901123 901128 4194304 256 0 0 24 24 14528 0x7f35ead59600 0x7f34bac35200 524288 11846202 1516289108 12075941336618556 12075941336803946 12075941336938026 12075941336941276
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 12 901123 901128 4194304 256 0 0 24 24 14976 0x7f35ead59500 0x7f34bac35240 524288 12320378 1576894116 12075941336992060 12075941337166665 12075941337297384 12075941337300834
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 14 901123 901128 4194304 256 0 0 24 24 15424 0x7f35ead59400 0x7f34bac35280 524288 12661711 1620725488 12075941337380412 12075941337551623 12075941337681702 12075941337685018
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 901123 901128 4194304 256 0 0 28 24 16128 0x7f35ead59300 0x7f34bac352c0 524288 13923625 1782206516 12075941337740571 12075941337902021 12075941338156260 12075941338224401
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 18 901123 901128 4194304 256 0 0 28 24 16832 0x7f35ead59a00 0x7f34bac35300 524288 14364290 1838601808 12075941338250970 12075941338430339 12075941338681058 12075941338721194
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 20 901123 901128 4194304 256 0 0 24 24 17536 0x7f35ead59900 0x7f34bac35340 524288 12121934 1551545080 12075941338745309 12075941338934976 12075941339066496 12075941339070293
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 22 901123 901128 4194304 256 0 0 24 24 18240 0x7f35ead59800 0x7f34bac35380 524288 12295928 1573961776 12075941339121768 12075941339296575 12075941339429054 12075941339432706
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 24 901123 901128 4194304 256 0 0 24 24 18944 0x7f35ead59700 0x7f34bac353c0 524288 12754550 1632620856 12075941339495172 12075941339656733 12075941339786332 12075941339789439
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 901123 901128 4194304 256 0 0 28 24 19904 0x7f35ead59600 0x7f34bac35400 524288 13435440 1719754172 12075941339840194 12075941340002171 12075941340257370 12075941340324974
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 28 901123 901128 4194304 256 0 0 28 24 20608 0x7f35ead59500 0x7f34bac35440 524288 13925867 1782592428 12075941340349891 12075941340534169 12075941340786008 12075941340852705
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 30 901123 901128 4194304 256 0 0 24 24 21312 0x7f35ead59400 0x7f34bac35480 524288 12809035 1639523772 12075941340879635 12075941341068086 12075941341198006 12075941341201373
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 32 901123 901128 4194304 256 0 0 24 24 22016 0x7f35ead59300 0x7f34bac354c0 524288 12558038 1607355812 12075941341250775 12075941341416085 12075941341546484 12075941341549961
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 34 901123 901128 4194304 256 0 0 24 24 22720 0x7f35ead59a00 0x7f34bac35500 524288 13017882 1666221916 12075941341610984 12075941341772083 12075941341901202 12075941341904690
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 901123 901128 4194304 256 0 0 28 24 23680 0x7f35ead59900 0x7f34bac35540 524288 14287812 1828820564 12075941341953000 12075941342132081 12075941342385680 12075941342454352
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 38 901123 901128 4194304 256 0 0 28 24 24384 0x7f35ead59800 0x7f34bac35580 524288 13836888 1771164088 12075941342478867 12075941342666159 12075941342920238 12075941342961484
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 40 901123 901128 4194304 256 0 0 24 24 25088 0x7f35ead59700 0x7f34bac355c0 524288 12824198 1641489492 12075941342988815 12075941343179916 12075941343309516 12075941343313208
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 42 901123 901128 4194304 256 0 0 24 24 25792 0x7f35ead59600 0x7f34bac35600 524288 12501384 1600220792 12075941343358482 12075941343545195 12075941343677194 12075941343680671
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 44 901123 901128 4194304 256 0 0 24 24 26496 0x7f35ead59500 0x7f34bac35640 524288 13061932 1671874556 12075941343743187 12075941343905513 12075941344033032 12075941344036502
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 901123 901128 4194304 256 0 0 28 24 27712 0x7f35ead59400 0x7f34bac35680 524288 14229473 1821327376 12075941344086746 12075941344259751 12075941344513510 12075941344580523
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 48 901123 901128 4194304 256 0 0 28 24 28416 0x7f35ead59300 0x7f34bac356c0 524288 14281620 1828091580 12075941344606992 12075941344786789 12075941345039108 12075941345110338
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 50 901123 901128 4194304 256 0 0 24 24 29120 0x7f35ead59a00 0x7f34bac35700 524288 12216801 1563868688 12075941345135484 12075941345317506 12075941345448546 12075941345451953
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 52 901123 901128 4194304 256 0 0 24 24 30080 0x7f35ead59900 0x7f34bac35740 524288 11178209 1430796288 12075941345501034 12075941345663105 12075941345800384 12075941345803857
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 54 901123 901128 4194304 256 0 0 24 24 30784 0x7f35ead59800 0x7f34bac35780 524288 12957083 1658486552 12075941345867355 12075941346034303 12075941346164063 12075941346168144
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 901123 901128 4194304 256 0 0 28 24 32000 0x7f35ead59700 0x7f34bac357c0 524288 14211379 1819014236 12075941346218127 12075941346397021 12075941346652700 12075941346695053
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 58 901123 901128 4194304 256 0 0 28 24 32960 0x7f35ead59600 0x7f34bac35800 524288 14173967 1814269816 12075941346720981 12075941346896379 12075941347143258 12075941347212885
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 60 901123 901128 4194304 256 0 0 24 24 33920 0x7f35ead59500 0x7f34bac35840 524288 11387218 1457420568 12075941347239234 12075941347417817 12075941347553176 12075941347556664
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 62 901123 901128 4194304 256 0 0 24 24 34880 0x7f35ead59400 0x7f34bac35880 524288 13140501 1681986640 12075941347605104 12075941347773015 12075941347902134 12075941347905623
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 64 901123 901128 4194304 256 0 0 24 24 35840 0x7f35ead59300 0x7f34bac358c0 524288 12083419 1546626624 12075941347966917 12075941348131893 12075941348264853 12075941348268838
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 901123 901128 4194304 256 0 0 28 24 37312 0x7f35ead59a00 0x7f34bac35900 524288 13812879 1768101904 12075941348317608 12075941348489812 12075941348745010 12075941348812318
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 68 901123 901128 4194304 256 0 0 28 24 38272 0x7f35ead59900 0x7f34bac35940 524288 13663026 1748803952 12075941348838547 12075941349013329 12075941349271088 12075941349341632
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 70 901123 901128 4194304 256 0 0 24 24 39232 0x7f35ead59800 0x7f34bac35980 524288 11935524 1527683272 12075941349368131 12075941349545967 12075941349678766 12075941349682425
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 72 901123 901128 4194304 256 0 0 24 24 40192 0x7f35ead59700 0x7f34bac359c0 524288 11997706 1535696976 12075941349732328 12075941349901965 12075941350035884 12075941350039729
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 74 901123 901128 4194304 256 0 0 24 24 41152 0x7f35ead59600 0x7f34bac35a00 524288 12513785 1601718828 12075941350101924 12075941350265643 12075941350396683 12075941350400159
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 901123 901128 4194304 256 0 0 28 24 42624 0x7f35ead59500 0x7f34bac35a40 524288 13045409 1669837856 12075941350449450 12075941350612362 12075941350870761 12075941350912601
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 78 901123 901128 4194304 256 0 0 28 24 43584 0x7f35ead59400 0x7f34bac35a80 524288 13718177 1755951836 12075941350937588 12075941351116839 12075941351405798 12075941351474485
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 80 901123 901128 4194304 256 0 0 24 24 44544 0x7f35ead59300 0x7f34bac35ac0 524288 12607261 1613586480 12075941351501345 12075941351677157 12075941351809316 12075941351812824
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 82 901123 901128 4194304 256 0 0 24 24 45760 0x7f35ead59a00 0x7f34bac35b00 524288 12281335 1572113032 12075941351862026 12075941352036355 12075941352168834 12075941352172513
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 84 901123 901128 4194304 256 0 0 24 24 46720 0x7f35ead59900 0x7f34bac35b40 524288 12200786 1561792864 12075941352233295 12075941352393953 12075941352525953 12075941352529586
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 901123 901128 4194304 256 0 0 28 24 48448 0x7f35ead59800 0x7f34bac35b80 524288 14159216 1812328088 12075941352578637 12075941352737152 12075941352992191 12075941353060603
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 88 901123 901128 4194304 256 0 0 28 24 49408 0x7f35ead59700 0x7f34bac35bc0 524288 14265797 1826001812 12075941353084708 12075941353263389 12075941353514268 12075941353582122
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 90 901123 901128 4194304 256 0 0 24 24 50368 0x7f35ead59600 0x7f34bac35c00 524288 11014339 1409820884 12075941353600697 12075941353785147 12075941353921946 12075941353925510
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 92 901123 901128 4194304 256 0 0 24 24 51584 0x7f35ead59500 0x7f34bac35c40 524288 11574756 1481574580 12075941353974652 12075941354144185 12075941354280985 12075941354284748
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 94 901123 901128 4194304 256 0 0 24 24 52544 0x7f35ead59400 0x7f34bac35c80 524288 12231612 1565600244 12075941354347685 12075941354511064 12075941354643063 12075941354646540
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 901123 901128 4194304 256 0 0 28 24 54272 0x7f35ead59300 0x7f34bac35cc0 524288 13401925 1715406044 12075941354698657 12075941354858102 12075941355126261 12075941355195771
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 98 901123 901128 4194304 256 0 0 28 24 55488 0x7f35ead59a00 0x7f34bac35d00 524288 14241911 1822943244 12075941355220868 12075941355403219 12075941355656338 12075941355724794
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 100 901123 901128 4194304 256 0 0 24 24 56704 0x7f35ead59900 0x7f34bac35d40 524288 12877435 1648285668 12075941355750542 12075941355924337 12075941356053616 12075941356057392
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 102 901123 901128 4194304 256 0 0 24 24 58176 0x7f35ead59800 0x7f34bac35d80 524288 11153587 1427696540 12075941356099621 12075941356273615 12075941356407855 12075941356411521
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 104 901123 901128 4194304 256 0 0 24 24 59392 0x7f35ead59700 0x7f34bac35dc0 524288 11663651 1492993708 12075941356473666 12075941356631694 12075941356766413 12075941356769957
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 901123 901128 4194304 256 0 0 28 24 61376 0x7f35ead59600 0x7f34bac35e00 524288 13892877 1778318404 12075941356818317 12075941356984332 12075941357251371 12075941357320410
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 108 901123 901128 4194304 256 0 0 28 24 62592 0x7f35ead59500 0x7f34bac35e40 524288 14207833 1818629776 12075941357344054 12075941357531689 12075941357777768 12075941357845085
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 110 901123 901128 4194304 256 0 0 24 24 63808 0x7f35ead59400 0x7f34bac35e80 524288 12370766 1583575676 12075941357868378 12075941358049927 12075941358180646 12075941358184395
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 112 901123 901128 4194304 256 0 0 24 24 65280 0x7f35ead59300 0x7f34bac35ec0 524288 8879272 1136491052 12075941358232565 12075941358399845 12075941358535045 12075941358538463
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 114 901123 901128 4194304 256 0 0 24 24 66496 0x7f35ead59a00 0x7f34bac35f00 524288 11394146 1458491948 12075941358599867 12075941358757444 12075941358892963 12075941358896459
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 901123 901128 4194304 256 0 0 28 24 68480 0x7f35ead59900 0x7f34bac35f40 524288 12986316 1662175360 12075941358944428 12075941359112642 12075941359375521 12075941359427145
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 118 901123 901128 4194304 256 0 0 28 24 69696 0x7f35ead59800 0x7f34bac35f80 524288 14111739 1806299644 12075941359449336 12075941359626560 12075941359874718 12075941359924229
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 120 901123 901128 4194304 256 0 0 24 24 70912 0x7f35ead59700 0x7f34bac35fc0 524288 11823209 1513326296 12075941359950057 12075941360129757 12075941360263517 12075941360267226
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 122 901123 901128 4194304 256 0 0 24 24 72384 0x7f35ead59600 0x7f34bac36000 524288 7359701 942000352 12075941360316488 12075941360482396 12075941360620635 12075941360624270
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 124 901123 901128 4194304 256 0 0 24 24 73600 0x7f35ead59500 0x7f34bac36040 524288 11046478 1413963584 12075941360683881 12075941360843834 12075941360980953 12075941360984720
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 901123 901128 4194304 256 0 0 28 24 75840 0x7f35ead59400 0x7f34bac36080 524288 11790360 1509148136 12075941361031456 12075941361210072 12075941361476791 12075941361526426
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 128 901123 901128 4194304 256 0 0 28 24 77056 0x7f35ead59300 0x7f34bac360c0 524288 13937127 1783918532 12075941361549469 12075941361726710 12075941361981589 12075941362031685
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 130 901123 901128 4194304 256 0 0 24 24 78272 0x7f35ead59a00 0x7f34bac36100 524288 11716925 1499760940 12075941362057884 12075941362233107 12075941362365747 12075941362369323
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 132 901123 901128 4194304 256 0 0 24 24 80000 0x7f35ead59900 0x7f34bac36140 524288 7304085 935115064 12075941362423103 12075941362584306 12075941362729425 12075941362732838
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 134 901123 901128 4194304 256 0 0 24 24 81216 0x7f35ead59800 0x7f34bac36180 524288 11969279 1531964272 12075941362793601 12075941362953104 12075941363086063 12075941363089822
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 901123 901128 4194304 256 0 0 28 24 83456 0x7f35ead59700 0x7f34bac361c0 524288 14020291 1794568384 12075941363139394 12075941363308942 12075941363574861 12075941363626339
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 138 901123 901128 4194304 256 0 0 28 24 84928 0x7f35ead59600 0x7f34bac36200 524288 14135678 1809359296 12075941363656044 12075941363829100 12075941364077579 12075941364126238
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 140 901123 901128 4194304 256 0 0 24 24 86400 0x7f35ead59500 0x7f34bac36240 524288 12516572 1602146548 12075941364151946 12075941364333418 12075941364464297 12075941364467993
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 142 901123 901128 4194304 256 0 0 24 24 88128 0x7f35ead59400 0x7f34bac36280 524288 5999343 767927368 12075941364517275 12075941364680776 12075941364831015 12075941364834604
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 144 901123 901128 4194304 256 0 0 24 24 89600 0x7f35ead59300 0x7f34bac362c0 524288 13160509 1684571980 12075941364911708 12075941365079334 12075941365207334 12075941365211204
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 901123 901128 4194304 256 0 0 28 24 92096 0x7f35ead59a00 0x7f34bac36300 524288 12382816 1585020452 12075941365258943 12075941365427973 12075941365694051 12075941365741590
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 148 901123 901128 4194304 256 0 0 28 24 93568 0x7f35ead59900 0x7f34bac36340 524288 14119658 1807288388 12075941365765014 12075941365943010 12075941366226529 12075941366276825
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 150 901123 901128 4194304 256 0 0 24 24 95040 0x7f35ead59800 0x7f34bac36380 524288 11111074 1422209636 12075941366300308 12075941366480928 12075941366615327 12075941366619031
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 152 901123 901128 4194304 256 0 0 24 24 96768 0x7f35ead59700 0x7f34bac363c0 524288 4567073 584458584 12075941366667932 12075941366833246 12075941366990685 12075941366994198
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 154 901123 901128 4194304 256 0 0 24 24 98240 0x7f35ead59600 0x7f34bac36400 524288 11072032 1417247668 12075941367055732 12075941367216764 12075941367352764 12075941367356722
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 901123 901128 4194304 256 0 0 28 24 100736 0x7f35ead59500 0x7f34bac36440 524288 10940691 1400432356 12075941367400794 12075941367570043 12075941367836761 12075941367884002
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 158 901123 901128 4194304 256 0 0 28 24 102208 0x7f35ead59400 0x7f34bac36480 524288 14150327 1811202328 12075941367910451 12075941368090680 12075941368344759 12075941368395372
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 160 901123 901128 4194304 256 0 0 24 24 103680 0x7f35ead59300 0x7f34bac364c0 524288 12556595 1607181392 12075941368422262 12075941368597238 12075941368729237 12075941368733029
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 162 901123 901128 4194304 256 0 0 24 24 105664 0x7f35ead59a00 0x7f34bac36500 524288 3619555 463195720 12075941368781099 12075941368953716 12075941369120435 12075941369124347
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 164 901123 901128 4194304 256 0 0 24 24 107136 0x7f35ead59900 0x7f34bac36540 524288 11346463 1452246776 12075941369185841 12075941369344274 12075941369480594 12075941369484175
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 901123 901128 4194304 256 0 0 28 24 109888 0x7f35ead59800 0x7f34bac36580 524288 9861627 1262405588 12075941369533167 12075941369693073 12075941369957071 12075941370011806
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 168 901123 901128 4194304 256 0 0 28 24 111360 0x7f35ead59700 0x7f34bac365c0 524288 13578265 1737987808 12075941370039077 12075941370215630 12075941370470669 12075941370521183
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 170 901123 901128 4194304 256 0 0 24 24 112832 0x7f35ead59600 0x7f34bac36600 524288 10862889 1390332780 12075941370545758 12075941370719628 12075941370856747 12075941370860213
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 172 901123 901128 4194304 256 0 0 24 24 114816 0x7f35ead59500 0x7f34bac36640 524288 3768399 482466372 12075941370908963 12075941371068586 12075941371243625 12075941371247322
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 174 901123 901128 4194304 256 0 0 24 24 116288 0x7f35ead59400 0x7f34bac36680 524288 11125523 1424189248 12075941371310259 12075941371470184 12075941371606024 12075941371609836
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 901123 901128 4194304 256 0 0 28 24 119040 0x7f35ead59300 0x7f34bac366c0 524288 10166911 1301412412 12075941371658025 12075941371823783 12075941372092421 12075941372143728
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 178 901123 901128 4194304 256 0 0 28 24 120768 0x7f35ead59a00 0x7f34bac36700 524288 14193603 1816787272 12075941372162573 12075941372350340 12075941372604739 12075941372652243
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 180 901123 901128 4194304 256 0 0 24 24 122496 0x7f35ead59900 0x7f34bac36740 524288 11340321 1451512340 12075941372678592 12075941372850978 12075941372987297 12075941372990913
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 182 901123 901128 4194304 256 0 0 24 24 124736 0x7f35ead59800 0x7f34bac36780 524288 3504091 448482292 12075941373041597 12075941373209856 12075941373393055 12075941373396667
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 184 901123 901128 4194304 256 0 0 24 24 126464 0x7f35ead59700 0x7f34bac367c0 524288 10317857 1320505200 12075941373457229 12075941373614334 12075941373755614 12075941373759341
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 901123 901128 4194304 256 0 0 20 24 127936 0x7f35ead59600 0x7f34bac36800 524288 4101828 524956188 12075941373808222 12075941373971933 12075941374238011 12075941374285769
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 188 901123 901128 4194304 256 0 0 28 24 129664 0x7f35ead59500 0x7f34bac36840 524288 12508930 1601156888 12075941374312719 12075941374491930 12075941374748889 12075941374769799
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 190 901123 901128 4194304 256 0 0 24 24 131392 0x7f35ead59400 0x7f34bac36880 524288 11711559 1499006932 12075941374817227 12075941374974648 12075941375109687 12075941375113568
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 192 901123 901128 4194304 256 0 0 24 24 133632 0x7f35ead59300 0x7f34bac368c0 524288 3653621 467870008 12075941375153953 12075941375333206 12075941375525525 12075941375575596
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 194 901123 901128 4194304 256 0 0 24 24 135360 0x7f35ead59a00 0x7f34bac36900 524288 10432998 1335562824 12075941375611563 12075941375770644 12075941375909204 12075941375912863
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 901123 901128 4194304 256 0 0 20 24 136832 0x7f35ead59900 0x7f34bac36940 524288 2885035 369285468 12075941375962936 12075941376138162 12075941376423921 12075941376472032
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 198 901123 901128 4194304 256 0 0 28 24 138560 0x7f35ead59800 0x7f34bac36980 524288 13860509 1774178164 12075941376500756 12075941376672400 12075941376929839 12075941376977942
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 200 901123 901128 4194304 256 0 0 24 24 140288 0x7f35ead59700 0x7f34bac369c0 524288 11868610 1518994548 12075941377006776 12075941377180878 12075941377316397 12075941377319938
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 202 901123 901128 4194304 256 0 0 24 24 142784 0x7f35ead59600 0x7f34bac36a00 524288 3277846 419504484 12075941377362196 12075941377531596 12075941377742795 12075941377790993
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 204 901123 901128 4194304 256 0 0 24 24 144768 0x7f35ead59500 0x7f34bac36a40 524288 10948403 1401520460 12075941377828162 12075941377985034 12075941378122473 12075941378126647
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 901123 901128 4194304 256 0 0 20 24 145728 0x7f35ead59400 0x7f34bac36a80 524288 2539792 325196848 12075941378174306 12075941378342152 12075941378650791 12075941378675718
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 208 901123 901128 4194304 256 0 0 28 24 147712 0x7f35ead59300 0x7f34bac36ac0 524288 13250388 1696016800 12075941378718527 12075941378876550 12075941379136708 12075941379165287
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 210 901123 901128 4194304 256 0 0 24 24 149696 0x7f35ead59a00 0x7f34bac36b00 524288 10710142 1370961328 12075941379205863 12075941379363907 12075941379503427 12075941379507223
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 212 901123 901128 4194304 256 0 0 24 24 152192 0x7f35ead59900 0x7f34bac36b40 524288 3120835 399334568 12075941379554831 12075941379718466 12075941379945505 12075941379970494
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 214 901123 901128 4194304 256 0 0 24 24 154176 0x7f35ead59800 0x7f34bac36b80 524288 11216129 1435653884 12075941380032038 12075941380192384 12075941380328223 12075941380332046
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 901123 901128 4194304 256 0 0 20 24 155648 0x7f35ead59700 0x7f34bac36bc0 524288 2493114 319246408 12075941380380325 12075941380553182 12075941380883580 12075941380907776
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 218 901123 901128 4194304 256 0 0 28 24 157632 0x7f35ead59600 0x7f34bac36c00 524288 14094306 1804076396 12075941380954984 12075941381120699 12075941381379418 12075941381407685
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 220 901123 901128 4194304 256 0 0 24 24 159616 0x7f35ead59500 0x7f34bac36c40 524288 10111014 1294254764 12075941381449422 12075941381604697 12075941381746296 12075941381749951
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 222 901123 901128 4194304 256 0 0 24 24 162368 0x7f35ead59400 0x7f34bac36c80 524288 3436745 439760088 12075941381798130 12075941381960855 12075941382206134 12075941382231466
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 224 901123 901128 4194304 256 0 0 24 24 164608 0x7f35ead59300 0x7f34bac36cc0 524288 9693626 1240839820 12075941382288051 12075941382446933 12075941382589332 12075941382593068
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 901123 901128 4194304 256 0 0 20 24 166336 0x7f35ead59a00 0x7f34bac36d00 524288 2360670 302228600 12075941382641207 12075941382808702 12075941383184701 12075941383219211
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 228 901123 901128 4194304 256 0 0 28 24 168576 0x7f35ead59900 0x7f34bac36d40 524288 13997276 1791629420 12075941383254647 12075941383416379 12075941383676858 12075941383700696
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 230 901123 901128 4194304 256 0 0 24 24 170816 0x7f35ead59800 0x7f34bac36d80 524288 9437555 1207951892 12075941383744728 12075941383901337 12075941384046296 12075941384049735
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 232 901123 901128 4194304 256 0 0 24 24 174080 0x7f35ead59700 0x7f34bac36dc0 524288 3461187 443081552 12075941384099047 12075941384270615 12075941384581174 12075941384605047
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 234 901123 901128 4194304 256 0 0 24 24 176576 0x7f35ead59600 0x7f34bac36e00 524288 7941659 1016697620 12075941384662484 12075941384823253 12075941384964372 12075941384967761
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 901123 901128 4194304 256 0 0 20 24 177792 0x7f35ead59500 0x7f34bac36e40 524288 2340566 299456684 12075941385023475 12075941385184052 12075941385608050 12075941385635833
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 238 901123 901128 4194304 256 0 0 28 24 180288 0x7f35ead59400 0x7f34bac36e80 524288 12630735 1616795204 12075941385677660 12075941385834929 12075941386104208 12075941386133127
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 240 901123 901128 4194304 256 0 0 24 24 182784 0x7f35ead59300 0x7f34bac36ec0 524288 7344495 940088460 12075941386176097 12075941386339407 12075941386479566 12075941386482907
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 242 901123 901128 4194304 256 0 0 24 24 186304 0x7f35ead59a00 0x7f34bac36f00 524288 3462569 443232556 12075941386532158 12075941386691085 12075941387007724 12075941387032769
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 244 901123 901128 4194304 256 0 0 24 24 189312 0x7f35ead59900 0x7f34bac36f40 524288 3511513 449361624 12075941387092670 12075941387254763 12075941387406923 12075941387410230
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 901123 901128 4194304 256 0 0 20 24 190784 0x7f35ead59800 0x7f34bac36f80 524288 2304428 295010200 12075941387461906 12075941387619722 12075941388137320 12075941388162919
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 248 901123 901128 4194304 256 0 0 28 24 193792 0x7f35ead59700 0x7f34bac36fc0 524288 7922407 1014020540 12075941388205629 12075941388363239 12075941388660517 12075941388684398
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 250 901123 901128 4194304 256 0 0 24 24 196800 0x7f35ead59600 0x7f34bac37000 524288 3634989 465362128 12075941388732738 12075941388890277 12075941389046276 12075941389049647
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 252 901123 901128 4194304 256 0 0 24 24 201088 0x7f35ead59500 0x7f34bac37040 524288 3264320 417970424 12075941389101774 12075941389261315 12075941389646593 12075941389673356
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 254 901123 901128 4194304 256 0 0 24 24 204608 0x7f35ead59400 0x7f34bac37080 524288 3419795 437808280 12075941389730973 12075941389890432 12075941390068032 12075941390071316
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 901123 901128 4194304 256 0 0 20 24 206080 0x7f35ead59300 0x7f34bac370c0 524288 2342972 300028836 12075941390119265 12075941390299231 12075941390909788 12075941390934560
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 258 901123 901128 4194304 256 0 0 28 24 209600 0x7f35ead59a00 0x7f34bac37100 524288 4239022 542724156 12075941390978792 12075941391141467 12075941391469306 12075941391497476
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 260 901123 901128 4194304 256 0 0 24 24 213120 0x7f35ead59900 0x7f34bac37140 524288 3156831 404335252 12075941391537831 12075941391694265 12075941391874424 12075941391877753
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 262 901123 901128 4194304 256 0 0 24 24 218176 0x7f35ead59800 0x7f34bac37180 524288 3527636 451606824 12075941391926033 12075941392094584 12075941392551062 12075941392576111
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 264 901123 901128 4194304 256 0 0 24 24 222208 0x7f35ead59700 0x7f34bac371c0 524288 3123762 399628880 12075941392632325 12075941392793301 12075941392993300 12075941393018132
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 901123 901128 4194304 256 0 0 20 24 223936 0x7f35ead59600 0x7f34bac37200 524288 2318630 296929744 12075941393067013 12075941393225939 12075941393929616 12075941393979940
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 268 901123 901128 4194304 256 0 0 28 24 227968 0x7f35ead59500 0x7f34bac37240 524288 3723177 476514456 12075941394010046 12075941394187855 12075941394563374 12075941394611393
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 270 901123 901128 4194304 256 0 0 24 24 232000 0x7f35ead59400 0x7f34bac37280 524288 3027860 387429044 12075941394638474 12075941394813132 12075941395016492 12075941395064505
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 272 901123 901128 4194304 256 0 0 24 24 237824 0x7f35ead59300 0x7f34bac372c0 524288 3271517 418710948 12075941395091606 12075941395266091 12075941395792809 12075941395840247
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 274 901123 901128 4194304 256 0 0 24 24 242368 0x7f35ead59a00 0x7f34bac37300 524288 3191215 408404284 12075941395880592 12075941396046407 12075941396271687 12075941396319047
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 901123 901128 4194304 256 0 0 20 24 243584 0x7f35ead59900 0x7f34bac37340 524288 2296875 294173120 12075941396345706 12075941396521286 12075941397320162 12075941397369589
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 278 901123 901128 4194304 256 0 0 28 24 248128 0x7f35ead59800 0x7f34bac37380 524288 3684102 471608300 12075941397393574 12075941397572641 12075941398015680 12075941398041819
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 280 901123 901128 4194304 256 0 0 24 24 252672 0x7f35ead59700 0x7f34bac373c0 524288 3239223 414548536 12075941398090679 12075941398266878 12075941398528157 12075941398577294
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 282 901123 901128 4194304 256 0 0 24 24 259264 0x7f35ead59600 0x7f34bac37400 524288 3722152 476358204 12075941398606488 12075941398775836 12075941399373114 12075941399422695
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 284 901123 901128 4194304 256 0 0 24 24 264832 0x7f35ead59500 0x7f34bac37440 524288 3279408 419684984 12075941399458271 12075941399628153 12075941399896952 12075941399946949
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 901123 901128 4194304 256 0 0 20 24 266304 0x7f35ead59400 0x7f34bac37480 524288 2305992 295057208 12075941399968670 12075941400159991 12075941401144467 12075941401214194
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 288 901123 901128 4194304 256 0 0 28 24 271872 0x7f35ead59300 0x7f34bac374c0 524288 3454546 442318960 12075941401242968 12075941401423666 12075941401939344 12075941402013450
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 290 901123 901128 4194304 256 0 0 24 24 277440 0x7f35ead59a00 0x7f34bac37500 524288 3233069 413736316 12075941402046701 12075941402220302 12075941402492461 12075941402560186
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 292 901123 901128 4194304 256 0 0 12 24 279936 0x7f35ead59900 0x7f34bac37540 524288 2208117 282588208 12075941402585062 12075941402758060 12075941403496777 12075941403564622
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 294 901123 901128 4194304 256 0 0 24 24 286528 0x7f35ead59800 0x7f34bac37580 524288 3121979 399732712 12075941403601481 12075941403761896 12075941404078375 12075941404147235
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 901123 901128 4194304 256 0 0 20 24 288000 0x7f35ead59700 0x7f34bac375c0 524288 2276762 291266148 12075941404176329 12075941404353254 12075941405523809 12075941405593203
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 298 901123 901128 4194304 256 0 0 32 24 294592 0x7f35ead59600 0x7f34bac37600 524288 3470031 444046844 12075941405624671 12075941405805728 12075941406416285 12075941406487715
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 300 901123 901128 4194304 256 0 0 24 24 301184 0x7f35ead59500 0x7f34bac37640 524288 3216318 411644140 12075941406514144 12075941406689564 12075941407009083 12075941407076649
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 302 901123 901128 4194304 256 0 0 12 24 304960 0x7f35ead59400 0x7f34bac37680 524288 2210352 282859868 12075941407101796 12075941407292922 12075941408171318 12075941408240462
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 304 901123 901128 4194304 256 0 0 24 24 313600 0x7f35ead59300 0x7f34bac376c0 524288 3134829 401167460 12075941408285486 12075941408448917 12075941408880595 12075941408948408
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 901123 901128 4194304 256 0 0 20 24 314816 0x7f35ead59a00 0x7f34bac37700 524288 2304562 294814896 12075941408979766 12075941409160594 12075941410708908 12075941410778710
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 308 901123 901128 4194304 256 0 0 20 24 317568 0x7f35ead59900 0x7f34bac37740 524288 2256011 288722584 12075941410809577 12075941410988267 12075941411783944 12075941411854970
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 310 901123 901128 4194304 256 0 0 12 24 320320 0x7f35ead59800 0x7f34bac37780 524288 2165744 277297756 12075941411885597 12075941412060903 12075941412476101 12075941412543139
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 312 901123 901128 4194304 256 0 0 12 24 324096 0x7f35ead59700 0x7f34bac377c0 524288 2268843 290249632 12075941412569468 12075941412745060 12075941413905055 12075941413972776
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 314 901123 901128 4194304 256 0 0 12 24 328896 0x7f35ead59600 0x7f34bac37800 524288 2183015 279412272 12075941414017429 12075941414179294 12075941414965531 12075941415035310
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 901123 901128 4194304 256 0 0 20 24 330112 0x7f35ead59500 0x7f34bac37840 524288 2607429 333886484 12075941415065987 12075941415242650 12075941418292237 12075941418360760
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 318 901123 901128 4194304 256 0 0 20 24 332864 0x7f35ead59400 0x7f34bac37880 524288 2305239 295018316 12075941418397589 12075941418560716 12075941420102790 12075941420171956
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 320 901123 901128 4194304 256 0 0 12 24 335616 0x7f35ead59300 0x7f34bac378c0 524288 2212707 283063448 12075941420205950 12075941420385029 12075941421175426 12075941421243638
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 322 901123 901128 4194304 256 0 0 12 24 339392 0x7f35ead59a00 0x7f34bac37900 524288 2543016 325743776 12075941421275077 12075941421454465 12075941423737015 12075941423805660
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 324 901123 901128 4194304 256 0 0 12 24 344192 0x7f35ead59900 0x7f34bac37940 524288 2356147 301682824 12075941423852016 12075941424013654 12075941425549008 12075941425619971
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 901123 901128 4194304 256 0 0 20 24 345408 0x7f35ead59800 0x7f34bac37980 524288 2916112 373306396 12075941425649997 12075941425827567 12075941431883222 12075941431952370
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 328 901123 901128 4194304 256 0 0 20 24 348160 0x7f35ead59700 0x7f34bac379c0 524288 3345927 428390632 12075941431982816 12075941432162581 12075941435206089 12075941435276628
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 330 901123 901128 4194304 256 0 0 12 24 350912 0x7f35ead59600 0x7f34bac37a00 524288 2278656 291716872 12075941435308106 12075941435487208 12075941437026241 12075941437095168
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 332 901123 901128 4194304 256 0 0 12 24 0 0x7f35ead59500 0x7f34bac37a40 524288 2546903 326018512 12075941437125083 12075941437302400 12075941441829102 12075941441898384
@@ -1,168 +0,0 @@
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",0,0,0,901499,901504,33554432,256,0,0,8,32,6464,0x0,0x7f2728204180,503201,503201,16824,4025616,524288,368372692,3819010,0,1488255924,12075943579867225,12075943823748052,12075943824071410,12075943824181973
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,901499,901504,32768,256,0,0,24,24,12480,0x0,0x7f2728235100,27688,27688,20343,221512,512,1099987,74919,0,4414100,12075943838718799,12075943839049613,12075943839056013,12075943839064461
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,901499,901504,4194304,256,0,0,24,24,12928,0x7f2833ec6900,0x7f2728235140,226925,226925,20091,1815408,65536,115632522,1642353,0,464339996,12075943839137166,12075943839377931,12075943839516651,12075943839520970
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,901499,901504,4194304,256,0,0,36,24,13632,0x7f2833ec6800,0x7f2728235180,397149,397149,32891,3177200,65536,220308418,3008605,0,883049628,12075943839599165,12075943839794729,12075943840047208,12075943840114402
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,901499,901504,4194304,256,0,0,28,24,14080,0x7f2833ec6700,0x7f27282351c0,402172,402172,29842,3217384,65536,324202410,3048181,0,1298625968,12075943840150750,12075943840358566,12075943840614405,12075943840680444
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,901499,901504,4194304,256,0,0,24,24,14528,0x7f2833ec6600,0x7f2728235200,230804,230804,21028,1846440,65536,124342287,1673899,0,499177472,12075943840704950,12075943840909444,12075943841050723,12075943841054950
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,901499,901504,4194304,256,0,0,24,24,14976,0x7f2833ec6500,0x7f2728235240,226013,226013,20266,1808112,65536,124688298,1635192,0,500562804,12075943841114922,12075943841313762,12075943841451681,12075943841455835
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,901499,901504,4194304,256,0,0,24,24,15424,0x7f2833ec6400,0x7f2728235280,223876,223876,22759,1791016,65536,137829862,1623063,0,553138336,12075943841547596,12075943841728479,12075943841865279,12075943841869274
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,901499,901504,4194304,256,0,0,28,24,16128,0x7f2833ec6300,0x7f27282352c0,390141,390141,31390,3121136,65536,345080691,2947808,0,1382139668,12075943841927552,12075943842139517,12075943842387676,12075943842428072
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,901499,901504,4194304,256,0,0,28,24,16832,0x7f2833ec6a00,0x7f2728235300,406676,406676,29441,3253416,65536,293176718,3079704,0,1174520272,12075943842471172,12075943842656955,12075943842915993,12075943842981992
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,901499,901504,4194304,256,0,0,24,24,17536,0x7f2833ec6900,0x7f2728235340,218157,218157,23368,1745264,65536,148264447,1567113,0,594874028,12075943843010835,12075943843217432,12075943843349911,12075943843353913
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,901499,901504,4194304,256,0,0,24,24,18240,0x7f2833ec6800,0x7f2728235380,225045,225045,25377,1800368,65536,136159934,1606526,0,546455392,12075943843414486,12075943843619670,12075943843755509,12075943843759357
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,901499,901504,4194304,256,0,0,24,24,18944,0x7f2833ec6700,0x7f27282353c0,215292,215292,22336,1722344,65536,153792507,1550178,0,616986180,12075943843834526,12075943844024148,12075943844155027,12075943844159300
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,901499,901504,4194304,256,0,0,28,24,19904,0x7f2833ec6600,0x7f2728235400,405349,405349,24433,3242800,65536,298877638,3049929,0,1197327388,12075943844221405,12075943844416626,12075943844674384,12075943844739628
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,901499,901504,4194304,256,0,0,28,24,20608,0x7f2833ec6500,0x7f2728235440,403173,403173,24833,3225392,65536,234678966,3041301,0,940533500,12075943844764244,12075943844968943,12075943845225582,12075943845294069
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,901499,901504,4194304,256,0,0,24,24,21312,0x7f2833ec6400,0x7f2728235480,217876,217876,23354,1743016,65536,153577008,1569729,0,616122488,12075943845319997,12075943845526700,12075943845659659,12075943845663736
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,901499,901504,4194304,256,0,0,24,24,22016,0x7f2833ec6300,0x7f27282354c0,228204,228204,23446,1825640,65536,126081171,1656233,0,506134184,12075943845721663,12075943845915178,12075943846055017,12075943846058880
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,901499,901504,4194304,256,0,0,24,24,22720,0x7f2833ec6a00,0x7f2728235500,211421,211421,24053,1691376,65536,159886425,1513557,0,641366484,12075943846132186,12075943846312616,12075943846440935,12075943846444897
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,901499,901504,4194304,256,0,0,28,24,23680,0x7f2833ec6900,0x7f2728235540,400364,400364,32980,3202920,65536,308697741,3033595,0,1236607880,12075943846503927,12075943846698054,12075943846953413,12075943847020096
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,901499,901504,4194304,256,0,0,28,24,24384,0x7f2833ec6800,0x7f2728235580,407677,407677,33449,3261424,65536,326984453,3089943,0,1309751476,12075943847044361,12075943847251811,12075943847511010,12075943847576320
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,901499,901504,4194304,256,0,0,24,24,25088,0x7f2833ec6700,0x7f27282355c0,217796,217796,23283,1742376,65536,148166363,1566179,0,594485740,12075943847603481,12075943847797089,12075943847929568,12075943847933654
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,901499,901504,4194304,256,0,0,24,24,25792,0x7f2833ec6600,0x7f2728235600,231372,231372,21863,1850984,65536,131827920,1679374,0,529117860,12075943847993666,12075943848196607,12075943848338526,12075943848342554
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,901499,901504,4194304,256,0,0,24,24,26496,0x7f2833ec6500,0x7f2728235640,218605,218605,22430,1748848,65536,152700893,1577012,0,612627772,12075943848414688,12075943848593405,12075943848726524,12075943848730465
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,901499,901504,4194304,256,0,0,28,24,27712,0x7f2833ec6400,0x7f2728235680,400852,400852,30944,3206824,65536,312579158,3030038,0,1252131348,12075943848790326,12075943848979963,12075943849236281,12075943849303610
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,901499,901504,4194304,256,0,0,28,24,28416,0x7f2833ec6300,0x7f27282356c0,414340,414340,28606,3314728,65536,284886986,3137682,0,1141359160,12075943849327525,12075943849528920,12075943849792758,12075943849858822
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,901499,901504,4194304,256,0,0,24,24,29120,0x7f2833ec6a00,0x7f2728235700,210917,210917,20892,1687344,65536,167499738,1504307,0,671818304,12075943849883318,12075943850088597,12075943850216756,12075943850220715
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,901499,901504,4194304,256,0,0,24,24,30080,0x7f2833ec6900,0x7f2728235740,214613,214613,24502,1716912,65536,158531673,1545098,0,635945368,12075943850281828,12075943850467155,12075943850598514,12075943850602264
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,901499,901504,4194304,256,0,0,24,24,30784,0x7f2833ec6800,0x7f2728235780,217124,217124,20214,1737000,65536,150669092,1569196,0,604498008,12075943850675039,12075943850850353,12075943850982992,12075943850987079
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,901499,901504,4194304,256,0,0,28,24,32000,0x7f2833ec6700,0x7f27282357c0,396061,396061,33275,3168496,65536,360068426,2995192,0,1442091360,12075943851045638,12075943851243151,12075943851496430,12075943851561637
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,901499,901504,4194304,256,0,0,28,24,32960,0x7f2833ec6600,0x7f2728235800,410909,410909,30566,3287280,65536,313923883,3114070,0,1257506660,12075943851584880,12075943851784268,12075943852046987,12075943852114935
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,901499,901504,4194304,256,0,0,24,24,33920,0x7f2833ec6500,0x7f2728235840,216124,216124,22402,1729000,65536,155105567,1560767,0,622238804,12075943852139070,12075943852339786,12075943852471625,12075943852475515
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,901499,901504,4194304,256,0,0,24,24,34880,0x7f2833ec6400,0x7f2728235880,219460,219460,22755,1755688,65536,146918137,1589848,0,589507916,12075943852536348,12075943852720264,12075943852855143,12075943852858817
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,901499,901504,4194304,256,0,0,24,24,35840,0x7f2833ec6300,0x7f27282358c0,211493,211493,22558,1691952,65536,161948984,1517107,0,649620108,12075943852930611,12075943853103782,12075943853232741,12075943853236920
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,901499,901504,4194304,256,0,0,28,24,37312,0x7f2833ec6a00,0x7f2728235900,408685,408685,35734,3269488,65536,346705705,3084568,0,1388637852,12075943853297433,12075943853483140,12075943853744258,12075943853809725
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,901499,901504,4194304,256,0,0,28,24,38272,0x7f2833ec6900,0x7f2728235940,400644,400644,33849,3205160,65536,338409532,3029252,0,1355453116,12075943853832808,12075943854039457,12075943854295136,12075943854362642
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,901499,901504,4194304,256,0,0,24,24,39232,0x7f2833ec6800,0x7f2728235980,208708,208708,22996,1669672,65536,162493427,1502139,0,651812708,12075943854388560,12075943854585534,12075943854712893,12075943854717031
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,901499,901504,4194304,256,0,0,24,24,40192,0x7f2833ec6700,0x7f27282359c0,227884,227884,22904,1823080,65536,140967344,1643817,0,565698104,12075943854775900,12075943854962812,12075943855102812,12075943855107116
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,901499,901504,4194304,256,0,0,24,24,41152,0x7f2833ec6600,0x7f2728235a00,220437,220437,25512,1763504,65536,149706928,1565310,0,600643304,12075943855181234,12075943855360570,12075943855493530,12075943855497511
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,901499,901504,4194304,256,0,0,28,24,42624,0x7f2833ec6500,0x7f2728235a40,410452,410452,27625,3283624,65536,259102872,3099115,0,1038230064,12075943855557453,12075943855747448,12075943856010167,12075943856075676
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,901499,901504,4194304,256,0,0,28,24,43584,0x7f2833ec6400,0x7f2728235a80,395212,395212,32765,3161704,65536,352107282,2982085,0,1410247936,12075943856100813,12075943856300885,12075943856552564,12075943856617182
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,901499,901504,4194304,256,0,0,24,24,44544,0x7f2833ec6300,0x7f2728235ac0,209997,209997,23303,1679984,65536,163418660,1503883,0,655499492,12075943856642780,12075943856843603,12075943856971922,12075943856975909
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,901499,901504,4194304,256,0,0,24,24,45760,0x7f2833ec6a00,0x7f2728235b00,215412,215412,26025,1723304,65536,150916263,1536151,0,605488984,12075943857035039,12075943857234321,12075943857366480,12075943857371043
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,901499,901504,4194304,256,0,0,24,24,46720,0x7f2833ec6900,0x7f2728235b40,210277,210277,22582,1682224,65536,157107260,1509208,0,630255412,12075943857443638,12075943857620079,12075943857748718,12075943857752743
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,901499,901504,4194304,256,0,0,28,24,48448,0x7f2833ec6800,0x7f2728235b80,410973,410973,33830,3287792,65536,342461983,3104918,0,1371684004,12075943857811963,12075943858001517,12075943858265195,12075943858334093
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,901499,901504,4194304,256,0,0,28,24,49408,0x7f2833ec6700,0x7f2728235bc0,404461,404461,28249,3235696,65536,271902829,3048487,0,1089431076,12075943858357847,12075943858559114,12075943858817513,12075943858882903
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,901499,901504,4194304,256,0,0,24,24,50368,0x7f2833ec6600,0x7f2728235c00,213621,213621,23098,1708976,65536,162827096,1535831,0,653130032,12075943858906938,12075943859102151,12075943859232871,12075943859236991
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,901499,901504,4194304,256,0,0,24,24,51584,0x7f2833ec6500,0x7f2728235c40,221805,221805,26423,1774448,65536,152891574,1590705,0,613391732,12075943859298085,12075943859480549,12075943859617189,12075943859621225
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,901499,901504,4194304,256,0,0,24,24,52544,0x7f2833ec6400,0x7f2728235c80,211916,211916,23689,1695336,65536,155681469,1522433,0,624558124,12075943859692958,12075943859865987,12075943859995267,12075943859999288
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,901499,901504,4194304,256,0,0,28,24,54272,0x7f2833ec6300,0x7f2728235cc0,417909,417909,29640,3343280,65536,306405604,3158093,0,1227438888,12075943860060291,12075943860254145,12075943860522624,12075943860587932
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,901499,901504,4194304,256,0,0,28,24,55488,0x7f2833ec6a00,0x7f2728235d00,401916,401916,24138,3215336,65536,244534355,3030467,0,979955516,12075943860610724,12075943860807263,12075943861065021,12075943861131903
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,901499,901504,4194304,256,0,0,24,24,56704,0x7f2833ec6900,0x7f2728235d40,213221,213221,25587,1705776,65536,163129865,1529863,0,654371932,12075943861157971,12075943861356060,12075943861486299,12075943861490369
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,901499,901504,4194304,256,0,0,24,24,58176,0x7f2833ec6800,0x7f2728235d80,230332,230332,27777,1842664,65536,158596206,1662577,0,636242524,12075943861549048,12075943861735578,12075943861878137,12075943861882327
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,901499,901504,4194304,256,0,0,24,24,59392,0x7f2833ec6700,0x7f2728235dc0,218940,218940,21881,1751528,65536,152415847,1571945,0,611485308,12075943861953760,12075943862135096,12075943862269335,12075943862273454
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,901499,901504,4194304,256,0,0,28,24,61376,0x7f2833ec6600,0x7f2728235e00,405133,405133,35185,3241072,65536,306801667,3062610,0,1229023048,12075943862332344,12075943862520374,12075943862780693,12075943862846219
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,901499,901504,4194304,256,0,0,28,24,62592,0x7f2833ec6500,0x7f2728235e40,396524,396524,26633,3172200,65536,291477781,2985194,0,1167729616,12075943862869121,12075943863061331,12075943863315410,12075943863380892
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,901499,901504,4194304,256,0,0,24,24,63808,0x7f2833ec6400,0x7f2728235e80,218460,218460,20760,1747688,65536,154802391,1560592,0,621029984,12075943863406239,12075943863607728,12075943863741488,12075943863745650
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,901499,901504,4194304,256,0,0,24,24,65280,0x7f2833ec6300,0x7f2728235ec0,230101,230101,28876,1840816,65536,172741250,1659195,0,692820492,12075943863805081,12075943863991246,12075943864133646,12075943864137989
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,901499,901504,4194304,256,0,0,24,24,66496,0x7f2833ec6a00,0x7f2728235f00,226012,226012,24044,1808104,65536,150477428,1627768,0,603732196,12075943864212187,12075943864389644,12075943864528044,12075943864532072
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,901499,901504,4194304,256,0,0,28,24,68480,0x7f2833ec6900,0x7f2728235f40,410789,410789,32399,3286320,65536,331582611,3102661,0,1328157608,12075943864592905,12075943864779242,12075943865043241,12075943865109906
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,901499,901504,4194304,256,0,0,28,24,69696,0x7f2833ec6800,0x7f2728235f80,405813,405813,31305,3246512,65536,329963958,3069370,0,1321673912,12075943865134080,12075943865333640,12075943865593798,12075943865658806
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,901499,901504,4194304,256,0,0,24,24,70912,0x7f2833ec6700,0x7f2728235fc0,224468,224468,26117,1795752,65536,144023189,1601546,0,577951476,12075943865682500,12075943865877797,12075943866013956,12075943866018474
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,901499,901504,4194304,256,0,0,24,24,72384,0x7f2833ec6600,0x7f2728236000,225781,225781,28371,1806256,65536,153288482,1614394,0,614992692,12075943866083044,12075943866273635,12075943866412834,12075943866416894
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,901499,901504,4194304,256,0,0,24,24,73600,0x7f2833ec6500,0x7f2728236040,222676,222676,22307,1781416,65536,146218989,1612361,0,586749216,12075943866489519,12075943866664033,12075943866800832,12075943866805236
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,901499,901504,4194304,256,0,0,28,24,75840,0x7f2833ec6400,0x7f2728236080,416477,416477,31942,3331824,65536,296766774,3139894,0,1188884104,12075943866864056,12075943867054111,12075943867322269,12075943867388079
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,901499,901504,4194304,256,0,0,28,24,77056,0x7f2833ec6300,0x7f27282360c0,405709,405709,31903,3245680,65536,333756213,3052040,0,1336839644,12075943867411824,12075943867610908,12075943867870427,12075943867935707
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,901499,901504,4194304,256,0,0,24,24,78272,0x7f2833ec6a00,0x7f2728236100,210572,210572,23672,1684584,65536,150395532,1505707,0,603418440,12075943867961455,12075943868163545,12075943868292505,12075943868296598
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,901499,901504,4194304,256,0,0,24,24,80000,0x7f2833ec6900,0x7f2728236140,233373,233373,27366,1866992,65536,173928499,1682626,0,697580548,12075943868357832,12075943868546423,12075943868691063,12075943868695108
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,901499,901504,4194304,256,0,0,24,24,81216,0x7f2833ec6800,0x7f2728236180,212452,212452,20676,1699624,65536,148118715,1517140,0,594301168,12075943868768134,12075943868943541,12075943869073301,12075943869077730
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,901499,901504,4194304,256,0,0,28,24,83456,0x7f2833ec6700,0x7f27282361c0,411837,411837,36462,3294704,65536,344373184,3107311,0,1379332240,12075943869136238,12075943869336179,12075943869601458,12075943869667375
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,901499,901504,4194304,256,0,0,28,24,84928,0x7f2833ec6600,0x7f2728236200,393861,393861,31029,3150896,65536,318696306,2966074,0,1276603260,12075943869689517,12075943869887376,12075943870139855,12075943870210795
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,901499,901504,4194304,256,0,0,24,24,86400,0x7f2833ec6500,0x7f2728236240,224877,224877,26691,1799024,65536,153459018,1607858,0,615712296,12075943870234509,12075943870433294,12075943870571373,12075943870575683
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,901499,901504,4194304,256,0,0,24,24,88128,0x7f2833ec6400,0x7f2728236280,242148,242148,28316,1937192,65536,208237617,1765363,0,834809280,12075943870635324,12075943870820812,12075943870971211,12075943870975426
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,901499,901504,4194304,256,0,0,24,24,89600,0x7f2833ec6300,0x7f27282362c0,228860,228860,22164,1830888,65536,155538452,1656988,0,624017748,12075943871072276,12075943871247050,12075943871388009,12075943871392121
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,901499,901504,4194304,256,0,0,28,24,92096,0x7f2833ec6a00,0x7f2728236300,415140,415140,32795,3321128,65536,340363523,3131702,0,1363270708,12075943871451561,12075943871635688,12075943871903046,12075943871942924
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,901499,901504,4194304,256,0,0,28,24,93568,0x7f2833ec6900,0x7f2728236340,447029,447029,16623,3576240,65536,354130094,2953540,0,1418336800,12075943871978971,12075943872169285,12075943872457123,12075943872525086
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,901499,901504,4194304,256,0,0,24,24,95040,0x7f2833ec6800,0x7f2728236380,228260,228260,23538,1826088,65536,155398449,1650590,0,623439896,12075943872547889,12075943872750562,12075943872890721,12075943872894974
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,901499,901504,4194304,256,0,0,24,24,96768,0x7f2833ec6700,0x7f27282363c0,253956,253956,30997,2031656,65536,221903873,1844049,0,889469280,12075943872953583,12075943873147520,12075943873305599,12075943873310175
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,901499,901504,4194304,256,0,0,24,24,98240,0x7f2833ec6600,0x7f2728236400,220085,220085,24479,1760688,65536,155888715,1584732,0,625380768,12075943873381578,12075943873558878,12075943873694077,12075943873698417
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,901499,901504,4194304,256,0,0,28,24,100736,0x7f2833ec6500,0x7f2728236440,418741,418741,35290,3349936,65536,319802448,3135011,0,1281030504,12075943873757387,12075943873944636,12075943874214874,12075943874282633
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,901499,901504,4194304,256,0,0,28,24,102208,0x7f2833ec6400,0x7f2728236480,401220,401220,34579,3209768,65536,338638139,3026828,0,1356371684,12075943874305485,12075943874503033,12075943874760632,12075943874800104
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,901499,901504,4194304,256,0,0,24,24,103680,0x7f2833ec6300,0x7f27282364c0,223548,223548,24739,1788392,65536,152133926,1600849,0,610429540,12075943874840399,12075943875013430,12075943875150230,12075943875154543
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,901499,901504,4194304,256,0,0,24,24,105664,0x7f2833ec6a00,0x7f2728236500,263996,263996,29853,2111976,65536,229939586,1940084,0,921611244,12075943875214304,12075943875407508,12075943875573108,12075943875577239
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,901499,901504,4194304,256,0,0,24,24,107136,0x7f2833ec6900,0x7f2728236540,224308,224308,22905,1794472,65536,144992619,1613236,0,581811692,12075943875649573,12075943875825586,12075943875963666,12075943875967835
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,901499,901504,4194304,256,0,0,28,24,109888,0x7f2833ec6800,0x7f2728236580,410332,410332,36354,3282664,65536,327590716,3085805,0,1312183464,12075943876029179,12075943876222704,12075943876487503,12075943876554986
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,901499,901504,4194304,256,0,0,28,24,111360,0x7f2833ec6700,0x7f27282365c0,456109,456109,16956,3648880,65536,286095802,3044022,0,1146199820,12075943876577237,12075943876775981,12075943877070060,12075943877136436
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,901499,901504,4194304,256,0,0,24,24,112832,0x7f2833ec6600,0x7f2728236600,224668,224668,26197,1797352,65536,156181823,1613663,0,626586180,12075943877163637,12075943877366378,12075943877504298,12075943877508418
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,901499,901504,4194304,256,0,0,24,24,114816,0x7f2833ec6500,0x7f2728236640,278364,278364,32488,2226920,65536,245365851,2034703,0,983312676,12075943877567808,12075943877763176,12075943877936296,12075943877940230
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,901499,901504,4194304,256,0,0,24,24,116288,0x7f2833ec6400,0x7f2728236680,221484,221484,26031,1771880,65536,143156845,1590458,0,574458676,12075943878021141,12075943878200134,12075943878335814,12075943878339913
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,901499,901504,4194304,256,0,0,28,24,119040,0x7f2833ec6300,0x7f27282366c0,410636,410636,36630,3285096,65536,348434729,3102293,0,1395568104,12075943878398602,12075943878593732,12075943878858531,12075943878924299
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,901499,901504,4194304,256,0,0,28,24,120768,0x7f2833ec6a00,0x7f2728236700,397108,397108,34014,3176872,65536,276051426,2995597,0,1106024508,12075943878947332,12075943879148609,12075943879403648,12075943879472568
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,901499,901504,4194304,256,0,0,24,24,122496,0x7f2833ec6900,0x7f2728236740,227221,227221,24613,1817776,65536,146976532,1643384,0,589790616,12075943879496793,12075943879692127,12075943879832446,12075943879836594
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,901499,901504,4194304,256,0,0,24,24,124736,0x7f2833ec6800,0x7f2728236780,290484,290484,31210,2323880,65536,254755939,2153574,0,1020868484,12075943879896155,12075943880086205,12075943880269884,12075943880274318
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,901499,901504,4194304,256,0,0,24,24,126464,0x7f2833ec6700,0x7f27282367c0,223845,223845,25125,1790768,65536,154060633,1611671,0,618127936,12075943880373903,12075943880548282,12075943880686042,12075943880690431
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,901499,901504,4194304,256,0,0,20,24,127936,0x7f2833ec6600,0x7f2728236800,412652,412652,36816,3301224,65536,379270092,3128163,0,1518901208,12075943880748780,12075943880938680,12075943881206039,12075943881272393
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,901499,901504,4194304,256,0,0,28,24,129664,0x7f2833ec6500,0x7f2728236840,407701,407701,32068,3261616,65536,314779749,3072866,0,1260934060,12075943881295406,12075943881497878,12075943881760116,12075943881799813
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,901499,901504,4194304,256,0,0,24,24,131392,0x7f2833ec6400,0x7f2728236880,214572,214572,25090,1716584,65536,159744311,1542482,0,640819284,12075943881838755,12075943882021555,12075943882153714,12075943882158059
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,901499,901504,4194304,256,0,0,24,24,133632,0x7f2833ec6300,0x7f27282368c0,304365,304365,31912,2434928,65536,261113216,2255399,0,1046303288,12075943882218722,12075943882407153,12075943882599792,12075943882665171
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,901499,901504,4194304,256,0,0,24,24,135360,0x7f2833ec6a00,0x7f2728236900,228509,228509,26506,1828080,65536,144482142,1641593,0,579812268,12075943882699515,12075943882884750,12075943883025390,12075943883029589
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,901499,901504,4194304,256,0,0,20,24,136832,0x7f2833ec6900,0x7f2728236940,436532,436532,40847,3492264,65536,403052411,3312962,0,1614029556,12075943883089480,12075943883278668,12075943883561547,12075943883629674
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,901499,901504,4194304,256,0,0,28,24,138560,0x7f2833ec6800,0x7f2728236980,411988,411988,33958,3295912,65536,303080274,3096147,0,1214148688,12075943883652606,12075943883850826,12075943884116424,12075943884184264
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,901499,901504,4194304,256,0,0,24,24,140288,0x7f2833ec6700,0x7f27282369c0,223508,223508,27820,1788072,65536,156243685,1607493,0,626819828,12075943884207898,12075943884404903,12075943884542502,12075943884546798
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,901499,901504,4194304,256,0,0,24,24,142784,0x7f2833ec6600,0x7f2728236a00,330989,330989,34541,2647920,65536,299483736,2474388,0,1199792436,12075943884606279,12075943884798501,12075943885008740,12075943885074729
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,901499,901504,4194304,256,0,0,24,24,144768,0x7f2833ec6500,0x7f2728236a40,224940,224940,26035,1799528,65536,150407245,1623890,0,603513640,12075943885112329,12075943885300098,12075943885438977,12075943885443154
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,901499,901504,4194304,256,0,0,20,24,145728,0x7f2833ec6400,0x7f2728236a80,518301,518301,16953,4146416,65536,440442120,3611878,0,1763588476,12075943885501262,12075943885687776,12075943886025855,12075943886090627
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,901499,901504,4194304,256,0,0,28,24,147712,0x7f2833ec6300,0x7f2728236ac0,406589,406589,32501,3252720,65536,284984313,3053262,0,1141757164,12075943886116736,12075943886315453,12075943886577532,12075943886617126
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,901499,901504,4194304,256,0,0,24,24,149696,0x7f2833ec6a00,0x7f2728236b00,224020,224020,24227,1792168,65536,152296393,1603190,0,611055404,12075943886652401,12075943886834349,12075943886972109,12075943886979710
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,901499,901504,4194304,256,0,0,24,24,152192,0x7f2833ec6900,0x7f2728236b40,357653,357653,34340,2861232,65536,316619179,2679689,0,1268314772,12075943887035814,12075943887229706,12075943887457386,12075943887522538
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,901499,901504,4194304,256,0,0,24,24,154176,0x7f2833ec6800,0x7f2728236b80,218036,218036,25342,1744296,65536,155759799,1549252,0,624933564,12075943887561441,12075943887741224,12075943887875624,12075943887878931
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,901499,901504,4194304,256,0,0,20,24,155648,0x7f2833ec6700,0x7f2728236bc0,507037,507037,45207,4056304,65536,472327466,3879243,0,1891129128,12075943887937740,12075943888138183,12075943888468741,12075943888534750
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,901499,901504,4194304,256,0,0,28,24,157632,0x7f2833ec6600,0x7f2728236c00,412844,412844,39735,3302760,65536,331374545,3092868,0,1327317820,12075943888559385,12075943888754660,12075943889019299,12075943889085453
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,901499,901504,4194304,256,0,0,24,24,159616,0x7f2833ec6500,0x7f2728236c40,225325,225325,25897,1802608,65536,157228016,1625722,0,630801752,12075943889115599,12075943889309218,12075943889449058,12075943889452545
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,901499,901504,4194304,256,0,0,24,24,162368,0x7f2833ec6400,0x7f2728236c80,383293,383293,37752,3066352,65536,350268568,2888367,0,1402915064,12075943889511926,12075943889697217,12075943889942336,12075943890015271
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,901499,901504,4194304,256,0,0,24,24,164608,0x7f2833ec6300,0x7f2728236cc0,221788,221788,29712,1774312,65536,162796451,1584037,0,653048804,12075943890052851,12075943890239614,12075943890376574,12075943890379969
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,901499,901504,4194304,256,0,0,20,24,166336,0x7f2833ec6a00,0x7f2728236d00,577901,577901,49604,4623216,65536,541965699,4443938,0,2169682216,12075943890434380,12075943890624733,12075943891003291,12075943891069360
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,901499,901504,4194304,256,0,0,28,24,168576,0x7f2833ec6900,0x7f2728236d40,410781,410781,36771,3286256,65536,320059410,3099013,0,1282058064,12075943891092774,12075943891296730,12075943891562009,12075943891627247
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,901499,901504,4194304,256,0,0,24,24,170816,0x7f2833ec6800,0x7f2728236d80,221684,221684,29422,1773480,65536,167911808,1586507,0,673502360,12075943891649819,12075943891848408,12075943891985527,12075943891989029
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,901499,901504,4194304,256,0,0,24,24,174080,0x7f2833ec6700,0x7f2728236dc0,481765,481765,16360,3854128,65536,402120660,3310494,0,1610325888,12075943892049121,12075943892246806,12075943892557525,12075943892624480
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,901499,901504,4194304,256,0,0,24,24,176576,0x7f2833ec6600,0x7f2728236e00,226252,226252,28971,1810024,65536,187168992,1627147,0,750570600,12075943892663192,12075943892842804,12075943892982803,12075943892986463
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,901499,901504,4194304,256,0,0,20,24,177792,0x7f2833ec6500,0x7f2728236e40,647708,647708,53185,5181672,65536,612285671,5003695,0,2450962368,12075943893047306,12075943893234962,12075943893661201,12075943893699678
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,901499,901504,4194304,256,0,0,28,24,180288,0x7f2833ec6400,0x7f2728236e80,411765,411765,34547,3294128,65536,286679662,3074900,0,1148540192,12075943893734593,12075943893912240,12075943894178798,12075943894245453
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,901499,901504,4194304,256,0,0,24,24,182784,0x7f2833ec6300,0x7f2728236ec0,228221,228221,27516,1825776,65536,178126479,1621386,0,714396828,12075943894269778,12075943894474797,12075943894616237,12075943894619648
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,901499,901504,4194304,256,0,0,24,24,186304,0x7f2833ec6a00,0x7f2728236f00,491421,491421,44345,3931376,65536,430227293,3737822,0,1722749648,12075943894679229,12075943894873996,12075943895190954,12075943895257934
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,901499,901504,4194304,256,0,0,24,24,189312,0x7f2833ec6900,0x7f2728236f40,244316,244316,28671,1954536,65536,213711814,1781014,0,856740416,12075943895292949,12075943895481353,12075943895633673,12075943895637019
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,901499,901504,4194304,256,0,0,20,24,190784,0x7f2833ec6800,0x7f2728236f80,788173,788173,62390,6305392,65536,749782705,6127621,0,3000950292,12075943895695658,12075943895882312,12075943896400870,12075943896471460
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,901499,901504,4194304,256,0,0,28,24,193792,0x7f2833ec6700,0x7f2728236fc0,457101,457101,39544,3656816,65536,385027030,3467142,0,1541957124,12075943896494673,12075943896693028,12075943896990627,12075943897033204
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,901499,901504,4194304,256,0,0,24,24,196800,0x7f2833ec6600,0x7f2728237000,247644,247644,28133,1981160,65536,217527304,1811658,0,871998996,12075943897071164,12075943897256386,12075943897411585,12075943897415224
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,901499,901504,4194304,256,0,0,24,24,201088,0x7f2833ec6500,0x7f2728237040,596100,596100,49428,4768808,65536,563494481,4593090,0,2255838524,12075943897473772,12075943897662624,12075943898049343,12075943898115465
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,901499,901504,4194304,256,0,0,24,24,204608,0x7f2833ec6400,0x7f2728237080,279205,279205,30931,2233648,65536,247520846,2054119,0,991955796,12075943898156802,12075943898340862,12075943898516381,12075943898520227
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,901499,901504,4194304,256,0,0,20,24,206080,0x7f2833ec6300,0x7f27282370c0,926909,926909,69719,7415280,65536,888659474,7235930,0,3556458484,12075943898580539,12075943898775420,12075943899386457,12075943899452961
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,901499,901504,4194304,256,0,0,28,24,209600,0x7f2833ec6a00,0x7f2728237100,502676,502676,44360,4021416,65536,464051408,3845778,0,1858051812,12075943899480742,12075943899682616,12075943900011575,12075943900076229
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,901499,901504,4194304,256,0,0,24,24,213120,0x7f2833ec6900,0x7f2728237140,282077,282077,30650,2256624,65536,253157667,2088206,0,1014521132,12075943900106525,12075943900303574,12075943900482293,12075943900485870
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,901499,901504,4194304,256,0,0,24,24,218176,0x7f2833ec6800,0x7f2728237180,732844,732844,16552,5862760,65536,657684595,5423302,0,2632588084,12075943900545261,12075943900729972,12075943901207890,12075943901273744
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,901499,901504,4194304,256,0,0,24,24,222208,0x7f2833ec6700,0x7f27282371c0,315173,315173,33721,2521392,65536,282875447,2338568,0,1133384792,12075943901311314,12075943901494289,12075943901694128,12075943901758746
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,901499,901504,4194304,256,0,0,20,24,223936,0x7f2833ec6600,0x7f2728237200,1068900,1068900,79070,8551208,65536,1029329425,8362164,0,4119138172,12075943901781859,12075943901978127,12075943902683404,12075943902751761
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,901499,901504,4194304,256,0,0,28,24,227968,0x7f2833ec6500,0x7f2728237240,569949,569949,48566,4559600,65536,533035577,4379064,0,2133985064,12075943902775305,12075943902978763,12075943903352841,12075943903416998
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,901499,901504,4194304,256,0,0,24,24,232000,0x7f2833ec6400,0x7f2728237280,321213,321213,35510,2569712,65536,288614411,2376143,0,1156347164,12075943903441974,12075943903640040,12075943903842760,12075943903907479
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,901499,901504,4194304,256,0,0,24,24,237824,0x7f2833ec6300,0x7f27282372c0,803397,803397,61079,6427184,65536,767097144,6256061,0,3070239112,12075943903930161,12075943904131878,12075943904657796,12075943904723375
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,901499,901504,4194304,256,0,0,24,24,242368,0x7f2833ec6a00,0x7f2728237300,350269,350269,35246,2802160,65536,320288092,2631722,0,1283055756,12075943904766055,12075943904939075,12075943905163234,12075943905228424
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,901499,901504,4194304,256,0,0,20,24,243584,0x7f2833ec6900,0x7f2728237340,1208173,1208173,85388,9665392,65536,1168856591,9488625,0,4677246364,12075943905251838,12075943905448353,12075943906247550,12075943906312439
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,901499,901504,4194304,256,0,0,28,24,248128,0x7f2833ec6800,0x7f2728237380,641589,641589,53753,5132720,65536,599989186,4947715,0,2401800904,12075943906343837,12075943906540029,12075943906962267,12075943907028780
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,901499,901504,4194304,256,0,0,24,24,252672,0x7f2833ec6700,0x7f27282373c0,354357,354357,35151,2834864,65536,323990153,2657775,0,1297850156,12075943907056732,12075943907253946,12075943907479865,12075943907544148
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,901499,901504,4194304,256,0,0,24,24,259264,0x7f2833ec6600,0x7f2728237400,911996,911996,68068,7295976,65536,871208740,7119036,0,3486683772,12075943907569144,12075943907767064,12075943908365141,12075943908429413
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,901499,901504,4194304,256,0,0,24,24,264832,0x7f2833ec6500,0x7f2728237440,419020,419020,39735,3352168,65536,387592701,3180819,0,1552261044,12075943908467574,12075943908647540,12075943908916979,12075943908982972
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,901499,901504,4194304,256,0,0,20,24,266304,0x7f2833ec6400,0x7f2728237480,1489389,1489389,101895,11915120,65536,1447774545,11737355,0,5792917820,12075943909014360,12075943909216178,12075943910202094,12075943910271677
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,901499,901504,4194304,256,0,0,28,24,271872,0x7f2833ec6300,0x7f27282374c0,777636,777636,60998,6221096,65536,741479534,6050316,0,2967764160,12075943910299659,12075943910504333,12075943911019051,12075943911089326
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,901499,901504,4194304,256,0,0,24,24,277440,0x7f2833ec6a00,0x7f2728237500,423653,423653,40948,3389232,65536,389392067,3210551,0,1559451436,12075943911109995,12075943911324329,12075943911596648,12075943911662421
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,901499,901504,4194304,256,0,0,12,24,279936,0x7f2833ec6900,0x7f2728237540,1127572,1127572,80511,9020584,65536,1090308266,8845198,0,4363056584,12075943911690874,12075943911882407,12075943912621284,12075943912686915
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,901499,901504,4194304,256,0,0,24,24,286528,0x7f2833ec6800,0x7f2728237580,487333,487333,44057,3898672,65536,454059184,3726019,0,1818126576,12075943912726870,12075943912902883,12075943913218082,12075943913288042
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,901499,901504,4194304,256,0,0,20,24,288000,0x7f2833ec6700,0x7f27282375c0,1770373,1770373,48409,14162992,65536,1725654670,13986123,0,6904437832,12075943913310685,12075943913514081,12075943914686396,12075943914753556
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,901499,901504,4194304,256,0,0,32,24,294592,0x7f2833ec6600,0x7f2728237600,924469,924469,67341,7395760,65536,816289864,7211112,0,3267029600,12075943914779655,12075943914983995,12075943915597272,12075943915663537
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,901499,901504,4194304,256,0,0,24,24,301184,0x7f2833ec6500,0x7f2728237640,495308,495308,45628,3962472,65536,457790922,3769424,0,1833054100,12075943915688033,12075943915894551,12075943916214710,12075943916282307
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,901499,901504,4194304,256,0,0,12,24,304960,0x7f2833ec6400,0x7f2728237680,1337533,1337533,92716,10700272,65536,1298169355,10527781,0,5194500296,12075943916307945,12075943916508148,12075943917386545,12075943917453454
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,901499,901504,4194304,256,0,0,24,24,313600,0x7f2833ec6300,0x7f27282376c0,632485,632485,53508,5059888,65536,595865680,4880183,0,2385368828,12075943917488409,12075943917686544,12075943918098222,12075943918163022
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,901499,901504,4194304,256,0,0,20,24,314816,0x7f2833ec6a00,0x7f2728237700,2333052,2333052,80176,18664424,65536,2284451333,18492786,0,9139626016,12075943918192567,12075943918391821,12075943919941735,12075943920012680
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,901499,901504,4194304,256,0,0,20,24,317568,0x7f2833ec6900,0x7f2728237740,1201797,1201797,84970,9614384,65536,1163473783,9439474,0,4655719656,12075943920042014,12075943920245573,12075943921042690,12075943921109057
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,901499,901504,4194304,256,0,0,12,24,320320,0x7f2833ec6800,0x7f2728237780,642476,642476,51974,5139816,65536,607735386,4956008,0,2432777924,12075943921140035,12075943921335969,12075943921751807,12075943921816102
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,901499,901504,4194304,256,0,0,12,24,324096,0x7f2833ec6700,0x7f27282377c0,1758925,1758925,117967,14071408,65536,1713798204,13899985,0,6857014988,12075943921839455,12075943922043006,12075943923202201,12075943923271396
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,901499,901504,4194304,256,0,0,12,24,328896,0x7f2833ec6600,0x7f2728237800,1198540,1198540,84208,9588328,65536,1160689006,9414373,0,4644583476,12075943923309387,12075943923506040,12075943924290997,12075943924355591
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,901499,901504,4194304,256,0,0,20,24,330112,0x7f2833ec6500,0x7f2728237840,4587684,4587684,285265,36701480,65536,4515247345,36504711,0,18062810704,12075943924387240,12075943924583316,12075943927636104,12075943927703433
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,901499,901504,4194304,256,0,0,20,24,332864,0x7f2833ec6400,0x7f2728237880,2327149,2327149,151993,18617200,65536,2275792467,18433501,0,9104990908,12075943927729181,12075943927932262,12075943929475936,12075943929545606
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,901499,901504,4194304,256,0,0,12,24,335616,0x7f2833ec6300,0x7f27282378c0,1203693,1203693,84505,9629552,65536,1165915769,9457106,0,4665487316,12075943929574250,12075943929777215,12075943930566972,12075943930633348
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,901499,901504,4194304,256,0,0,12,24,339392,0x7f2833ec6a00,0x7f2728237900,3443372,3443372,215948,27546984,65536,3384869872,27374785,0,13541305444,12075943930661029,12075943930862331,12075943933143601,12075943933209065
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,901499,901504,4194304,256,0,0,12,24,344192,0x7f2833ec6900,0x7f2728237940,2324941,2324941,151444,18599536,65536,2273596916,18419075,0,9096213128,12075943933257264,12075943933434960,12075943934970474,12075943935037363
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,901499,901504,4194304,256,0,0,20,24,345408,0x7f2833ec6800,0x7f2728237980,9087885,9087885,545060,72703088,65536,8977205475,72528083,0,35910642280,12075943935063882,12075943935265673,12075943941320048,12075943941387654
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,901499,901504,4194304,256,0,0,20,24,348160,0x7f2833ec6700,0x7f27282379c0,4575388,4575388,283993,36603112,65536,4502950849,36423125,0,18013626812,12075943941415326,12075943941618607,12075943944664355,12075943944732400
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,901499,901504,4194304,256,0,0,12,24,350912,0x7f2833ec6600,0x7f2728237a00,2330092,2330092,151791,18640744,65536,2276956701,18463764,0,9109650960,12075943944758609,12075943944962114,12075943946502108,12075943946572220
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,901499,901504,4194304,256,0,0,12,24,0,0x7f2833ec6500,0x7f2728237a40,6813957,6813957,412941,54511664,65536,6723912460,54328501,0,26897479048,12075943946601384,12075943946801649,12075943951330113,12075943951401184
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 901499 901504 33554432 256 0 0 8 32 6464 0x0 0x7f2728204180 503201 503201 16824 4025616 524288 368372692 3819010 0 1488255924 12075943579867225 12075943823748052 12075943824071410 12075943824181973
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 901499 901504 32768 256 0 0 24 24 12480 0x0 0x7f2728235100 27688 27688 20343 221512 512 1099987 74919 0 4414100 12075943838718799 12075943839049613 12075943839056013 12075943839064461
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 4 901499 901504 4194304 256 0 0 24 24 12928 0x7f2833ec6900 0x7f2728235140 226925 226925 20091 1815408 65536 115632522 1642353 0 464339996 12075943839137166 12075943839377931 12075943839516651 12075943839520970
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 901499 901504 4194304 256 0 0 36 24 13632 0x7f2833ec6800 0x7f2728235180 397149 397149 32891 3177200 65536 220308418 3008605 0 883049628 12075943839599165 12075943839794729 12075943840047208 12075943840114402
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 8 901499 901504 4194304 256 0 0 28 24 14080 0x7f2833ec6700 0x7f27282351c0 402172 402172 29842 3217384 65536 324202410 3048181 0 1298625968 12075943840150750 12075943840358566 12075943840614405 12075943840680444
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 10 901499 901504 4194304 256 0 0 24 24 14528 0x7f2833ec6600 0x7f2728235200 230804 230804 21028 1846440 65536 124342287 1673899 0 499177472 12075943840704950 12075943840909444 12075943841050723 12075943841054950
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 12 901499 901504 4194304 256 0 0 24 24 14976 0x7f2833ec6500 0x7f2728235240 226013 226013 20266 1808112 65536 124688298 1635192 0 500562804 12075943841114922 12075943841313762 12075943841451681 12075943841455835
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 14 901499 901504 4194304 256 0 0 24 24 15424 0x7f2833ec6400 0x7f2728235280 223876 223876 22759 1791016 65536 137829862 1623063 0 553138336 12075943841547596 12075943841728479 12075943841865279 12075943841869274
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 901499 901504 4194304 256 0 0 28 24 16128 0x7f2833ec6300 0x7f27282352c0 390141 390141 31390 3121136 65536 345080691 2947808 0 1382139668 12075943841927552 12075943842139517 12075943842387676 12075943842428072
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 18 901499 901504 4194304 256 0 0 28 24 16832 0x7f2833ec6a00 0x7f2728235300 406676 406676 29441 3253416 65536 293176718 3079704 0 1174520272 12075943842471172 12075943842656955 12075943842915993 12075943842981992
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 20 901499 901504 4194304 256 0 0 24 24 17536 0x7f2833ec6900 0x7f2728235340 218157 218157 23368 1745264 65536 148264447 1567113 0 594874028 12075943843010835 12075943843217432 12075943843349911 12075943843353913
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 22 901499 901504 4194304 256 0 0 24 24 18240 0x7f2833ec6800 0x7f2728235380 225045 225045 25377 1800368 65536 136159934 1606526 0 546455392 12075943843414486 12075943843619670 12075943843755509 12075943843759357
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 24 901499 901504 4194304 256 0 0 24 24 18944 0x7f2833ec6700 0x7f27282353c0 215292 215292 22336 1722344 65536 153792507 1550178 0 616986180 12075943843834526 12075943844024148 12075943844155027 12075943844159300
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 901499 901504 4194304 256 0 0 28 24 19904 0x7f2833ec6600 0x7f2728235400 405349 405349 24433 3242800 65536 298877638 3049929 0 1197327388 12075943844221405 12075943844416626 12075943844674384 12075943844739628
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 28 901499 901504 4194304 256 0 0 28 24 20608 0x7f2833ec6500 0x7f2728235440 403173 403173 24833 3225392 65536 234678966 3041301 0 940533500 12075943844764244 12075943844968943 12075943845225582 12075943845294069
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 30 901499 901504 4194304 256 0 0 24 24 21312 0x7f2833ec6400 0x7f2728235480 217876 217876 23354 1743016 65536 153577008 1569729 0 616122488 12075943845319997 12075943845526700 12075943845659659 12075943845663736
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 32 901499 901504 4194304 256 0 0 24 24 22016 0x7f2833ec6300 0x7f27282354c0 228204 228204 23446 1825640 65536 126081171 1656233 0 506134184 12075943845721663 12075943845915178 12075943846055017 12075943846058880
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 34 901499 901504 4194304 256 0 0 24 24 22720 0x7f2833ec6a00 0x7f2728235500 211421 211421 24053 1691376 65536 159886425 1513557 0 641366484 12075943846132186 12075943846312616 12075943846440935 12075943846444897
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 901499 901504 4194304 256 0 0 28 24 23680 0x7f2833ec6900 0x7f2728235540 400364 400364 32980 3202920 65536 308697741 3033595 0 1236607880 12075943846503927 12075943846698054 12075943846953413 12075943847020096
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 38 901499 901504 4194304 256 0 0 28 24 24384 0x7f2833ec6800 0x7f2728235580 407677 407677 33449 3261424 65536 326984453 3089943 0 1309751476 12075943847044361 12075943847251811 12075943847511010 12075943847576320
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 40 901499 901504 4194304 256 0 0 24 24 25088 0x7f2833ec6700 0x7f27282355c0 217796 217796 23283 1742376 65536 148166363 1566179 0 594485740 12075943847603481 12075943847797089 12075943847929568 12075943847933654
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 42 901499 901504 4194304 256 0 0 24 24 25792 0x7f2833ec6600 0x7f2728235600 231372 231372 21863 1850984 65536 131827920 1679374 0 529117860 12075943847993666 12075943848196607 12075943848338526 12075943848342554
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 44 901499 901504 4194304 256 0 0 24 24 26496 0x7f2833ec6500 0x7f2728235640 218605 218605 22430 1748848 65536 152700893 1577012 0 612627772 12075943848414688 12075943848593405 12075943848726524 12075943848730465
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 901499 901504 4194304 256 0 0 28 24 27712 0x7f2833ec6400 0x7f2728235680 400852 400852 30944 3206824 65536 312579158 3030038 0 1252131348 12075943848790326 12075943848979963 12075943849236281 12075943849303610
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 48 901499 901504 4194304 256 0 0 28 24 28416 0x7f2833ec6300 0x7f27282356c0 414340 414340 28606 3314728 65536 284886986 3137682 0 1141359160 12075943849327525 12075943849528920 12075943849792758 12075943849858822
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 50 901499 901504 4194304 256 0 0 24 24 29120 0x7f2833ec6a00 0x7f2728235700 210917 210917 20892 1687344 65536 167499738 1504307 0 671818304 12075943849883318 12075943850088597 12075943850216756 12075943850220715
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 52 901499 901504 4194304 256 0 0 24 24 30080 0x7f2833ec6900 0x7f2728235740 214613 214613 24502 1716912 65536 158531673 1545098 0 635945368 12075943850281828 12075943850467155 12075943850598514 12075943850602264
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 54 901499 901504 4194304 256 0 0 24 24 30784 0x7f2833ec6800 0x7f2728235780 217124 217124 20214 1737000 65536 150669092 1569196 0 604498008 12075943850675039 12075943850850353 12075943850982992 12075943850987079
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 901499 901504 4194304 256 0 0 28 24 32000 0x7f2833ec6700 0x7f27282357c0 396061 396061 33275 3168496 65536 360068426 2995192 0 1442091360 12075943851045638 12075943851243151 12075943851496430 12075943851561637
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 58 901499 901504 4194304 256 0 0 28 24 32960 0x7f2833ec6600 0x7f2728235800 410909 410909 30566 3287280 65536 313923883 3114070 0 1257506660 12075943851584880 12075943851784268 12075943852046987 12075943852114935
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 60 901499 901504 4194304 256 0 0 24 24 33920 0x7f2833ec6500 0x7f2728235840 216124 216124 22402 1729000 65536 155105567 1560767 0 622238804 12075943852139070 12075943852339786 12075943852471625 12075943852475515
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 62 901499 901504 4194304 256 0 0 24 24 34880 0x7f2833ec6400 0x7f2728235880 219460 219460 22755 1755688 65536 146918137 1589848 0 589507916 12075943852536348 12075943852720264 12075943852855143 12075943852858817
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 64 901499 901504 4194304 256 0 0 24 24 35840 0x7f2833ec6300 0x7f27282358c0 211493 211493 22558 1691952 65536 161948984 1517107 0 649620108 12075943852930611 12075943853103782 12075943853232741 12075943853236920
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 901499 901504 4194304 256 0 0 28 24 37312 0x7f2833ec6a00 0x7f2728235900 408685 408685 35734 3269488 65536 346705705 3084568 0 1388637852 12075943853297433 12075943853483140 12075943853744258 12075943853809725
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 68 901499 901504 4194304 256 0 0 28 24 38272 0x7f2833ec6900 0x7f2728235940 400644 400644 33849 3205160 65536 338409532 3029252 0 1355453116 12075943853832808 12075943854039457 12075943854295136 12075943854362642
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 70 901499 901504 4194304 256 0 0 24 24 39232 0x7f2833ec6800 0x7f2728235980 208708 208708 22996 1669672 65536 162493427 1502139 0 651812708 12075943854388560 12075943854585534 12075943854712893 12075943854717031
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 72 901499 901504 4194304 256 0 0 24 24 40192 0x7f2833ec6700 0x7f27282359c0 227884 227884 22904 1823080 65536 140967344 1643817 0 565698104 12075943854775900 12075943854962812 12075943855102812 12075943855107116
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 74 901499 901504 4194304 256 0 0 24 24 41152 0x7f2833ec6600 0x7f2728235a00 220437 220437 25512 1763504 65536 149706928 1565310 0 600643304 12075943855181234 12075943855360570 12075943855493530 12075943855497511
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 901499 901504 4194304 256 0 0 28 24 42624 0x7f2833ec6500 0x7f2728235a40 410452 410452 27625 3283624 65536 259102872 3099115 0 1038230064 12075943855557453 12075943855747448 12075943856010167 12075943856075676
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 78 901499 901504 4194304 256 0 0 28 24 43584 0x7f2833ec6400 0x7f2728235a80 395212 395212 32765 3161704 65536 352107282 2982085 0 1410247936 12075943856100813 12075943856300885 12075943856552564 12075943856617182
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 80 901499 901504 4194304 256 0 0 24 24 44544 0x7f2833ec6300 0x7f2728235ac0 209997 209997 23303 1679984 65536 163418660 1503883 0 655499492 12075943856642780 12075943856843603 12075943856971922 12075943856975909
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 82 901499 901504 4194304 256 0 0 24 24 45760 0x7f2833ec6a00 0x7f2728235b00 215412 215412 26025 1723304 65536 150916263 1536151 0 605488984 12075943857035039 12075943857234321 12075943857366480 12075943857371043
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 84 901499 901504 4194304 256 0 0 24 24 46720 0x7f2833ec6900 0x7f2728235b40 210277 210277 22582 1682224 65536 157107260 1509208 0 630255412 12075943857443638 12075943857620079 12075943857748718 12075943857752743
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 901499 901504 4194304 256 0 0 28 24 48448 0x7f2833ec6800 0x7f2728235b80 410973 410973 33830 3287792 65536 342461983 3104918 0 1371684004 12075943857811963 12075943858001517 12075943858265195 12075943858334093
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 88 901499 901504 4194304 256 0 0 28 24 49408 0x7f2833ec6700 0x7f2728235bc0 404461 404461 28249 3235696 65536 271902829 3048487 0 1089431076 12075943858357847 12075943858559114 12075943858817513 12075943858882903
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 90 901499 901504 4194304 256 0 0 24 24 50368 0x7f2833ec6600 0x7f2728235c00 213621 213621 23098 1708976 65536 162827096 1535831 0 653130032 12075943858906938 12075943859102151 12075943859232871 12075943859236991
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 92 901499 901504 4194304 256 0 0 24 24 51584 0x7f2833ec6500 0x7f2728235c40 221805 221805 26423 1774448 65536 152891574 1590705 0 613391732 12075943859298085 12075943859480549 12075943859617189 12075943859621225
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 94 901499 901504 4194304 256 0 0 24 24 52544 0x7f2833ec6400 0x7f2728235c80 211916 211916 23689 1695336 65536 155681469 1522433 0 624558124 12075943859692958 12075943859865987 12075943859995267 12075943859999288
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 901499 901504 4194304 256 0 0 28 24 54272 0x7f2833ec6300 0x7f2728235cc0 417909 417909 29640 3343280 65536 306405604 3158093 0 1227438888 12075943860060291 12075943860254145 12075943860522624 12075943860587932
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 98 901499 901504 4194304 256 0 0 28 24 55488 0x7f2833ec6a00 0x7f2728235d00 401916 401916 24138 3215336 65536 244534355 3030467 0 979955516 12075943860610724 12075943860807263 12075943861065021 12075943861131903
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 100 901499 901504 4194304 256 0 0 24 24 56704 0x7f2833ec6900 0x7f2728235d40 213221 213221 25587 1705776 65536 163129865 1529863 0 654371932 12075943861157971 12075943861356060 12075943861486299 12075943861490369
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 102 901499 901504 4194304 256 0 0 24 24 58176 0x7f2833ec6800 0x7f2728235d80 230332 230332 27777 1842664 65536 158596206 1662577 0 636242524 12075943861549048 12075943861735578 12075943861878137 12075943861882327
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 104 901499 901504 4194304 256 0 0 24 24 59392 0x7f2833ec6700 0x7f2728235dc0 218940 218940 21881 1751528 65536 152415847 1571945 0 611485308 12075943861953760 12075943862135096 12075943862269335 12075943862273454
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 901499 901504 4194304 256 0 0 28 24 61376 0x7f2833ec6600 0x7f2728235e00 405133 405133 35185 3241072 65536 306801667 3062610 0 1229023048 12075943862332344 12075943862520374 12075943862780693 12075943862846219
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 108 901499 901504 4194304 256 0 0 28 24 62592 0x7f2833ec6500 0x7f2728235e40 396524 396524 26633 3172200 65536 291477781 2985194 0 1167729616 12075943862869121 12075943863061331 12075943863315410 12075943863380892
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 110 901499 901504 4194304 256 0 0 24 24 63808 0x7f2833ec6400 0x7f2728235e80 218460 218460 20760 1747688 65536 154802391 1560592 0 621029984 12075943863406239 12075943863607728 12075943863741488 12075943863745650
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 112 901499 901504 4194304 256 0 0 24 24 65280 0x7f2833ec6300 0x7f2728235ec0 230101 230101 28876 1840816 65536 172741250 1659195 0 692820492 12075943863805081 12075943863991246 12075943864133646 12075943864137989
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 114 901499 901504 4194304 256 0 0 24 24 66496 0x7f2833ec6a00 0x7f2728235f00 226012 226012 24044 1808104 65536 150477428 1627768 0 603732196 12075943864212187 12075943864389644 12075943864528044 12075943864532072
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 901499 901504 4194304 256 0 0 28 24 68480 0x7f2833ec6900 0x7f2728235f40 410789 410789 32399 3286320 65536 331582611 3102661 0 1328157608 12075943864592905 12075943864779242 12075943865043241 12075943865109906
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 118 901499 901504 4194304 256 0 0 28 24 69696 0x7f2833ec6800 0x7f2728235f80 405813 405813 31305 3246512 65536 329963958 3069370 0 1321673912 12075943865134080 12075943865333640 12075943865593798 12075943865658806
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 120 901499 901504 4194304 256 0 0 24 24 70912 0x7f2833ec6700 0x7f2728235fc0 224468 224468 26117 1795752 65536 144023189 1601546 0 577951476 12075943865682500 12075943865877797 12075943866013956 12075943866018474
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 122 901499 901504 4194304 256 0 0 24 24 72384 0x7f2833ec6600 0x7f2728236000 225781 225781 28371 1806256 65536 153288482 1614394 0 614992692 12075943866083044 12075943866273635 12075943866412834 12075943866416894
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 124 901499 901504 4194304 256 0 0 24 24 73600 0x7f2833ec6500 0x7f2728236040 222676 222676 22307 1781416 65536 146218989 1612361 0 586749216 12075943866489519 12075943866664033 12075943866800832 12075943866805236
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 901499 901504 4194304 256 0 0 28 24 75840 0x7f2833ec6400 0x7f2728236080 416477 416477 31942 3331824 65536 296766774 3139894 0 1188884104 12075943866864056 12075943867054111 12075943867322269 12075943867388079
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 128 901499 901504 4194304 256 0 0 28 24 77056 0x7f2833ec6300 0x7f27282360c0 405709 405709 31903 3245680 65536 333756213 3052040 0 1336839644 12075943867411824 12075943867610908 12075943867870427 12075943867935707
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 130 901499 901504 4194304 256 0 0 24 24 78272 0x7f2833ec6a00 0x7f2728236100 210572 210572 23672 1684584 65536 150395532 1505707 0 603418440 12075943867961455 12075943868163545 12075943868292505 12075943868296598
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 132 901499 901504 4194304 256 0 0 24 24 80000 0x7f2833ec6900 0x7f2728236140 233373 233373 27366 1866992 65536 173928499 1682626 0 697580548 12075943868357832 12075943868546423 12075943868691063 12075943868695108
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 134 901499 901504 4194304 256 0 0 24 24 81216 0x7f2833ec6800 0x7f2728236180 212452 212452 20676 1699624 65536 148118715 1517140 0 594301168 12075943868768134 12075943868943541 12075943869073301 12075943869077730
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 901499 901504 4194304 256 0 0 28 24 83456 0x7f2833ec6700 0x7f27282361c0 411837 411837 36462 3294704 65536 344373184 3107311 0 1379332240 12075943869136238 12075943869336179 12075943869601458 12075943869667375
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 138 901499 901504 4194304 256 0 0 28 24 84928 0x7f2833ec6600 0x7f2728236200 393861 393861 31029 3150896 65536 318696306 2966074 0 1276603260 12075943869689517 12075943869887376 12075943870139855 12075943870210795
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 140 901499 901504 4194304 256 0 0 24 24 86400 0x7f2833ec6500 0x7f2728236240 224877 224877 26691 1799024 65536 153459018 1607858 0 615712296 12075943870234509 12075943870433294 12075943870571373 12075943870575683
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 142 901499 901504 4194304 256 0 0 24 24 88128 0x7f2833ec6400 0x7f2728236280 242148 242148 28316 1937192 65536 208237617 1765363 0 834809280 12075943870635324 12075943870820812 12075943870971211 12075943870975426
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 144 901499 901504 4194304 256 0 0 24 24 89600 0x7f2833ec6300 0x7f27282362c0 228860 228860 22164 1830888 65536 155538452 1656988 0 624017748 12075943871072276 12075943871247050 12075943871388009 12075943871392121
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 901499 901504 4194304 256 0 0 28 24 92096 0x7f2833ec6a00 0x7f2728236300 415140 415140 32795 3321128 65536 340363523 3131702 0 1363270708 12075943871451561 12075943871635688 12075943871903046 12075943871942924
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 148 901499 901504 4194304 256 0 0 28 24 93568 0x7f2833ec6900 0x7f2728236340 447029 447029 16623 3576240 65536 354130094 2953540 0 1418336800 12075943871978971 12075943872169285 12075943872457123 12075943872525086
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 150 901499 901504 4194304 256 0 0 24 24 95040 0x7f2833ec6800 0x7f2728236380 228260 228260 23538 1826088 65536 155398449 1650590 0 623439896 12075943872547889 12075943872750562 12075943872890721 12075943872894974
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 152 901499 901504 4194304 256 0 0 24 24 96768 0x7f2833ec6700 0x7f27282363c0 253956 253956 30997 2031656 65536 221903873 1844049 0 889469280 12075943872953583 12075943873147520 12075943873305599 12075943873310175
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 154 901499 901504 4194304 256 0 0 24 24 98240 0x7f2833ec6600 0x7f2728236400 220085 220085 24479 1760688 65536 155888715 1584732 0 625380768 12075943873381578 12075943873558878 12075943873694077 12075943873698417
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 901499 901504 4194304 256 0 0 28 24 100736 0x7f2833ec6500 0x7f2728236440 418741 418741 35290 3349936 65536 319802448 3135011 0 1281030504 12075943873757387 12075943873944636 12075943874214874 12075943874282633
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 158 901499 901504 4194304 256 0 0 28 24 102208 0x7f2833ec6400 0x7f2728236480 401220 401220 34579 3209768 65536 338638139 3026828 0 1356371684 12075943874305485 12075943874503033 12075943874760632 12075943874800104
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 160 901499 901504 4194304 256 0 0 24 24 103680 0x7f2833ec6300 0x7f27282364c0 223548 223548 24739 1788392 65536 152133926 1600849 0 610429540 12075943874840399 12075943875013430 12075943875150230 12075943875154543
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 162 901499 901504 4194304 256 0 0 24 24 105664 0x7f2833ec6a00 0x7f2728236500 263996 263996 29853 2111976 65536 229939586 1940084 0 921611244 12075943875214304 12075943875407508 12075943875573108 12075943875577239
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 164 901499 901504 4194304 256 0 0 24 24 107136 0x7f2833ec6900 0x7f2728236540 224308 224308 22905 1794472 65536 144992619 1613236 0 581811692 12075943875649573 12075943875825586 12075943875963666 12075943875967835
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 901499 901504 4194304 256 0 0 28 24 109888 0x7f2833ec6800 0x7f2728236580 410332 410332 36354 3282664 65536 327590716 3085805 0 1312183464 12075943876029179 12075943876222704 12075943876487503 12075943876554986
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 168 901499 901504 4194304 256 0 0 28 24 111360 0x7f2833ec6700 0x7f27282365c0 456109 456109 16956 3648880 65536 286095802 3044022 0 1146199820 12075943876577237 12075943876775981 12075943877070060 12075943877136436
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 170 901499 901504 4194304 256 0 0 24 24 112832 0x7f2833ec6600 0x7f2728236600 224668 224668 26197 1797352 65536 156181823 1613663 0 626586180 12075943877163637 12075943877366378 12075943877504298 12075943877508418
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 172 901499 901504 4194304 256 0 0 24 24 114816 0x7f2833ec6500 0x7f2728236640 278364 278364 32488 2226920 65536 245365851 2034703 0 983312676 12075943877567808 12075943877763176 12075943877936296 12075943877940230
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 174 901499 901504 4194304 256 0 0 24 24 116288 0x7f2833ec6400 0x7f2728236680 221484 221484 26031 1771880 65536 143156845 1590458 0 574458676 12075943878021141 12075943878200134 12075943878335814 12075943878339913
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 901499 901504 4194304 256 0 0 28 24 119040 0x7f2833ec6300 0x7f27282366c0 410636 410636 36630 3285096 65536 348434729 3102293 0 1395568104 12075943878398602 12075943878593732 12075943878858531 12075943878924299
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 178 901499 901504 4194304 256 0 0 28 24 120768 0x7f2833ec6a00 0x7f2728236700 397108 397108 34014 3176872 65536 276051426 2995597 0 1106024508 12075943878947332 12075943879148609 12075943879403648 12075943879472568
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 180 901499 901504 4194304 256 0 0 24 24 122496 0x7f2833ec6900 0x7f2728236740 227221 227221 24613 1817776 65536 146976532 1643384 0 589790616 12075943879496793 12075943879692127 12075943879832446 12075943879836594
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 182 901499 901504 4194304 256 0 0 24 24 124736 0x7f2833ec6800 0x7f2728236780 290484 290484 31210 2323880 65536 254755939 2153574 0 1020868484 12075943879896155 12075943880086205 12075943880269884 12075943880274318
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 184 901499 901504 4194304 256 0 0 24 24 126464 0x7f2833ec6700 0x7f27282367c0 223845 223845 25125 1790768 65536 154060633 1611671 0 618127936 12075943880373903 12075943880548282 12075943880686042 12075943880690431
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 901499 901504 4194304 256 0 0 20 24 127936 0x7f2833ec6600 0x7f2728236800 412652 412652 36816 3301224 65536 379270092 3128163 0 1518901208 12075943880748780 12075943880938680 12075943881206039 12075943881272393
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 188 901499 901504 4194304 256 0 0 28 24 129664 0x7f2833ec6500 0x7f2728236840 407701 407701 32068 3261616 65536 314779749 3072866 0 1260934060 12075943881295406 12075943881497878 12075943881760116 12075943881799813
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 190 901499 901504 4194304 256 0 0 24 24 131392 0x7f2833ec6400 0x7f2728236880 214572 214572 25090 1716584 65536 159744311 1542482 0 640819284 12075943881838755 12075943882021555 12075943882153714 12075943882158059
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 192 901499 901504 4194304 256 0 0 24 24 133632 0x7f2833ec6300 0x7f27282368c0 304365 304365 31912 2434928 65536 261113216 2255399 0 1046303288 12075943882218722 12075943882407153 12075943882599792 12075943882665171
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 194 901499 901504 4194304 256 0 0 24 24 135360 0x7f2833ec6a00 0x7f2728236900 228509 228509 26506 1828080 65536 144482142 1641593 0 579812268 12075943882699515 12075943882884750 12075943883025390 12075943883029589
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 901499 901504 4194304 256 0 0 20 24 136832 0x7f2833ec6900 0x7f2728236940 436532 436532 40847 3492264 65536 403052411 3312962 0 1614029556 12075943883089480 12075943883278668 12075943883561547 12075943883629674
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 198 901499 901504 4194304 256 0 0 28 24 138560 0x7f2833ec6800 0x7f2728236980 411988 411988 33958 3295912 65536 303080274 3096147 0 1214148688 12075943883652606 12075943883850826 12075943884116424 12075943884184264
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 200 901499 901504 4194304 256 0 0 24 24 140288 0x7f2833ec6700 0x7f27282369c0 223508 223508 27820 1788072 65536 156243685 1607493 0 626819828 12075943884207898 12075943884404903 12075943884542502 12075943884546798
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 202 901499 901504 4194304 256 0 0 24 24 142784 0x7f2833ec6600 0x7f2728236a00 330989 330989 34541 2647920 65536 299483736 2474388 0 1199792436 12075943884606279 12075943884798501 12075943885008740 12075943885074729
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 204 901499 901504 4194304 256 0 0 24 24 144768 0x7f2833ec6500 0x7f2728236a40 224940 224940 26035 1799528 65536 150407245 1623890 0 603513640 12075943885112329 12075943885300098 12075943885438977 12075943885443154
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 901499 901504 4194304 256 0 0 20 24 145728 0x7f2833ec6400 0x7f2728236a80 518301 518301 16953 4146416 65536 440442120 3611878 0 1763588476 12075943885501262 12075943885687776 12075943886025855 12075943886090627
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 208 901499 901504 4194304 256 0 0 28 24 147712 0x7f2833ec6300 0x7f2728236ac0 406589 406589 32501 3252720 65536 284984313 3053262 0 1141757164 12075943886116736 12075943886315453 12075943886577532 12075943886617126
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 210 901499 901504 4194304 256 0 0 24 24 149696 0x7f2833ec6a00 0x7f2728236b00 224020 224020 24227 1792168 65536 152296393 1603190 0 611055404 12075943886652401 12075943886834349 12075943886972109 12075943886979710
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 212 901499 901504 4194304 256 0 0 24 24 152192 0x7f2833ec6900 0x7f2728236b40 357653 357653 34340 2861232 65536 316619179 2679689 0 1268314772 12075943887035814 12075943887229706 12075943887457386 12075943887522538
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 214 901499 901504 4194304 256 0 0 24 24 154176 0x7f2833ec6800 0x7f2728236b80 218036 218036 25342 1744296 65536 155759799 1549252 0 624933564 12075943887561441 12075943887741224 12075943887875624 12075943887878931
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 901499 901504 4194304 256 0 0 20 24 155648 0x7f2833ec6700 0x7f2728236bc0 507037 507037 45207 4056304 65536 472327466 3879243 0 1891129128 12075943887937740 12075943888138183 12075943888468741 12075943888534750
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 218 901499 901504 4194304 256 0 0 28 24 157632 0x7f2833ec6600 0x7f2728236c00 412844 412844 39735 3302760 65536 331374545 3092868 0 1327317820 12075943888559385 12075943888754660 12075943889019299 12075943889085453
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 220 901499 901504 4194304 256 0 0 24 24 159616 0x7f2833ec6500 0x7f2728236c40 225325 225325 25897 1802608 65536 157228016 1625722 0 630801752 12075943889115599 12075943889309218 12075943889449058 12075943889452545
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 222 901499 901504 4194304 256 0 0 24 24 162368 0x7f2833ec6400 0x7f2728236c80 383293 383293 37752 3066352 65536 350268568 2888367 0 1402915064 12075943889511926 12075943889697217 12075943889942336 12075943890015271
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 224 901499 901504 4194304 256 0 0 24 24 164608 0x7f2833ec6300 0x7f2728236cc0 221788 221788 29712 1774312 65536 162796451 1584037 0 653048804 12075943890052851 12075943890239614 12075943890376574 12075943890379969
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 901499 901504 4194304 256 0 0 20 24 166336 0x7f2833ec6a00 0x7f2728236d00 577901 577901 49604 4623216 65536 541965699 4443938 0 2169682216 12075943890434380 12075943890624733 12075943891003291 12075943891069360
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 228 901499 901504 4194304 256 0 0 28 24 168576 0x7f2833ec6900 0x7f2728236d40 410781 410781 36771 3286256 65536 320059410 3099013 0 1282058064 12075943891092774 12075943891296730 12075943891562009 12075943891627247
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 230 901499 901504 4194304 256 0 0 24 24 170816 0x7f2833ec6800 0x7f2728236d80 221684 221684 29422 1773480 65536 167911808 1586507 0 673502360 12075943891649819 12075943891848408 12075943891985527 12075943891989029
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 232 901499 901504 4194304 256 0 0 24 24 174080 0x7f2833ec6700 0x7f2728236dc0 481765 481765 16360 3854128 65536 402120660 3310494 0 1610325888 12075943892049121 12075943892246806 12075943892557525 12075943892624480
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 234 901499 901504 4194304 256 0 0 24 24 176576 0x7f2833ec6600 0x7f2728236e00 226252 226252 28971 1810024 65536 187168992 1627147 0 750570600 12075943892663192 12075943892842804 12075943892982803 12075943892986463
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 901499 901504 4194304 256 0 0 20 24 177792 0x7f2833ec6500 0x7f2728236e40 647708 647708 53185 5181672 65536 612285671 5003695 0 2450962368 12075943893047306 12075943893234962 12075943893661201 12075943893699678
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 238 901499 901504 4194304 256 0 0 28 24 180288 0x7f2833ec6400 0x7f2728236e80 411765 411765 34547 3294128 65536 286679662 3074900 0 1148540192 12075943893734593 12075943893912240 12075943894178798 12075943894245453
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 240 901499 901504 4194304 256 0 0 24 24 182784 0x7f2833ec6300 0x7f2728236ec0 228221 228221 27516 1825776 65536 178126479 1621386 0 714396828 12075943894269778 12075943894474797 12075943894616237 12075943894619648
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 242 901499 901504 4194304 256 0 0 24 24 186304 0x7f2833ec6a00 0x7f2728236f00 491421 491421 44345 3931376 65536 430227293 3737822 0 1722749648 12075943894679229 12075943894873996 12075943895190954 12075943895257934
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 244 901499 901504 4194304 256 0 0 24 24 189312 0x7f2833ec6900 0x7f2728236f40 244316 244316 28671 1954536 65536 213711814 1781014 0 856740416 12075943895292949 12075943895481353 12075943895633673 12075943895637019
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 901499 901504 4194304 256 0 0 20 24 190784 0x7f2833ec6800 0x7f2728236f80 788173 788173 62390 6305392 65536 749782705 6127621 0 3000950292 12075943895695658 12075943895882312 12075943896400870 12075943896471460
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 248 901499 901504 4194304 256 0 0 28 24 193792 0x7f2833ec6700 0x7f2728236fc0 457101 457101 39544 3656816 65536 385027030 3467142 0 1541957124 12075943896494673 12075943896693028 12075943896990627 12075943897033204
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 250 901499 901504 4194304 256 0 0 24 24 196800 0x7f2833ec6600 0x7f2728237000 247644 247644 28133 1981160 65536 217527304 1811658 0 871998996 12075943897071164 12075943897256386 12075943897411585 12075943897415224
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 252 901499 901504 4194304 256 0 0 24 24 201088 0x7f2833ec6500 0x7f2728237040 596100 596100 49428 4768808 65536 563494481 4593090 0 2255838524 12075943897473772 12075943897662624 12075943898049343 12075943898115465
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 254 901499 901504 4194304 256 0 0 24 24 204608 0x7f2833ec6400 0x7f2728237080 279205 279205 30931 2233648 65536 247520846 2054119 0 991955796 12075943898156802 12075943898340862 12075943898516381 12075943898520227
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 901499 901504 4194304 256 0 0 20 24 206080 0x7f2833ec6300 0x7f27282370c0 926909 926909 69719 7415280 65536 888659474 7235930 0 3556458484 12075943898580539 12075943898775420 12075943899386457 12075943899452961
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 258 901499 901504 4194304 256 0 0 28 24 209600 0x7f2833ec6a00 0x7f2728237100 502676 502676 44360 4021416 65536 464051408 3845778 0 1858051812 12075943899480742 12075943899682616 12075943900011575 12075943900076229
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 260 901499 901504 4194304 256 0 0 24 24 213120 0x7f2833ec6900 0x7f2728237140 282077 282077 30650 2256624 65536 253157667 2088206 0 1014521132 12075943900106525 12075943900303574 12075943900482293 12075943900485870
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 262 901499 901504 4194304 256 0 0 24 24 218176 0x7f2833ec6800 0x7f2728237180 732844 732844 16552 5862760 65536 657684595 5423302 0 2632588084 12075943900545261 12075943900729972 12075943901207890 12075943901273744
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 264 901499 901504 4194304 256 0 0 24 24 222208 0x7f2833ec6700 0x7f27282371c0 315173 315173 33721 2521392 65536 282875447 2338568 0 1133384792 12075943901311314 12075943901494289 12075943901694128 12075943901758746
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 901499 901504 4194304 256 0 0 20 24 223936 0x7f2833ec6600 0x7f2728237200 1068900 1068900 79070 8551208 65536 1029329425 8362164 0 4119138172 12075943901781859 12075943901978127 12075943902683404 12075943902751761
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 268 901499 901504 4194304 256 0 0 28 24 227968 0x7f2833ec6500 0x7f2728237240 569949 569949 48566 4559600 65536 533035577 4379064 0 2133985064 12075943902775305 12075943902978763 12075943903352841 12075943903416998
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 270 901499 901504 4194304 256 0 0 24 24 232000 0x7f2833ec6400 0x7f2728237280 321213 321213 35510 2569712 65536 288614411 2376143 0 1156347164 12075943903441974 12075943903640040 12075943903842760 12075943903907479
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 272 901499 901504 4194304 256 0 0 24 24 237824 0x7f2833ec6300 0x7f27282372c0 803397 803397 61079 6427184 65536 767097144 6256061 0 3070239112 12075943903930161 12075943904131878 12075943904657796 12075943904723375
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 274 901499 901504 4194304 256 0 0 24 24 242368 0x7f2833ec6a00 0x7f2728237300 350269 350269 35246 2802160 65536 320288092 2631722 0 1283055756 12075943904766055 12075943904939075 12075943905163234 12075943905228424
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 901499 901504 4194304 256 0 0 20 24 243584 0x7f2833ec6900 0x7f2728237340 1208173 1208173 85388 9665392 65536 1168856591 9488625 0 4677246364 12075943905251838 12075943905448353 12075943906247550 12075943906312439
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 278 901499 901504 4194304 256 0 0 28 24 248128 0x7f2833ec6800 0x7f2728237380 641589 641589 53753 5132720 65536 599989186 4947715 0 2401800904 12075943906343837 12075943906540029 12075943906962267 12075943907028780
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 280 901499 901504 4194304 256 0 0 24 24 252672 0x7f2833ec6700 0x7f27282373c0 354357 354357 35151 2834864 65536 323990153 2657775 0 1297850156 12075943907056732 12075943907253946 12075943907479865 12075943907544148
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 282 901499 901504 4194304 256 0 0 24 24 259264 0x7f2833ec6600 0x7f2728237400 911996 911996 68068 7295976 65536 871208740 7119036 0 3486683772 12075943907569144 12075943907767064 12075943908365141 12075943908429413
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 284 901499 901504 4194304 256 0 0 24 24 264832 0x7f2833ec6500 0x7f2728237440 419020 419020 39735 3352168 65536 387592701 3180819 0 1552261044 12075943908467574 12075943908647540 12075943908916979 12075943908982972
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 901499 901504 4194304 256 0 0 20 24 266304 0x7f2833ec6400 0x7f2728237480 1489389 1489389 101895 11915120 65536 1447774545 11737355 0 5792917820 12075943909014360 12075943909216178 12075943910202094 12075943910271677
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 288 901499 901504 4194304 256 0 0 28 24 271872 0x7f2833ec6300 0x7f27282374c0 777636 777636 60998 6221096 65536 741479534 6050316 0 2967764160 12075943910299659 12075943910504333 12075943911019051 12075943911089326
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 290 901499 901504 4194304 256 0 0 24 24 277440 0x7f2833ec6a00 0x7f2728237500 423653 423653 40948 3389232 65536 389392067 3210551 0 1559451436 12075943911109995 12075943911324329 12075943911596648 12075943911662421
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 292 901499 901504 4194304 256 0 0 12 24 279936 0x7f2833ec6900 0x7f2728237540 1127572 1127572 80511 9020584 65536 1090308266 8845198 0 4363056584 12075943911690874 12075943911882407 12075943912621284 12075943912686915
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 294 901499 901504 4194304 256 0 0 24 24 286528 0x7f2833ec6800 0x7f2728237580 487333 487333 44057 3898672 65536 454059184 3726019 0 1818126576 12075943912726870 12075943912902883 12075943913218082 12075943913288042
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 901499 901504 4194304 256 0 0 20 24 288000 0x7f2833ec6700 0x7f27282375c0 1770373 1770373 48409 14162992 65536 1725654670 13986123 0 6904437832 12075943913310685 12075943913514081 12075943914686396 12075943914753556
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 298 901499 901504 4194304 256 0 0 32 24 294592 0x7f2833ec6600 0x7f2728237600 924469 924469 67341 7395760 65536 816289864 7211112 0 3267029600 12075943914779655 12075943914983995 12075943915597272 12075943915663537
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 300 901499 901504 4194304 256 0 0 24 24 301184 0x7f2833ec6500 0x7f2728237640 495308 495308 45628 3962472 65536 457790922 3769424 0 1833054100 12075943915688033 12075943915894551 12075943916214710 12075943916282307
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 302 901499 901504 4194304 256 0 0 12 24 304960 0x7f2833ec6400 0x7f2728237680 1337533 1337533 92716 10700272 65536 1298169355 10527781 0 5194500296 12075943916307945 12075943916508148 12075943917386545 12075943917453454
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 304 901499 901504 4194304 256 0 0 24 24 313600 0x7f2833ec6300 0x7f27282376c0 632485 632485 53508 5059888 65536 595865680 4880183 0 2385368828 12075943917488409 12075943917686544 12075943918098222 12075943918163022
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 901499 901504 4194304 256 0 0 20 24 314816 0x7f2833ec6a00 0x7f2728237700 2333052 2333052 80176 18664424 65536 2284451333 18492786 0 9139626016 12075943918192567 12075943918391821 12075943919941735 12075943920012680
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 308 901499 901504 4194304 256 0 0 20 24 317568 0x7f2833ec6900 0x7f2728237740 1201797 1201797 84970 9614384 65536 1163473783 9439474 0 4655719656 12075943920042014 12075943920245573 12075943921042690 12075943921109057
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 310 901499 901504 4194304 256 0 0 12 24 320320 0x7f2833ec6800 0x7f2728237780 642476 642476 51974 5139816 65536 607735386 4956008 0 2432777924 12075943921140035 12075943921335969 12075943921751807 12075943921816102
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 312 901499 901504 4194304 256 0 0 12 24 324096 0x7f2833ec6700 0x7f27282377c0 1758925 1758925 117967 14071408 65536 1713798204 13899985 0 6857014988 12075943921839455 12075943922043006 12075943923202201 12075943923271396
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 314 901499 901504 4194304 256 0 0 12 24 328896 0x7f2833ec6600 0x7f2728237800 1198540 1198540 84208 9588328 65536 1160689006 9414373 0 4644583476 12075943923309387 12075943923506040 12075943924290997 12075943924355591
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 901499 901504 4194304 256 0 0 20 24 330112 0x7f2833ec6500 0x7f2728237840 4587684 4587684 285265 36701480 65536 4515247345 36504711 0 18062810704 12075943924387240 12075943924583316 12075943927636104 12075943927703433
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 318 901499 901504 4194304 256 0 0 20 24 332864 0x7f2833ec6400 0x7f2728237880 2327149 2327149 151993 18617200 65536 2275792467 18433501 0 9104990908 12075943927729181 12075943927932262 12075943929475936 12075943929545606
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 320 901499 901504 4194304 256 0 0 12 24 335616 0x7f2833ec6300 0x7f27282378c0 1203693 1203693 84505 9629552 65536 1165915769 9457106 0 4665487316 12075943929574250 12075943929777215 12075943930566972 12075943930633348
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 322 901499 901504 4194304 256 0 0 12 24 339392 0x7f2833ec6a00 0x7f2728237900 3443372 3443372 215948 27546984 65536 3384869872 27374785 0 13541305444 12075943930661029 12075943930862331 12075943933143601 12075943933209065
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 324 901499 901504 4194304 256 0 0 12 24 344192 0x7f2833ec6900 0x7f2728237940 2324941 2324941 151444 18599536 65536 2273596916 18419075 0 9096213128 12075943933257264 12075943933434960 12075943934970474 12075943935037363
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 901499 901504 4194304 256 0 0 20 24 345408 0x7f2833ec6800 0x7f2728237980 9087885 9087885 545060 72703088 65536 8977205475 72528083 0 35910642280 12075943935063882 12075943935265673 12075943941320048 12075943941387654
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 328 901499 901504 4194304 256 0 0 20 24 348160 0x7f2833ec6700 0x7f27282379c0 4575388 4575388 283993 36603112 65536 4502950849 36423125 0 18013626812 12075943941415326 12075943941618607 12075943944664355 12075943944732400
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 330 901499 901504 4194304 256 0 0 12 24 350912 0x7f2833ec6600 0x7f2728237a00 2330092 2330092 151791 18640744 65536 2276956701 18463764 0 9109650960 12075943944758609 12075943944962114 12075943946502108 12075943946572220
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 332 901499 901504 4194304 256 0 0 12 24 0 0x7f2833ec6500 0x7f2728237a40 6813957 6813957 412941 54511664 65536 6723912460 54328501 0 26897479048 12075943946601384 12075943946801649 12075943951330113 12075943951401184
@@ -1,5 +0,0 @@
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -1,5 +0,0 @@
pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -1,5 +0,0 @@
pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -1,5 +0,0 @@
pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -1,5 +0,0 @@
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:
@@ -1,21 +0,0 @@
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:
@@ -1,168 +0,0 @@
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
@@ -1,11 +0,0 @@
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]",1,6051952.0,6051952.0,6051952.0,9.136726903467284
"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",1,4525565.0,4525565.0,4525565.0,6.832316497039289
"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",1,3050056.0,3050056.0,3050056.0,4.604717405604309
"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",1,3040936.0,3040936.0,3040936.0,4.590948798490501
"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",1,2280142.0,2280142.0,2280142.0,3.4423661580801865
"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",1,1548468.0,1548468.0,1548468.0,2.337746438629748
"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",1,1540788.0,1540788.0,1540788.0,2.326151822112857
"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",1,1539027.0,1539027.0,1539027.0,2.3234932127787107
"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",1,1535188.0,1535188.0,1535188.0,2.317697414235958
"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",1,1170548.0,1170548.0,1170548.0,1.7671946841944255
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 6051952.0 6051952.0 6051952.0 9.136726903467284
3 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 1 4525565.0 4525565.0 4525565.0 6.832316497039289
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 3050056.0 3050056.0 3050056.0 4.604717405604309
5 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 1 3040936.0 3040936.0 3040936.0 4.590948798490501
6 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 1 2280142.0 2280142.0 2280142.0 3.4423661580801865
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 1548468.0 1548468.0 1548468.0 2.337746438629748
8 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 1 1540788.0 1540788.0 1540788.0 2.326151822112857
9 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 1 1539027.0 1539027.0 1539027.0 2.3234932127787107
10 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 1 1535188.0 1535188.0 1535188.0 2.317697414235958
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 1170548.0 1170548.0 1170548.0 1.7671946841944255
@@ -1,9 +0,0 @@
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
@@ -1,16 +0,0 @@
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
@@ -1,9 +0,0 @@
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
@@ -1,6 +0,0 @@
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
@@ -1,26 +0,0 @@
Info
Axes1
vesuvius
AMD EPYC 7542 32-Core Processor
""
4.18.0-240.15.1.el8_3.x86_64
4.2.0-21
Thu Sep 22 11:24:51 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 Axes1
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 11:24:51 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
@@ -1,7 +0,0 @@
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
@@ -1,8 +0,0 @@
Metric,Avg,Min,Max,Unit
IPC (Avg),0.5986214923046881,0.031383920005116944,1.426931439244247,Instr/cycle
IPC (Issue),0.8437266214800547,0.5168914822176773,0.9995913989478523,Instr/cycle
SALU Util,2.1150671644926504,0.029829528903182204,23.367499207053708,Pct
VALU Util,59.58449821812784,0.879971102643875,99.10568498222484,Pct
VALU Active Threads,63.967830830447085,63.7211189327576,64.0,Threads
MFMA Util,,,,Pct
MFMA Instr Cycles,,,,Cycles/instr
1 Metric Avg Min Max Unit
2 IPC (Avg) 0.5986214923046881 0.031383920005116944 1.426931439244247 Instr/cycle
3 IPC (Issue) 0.8437266214800547 0.5168914822176773 0.9995913989478523 Instr/cycle
4 SALU Util 2.1150671644926504 0.029829528903182204 23.367499207053708 Pct
5 VALU Util 59.58449821812784 0.879971102643875 99.10568498222484 Pct
6 VALU Active Threads 63.967830830447085 63.7211189327576 64.0 Threads
7 MFMA Util Pct
8 MFMA Instr Cycles Cycles/instr
@@ -1,7 +0,0 @@
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
@@ -1,5 +0,0 @@
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
@@ -1,12 +0,0 @@
Metric,Avg,Min,Max,Unit
Wave Cycles,33669.99006456386,2852.8163681030273,547920.7350463867,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 33669.99006456386 2852.8163681030273 547920.7350463867 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
@@ -1,3 +0,0 @@
Metric,Value
Bandwidth,30.395110518124188
Cache Hit,99.51029538290115
1 Metric Value
2 Bandwidth 30.395110518124188
3 Cache Hit 99.51029538290115
@@ -1,6 +0,0 @@
L1I Metric,Mean,Min,Max,Unit
Req,162.66467065868264,12.0,3215.0,Req per wave
Hits,162.47084841471232,11.995820999145508,3214.980026245117,Hits per wave
Misses - Non Duplicated,0.001978708598428144,0.00018310546875,0.09375,Misses per wave
Misses - Duplicated,0.3061763169522771,0.0044765472412109375,3.046875,Misses per wave
Cache Hit,99.51029538290115,80.37109375,99.9992581816935,Pct
1 L1I Metric Mean Min Max Unit
2 Req 162.66467065868264 12.0 3215.0 Req per wave
3 Hits 162.47084841471232 11.995820999145508 3214.980026245117 Hits per wave
4 Misses - Non Duplicated 0.001978708598428144 0.00018310546875 0.09375 Misses per wave
5 Misses - Duplicated 0.3061763169522771 0.0044765472412109375 3.046875 Misses per wave
6 Cache Hit 99.51029538290115 80.37109375 99.9992581816935 Pct
@@ -1,3 +0,0 @@
Metric,Value
Bandwidth,0.9292741972263151
Cache Hit,98.02738278211947
1 Metric Value
2 Bandwidth 0.9292741972263151
3 Cache Hit 98.02738278211947
@@ -1,13 +0,0 @@
Metric,Mean,Min,Max,Unit
Req,1.8083832335329342,1.0,8.0,Req per wave
Hits,1.7799113724759952,0.0,7.991537094116211,Req per wave
Misses - Non Duplicated,0.0012866722609468563,0.000274658203125,0.09375,Req per wave
Misses- Duplicated,0.027185188795992,0.008188247680664062,0.90625,Req per wave
Cache Hit,98.02738278211947,0.0,99.89421367645264,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 1.7799113724759952 0.0 7.991537094116211 Req per wave
4 Misses - Non Duplicated 0.0012866722609468563 0.000274658203125 0.09375 Req per wave
5 Misses- Duplicated 0.027185188795992 0.008188247680664062 0.90625 Req per wave
6 Cache Hit 98.02738278211947 0.0 99.89421367645264 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
@@ -1,5 +0,0 @@
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
@@ -1,17 +0,0 @@
Metric,Avg,Min,Max,Unit
TA Busy,59.22986693031751,2.271568815837845,92.90179311960573,Pct
TC2TA Addr Stall,45.12817866618998,0.07635209534391343,80.11882558068874,Pct
TC2TA Data Stall,0.3673194591546588,0.0,61.34234967882802,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 59.22986693031751 2.271568815837845 92.90179311960573 Pct
3 TC2TA Addr Stall 45.12817866618998 0.07635209534391343 80.11882558068874 Pct
4 TC2TA Data Stall 0.3673194591546588 0.0 61.34234967882802 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
@@ -1,8 +0,0 @@
Metric,Avg,Min,Max,Unit
TD Busy,74.82204768566393,15.950966151131805,93.7339824152825,Pct
TC2TD Stall,64.82101116024333,13.310812883562745,89.13016387559573,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 74.82204768566393 15.950966151131805 93.7339824152825 Pct
3 TC2TD Stall 64.82101116024333 13.310812883562745 89.13016387559573 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
@@ -1,5 +0,0 @@
Metric,Value
Buffer Coalescing,69.91017964071857
Cache Util,80.68803649884886
Cache BW,2.43900609920227
Cache Hit,20.508982035928145
1 Metric Value
2 Buffer Coalescing 69.91017964071857
3 Cache Util 80.68803649884886
4 Cache BW 2.43900609920227
5 Cache Hit 20.508982035928145
@@ -1,6 +0,0 @@
Metric,Mean,Min,Max,Unit
Stalled on L2 Data,61.18504314218415,14.197522720550062,85.80516026457597,Pct
Stalled on L2 Req,29.971955383455935,0.004759882018954708,69.8714751617945,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 61.18504314218415 14.197522720550062 85.80516026457597 Pct
3 Stalled on L2 Req 29.971955383455935 0.004759882018954708 69.8714751617945 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
@@ -1,15 +0,0 @@
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,1522.1559764268156,409.6573677062988,2941.1611328125,Cycles
L1-L2 Read Latency,749.5058416673936,352.7480833530426,2091.562255859375,Cycles
L1-L2 Write Latency,333.05051696300507,333.05051696300507,333.05051696300507,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 1522.1559764268156 409.6573677062988 2941.1611328125 Cycles
14 L1-L2 Read Latency 749.5058416673936 352.7480833530426 2091.562255859375 Cycles
15 L1-L2 Write Latency 333.05051696300507 333.05051696300507 333.05051696300507 Cycles
@@ -1,13 +0,0 @@
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
@@ -1,6 +0,0 @@
Metric,Mean,Min,Max,Units
Req,69.94011976047904,32.0,128.0, per wave
Hit Ratio,97.73588980029443,91.943359375,98.99430274963379,Pct
Hits,68.51626276256081,29.421875,126.06752014160156, per wave
Misses (Translation),0.15803281133046407,0.0292816162109375,0.234375, 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 97.73588980029443 91.943359375 98.99430274963379 Pct
4 Hits 68.51626276256081 29.421875 126.06752014160156 per wave
5 Misses (Translation) 0.15803281133046407 0.0292816162109375 0.234375 per wave
6 Misses (Permission) 0.0 0.0 0.0 per wave
@@ -1,5 +0,0 @@
Metric,Value,Unit
L2 Util,87.9003949504065,Pct
Cache Hit,0.3929594115290852,Pct
L2-EA Rd BW,832.6393531628229,Gb/s
L2-EA Wr BW,4.953907222722173,Gb/s
1 Metric Value Unit
2 L2 Util 87.9003949504065 Pct
3 Cache Hit 0.3929594115290852 Pct
4 L2-EA Rd BW 832.6393531628229 Gb/s
5 L2-EA Wr BW 4.953907222722173 Gb/s
@@ -1,16 +0,0 @@
Metric,Avg,Min,Max,Unit
Read BW,2841.0276741438997,1.32666015625,4100.029296875,Bytes per wave
Write BW,3.06591796875,0.0,512.00830078125,Bytes per wave
Read (32B),0.0,0.0,0.0,Req per wave
Read (Uncached 32B),0.06228644548062079,0.01116943359375,0.85546875,Req per wave
Read (64B),44.39105740849843,0.02072906494140625,64.06295776367188,Req per wave
HBM Read,44.391569046203244,0.020128250122070312,64.05244445800781,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),0.04790496826171875,0.0,8.000129699707031,Req per wave
HBM Write,0.047904922576721555,0.0,8.0001220703125,Req per wave
Read Latency,428.04498680959387,240.32872860283072,1196.6595509753404,Cycles
Write Latency,144.29924861218794,144.29924861218794,144.29924861218794,Cycles
Atomic Latency,,,,Cycles
Read Stall,5.293112078599601,0.0,15.655975504916224,Pct
Write Stall,0.008657776867195096,0.0,1.4458487368215809,Pct
1 Metric Avg Min Max Unit
2 Read BW 2841.0276741438997 1.32666015625 4100.029296875 Bytes per wave
3 Write BW 3.06591796875 0.0 512.00830078125 Bytes per wave
4 Read (32B) 0.0 0.0 0.0 Req per wave
5 Read (Uncached 32B) 0.06228644548062079 0.01116943359375 0.85546875 Req per wave
6 Read (64B) 44.39105740849843 0.02072906494140625 64.06295776367188 Req per wave
7 HBM Read 44.391569046203244 0.020128250122070312 64.05244445800781 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) 0.04790496826171875 0.0 8.000129699707031 Req per wave
11 HBM Write 0.047904922576721555 0.0 8.0001220703125 Req per wave
12 Read Latency 428.04498680959387 240.32872860283072 1196.6595509753404 Cycles
13 Write Latency 144.29924861218794 144.29924861218794 144.29924861218794 Cycles
14 Atomic Latency Cycles
15 Read Stall 5.293112078599601 0.0 15.655975504916224 Pct
16 Write Stall 0.008657776867195096 0.0 1.4458487368215809 Pct
@@ -1,19 +0,0 @@
Metric,Avg,Min,Max,Unit
Req,44.51596415399791,16.021024703979492,64.09042358398438,Req per wave
Streaming Req,0.0,0.0,0.0,Req per wave
Read Req,44.421211813738246,0.021190643310546875,64.08859252929688,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,44.43832077665957,8.020217895507812,64.05996704101562,Misses per wave
Cache Hit,0.3929594115290852,0.010077006914541978,49.93941995785291,Pct
Writeback,0.04873490476322745,0.0004730224609375,8.000133514404297, per wave
NC Req,0.0012861240409805389,0.00018310546875,0.09375,Req per wave
UC Req,0.02894719061023461,0.0060577392578125,0.431640625,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),0.047156465267706775,0.0,7.875129699707031, per wave
Writeback (TC Req),0.0007485029940119761,0.0,0.125, per wave
Evict (Normal),42.334398703660796,0.0,62.00164794921875, per wave
Evict (TC Req),0.0,0.0,0.0, per wave
1 Metric Avg Min Max Unit
2 Req 44.51596415399791 16.021024703979492 64.09042358398438 Req per wave
3 Streaming Req 0.0 0.0 0.0 Req per wave
4 Read Req 44.421211813738246 0.021190643310546875 64.08859252929688 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 44.43832077665957 8.020217895507812 64.05996704101562 Misses per wave
10 Cache Hit 0.3929594115290852 0.010077006914541978 49.93941995785291 Pct
11 Writeback 0.04873490476322745 0.0004730224609375 8.000133514404297 per wave
12 NC Req 0.0012861240409805389 0.00018310546875 0.09375 Req per wave
13 UC Req 0.02894719061023461 0.0060577392578125 0.431640625 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) 0.047156465267706775 0.0 7.875129699707031 per wave
17 Writeback (TC Req) 0.0007485029940119761 0.0 0.125 per wave
18 Evict (Normal) 42.334398703660796 0.0 62.00164794921875 per wave
19 Evict (TC Req) 0.0 0.0 0.0 per wave
@@ -1,8 +0,0 @@
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,6.903438088422764,0.0,29.488800048828125,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,0.0025322851306664017,0.0,0.42289161682128906,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 6.903438088422764 0.0 29.488800048828125 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 0.0025322851306664017 0.0 0.42289161682128906 Req per wave
8 Write - Credit Starvation 0.0 0.0 0.0 Req per wave
@@ -1,17 +0,0 @@
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
0,0.35970175952956085,1.3912882662104988,1.388294254234451,0.0029940119760479044,0.0,1.3979211795829727,0.0014970516730211452,0.0,546.4228688557511,133.06601513625682,,0.0,0.0,0.6873966605363492,0.0,0.0,1.1718201780033683e-05,0.0
1,0.3655633741152853,1.389973748943763,1.386979736967715,0.0029940119760479044,0.0,1.386243214864217,0.0014970516730211452,0.0,473.25910710618524,130.77969269736641,,0.0,0.0,0.4018274181617234,0.0,0.0,1.1090033068628369e-05,0.0
2,0.3568017238180907,1.389967136040419,1.3869731240643712,0.0029940119760479044,0.0,1.3862698606388297,0.0014970516730211452,0.0,409.79318132418786,130.2371601208459,,0.0,0.0,0.12885736705300338,0.0,0.0,1.3808290401618638e-05,0.0
3,0.3573898662800179,1.3909310323749473,1.3879370203988994,0.0029940119760479044,0.0,1.3862431691792196,0.0014970059880239522,0.0,418.56256567089747,132.2131805419922,,0.0,0.0,0.15931537194166354,0.0,0.0,2.400746602498129e-05,0.0
4,0.35659037293283263,1.3899759075598803,1.3869818955838322,0.0029940119760479044,0.0,1.3875094202464213,0.0014970059880239522,0.0,435.008454128592,134.19815826416016,,0.0,0.0,0.2770758531764596,0.0,0.0,1.2140788004069984e-05,0.0
5,0.36279067181399044,1.3899759075598803,1.3869818955838322,0.0029940119760479044,0.0,1.386243294812962,0.0014970059880239522,0.0,443.01021580005806,132.48015594482422,,0.0,0.0,0.20645708095527696,0.0,0.0,1.1101454317926647e-05,0.0
6,0.3589398273883731,1.3899715218001496,1.3869775098241017,0.0029940119760479044,0.0,1.386243717399186,0.0014970059880239522,0.0,434.83863447651987,135.20436096191406,,0.0,0.0,0.1757095245544068,0.0,0.0,9.057050693534805e-06,0.0
7,0.3602145621489667,1.3899759075598803,1.3869818955838322,0.0029940119760479044,0.0,1.3875556191998328,0.0014970516730211452,0.0,440.314044255467,142.59915621471512,,0.0,0.0,0.18689156720738212,0.0,0.0,2.103794120742889e-05,0.0
8,0.35671851502637353,1.3928621486275496,1.3898681366515018,0.0029940119760479044,0.0,1.386243260549214,0.0014970516730211452,0.0,421.50850347449835,132.51500656107908,,0.0,0.0,0.12503335004795096,0.0,0.0,2.0649618731287425e-05,0.0
9,0.3604368304672359,1.3899715218001496,1.3869775098241017,0.0029940119760479044,0.0,1.3862431691792196,0.0014970059880239522,0.0,424.2068210797029,133.26403045654297,,0.0,0.0,0.14083551646706588,0.0,0.0,2.0878043717252995e-05,0.0
10,0.3565881786288848,1.3899452072417664,1.3869511952657185,0.0029940119760479044,0.0,1.3862694037888579,0.0014970516730211452,0.0,419.59836629853027,129.42418139094877,,0.0,0.0,0.17583908720644648,0.0,0.0,8.360354486339821e-06,0.0
11,0.3604390230545021,1.389967136040419,1.3869731240643712,0.0029940119760479044,0.0,1.3862430778092254,0.0014970059880239522,0.0,422.7740191355286,233.24433135986328,,0.0,0.0,0.19158889861877806,0.0,0.0,0.0005727185460621725,0.0
12,0.35958609816860904,1.3899890648390718,1.386995052863024,0.0029940119760479044,0.0,1.3862435346591973,0.0014970059880239522,0.0,428.75975530691034,134.54219818115234,,0.0,0.0,0.15044270589680014,0.0,0.0,1.4059557886180763e-05,0.0
13,0.3641235025867237,1.3899988528497205,1.3870048408736726,0.0029940119760479044,0.0,1.3862431691792196,0.0014970973580183383,0.0,436.3110439641028,132.57274183704607,,0.0,0.0,0.13464346331750562,0.0,0.0,1.0222018121959206e-05,0.0
14,0.6077359212903574,1.392235042092329,1.3892410301162812,0.0029940119760479044,0.0,1.3862897678763566,0.0014970059880239522,0.0,428.37841558520535,136.21092224121094,,0.0,0.0,0.12912069537682447,0.0,0.0,8.246141993357036e-06,0.0
15,0.35661593485906184,1.4028957732423337,1.3999017612662858,0.0029940119760479044,0.0,1.3862430778092254,0.0014970059880239522,0.0,443.8206779956455,141.3322525024414,,0.0,0.0,0.16600657937055577,0.0,0.0,1.8456738866017964e-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 0.35970175952956085 1.3912882662104988 1.388294254234451 0.0029940119760479044 0.0 1.3979211795829727 0.0014970516730211452 0.0 546.4228688557511 133.06601513625682 0.0 0.0 0.6873966605363492 0.0 0.0 1.1718201780033683e-05 0.0
3 1 0.3655633741152853 1.389973748943763 1.386979736967715 0.0029940119760479044 0.0 1.386243214864217 0.0014970516730211452 0.0 473.25910710618524 130.77969269736641 0.0 0.0 0.4018274181617234 0.0 0.0 1.1090033068628369e-05 0.0
4 2 0.3568017238180907 1.389967136040419 1.3869731240643712 0.0029940119760479044 0.0 1.3862698606388297 0.0014970516730211452 0.0 409.79318132418786 130.2371601208459 0.0 0.0 0.12885736705300338 0.0 0.0 1.3808290401618638e-05 0.0
5 3 0.3573898662800179 1.3909310323749473 1.3879370203988994 0.0029940119760479044 0.0 1.3862431691792196 0.0014970059880239522 0.0 418.56256567089747 132.2131805419922 0.0 0.0 0.15931537194166354 0.0 0.0 2.400746602498129e-05 0.0
6 4 0.35659037293283263 1.3899759075598803 1.3869818955838322 0.0029940119760479044 0.0 1.3875094202464213 0.0014970059880239522 0.0 435.008454128592 134.19815826416016 0.0 0.0 0.2770758531764596 0.0 0.0 1.2140788004069984e-05 0.0
7 5 0.36279067181399044 1.3899759075598803 1.3869818955838322 0.0029940119760479044 0.0 1.386243294812962 0.0014970059880239522 0.0 443.01021580005806 132.48015594482422 0.0 0.0 0.20645708095527696 0.0 0.0 1.1101454317926647e-05 0.0
8 6 0.3589398273883731 1.3899715218001496 1.3869775098241017 0.0029940119760479044 0.0 1.386243717399186 0.0014970059880239522 0.0 434.83863447651987 135.20436096191406 0.0 0.0 0.1757095245544068 0.0 0.0 9.057050693534805e-06 0.0
9 7 0.3602145621489667 1.3899759075598803 1.3869818955838322 0.0029940119760479044 0.0 1.3875556191998328 0.0014970516730211452 0.0 440.314044255467 142.59915621471512 0.0 0.0 0.18689156720738212 0.0 0.0 2.103794120742889e-05 0.0
10 8 0.35671851502637353 1.3928621486275496 1.3898681366515018 0.0029940119760479044 0.0 1.386243260549214 0.0014970516730211452 0.0 421.50850347449835 132.51500656107908 0.0 0.0 0.12503335004795096 0.0 0.0 2.0649618731287425e-05 0.0
11 9 0.3604368304672359 1.3899715218001496 1.3869775098241017 0.0029940119760479044 0.0 1.3862431691792196 0.0014970059880239522 0.0 424.2068210797029 133.26403045654297 0.0 0.0 0.14083551646706588 0.0 0.0 2.0878043717252995e-05 0.0
12 10 0.3565881786288848 1.3899452072417664 1.3869511952657185 0.0029940119760479044 0.0 1.3862694037888579 0.0014970516730211452 0.0 419.59836629853027 129.42418139094877 0.0 0.0 0.17583908720644648 0.0 0.0 8.360354486339821e-06 0.0
13 11 0.3604390230545021 1.389967136040419 1.3869731240643712 0.0029940119760479044 0.0 1.3862430778092254 0.0014970059880239522 0.0 422.7740191355286 233.24433135986328 0.0 0.0 0.19158889861877806 0.0 0.0 0.0005727185460621725 0.0
14 12 0.35958609816860904 1.3899890648390718 1.386995052863024 0.0029940119760479044 0.0 1.3862435346591973 0.0014970059880239522 0.0 428.75975530691034 134.54219818115234 0.0 0.0 0.15044270589680014 0.0 0.0 1.4059557886180763e-05 0.0
15 13 0.3641235025867237 1.3899988528497205 1.3870048408736726 0.0029940119760479044 0.0 1.3862431691792196 0.0014970973580183383 0.0 436.3110439641028 132.57274183704607 0.0 0.0 0.13464346331750562 0.0 0.0 1.0222018121959206e-05 0.0
16 14 0.6077359212903574 1.392235042092329 1.3892410301162812 0.0029940119760479044 0.0 1.3862897678763566 0.0014970059880239522 0.0 428.37841558520535 136.21092224121094 0.0 0.0 0.12912069537682447 0.0 0.0 8.246141993357036e-06 0.0
17 15 0.35661593485906184 1.4028957732423337 1.3999017612662858 0.0029940119760479044 0.0 1.3862430778092254 0.0014970059880239522 0.0 443.8206779956455 141.3322525024414 0.0 0.0 0.16600657937055577 0.0 0.0 1.8456738866017964e-05 0.0
@@ -1,17 +0,0 @@
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
16,0.5104985823353001,1.3912965694587387,1.3883025574826908,0.0029940119760479044,0.0,1.386243991509169,0.0014970516730211452,0.0,427.89946953555676,131.20892459336568,,0.0,0.0,0.16657170278583458,0.0,0.0,9.559585662659057e-06,0.0
17,0.3670100813688908,1.3899731664600488,1.3869791544840007,0.0029940119760479044,0.0,1.3862432034429675,0.0014970059880239522,0.0,426.1667904928029,226.83871459960938,,0.0,0.0,0.17479180433079153,0.0,0.0,0.00055243440730843,0.0
18,0.608297478227763,1.3922082592627245,1.3892142472866766,0.0029940119760479044,0.0,1.3862897678763566,0.0014970516730211452,0.0,431.2037692128149,128.39598400927707,,0.0,0.0,0.14504283059856848,0.0,0.0,1.3305755432494387e-05,0.0
19,0.3559304747026925,1.401616159313453,1.3986221473374052,0.0029940119760479044,0.0,1.3862428950692365,0.0014970516730211452,0.0,440.73424885610217,129.6899508681986,,0.0,0.0,0.19256509563880053,0.0,0.0,2.5480807184459206e-05,0.0
20,0.3570187143809455,1.3899802933196108,1.386986281343563,0.0029940119760479044,0.0,1.3875318630012923,0.0014970516730211452,0.0,414.2771616061969,133.60266562910067,,0.0,0.0,0.21183338279495695,0.0,0.0,8.657306968095059e-06,0.0
21,0.36364641610907317,1.3899890648390718,1.386995052863024,0.0029940119760479044,0.0,1.3862435346591973,0.0014970516730211452,0.0,438.64622587148216,132.20179132716896,,0.0,0.0,0.2076476319821295,0.0,0.0,1.0439021858626498e-05,0.0
22,0.3597969825898013,1.3899802933196108,1.386986281343563,0.0029940119760479044,0.0,1.3875289277402227,0.0014970059880239522,0.0,438.53028067671056,135.6368408203125,,0.0,0.0,0.15510047410062688,0.0,0.0,9.045629444236527e-06,0.0
23,0.36000958471288586,1.3899759075598803,1.3869818955838322,0.0029940119760479044,0.0,1.386243260549214,0.0014970516730211452,0.0,451.2033181063228,234.5704324208856,,0.0,0.0,0.1520512746479697,0.0,0.0,0.0004944144608731755,0.0
24,0.35637714141192556,1.389967136040419,1.3869731240643712,0.0029940119760479044,0.0,1.3948668976743779,0.0014970059880239522,0.0,436.34188375789466,129.67151641845703,,0.0,0.0,0.4576755912004117,0.0,0.0,7.252493304406811e-06,0.0
25,0.36086313590376146,1.3899539787612276,1.3869599667851797,0.0029940119760479044,0.0,1.3862428036992422,0.0014970059880239522,0.0,434.4188514059107,128.88497161865234,,0.0,0.0,0.16652766244854042,0.0,0.0,8.428881982129491e-06,0.0
26,0.35616109237090826,1.3899539787612276,1.3869599667851797,0.0029940119760479044,0.0,1.3862695865288466,0.0014970516730211452,0.0,419.18246774425404,128.8801840153804,,0.0,0.0,0.17971710387818113,0.0,0.0,7.77787077212762e-06,0.0
27,0.3585049569470193,1.3899627502806886,1.3869687383046407,0.0029940119760479044,0.0,1.386242986439231,0.0014970059880239522,0.0,426.3204124053096,221.94922637939453,,0.0,0.0,0.19211820499625748,0.0,0.0,0.000500958836721089,0.0
28,0.36065695238662526,1.390006607877994,1.3870125959019461,0.0029940119760479044,0.0,1.3891731993166987,0.0014970516730211452,0.0,1320.2150984614323,134.20930605145108,,0.0,0.0,0.3690895491731381,0.0,0.0,8.485988228620883e-06,0.0
29,0.3640717800237613,1.3899802933196108,1.386986281343563,0.0029940119760479044,0.0,1.3862433519192086,0.0014970059880239522,0.0,441.58321994030075,133.47675323486328,,0.0,0.0,0.25343286205908494,0.0,0.0,1.2963117953546034e-05,0.0
30,0.4492884530145984,1.3905465245960715,1.3875525126200237,0.0029940119760479044,0.0,1.386254590428518,0.0014970059880239522,0.0,417.5459751653438,136.24229431152344,,0.0,0.0,0.1709978480538922,0.0,0.0,7.640815780548278e-06,0.0
31,0.35752631455221073,1.3910653120029473,1.3880713000268994,0.0029940119760479044,0.0,1.3862431691792196,0.0014970059880239522,0.0,431.3200226244874,142.95814514160156,,0.0,0.0,0.1644791471744012,0.0,0.0,7.732185774934507e-06,0.0
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 0.5104985823353001 1.3912965694587387 1.3883025574826908 0.0029940119760479044 0.0 1.386243991509169 0.0014970516730211452 0.0 427.89946953555676 131.20892459336568 0.0 0.0 0.16657170278583458 0.0 0.0 9.559585662659057e-06 0.0
3 17 0.3670100813688908 1.3899731664600488 1.3869791544840007 0.0029940119760479044 0.0 1.3862432034429675 0.0014970059880239522 0.0 426.1667904928029 226.83871459960938 0.0 0.0 0.17479180433079153 0.0 0.0 0.00055243440730843 0.0
4 18 0.608297478227763 1.3922082592627245 1.3892142472866766 0.0029940119760479044 0.0 1.3862897678763566 0.0014970516730211452 0.0 431.2037692128149 128.39598400927707 0.0 0.0 0.14504283059856848 0.0 0.0 1.3305755432494387e-05 0.0
5 19 0.3559304747026925 1.401616159313453 1.3986221473374052 0.0029940119760479044 0.0 1.3862428950692365 0.0014970516730211452 0.0 440.73424885610217 129.6899508681986 0.0 0.0 0.19256509563880053 0.0 0.0 2.5480807184459206e-05 0.0
6 20 0.3570187143809455 1.3899802933196108 1.386986281343563 0.0029940119760479044 0.0 1.3875318630012923 0.0014970516730211452 0.0 414.2771616061969 133.60266562910067 0.0 0.0 0.21183338279495695 0.0 0.0 8.657306968095059e-06 0.0
7 21 0.36364641610907317 1.3899890648390718 1.386995052863024 0.0029940119760479044 0.0 1.3862435346591973 0.0014970516730211452 0.0 438.64622587148216 132.20179132716896 0.0 0.0 0.2076476319821295 0.0 0.0 1.0439021858626498e-05 0.0
8 22 0.3597969825898013 1.3899802933196108 1.386986281343563 0.0029940119760479044 0.0 1.3875289277402227 0.0014970059880239522 0.0 438.53028067671056 135.6368408203125 0.0 0.0 0.15510047410062688 0.0 0.0 9.045629444236527e-06 0.0
9 23 0.36000958471288586 1.3899759075598803 1.3869818955838322 0.0029940119760479044 0.0 1.386243260549214 0.0014970516730211452 0.0 451.2033181063228 234.5704324208856 0.0 0.0 0.1520512746479697 0.0 0.0 0.0004944144608731755 0.0
10 24 0.35637714141192556 1.389967136040419 1.3869731240643712 0.0029940119760479044 0.0 1.3948668976743779 0.0014970059880239522 0.0 436.34188375789466 129.67151641845703 0.0 0.0 0.4576755912004117 0.0 0.0 7.252493304406811e-06 0.0
11 25 0.36086313590376146 1.3899539787612276 1.3869599667851797 0.0029940119760479044 0.0 1.3862428036992422 0.0014970059880239522 0.0 434.4188514059107 128.88497161865234 0.0 0.0 0.16652766244854042 0.0 0.0 8.428881982129491e-06 0.0
12 26 0.35616109237090826 1.3899539787612276 1.3869599667851797 0.0029940119760479044 0.0 1.3862695865288466 0.0014970516730211452 0.0 419.18246774425404 128.8801840153804 0.0 0.0 0.17971710387818113 0.0 0.0 7.77787077212762e-06 0.0
13 27 0.3585049569470193 1.3899627502806886 1.3869687383046407 0.0029940119760479044 0.0 1.386242986439231 0.0014970059880239522 0.0 426.3204124053096 221.94922637939453 0.0 0.0 0.19211820499625748 0.0 0.0 0.000500958836721089 0.0
14 28 0.36065695238662526 1.390006607877994 1.3870125959019461 0.0029940119760479044 0.0 1.3891731993166987 0.0014970516730211452 0.0 1320.2150984614323 134.20930605145108 0.0 0.0 0.3690895491731381 0.0 0.0 8.485988228620883e-06 0.0
15 29 0.3640717800237613 1.3899802933196108 1.386986281343563 0.0029940119760479044 0.0 1.3862433519192086 0.0014970059880239522 0.0 441.58321994030075 133.47675323486328 0.0 0.0 0.25343286205908494 0.0 0.0 1.2963117953546034e-05 0.0
16 30 0.4492884530145984 1.3905465245960715 1.3875525126200237 0.0029940119760479044 0.0 1.386254590428518 0.0014970059880239522 0.0 417.5459751653438 136.24229431152344 0.0 0.0 0.1709978480538922 0.0 0.0 7.640815780548278e-06 0.0
17 31 0.35752631455221073 1.3910653120029473 1.3880713000268994 0.0029940119760479044 0.0 1.3862431691792196 0.0014970059880239522 0.0 431.3200226244874 142.95814514160156 0.0 0.0 0.1644791471744012 0.0 0.0 7.732185774934507e-06 0.0
@@ -1,55 +0,0 @@
Metric,Value,Alias
Wave Life,33670.0,wave_life_
Active CUs,90/120,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,1522.0,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,750.0,l2_rd_lat_
L2 Wr Lat,333.0,l2_wr_lat_
Fabric Rd Lat,428.0,fabric_rd_lat_
Fabric Wr Lat,144.0,fabric_wr_lat_
Fabric Atomic Lat,,fabric_atom_lat_
Fabric_L2 Rd,44.0,l2_fabric_rd_
Fabric_L2 Wr,0.0,l2_fabric_wr_
Fabric_l2 Atomic,0.0,l2_fabric_atom_
HBM Rd,44.0,hbm_rd_
HBM Wr,0.0,hbm_wr_
LDS_Per_Workgroup Util,0.0,lds_util_
VL1 Coalesce,70.0,vl1_coales_
VL1 Stall,30.0,vl1_stall_
LDS_Per_Workgroup Lat,,lds_lat_
vL1D Lat,,sl1_lat_
IL1 Lat,,il1_lat_
Wave Occupancy,35.0,wave_occ_
1 Metric Value Alias
2 Wave Life 33670.0 wave_life_
3 Active CUs 90/120 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 1522.0 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 750.0 l2_rd_lat_
40 L2 Wr Lat 333.0 l2_wr_lat_
41 Fabric Rd Lat 428.0 fabric_rd_lat_
42 Fabric Wr Lat 144.0 fabric_wr_lat_
43 Fabric Atomic Lat fabric_atom_lat_
44 Fabric_L2 Rd 44.0 l2_fabric_rd_
45 Fabric_L2 Wr 0.0 l2_fabric_wr_
46 Fabric_l2 Atomic 0.0 l2_fabric_atom_
47 HBM Rd 44.0 hbm_rd_
48 HBM Wr 0.0 hbm_wr_
49 LDS_Per_Workgroup Util 0.0 lds_util_
50 VL1 Coalesce 70.0 vl1_coales_
51 VL1 Stall 30.0 vl1_stall_
52 LDS_Per_Workgroup Lat lds_lat_
53 vL1D Lat sl1_lat_
54 IL1 Lat il1_lat_
55 Wave Occupancy 35.0 wave_occ_
@@ -1,168 +0,0 @@
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
@@ -1,30 +0,0 @@
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,90,Cus,120,75.0
SALU Util,2.11506716449265,Pct,100,2.11506716449265
VALU Util,59.58449821812784,Pct,100,59.58449821812784
MFMA Util,,Pct,100,
VALU Active Threads/Wave,63.967830830447085,Threads,64,99.94973567257357
IPC - Issue,0.8437266214800547,Instr/cycle,5,16.874532429601096
LDS_Per_Workgroup BW,0.0,Gb/sec,23070.72,0.0
LDS_Per_Workgroup Bank Conflict,,Conflicts/access,32,
Instr Cache Hit Rate,99.99343846471189,Pct,100,99.99343846471189
Instr Cache BW,1402.474168265396,Gb/s,4614.144,30.39511051812418
Scalar L1D Cache Hit Rate,99.35620448529356,Pct,100,99.35620448529356
Scalar L1D Cache BW,42.87804961486619,Gb/s,4614.144,0.9292741972263153
Vector L1D Cache Hit Rate,20.508982035928145,Pct,100,20.508982035928145
Vector L1D Cache BW,1209.4779187802392,Gb/s,11535.36,10.484960320096114
L2 Cache Hit Rate,0.3929594115290852,Pct,100,0.3929594115290852
L2-Fabric Read BW,832.6393531628229,Gb/s,1228.8,67.76036402692245
L2-Fabric Write BW,4.953907222722173,Gb/s,1228.8,0.4031500018491352
L2-Fabric Read Latency,428.04498680959387,Cycles,,
L2-Fabric Write Latency,144.29924861218794,Cycles,,
Wave Occupancy,3179.407834818687,Wavefronts,4800,66.23766322538933
Instr Fetch BW,683.7578338487325,Gb/s,2307.072,29.6374726861031
Instr Fetch Latency,18.62319807792158,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 90 Cus 120 75.0
10 SALU Util 2.11506716449265 Pct 100 2.11506716449265
11 VALU Util 59.58449821812784 Pct 100 59.58449821812784
12 MFMA Util Pct 100
13 VALU Active Threads/Wave 63.967830830447085 Threads 64 99.94973567257357
14 IPC - Issue 0.8437266214800547 Instr/cycle 5 16.874532429601096
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 99.99343846471189 Pct 100 99.99343846471189
18 Instr Cache BW 1402.474168265396 Gb/s 4614.144 30.39511051812418
19 Scalar L1D Cache Hit Rate 99.35620448529356 Pct 100 99.35620448529356
20 Scalar L1D Cache BW 42.87804961486619 Gb/s 4614.144 0.9292741972263153
21 Vector L1D Cache Hit Rate 20.508982035928145 Pct 100 20.508982035928145
22 Vector L1D Cache BW 1209.4779187802392 Gb/s 11535.36 10.484960320096114
23 L2 Cache Hit Rate 0.3929594115290852 Pct 100 0.3929594115290852
24 L2-Fabric Read BW 832.6393531628229 Gb/s 1228.8 67.76036402692245
25 L2-Fabric Write BW 4.953907222722173 Gb/s 1228.8 0.4031500018491352
26 L2-Fabric Read Latency 428.04498680959387 Cycles
27 L2-Fabric Write Latency 144.29924861218794 Cycles
28 Wave Occupancy 3179.407834818687 Wavefronts 4800 66.23766322538933
29 Instr Fetch BW 683.7578338487325 Gb/s 2307.072 29.6374726861031
30 Instr Fetch Latency 18.62319807792158 Cycles
@@ -1,9 +0,0 @@
Metric,Avg,Min,Max,Unit
GPU Busy Cycles,615155.4491017964,28607,9088052,Cycles/kernel
CPF Busy,615155.4491017964,28607,9088052,Cycles/kernel
CPF Util,100.0,100.0,100.0,Pct
CPF Stall,0.0013057658880960608,0.0,0.05750326640389858,Cycles/kernel
L2Cache Intf Busy,4096.754491017964,3762,6060,Cycles/kernel
L2Cache Intf Util,1.288557516271075,0.04396501243400984,14.14461955359053,Pct
L2Cache Intf Stall,0.0,0.0,0.0,Pct
UTCL1 Stall,11.353293413173652,0,158,Cycles/kernel
1 Metric Avg Min Max Unit
2 GPU Busy Cycles 615155.4491017964 28607 9088052 Cycles/kernel
3 CPF Busy 615155.4491017964 28607 9088052 Cycles/kernel
4 CPF Util 100.0 100.0 100.0 Pct
5 CPF Stall 0.0013057658880960608 0.0 0.05750326640389858 Cycles/kernel
6 L2Cache Intf Busy 4096.754491017964 3762 6060 Cycles/kernel
7 L2Cache Intf Util 1.288557516271075 0.04396501243400984 14.14461955359053 Pct
8 L2Cache Intf Stall 0.0 0.0 0.0 Pct
9 UTCL1 Stall 11.353293413173652 0 158 Cycles/kernel
@@ -1,13 +0,0 @@
Metric,Avg,Min,Max,Unit
GPU Busy Cycles,615155.4491017964,28607,9088052,Cycles
CPC Busy Cycles,611802.6646706586,28607,9088052,Cycles
CPC Util,99.4906738316286,78.3409215808303,100.0,Pct
CPC Stall Cycles,14155.071856287424,10548,70546,Cycles
CPC Stall Rate,3.916069506360725,0.7762499598373777,40.332785681826124,Pct
CPC Packet Decoding,45102.55688622755,15127,545621,Cycles
SPI Intf Busy Cycles,560909.1916167665,695,8537041,Cycles
SPI Intf Util,88.8381776363952,2.429475303247457,97.3915941285569,Pct
L2Cache Intf Util,0.24613378955819237,0.0082325506246833,2.3397388880739327,Pct
UTCL1 Stall Cycles,2572.9760479041915,2362,3248,Cycles
UTCL2 Intf Busy Cycles,2926.74251497006,2700,3778,Cycles
UTCL2 Intf Util,0.9218869170656802,0.034289216778607315,10.440954727667243,Pct
1 Metric Avg Min Max Unit
2 GPU Busy Cycles 615155.4491017964 28607 9088052 Cycles
3 CPC Busy Cycles 611802.6646706586 28607 9088052 Cycles
4 CPC Util 99.4906738316286 78.3409215808303 100.0 Pct
5 CPC Stall Cycles 14155.071856287424 10548 70546 Cycles
6 CPC Stall Rate 3.916069506360725 0.7762499598373777 40.332785681826124 Pct
7 CPC Packet Decoding 45102.55688622755 15127 545621 Cycles
8 SPI Intf Busy Cycles 560909.1916167665 695 8537041 Cycles
9 SPI Intf Util 88.8381776363952 2.429475303247457 97.3915941285569 Pct
10 L2Cache Intf Util 0.24613378955819237 0.0082325506246833 2.3397388880739327 Pct
11 UTCL1 Stall Cycles 2572.9760479041915 2362 3248 Cycles
12 UTCL2 Intf Busy Cycles 2926.74251497006 2700 3778 Cycles
13 UTCL2 Intf Util 0.9218869170656802 0.034289216778607315 10.440954727667243 Pct
@@ -1,9 +0,0 @@
Metric,Avg,Min,Max,Unit
GPU Busy,615155.4491017964,28607,9088052,Cycles
CS Busy,4751057.233532934,84925,72544223,Cycles
SPI Busy,595888.0718562874,11571,9068646,Cycles
SQ Busy,4742675.628742515,80304,72532581,Cycles
Dispatched Workgroups,16973.413173652694,128,131072,Workgroups
Dispatched Wavefronts,67893.65269461078,512,524288,Wavefronts
Wave Alloc Failed,280555.1856287425,114,1624894,Cycles
Wave Alloc Failed - CS,329720.02994011977,626,981318,Cycles
1 Metric Avg Min Max Unit
2 GPU Busy 615155.4491017964 28607 9088052 Cycles
3 CS Busy 4751057.233532934 84925 72544223 Cycles
4 SPI Busy 595888.0718562874 11571 9068646 Cycles
5 SQ Busy 4742675.628742515 80304 72532581 Cycles
6 Dispatched Workgroups 16973.413173652694 128 131072 Workgroups
7 Dispatched Wavefronts 67893.65269461078 512 524288 Wavefronts
8 Wave Alloc Failed 280555.1856287425 114 1624894 Cycles
9 Wave Alloc Failed - CS 329720.02994011977 626 981318 Cycles
@@ -1,15 +0,0 @@
Metric,Avg,Min,Max,Unit
Wave request Failed (CS),329720.02994011977,626,981318,Cycles
CS Stall,19528.616766467065,0,791539,Cycles
CS Stall Rate,4.9501409716008515,0.0,87.80828452254171,Pct
Scratch Stall,0.0,0,0,Cycles
Insufficient SIMD Waveslots,65959.77844311377,0,728283,Simd
Insufficient SIMD VGPRs,582374.6826347306,0,30915166,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) 329720.02994011977 626 981318 Cycles
3 CS Stall 19528.616766467065 0 791539 Cycles
4 CS Stall Rate 4.9501409716008515 0.0 87.80828452254171 Pct
5 Scratch Stall 0.0 0 0 Cycles
6 Insufficient SIMD Waveslots 65959.77844311377 0 728283 Simd
7 Insufficient SIMD VGPRs 582374.6826347306 0 30915166 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
@@ -1,10 +0,0 @@
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
@@ -1,9 +0,0 @@
Metric,Avg,Min,Max,Unit
Kernel Time (Nanosec),396632.55688622757,6560,6051952,Ns
Kernel Time (Cycles),615155.4491017964,28607,9088052,Cycle
Instr/wavefront,842.5329341317365,62.0,20596.0,Instr/wavefront
Wave Cycles,33669.99006456386,2852.8163681030273,547920.7350463867,Cycles/wave
Dependency Wait Cycles,4421.601850224112,1060.047119140625,26450.00244140625,Cycles/wave
Issue Wait Cycles,25348.783498113025,189.546875,443154.73260498047,Cycles/wave
Active Cycles,3899.6337799255007,248.0,78316.0,Cycles/wave
Wavefront Occupancy,3179.407834818687,159.4228546662814,3951.485112322614,Wavefronts
1 Metric Avg Min Max Unit
2 Kernel Time (Nanosec) 396632.55688622757 6560 6051952 Ns
3 Kernel Time (Cycles) 615155.4491017964 28607 9088052 Cycle
4 Instr/wavefront 842.5329341317365 62.0 20596.0 Instr/wavefront
5 Wave Cycles 33669.99006456386 2852.8163681030273 547920.7350463867 Cycles/wave
6 Dependency Wait Cycles 4421.601850224112 1060.047119140625 26450.00244140625 Cycles/wave
7 Issue Wait Cycles 25348.783498113025 189.546875 443154.73260498047 Cycles/wave
8 Active Cycles 3899.6337799255007 248.0 78316.0 Cycles/wave
9 Wavefront Occupancy 3179.407834818687 159.4228546662814 3951.485112322614 Wavefronts
@@ -1,2 +0,0 @@
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
Axes1,vesuvius,AMD EPYC 7542 32-Core Processor,,4.18.0-240.15.1.el8_3.x86_64,4.2.0-21,Thu Sep 22 11:24:51 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 Axes1 vesuvius AMD EPYC 7542 32-Core Processor 4.18.0-240.15.1.el8_3.x86_64 4.2.0-21 Thu Sep 22 11:24:51 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
@@ -1,168 +0,0 @@
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",0,0,0,901550,901555,33554432,256,0,0,8,32,6464,0x0,0x7f38b4604180,12075944713040777,12075944713091723,12075944713416199,12075944713499991
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,901550,901555,32768,256,0,0,24,24,12480,0x0,0x7f38b4635100,12075944728070880,12075944728173211,12075944728179771,12075944728183740
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,901550,901555,4194304,256,0,0,24,24,12928,0x7f39c020d900,0x7f38b4635140,12075944728232350,12075944728248250,12075944728379609,12075944728383171
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,901550,901555,4194304,256,0,0,36,24,13632,0x7f39c020d800,0x7f38b4635180,12075944728428375,12075944728443448,12075944728690646,12075944728762806
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,901550,901555,4194304,256,0,0,28,24,14080,0x7f39c020d700,0x7f38b46351c0,12075944728786180,12075944728801204,12075944729049202,12075944729122384
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,901550,901555,4194304,256,0,0,24,24,14528,0x7f39c020d600,0x7f38b4635200,12075944729141019,12075944729155441,12075944729281360,12075944729284486
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,901550,901555,4194304,256,0,0,24,24,14976,0x7f39c020d500,0x7f38b4635240,12075944729312718,12075944729325679,12075944729450478,12075944729453750
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,901550,901555,4194304,256,0,0,24,24,15424,0x7f39c020d400,0x7f38b4635280,12075944729515605,12075944729531437,12075944729655116,12075944729658381
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,901550,901555,4194304,256,0,0,28,24,16128,0x7f39c020d300,0x7f38b46352c0,12075944729687675,12075944729701835,12075944729954153,12075944730022778
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,901550,901555,4194304,256,0,0,28,24,16832,0x7f39c020da00,0x7f38b4635300,12075944730051070,12075944730065832,12075944730310789,12075944730377427
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,901550,901555,4194304,256,0,0,24,24,17536,0x7f39c020d900,0x7f38b4635340,12075944730400329,12075944730415428,12075944730539907,12075944730543325
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,901550,901555,4194304,256,0,0,24,24,18240,0x7f39c020d800,0x7f38b4635380,12075944730572319,12075944730586307,12075944730710625,12075944730713972
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,901550,901555,4194304,256,0,0,24,24,18944,0x7f39c020d700,0x7f38b46353c0,12075944730752654,12075944730769025,12075944730893023,12075944730896492
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,901550,901555,4194304,256,0,0,28,24,19904,0x7f39c020d600,0x7f38b4635400,12075944730924113,12075944730937503,12075944731183421,12075944731258074
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,901550,901555,4194304,256,0,0,28,24,20608,0x7f39c020d500,0x7f38b4635440,12075944731283391,12075944731297339,12075944731546937,12075944731618904
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,901550,901555,4194304,256,0,0,24,24,21312,0x7f39c020d400,0x7f38b4635480,12075944731644792,12075944731658936,12075944731783415,12075944731786556
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,901550,901555,4194304,256,0,0,24,24,22016,0x7f39c020d300,0x7f38b46354c0,12075944731814818,12075944731828214,12075944731953653,12075944731957063
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,901550,901555,4194304,256,0,0,24,24,22720,0x7f39c020da00,0x7f38b4635500,12075944732005322,12075944732019092,12075944732143091,12075944732146434
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,901550,901555,4194304,256,0,0,28,24,23680,0x7f39c020d900,0x7f38b4635540,12075944732176500,12075944732191730,12075944732437968,12075944732509379
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,901550,901555,4194304,256,0,0,28,24,24384,0x7f39c020d800,0x7f38b4635580,12075944732530598,12075944732544367,12075944732789165,12075944732855803
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,901550,901555,4194304,256,0,0,24,24,25088,0x7f39c020d700,0x7f38b46355c0,12075944732878746,12075944732892843,12075944733017802,12075944733021220
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,901550,901555,4194304,256,0,0,24,24,25792,0x7f39c020d600,0x7f38b4635600,12075944733053610,12075944733069322,12075944733194280,12075944733197668
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,901550,901555,4194304,256,0,0,24,24,26496,0x7f39c020d500,0x7f38b4635640,12075944733240207,12075944733253960,12075944733377319,12075944733380718
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,901550,901555,4194304,256,0,0,28,24,27712,0x7f39c020d400,0x7f38b4635680,12075944733409482,12075944733423238,12075944733708355,12075944733780561
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,901550,901555,4194304,256,0,0,28,24,28416,0x7f39c020d300,0x7f38b46356c0,12075944733802572,12075944733817314,12075944734062432,12075944734134800
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,901550,901555,4194304,256,0,0,24,24,29120,0x7f39c020da00,0x7f38b4635700,12075944734159395,12075944734173151,12075944734297469,12075944734300658
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,901550,901555,4194304,256,0,0,24,24,30080,0x7f39c020d900,0x7f38b4635740,12075944734334341,12075944734348669,12075944734474108,12075944734477396
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,901550,901555,4194304,256,0,0,24,24,30784,0x7f39c020d800,0x7f38b4635780,12075944734514706,12075944734528507,12075944734653146,12075944734656579
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,901550,901555,4194304,256,0,0,28,24,32000,0x7f39c020d700,0x7f38b46357c0,12075944734684391,12075944734698425,12075944734946423,12075944734993436
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,901550,901555,4194304,256,0,0,28,24,32960,0x7f39c020d600,0x7f38b4635800,12075944735015657,12075944735029462,12075944735272020,12075944735322026
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,901550,901555,4194304,256,0,0,24,24,33920,0x7f39c020d500,0x7f38b4635840,12075944735350990,12075944735365939,12075944735490737,12075944735494086
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,901550,901555,4194304,256,0,0,24,24,34880,0x7f39c020d400,0x7f38b4635880,12075944735521266,12075944735534737,12075944735659376,12075944735662970
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,901550,901555,4194304,256,0,0,24,24,35840,0x7f39c020d300,0x7f38b46358c0,12075944735701752,12075944735715055,12075944735839854,12075944735843024
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,901550,901555,4194304,256,0,0,28,24,37312,0x7f39c020da00,0x7f38b4635900,12075944735873501,12075944735887214,12075944736136651,12075944736184469
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,901550,901555,4194304,256,0,0,28,24,38272,0x7f39c020d900,0x7f38b4635940,12075944736207472,12075944736221290,12075944736470728,12075944736517788
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,901550,901555,4194304,256,0,0,24,24,39232,0x7f39c020d800,0x7f38b4635980,12075944736541082,12075944736556007,12075944736680966,12075944736684518
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,901550,901555,4194304,256,0,0,24,24,40192,0x7f39c020d700,0x7f38b46359c0,12075944736712240,12075944736725605,12075944736850724,12075944736853963
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,901550,901555,4194304,256,0,0,24,24,41152,0x7f39c020d600,0x7f38b4635a00,12075944736891693,12075944736905603,12075944737029442,12075944737033377
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,901550,901555,4194304,256,0,0,28,24,42624,0x7f39c020d500,0x7f38b4635a40,12075944737060898,12075944737078402,12075944737326399,12075944737357930
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,901550,901555,4194304,256,0,0,28,24,43584,0x7f39c020d400,0x7f38b4635a80,12075944737381854,12075944737395678,12075944737639836,12075944737669238
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,901550,901555,4194304,256,0,0,24,24,44544,0x7f39c020d300,0x7f38b4635ac0,12075944737692422,12075944737704955,12075944737829594,12075944737833303
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,901550,901555,4194304,256,0,0,24,24,45760,0x7f39c020da00,0x7f38b4635b00,12075944737863660,12075944737878554,12075944738005112,12075944738008689
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,901550,901555,4194304,256,0,0,24,24,46720,0x7f39c020d900,0x7f38b4635b40,12075944738047822,12075944738063192,12075944738187670,12075944738190858
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,901550,901555,4194304,256,0,0,28,24,48448,0x7f39c020d800,0x7f38b4635b80,12075944738219431,12075944738233910,12075944738530227,12075944738559513
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,901550,901555,4194304,256,0,0,28,24,49408,0x7f39c020d700,0x7f38b4635bc0,12075944738576114,12075944738589746,12075944738872304,12075944738900697
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,901550,901555,4194304,256,0,0,24,24,50368,0x7f39c020d600,0x7f38b4635c00,12075944738922357,12075944738936783,12075944739061262,12075944739065423
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,901550,901555,4194304,256,0,0,24,24,51584,0x7f39c020d500,0x7f38b4635c40,12075944739096651,12075944739114221,12075944739240780,12075944739244286
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,901550,901555,4194304,256,0,0,24,24,52544,0x7f39c020d400,0x7f38b4635c80,12075944739282006,12075944739295659,12075944739420618,12075944739423899
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,901550,901555,4194304,256,0,0,28,24,54272,0x7f39c020d300,0x7f38b4635cc0,12075944739450649,12075944739465258,12075944739723975,12075944739748753
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,901550,901555,4194304,256,0,0,28,24,55488,0x7f39c020da00,0x7f38b4635d00,12075944739769762,12075944739783335,12075944740026852,12075944740052217
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,901550,901555,4194304,256,0,0,24,24,56704,0x7f39c020d900,0x7f38b4635d40,12075944740075831,12075944740090851,12075944740215490,12075944740218847
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,901550,901555,4194304,256,0,0,24,24,58176,0x7f39c020d800,0x7f38b4635d80,12075944740247931,12075944740261250,12075944740389728,12075944740393030
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,901550,901555,4194304,256,0,0,24,24,59392,0x7f39c020d700,0x7f38b4635dc0,12075944740430640,12075944740444928,12075944740569727,12075944740573025
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,901550,901555,4194304,256,0,0,28,24,61376,0x7f39c020d600,0x7f38b4635e00,12075944740600486,12075944740614686,12075944740874204,12075944740894132
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,901550,901555,4194304,256,0,0,28,24,62592,0x7f39c020d500,0x7f38b4635e40,12075944740916864,12075944740929083,12075944741176121,12075944741203837
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,901550,901555,4194304,256,0,0,24,24,63808,0x7f39c020d400,0x7f38b4635e80,12075944741228403,12075944741241240,12075944741366519,12075944741369826
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,901550,901555,4194304,256,0,0,24,24,65280,0x7f39c020d300,0x7f38b4635ec0,12075944741397688,12075944741411638,12075944741541397,12075944741544731
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,901550,901555,4194304,256,0,0,24,24,66496,0x7f39c020da00,0x7f38b4635f00,12075944741584144,12075944741597876,12075944741723315,12075944741726829
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,901550,901555,4194304,256,0,0,28,24,68480,0x7f39c020d900,0x7f38b4635f40,12075944741754982,12075944741769235,12075944742028432,12075944742053857
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,901550,901555,4194304,256,0,0,28,24,69696,0x7f39c020d800,0x7f38b4635f80,12075944742076569,12075944742090831,12075944742375629,12075944742399820
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,901550,901555,4194304,256,0,0,24,24,70912,0x7f39c020d700,0x7f38b4635fc0,12075944742422713,12075944742436908,12075944742562347,12075944742566049
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,901550,901555,4194304,256,0,0,24,24,72384,0x7f39c020d600,0x7f38b4636000,12075944742593841,12075944742607626,12075944742744105,12075944742747416
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,901550,901555,4194304,256,0,0,24,24,73600,0x7f39c020d500,0x7f38b4636040,12075944742786549,12075944742801384,12075944742926183,12075944742929424
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,901550,901555,4194304,256,0,0,28,24,75840,0x7f39c020d400,0x7f38b4636080,12075944742956434,12075944742970663,12075944743231140,12075944743265479
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,901550,901555,4194304,256,0,0,28,24,77056,0x7f39c020d300,0x7f38b46360c0,12075944743289584,12075944743304579,12075944743552417,12075944743583229
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,901550,901555,4194304,256,0,0,24,24,78272,0x7f39c020da00,0x7f38b4636100,12075944743605952,12075944743619936,12075944743745215,12075944743748567
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,901550,901555,4194304,256,0,0,24,24,80000,0x7f39c020d900,0x7f38b4636140,12075944743776408,12075944743790174,12075944743932093,12075944743935464
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,901550,901555,4194304,256,0,0,24,24,81216,0x7f39c020d800,0x7f38b4636180,12075944743972954,12075944743986972,12075944744112091,12075944744116110
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,901550,901555,4194304,256,0,0,28,24,83456,0x7f39c020d700,0x7f38b46361c0,12075944744143851,12075944744157691,12075944744410968,12075944744434161
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,901550,901555,4194304,256,0,0,28,24,84928,0x7f39c020d600,0x7f38b4636200,12075944744455841,12075944744469848,12075944744714325,12075944744737645
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,901550,901555,4194304,256,0,0,24,24,86400,0x7f39c020d500,0x7f38b4636240,12075944744762030,12075944744776885,12075944744901843,12075944744905366
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,901550,901555,4194304,256,0,0,24,24,88128,0x7f39c020d400,0x7f38b4636280,12075944744931986,12075944744945203,12075944745093841,12075944745097674
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,901550,901555,4194304,256,0,0,24,24,89600,0x7f39c020d300,0x7f38b46362c0,12075944745154900,12075944745169201,12075944745294319,12075944745297886
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,901550,901555,4194304,256,0,0,28,24,92096,0x7f39c020da00,0x7f38b4636300,12075944745324796,12075944745338959,12075944745593836,12075944745620065
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,901550,901555,4194304,256,0,0,28,24,93568,0x7f39c020d900,0x7f38b4636340,12075944745642336,12075944745656556,12075944745901833,12075944745926654
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,901550,901555,4194304,256,0,0,24,24,95040,0x7f39c020d800,0x7f38b4636380,12075944745948655,12075944745962153,12075944746087751,12075944746091561
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,901550,901555,4194304,256,0,0,24,24,96768,0x7f39c020d700,0x7f38b46363c0,12075944746121376,12075944746134791,12075944746292389,12075944746295670
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,901550,901555,4194304,256,0,0,24,24,98240,0x7f39c020d600,0x7f38b4636400,12075944746334472,12075944746348229,12075944746473188,12075944746476606
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,901550,901555,4194304,256,0,0,28,24,100736,0x7f39c020d500,0x7f38b4636440,12075944746505290,12075944746519907,12075944746776065,12075944746799466
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,901550,901555,4194304,256,0,0,28,24,102208,0x7f39c020d400,0x7f38b4636480,12075944746821057,12075944746834784,12075944747080222,12075944747110985
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,901550,901555,4194304,256,0,0,24,24,103680,0x7f39c020d300,0x7f38b46364c0,12075944747134148,12075944747148541,12075944747273820,12075944747277395
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,901550,901555,4194304,256,0,0,24,24,105664,0x7f39c020da00,0x7f38b4636500,12075944747306419,12075944747320059,12075944747485177,12075944747488707
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,901550,901555,4194304,256,0,0,24,24,107136,0x7f39c020d900,0x7f38b4636540,12075944747526768,12075944747540697,12075944747667416,12075944747670716
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,901550,901555,4194304,256,0,0,28,24,109888,0x7f39c020d800,0x7f38b4636580,12075944747700281,12075944747715095,12075944747970293,12075944747993576
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,901550,901555,4194304,256,0,0,28,24,111360,0x7f39c020d700,0x7f38b46365c0,12075944748021558,12075944748036052,12075944748285809,12075944748313460
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,901550,901555,4194304,256,0,0,24,24,112832,0x7f39c020d600,0x7f38b4636600,12075944748336593,12075944748350929,12075944748476048,12075944748479379
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,901550,901555,4194304,256,0,0,24,24,114816,0x7f39c020d500,0x7f38b4636640,12075944748508112,12075944748521327,12075944748694285,12075944748697714
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,901550,901555,4194304,256,0,0,24,24,116288,0x7f39c020d400,0x7f38b4636680,12075944748736366,12075944748750285,12075944748876524,12075944748879783
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,901550,901555,4194304,256,0,0,28,24,119040,0x7f39c020d300,0x7f38b46366c0,12075944748907454,12075944748921323,12075944749173641,12075944749201821
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,901550,901555,4194304,256,0,0,28,24,120768,0x7f39c020da00,0x7f38b4636700,12075944749224834,12075944749239400,12075944749483877,12075944749507660
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,901550,901555,4194304,256,0,0,24,24,122496,0x7f39c020d900,0x7f38b4636740,12075944749529580,12075944749543557,12075944749668996,12075944749672386
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,901550,901555,4194304,256,0,0,24,24,124736,0x7f39c020d800,0x7f38b4636780,12075944749700207,12075944749713635,12075944749896193,12075944749899638
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,901550,901555,4194304,256,0,0,24,24,126464,0x7f39c020d700,0x7f38b46367c0,12075944749937849,12075944749951233,12075944750077952,12075944750082077
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,901550,901555,4194304,256,0,0,20,24,127936,0x7f39c020d600,0x7f38b4636800,12075944750111201,12075944750125631,12075944750387708,12075944750411680
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,901550,901555,4194304,256,0,0,28,24,129664,0x7f39c020d500,0x7f38b4636840,12075944750434192,12075944750448028,12075944750727865,12075944750751712
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,901550,901555,4194304,256,0,0,24,24,131392,0x7f39c020d400,0x7f38b4636880,12075944750773262,12075944750785304,12075944750911383,12075944750915386
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,901550,901555,4194304,256,0,0,24,24,133632,0x7f39c020d300,0x7f38b46368c0,12075944750942947,12075944750957143,12075944751148181,12075944751154130
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,901550,901555,4194304,256,0,0,24,24,135360,0x7f39c020da00,0x7f38b4636900,12075944751189956,12075944751203860,12075944751332499,12075944751335807
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,901550,901555,4194304,256,0,0,20,24,136832,0x7f39c020d900,0x7f38b4636940,12075944751364891,12075944751379219,12075944751692655,12075944751716184
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,901550,901555,4194304,256,0,0,28,24,138560,0x7f39c020d800,0x7f38b4636980,12075944751737834,12075944751751055,12075944751998572,12075944752023295
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,901550,901555,4194304,256,0,0,24,24,140288,0x7f39c020d700,0x7f38b46369c0,12075944752052098,12075944752066732,12075944752192330,12075944752195635
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,901550,901555,4194304,256,0,0,24,24,142784,0x7f39c020d600,0x7f38b4636a00,12075944752223236,12075944752236650,12075944752445608,12075944752473491
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,901550,901555,4194304,256,0,0,24,24,144768,0x7f39c020d500,0x7f38b4636a40,12075944752506353,12075944752521127,12075944752649446,12075944752653115
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,901550,901555,4194304,256,0,0,20,24,145728,0x7f39c020d400,0x7f38b4636a80,12075944752680667,12075944752694085,12075944752999842,12075944753029375
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,901550,901555,4194304,256,0,0,28,24,147712,0x7f39c020d300,0x7f38b4636ac0,12075944753052227,12075944753065922,12075944753316479,12075944753344320
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,901550,901555,4194304,256,0,0,24,24,149696,0x7f39c020da00,0x7f38b4636b00,12075944753366211,12075944753379838,12075944753509117,12075944753512723
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,901550,901555,4194304,256,0,0,24,24,152192,0x7f39c020d900,0x7f38b4636b40,12075944753541256,12075944753554557,12075944753781434,12075944753809364
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,901550,901555,4194304,256,0,0,24,24,154176,0x7f39c020d800,0x7f38b4636b80,12075944753842736,12075944753857754,12075944753984792,12075944753988196
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,901550,901555,4194304,256,0,0,20,24,155648,0x7f39c020d700,0x7f38b4636bc0,12075944754021478,12075944754035192,12075944754392148,12075944754424608
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,901550,901555,4194304,256,0,0,28,24,157632,0x7f39c020d600,0x7f38b4636c00,12075944754447961,12075944754461428,12075944754714865,12075944754743069
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,901550,901555,4194304,256,0,0,24,24,159616,0x7f39c020d500,0x7f38b4636c40,12075944754763878,12075944754778225,12075944754907663,12075944754911282
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,901550,901555,4194304,256,0,0,24,24,162368,0x7f39c020d400,0x7f38b4636c80,12075944754940416,12075944754953903,12075944755230540,12075944755258638
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,901550,901555,4194304,256,0,0,24,24,164608,0x7f39c020d300,0x7f38b4636cc0,12075944755291489,12075944755305739,12075944755434698,12075944755438672
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,901550,901555,4194304,256,0,0,20,24,166336,0x7f39c020da00,0x7f38b4636d00,12075944755465422,12075944755479977,12075944755881253,12075944755904177
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,901550,901555,4194304,256,0,0,28,24,168576,0x7f39c020d900,0x7f38b4636d40,12075944755926108,12075944755939493,12075944756196450,12075944756227017
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,901550,901555,4194304,256,0,0,24,24,170816,0x7f39c020d800,0x7f38b4636d80,12075944756249990,12075944756264130,12075944756393568,12075944756397093
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,901550,901555,4194304,256,0,0,24,24,174080,0x7f39c020d700,0x7f38b4636dc0,12075944756426488,12075944756439648,12075944756717725,12075944756745661
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,901550,901555,4194304,256,0,0,24,24,176576,0x7f39c020d600,0x7f38b4636e00,12075944756778302,12075944756791484,12075944756927003,12075944756930294
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,901550,901555,4194304,256,0,0,20,24,177792,0x7f39c020d500,0x7f38b4636e40,12075944756956934,12075944756971163,12075944757393078,12075944757426296
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,901550,901555,4194304,256,0,0,28,24,180288,0x7f39c020d400,0x7f38b4636e80,12075944757449459,12075944757462518,12075944757726035,12075944757754035
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,901550,901555,4194304,256,0,0,24,24,182784,0x7f39c020d300,0x7f38b4636ec0,12075944757776326,12075944757788434,12075944757924753,12075944757928139
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,901550,901555,4194304,256,0,0,24,24,186304,0x7f39c020da00,0x7f38b4636f00,12075944757957273,12075944757970673,12075944758283629,12075944758315699
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,901550,901555,4194304,256,0,0,24,24,189312,0x7f39c020d900,0x7f38b4636f40,12075944758350413,12075944758365069,12075944758516107,12075944758519708
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,901550,901555,4194304,256,0,0,20,24,190784,0x7f39c020d800,0x7f38b4636f80,12075944758547139,12075944758561227,12075944759077061,12075944759107651
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,901550,901555,4194304,256,0,0,28,24,193792,0x7f39c020d700,0x7f38b4636fc0,12075944759129511,12075944759143461,12075944759437378,12075944759464774
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,901550,901555,4194304,256,0,0,24,24,196800,0x7f39c020d600,0x7f38b4637000,12075944759486485,12075944759500417,12075944759655616,12075944759658925
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,901550,901555,4194304,256,0,0,24,24,201088,0x7f39c020d500,0x7f38b4637040,12075944759686847,12075944759700095,12075944760109851,12075944760139528
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,901550,901555,4194304,256,0,0,24,24,204608,0x7f39c020d400,0x7f38b4637080,12075944760172510,12075944760186970,12075944760400248,12075944760428085
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,901550,901555,4194304,256,0,0,20,24,206080,0x7f39c020d300,0x7f38b46370c0,12075944760448773,12075944760463128,12075944761072882,12075944761103340
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,901550,901555,4194304,256,0,0,28,24,209600,0x7f39c020da00,0x7f38b4637100,12075944761124880,12075944761138321,12075944761469358,12075944761497883
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,901550,901555,4194304,256,0,0,24,24,213120,0x7f39c020d900,0x7f38b4637140,12075944761520785,12075944761534797,12075944761712875,12075944761716650
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,901550,901555,4194304,256,0,0,24,24,218176,0x7f39c020d800,0x7f38b4637180,12075944761743509,12075944761756555,12075944762210790,12075944762241595
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,901550,901555,4194304,256,0,0,24,24,222208,0x7f39c020d700,0x7f38b46371c0,12075944762274626,12075944762289349,12075944762487907,12075944762515965
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,901550,901555,4194304,256,0,0,20,24,223936,0x7f39c020d600,0x7f38b4637200,12075944762537084,12075944762551107,12075944763253180,12075944763285535
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,901550,901555,4194304,256,0,0,28,24,227968,0x7f39c020d500,0x7f38b4637240,12075944763307646,12075944763321019,12075944763692215,12075944763721796
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,901550,901555,4194304,256,0,0,24,24,232000,0x7f39c020d400,0x7f38b4637280,12075944763744468,12075944763757975,12075944763960533,12075944763992299
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,901550,901555,4194304,256,0,0,24,24,237824,0x7f39c020d300,0x7f38b46372c0,12075944764016854,12075944764029972,12075944764554927,12075944764590841
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,901550,901555,4194304,256,0,0,24,24,242368,0x7f39c020da00,0x7f38b4637300,12075944764626527,12075944764641006,12075944764864204,12075944764893343
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,901550,901555,4194304,256,0,0,20,24,243584,0x7f39c020d900,0x7f38b4637340,12075944764915615,12075944764929643,12075944765726755,12075944765757249
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,901550,901555,4194304,256,0,0,28,24,248128,0x7f39c020d800,0x7f38b4637380,12075944765779971,12075944765793954,12075944766212030,12075944766241439
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,901550,901555,4194304,256,0,0,24,24,252672,0x7f39c020d700,0x7f38b46373c0,12075944766264151,12075944766277469,12075944766503227,12075944766527951
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,901550,901555,4194304,256,0,0,24,24,259264,0x7f39c020d600,0x7f38b4637400,12075944766551485,12075944766564507,12075944767160821,12075944767192085
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,901550,901555,4194304,256,0,0,24,24,264832,0x7f39c020d500,0x7f38b4637440,12075944767227030,12075944767241140,12075944767510737,12075944767538820
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,901550,901555,4194304,256,0,0,20,24,266304,0x7f39c020d400,0x7f38b4637480,12075944767560510,12075944767574576,12075944768559527,12075944768591907
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,901550,901555,4194304,256,0,0,28,24,271872,0x7f39c020d300,0x7f38b46374c0,12075944768614900,12075944768626886,12075944769157921,12075944769188776
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,901550,901555,4194304,256,0,0,24,24,277440,0x7f39c020da00,0x7f38b4637500,12075944769212700,12075944769226880,12075944769498557,12075944769527445
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,901550,901555,4194304,256,0,0,12,24,279936,0x7f39c020d900,0x7f38b4637540,12075944769550198,12075944769562877,12075944770300149,12075944770330588
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,901550,901555,4194304,256,0,0,24,24,286528,0x7f39c020d800,0x7f38b4637580,12075944770365122,12075944770379348,12075944770694705,12075944770723248
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,901550,901555,4194304,256,0,0,20,24,288000,0x7f39c020d700,0x7f38b46375c0,12075944770744277,12075944770758225,12075944771928773,12075944771963483
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,901550,901555,4194304,256,0,0,32,24,294592,0x7f39c020d600,0x7f38b4637600,12075944771988359,12075944772002692,12075944772615006,12075944772649277
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,901550,901555,4194304,256,0,0,24,24,301184,0x7f39c020d500,0x7f38b4637640,12075944772672300,12075944772686045,12075944773006362,12075944773039402
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,901550,901555,4194304,256,0,0,12,24,304960,0x7f39c020d400,0x7f38b4637680,12075944773063307,12075944773076761,12075944773953553,12075944773983647
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,901550,901555,4194304,256,0,0,24,24,313600,0x7f39c020d300,0x7f38b46376c0,12075944774029853,12075944774044112,12075944774454988,12075944774486111
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,901550,901555,4194304,256,0,0,20,24,314816,0x7f39c020da00,0x7f38b4637700,12075944774508873,12075944774523511,12075944776071979,12075944776148440
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,901550,901555,4194304,256,0,0,20,24,317568,0x7f39c020d900,0x7f38b4637740,12075944776172916,12075944776187497,12075944776979651,12075944777055085
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,901550,901555,4194304,256,0,0,12,24,320320,0x7f39c020d800,0x7f38b4637780,12075944777077507,12075944777092130,12075944777505887,12075944777576695
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,901550,901555,4194304,256,0,0,12,24,324096,0x7f39c020d700,0x7f38b46377c0,12075944777593726,12075944777608446,12075944778766037,12075944778838329
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,901550,901555,4194304,256,0,0,12,24,328896,0x7f39c020d600,0x7f38b4637800,12075944778876851,12075944778891636,12075944779676110,12075944779751306
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,901550,901555,4194304,256,0,0,20,24,330112,0x7f39c020d500,0x7f38b4637840,12075944779777655,12075944779792749,12075944782842805,12075944782920806
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,901550,901555,4194304,256,0,0,20,24,332864,0x7f39c020d400,0x7f38b4637880,12075944782945763,12075944782960404,12075944784501192,12075944784576333
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,901550,901555,4194304,256,0,0,12,24,335616,0x7f39c020d300,0x7f38b46378c0,12075944784601800,12075944784617031,12075944785405985,12075944785479482
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,901550,901555,4194304,256,0,0,12,24,339392,0x7f39c020da00,0x7f38b4637900,12075944785501442,12075944785515904,12075944787796046,12075944787870626
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,901550,901555,4194304,256,0,0,12,24,344192,0x7f39c020d900,0x7f38b4637940,12075944787905671,12075944787920045,12075944789455233,12075944789532173
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,901550,901555,4194304,256,0,0,20,24,345408,0x7f39c020d800,0x7f38b4637980,12075944789559113,12075944789574112,12075944795626064,12075944795698623
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,901550,901555,4194304,256,0,0,20,24,348160,0x7f39c020d700,0x7f38b46379c0,12075944795722307,12075944795736623,12075944798777559,12075944798850441
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,901550,901555,4194304,256,0,0,12,24,350912,0x7f39c020d600,0x7f38b4637a00,12075944798874506,12075944798889559,12075944800428586,12075944800507731
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,901550,901555,4194304,256,0,0,12,24,0,0x7f39c020d500,0x7f38b4637a40,12075944800532858,12075944800549705,12075944805075270,12075944805148536
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 901550 901555 33554432 256 0 0 8 32 6464 0x0 0x7f38b4604180 12075944713040777 12075944713091723 12075944713416199 12075944713499991
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 901550 901555 32768 256 0 0 24 24 12480 0x0 0x7f38b4635100 12075944728070880 12075944728173211 12075944728179771 12075944728183740
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 4 901550 901555 4194304 256 0 0 24 24 12928 0x7f39c020d900 0x7f38b4635140 12075944728232350 12075944728248250 12075944728379609 12075944728383171
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 901550 901555 4194304 256 0 0 36 24 13632 0x7f39c020d800 0x7f38b4635180 12075944728428375 12075944728443448 12075944728690646 12075944728762806
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 8 901550 901555 4194304 256 0 0 28 24 14080 0x7f39c020d700 0x7f38b46351c0 12075944728786180 12075944728801204 12075944729049202 12075944729122384
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 10 901550 901555 4194304 256 0 0 24 24 14528 0x7f39c020d600 0x7f38b4635200 12075944729141019 12075944729155441 12075944729281360 12075944729284486
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 12 901550 901555 4194304 256 0 0 24 24 14976 0x7f39c020d500 0x7f38b4635240 12075944729312718 12075944729325679 12075944729450478 12075944729453750
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 14 901550 901555 4194304 256 0 0 24 24 15424 0x7f39c020d400 0x7f38b4635280 12075944729515605 12075944729531437 12075944729655116 12075944729658381
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 901550 901555 4194304 256 0 0 28 24 16128 0x7f39c020d300 0x7f38b46352c0 12075944729687675 12075944729701835 12075944729954153 12075944730022778
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 18 901550 901555 4194304 256 0 0 28 24 16832 0x7f39c020da00 0x7f38b4635300 12075944730051070 12075944730065832 12075944730310789 12075944730377427
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 20 901550 901555 4194304 256 0 0 24 24 17536 0x7f39c020d900 0x7f38b4635340 12075944730400329 12075944730415428 12075944730539907 12075944730543325
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 22 901550 901555 4194304 256 0 0 24 24 18240 0x7f39c020d800 0x7f38b4635380 12075944730572319 12075944730586307 12075944730710625 12075944730713972
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 24 901550 901555 4194304 256 0 0 24 24 18944 0x7f39c020d700 0x7f38b46353c0 12075944730752654 12075944730769025 12075944730893023 12075944730896492
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 901550 901555 4194304 256 0 0 28 24 19904 0x7f39c020d600 0x7f38b4635400 12075944730924113 12075944730937503 12075944731183421 12075944731258074
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 28 901550 901555 4194304 256 0 0 28 24 20608 0x7f39c020d500 0x7f38b4635440 12075944731283391 12075944731297339 12075944731546937 12075944731618904
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 30 901550 901555 4194304 256 0 0 24 24 21312 0x7f39c020d400 0x7f38b4635480 12075944731644792 12075944731658936 12075944731783415 12075944731786556
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 32 901550 901555 4194304 256 0 0 24 24 22016 0x7f39c020d300 0x7f38b46354c0 12075944731814818 12075944731828214 12075944731953653 12075944731957063
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 34 901550 901555 4194304 256 0 0 24 24 22720 0x7f39c020da00 0x7f38b4635500 12075944732005322 12075944732019092 12075944732143091 12075944732146434
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 901550 901555 4194304 256 0 0 28 24 23680 0x7f39c020d900 0x7f38b4635540 12075944732176500 12075944732191730 12075944732437968 12075944732509379
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 38 901550 901555 4194304 256 0 0 28 24 24384 0x7f39c020d800 0x7f38b4635580 12075944732530598 12075944732544367 12075944732789165 12075944732855803
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 40 901550 901555 4194304 256 0 0 24 24 25088 0x7f39c020d700 0x7f38b46355c0 12075944732878746 12075944732892843 12075944733017802 12075944733021220
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 42 901550 901555 4194304 256 0 0 24 24 25792 0x7f39c020d600 0x7f38b4635600 12075944733053610 12075944733069322 12075944733194280 12075944733197668
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 44 901550 901555 4194304 256 0 0 24 24 26496 0x7f39c020d500 0x7f38b4635640 12075944733240207 12075944733253960 12075944733377319 12075944733380718
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 901550 901555 4194304 256 0 0 28 24 27712 0x7f39c020d400 0x7f38b4635680 12075944733409482 12075944733423238 12075944733708355 12075944733780561
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 48 901550 901555 4194304 256 0 0 28 24 28416 0x7f39c020d300 0x7f38b46356c0 12075944733802572 12075944733817314 12075944734062432 12075944734134800
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 50 901550 901555 4194304 256 0 0 24 24 29120 0x7f39c020da00 0x7f38b4635700 12075944734159395 12075944734173151 12075944734297469 12075944734300658
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 52 901550 901555 4194304 256 0 0 24 24 30080 0x7f39c020d900 0x7f38b4635740 12075944734334341 12075944734348669 12075944734474108 12075944734477396
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 54 901550 901555 4194304 256 0 0 24 24 30784 0x7f39c020d800 0x7f38b4635780 12075944734514706 12075944734528507 12075944734653146 12075944734656579
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 901550 901555 4194304 256 0 0 28 24 32000 0x7f39c020d700 0x7f38b46357c0 12075944734684391 12075944734698425 12075944734946423 12075944734993436
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 58 901550 901555 4194304 256 0 0 28 24 32960 0x7f39c020d600 0x7f38b4635800 12075944735015657 12075944735029462 12075944735272020 12075944735322026
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 60 901550 901555 4194304 256 0 0 24 24 33920 0x7f39c020d500 0x7f38b4635840 12075944735350990 12075944735365939 12075944735490737 12075944735494086
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 62 901550 901555 4194304 256 0 0 24 24 34880 0x7f39c020d400 0x7f38b4635880 12075944735521266 12075944735534737 12075944735659376 12075944735662970
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 64 901550 901555 4194304 256 0 0 24 24 35840 0x7f39c020d300 0x7f38b46358c0 12075944735701752 12075944735715055 12075944735839854 12075944735843024
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 901550 901555 4194304 256 0 0 28 24 37312 0x7f39c020da00 0x7f38b4635900 12075944735873501 12075944735887214 12075944736136651 12075944736184469
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 68 901550 901555 4194304 256 0 0 28 24 38272 0x7f39c020d900 0x7f38b4635940 12075944736207472 12075944736221290 12075944736470728 12075944736517788
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 70 901550 901555 4194304 256 0 0 24 24 39232 0x7f39c020d800 0x7f38b4635980 12075944736541082 12075944736556007 12075944736680966 12075944736684518
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 72 901550 901555 4194304 256 0 0 24 24 40192 0x7f39c020d700 0x7f38b46359c0 12075944736712240 12075944736725605 12075944736850724 12075944736853963
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 74 901550 901555 4194304 256 0 0 24 24 41152 0x7f39c020d600 0x7f38b4635a00 12075944736891693 12075944736905603 12075944737029442 12075944737033377
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 901550 901555 4194304 256 0 0 28 24 42624 0x7f39c020d500 0x7f38b4635a40 12075944737060898 12075944737078402 12075944737326399 12075944737357930
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 78 901550 901555 4194304 256 0 0 28 24 43584 0x7f39c020d400 0x7f38b4635a80 12075944737381854 12075944737395678 12075944737639836 12075944737669238
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 80 901550 901555 4194304 256 0 0 24 24 44544 0x7f39c020d300 0x7f38b4635ac0 12075944737692422 12075944737704955 12075944737829594 12075944737833303
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 82 901550 901555 4194304 256 0 0 24 24 45760 0x7f39c020da00 0x7f38b4635b00 12075944737863660 12075944737878554 12075944738005112 12075944738008689
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 84 901550 901555 4194304 256 0 0 24 24 46720 0x7f39c020d900 0x7f38b4635b40 12075944738047822 12075944738063192 12075944738187670 12075944738190858
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 901550 901555 4194304 256 0 0 28 24 48448 0x7f39c020d800 0x7f38b4635b80 12075944738219431 12075944738233910 12075944738530227 12075944738559513
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 88 901550 901555 4194304 256 0 0 28 24 49408 0x7f39c020d700 0x7f38b4635bc0 12075944738576114 12075944738589746 12075944738872304 12075944738900697
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 90 901550 901555 4194304 256 0 0 24 24 50368 0x7f39c020d600 0x7f38b4635c00 12075944738922357 12075944738936783 12075944739061262 12075944739065423
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 92 901550 901555 4194304 256 0 0 24 24 51584 0x7f39c020d500 0x7f38b4635c40 12075944739096651 12075944739114221 12075944739240780 12075944739244286
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 94 901550 901555 4194304 256 0 0 24 24 52544 0x7f39c020d400 0x7f38b4635c80 12075944739282006 12075944739295659 12075944739420618 12075944739423899
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 901550 901555 4194304 256 0 0 28 24 54272 0x7f39c020d300 0x7f38b4635cc0 12075944739450649 12075944739465258 12075944739723975 12075944739748753
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 98 901550 901555 4194304 256 0 0 28 24 55488 0x7f39c020da00 0x7f38b4635d00 12075944739769762 12075944739783335 12075944740026852 12075944740052217
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 100 901550 901555 4194304 256 0 0 24 24 56704 0x7f39c020d900 0x7f38b4635d40 12075944740075831 12075944740090851 12075944740215490 12075944740218847
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 102 901550 901555 4194304 256 0 0 24 24 58176 0x7f39c020d800 0x7f38b4635d80 12075944740247931 12075944740261250 12075944740389728 12075944740393030
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 104 901550 901555 4194304 256 0 0 24 24 59392 0x7f39c020d700 0x7f38b4635dc0 12075944740430640 12075944740444928 12075944740569727 12075944740573025
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 901550 901555 4194304 256 0 0 28 24 61376 0x7f39c020d600 0x7f38b4635e00 12075944740600486 12075944740614686 12075944740874204 12075944740894132
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 108 901550 901555 4194304 256 0 0 28 24 62592 0x7f39c020d500 0x7f38b4635e40 12075944740916864 12075944740929083 12075944741176121 12075944741203837
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 110 901550 901555 4194304 256 0 0 24 24 63808 0x7f39c020d400 0x7f38b4635e80 12075944741228403 12075944741241240 12075944741366519 12075944741369826
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 112 901550 901555 4194304 256 0 0 24 24 65280 0x7f39c020d300 0x7f38b4635ec0 12075944741397688 12075944741411638 12075944741541397 12075944741544731
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 114 901550 901555 4194304 256 0 0 24 24 66496 0x7f39c020da00 0x7f38b4635f00 12075944741584144 12075944741597876 12075944741723315 12075944741726829
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 901550 901555 4194304 256 0 0 28 24 68480 0x7f39c020d900 0x7f38b4635f40 12075944741754982 12075944741769235 12075944742028432 12075944742053857
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 118 901550 901555 4194304 256 0 0 28 24 69696 0x7f39c020d800 0x7f38b4635f80 12075944742076569 12075944742090831 12075944742375629 12075944742399820
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 120 901550 901555 4194304 256 0 0 24 24 70912 0x7f39c020d700 0x7f38b4635fc0 12075944742422713 12075944742436908 12075944742562347 12075944742566049
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 122 901550 901555 4194304 256 0 0 24 24 72384 0x7f39c020d600 0x7f38b4636000 12075944742593841 12075944742607626 12075944742744105 12075944742747416
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 124 901550 901555 4194304 256 0 0 24 24 73600 0x7f39c020d500 0x7f38b4636040 12075944742786549 12075944742801384 12075944742926183 12075944742929424
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 901550 901555 4194304 256 0 0 28 24 75840 0x7f39c020d400 0x7f38b4636080 12075944742956434 12075944742970663 12075944743231140 12075944743265479
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 128 901550 901555 4194304 256 0 0 28 24 77056 0x7f39c020d300 0x7f38b46360c0 12075944743289584 12075944743304579 12075944743552417 12075944743583229
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 130 901550 901555 4194304 256 0 0 24 24 78272 0x7f39c020da00 0x7f38b4636100 12075944743605952 12075944743619936 12075944743745215 12075944743748567
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 132 901550 901555 4194304 256 0 0 24 24 80000 0x7f39c020d900 0x7f38b4636140 12075944743776408 12075944743790174 12075944743932093 12075944743935464
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 134 901550 901555 4194304 256 0 0 24 24 81216 0x7f39c020d800 0x7f38b4636180 12075944743972954 12075944743986972 12075944744112091 12075944744116110
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 901550 901555 4194304 256 0 0 28 24 83456 0x7f39c020d700 0x7f38b46361c0 12075944744143851 12075944744157691 12075944744410968 12075944744434161
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 138 901550 901555 4194304 256 0 0 28 24 84928 0x7f39c020d600 0x7f38b4636200 12075944744455841 12075944744469848 12075944744714325 12075944744737645
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 140 901550 901555 4194304 256 0 0 24 24 86400 0x7f39c020d500 0x7f38b4636240 12075944744762030 12075944744776885 12075944744901843 12075944744905366
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 142 901550 901555 4194304 256 0 0 24 24 88128 0x7f39c020d400 0x7f38b4636280 12075944744931986 12075944744945203 12075944745093841 12075944745097674
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 144 901550 901555 4194304 256 0 0 24 24 89600 0x7f39c020d300 0x7f38b46362c0 12075944745154900 12075944745169201 12075944745294319 12075944745297886
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 901550 901555 4194304 256 0 0 28 24 92096 0x7f39c020da00 0x7f38b4636300 12075944745324796 12075944745338959 12075944745593836 12075944745620065
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 148 901550 901555 4194304 256 0 0 28 24 93568 0x7f39c020d900 0x7f38b4636340 12075944745642336 12075944745656556 12075944745901833 12075944745926654
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 150 901550 901555 4194304 256 0 0 24 24 95040 0x7f39c020d800 0x7f38b4636380 12075944745948655 12075944745962153 12075944746087751 12075944746091561
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 152 901550 901555 4194304 256 0 0 24 24 96768 0x7f39c020d700 0x7f38b46363c0 12075944746121376 12075944746134791 12075944746292389 12075944746295670
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 154 901550 901555 4194304 256 0 0 24 24 98240 0x7f39c020d600 0x7f38b4636400 12075944746334472 12075944746348229 12075944746473188 12075944746476606
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 901550 901555 4194304 256 0 0 28 24 100736 0x7f39c020d500 0x7f38b4636440 12075944746505290 12075944746519907 12075944746776065 12075944746799466
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 158 901550 901555 4194304 256 0 0 28 24 102208 0x7f39c020d400 0x7f38b4636480 12075944746821057 12075944746834784 12075944747080222 12075944747110985
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 160 901550 901555 4194304 256 0 0 24 24 103680 0x7f39c020d300 0x7f38b46364c0 12075944747134148 12075944747148541 12075944747273820 12075944747277395
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 162 901550 901555 4194304 256 0 0 24 24 105664 0x7f39c020da00 0x7f38b4636500 12075944747306419 12075944747320059 12075944747485177 12075944747488707
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 164 901550 901555 4194304 256 0 0 24 24 107136 0x7f39c020d900 0x7f38b4636540 12075944747526768 12075944747540697 12075944747667416 12075944747670716
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 901550 901555 4194304 256 0 0 28 24 109888 0x7f39c020d800 0x7f38b4636580 12075944747700281 12075944747715095 12075944747970293 12075944747993576
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 168 901550 901555 4194304 256 0 0 28 24 111360 0x7f39c020d700 0x7f38b46365c0 12075944748021558 12075944748036052 12075944748285809 12075944748313460
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 170 901550 901555 4194304 256 0 0 24 24 112832 0x7f39c020d600 0x7f38b4636600 12075944748336593 12075944748350929 12075944748476048 12075944748479379
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 172 901550 901555 4194304 256 0 0 24 24 114816 0x7f39c020d500 0x7f38b4636640 12075944748508112 12075944748521327 12075944748694285 12075944748697714
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 174 901550 901555 4194304 256 0 0 24 24 116288 0x7f39c020d400 0x7f38b4636680 12075944748736366 12075944748750285 12075944748876524 12075944748879783
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 901550 901555 4194304 256 0 0 28 24 119040 0x7f39c020d300 0x7f38b46366c0 12075944748907454 12075944748921323 12075944749173641 12075944749201821
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 178 901550 901555 4194304 256 0 0 28 24 120768 0x7f39c020da00 0x7f38b4636700 12075944749224834 12075944749239400 12075944749483877 12075944749507660
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 180 901550 901555 4194304 256 0 0 24 24 122496 0x7f39c020d900 0x7f38b4636740 12075944749529580 12075944749543557 12075944749668996 12075944749672386
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 182 901550 901555 4194304 256 0 0 24 24 124736 0x7f39c020d800 0x7f38b4636780 12075944749700207 12075944749713635 12075944749896193 12075944749899638
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 184 901550 901555 4194304 256 0 0 24 24 126464 0x7f39c020d700 0x7f38b46367c0 12075944749937849 12075944749951233 12075944750077952 12075944750082077
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 901550 901555 4194304 256 0 0 20 24 127936 0x7f39c020d600 0x7f38b4636800 12075944750111201 12075944750125631 12075944750387708 12075944750411680
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 188 901550 901555 4194304 256 0 0 28 24 129664 0x7f39c020d500 0x7f38b4636840 12075944750434192 12075944750448028 12075944750727865 12075944750751712
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 190 901550 901555 4194304 256 0 0 24 24 131392 0x7f39c020d400 0x7f38b4636880 12075944750773262 12075944750785304 12075944750911383 12075944750915386
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 192 901550 901555 4194304 256 0 0 24 24 133632 0x7f39c020d300 0x7f38b46368c0 12075944750942947 12075944750957143 12075944751148181 12075944751154130
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 194 901550 901555 4194304 256 0 0 24 24 135360 0x7f39c020da00 0x7f38b4636900 12075944751189956 12075944751203860 12075944751332499 12075944751335807
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 901550 901555 4194304 256 0 0 20 24 136832 0x7f39c020d900 0x7f38b4636940 12075944751364891 12075944751379219 12075944751692655 12075944751716184
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 198 901550 901555 4194304 256 0 0 28 24 138560 0x7f39c020d800 0x7f38b4636980 12075944751737834 12075944751751055 12075944751998572 12075944752023295
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 200 901550 901555 4194304 256 0 0 24 24 140288 0x7f39c020d700 0x7f38b46369c0 12075944752052098 12075944752066732 12075944752192330 12075944752195635
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 202 901550 901555 4194304 256 0 0 24 24 142784 0x7f39c020d600 0x7f38b4636a00 12075944752223236 12075944752236650 12075944752445608 12075944752473491
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 204 901550 901555 4194304 256 0 0 24 24 144768 0x7f39c020d500 0x7f38b4636a40 12075944752506353 12075944752521127 12075944752649446 12075944752653115
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 901550 901555 4194304 256 0 0 20 24 145728 0x7f39c020d400 0x7f38b4636a80 12075944752680667 12075944752694085 12075944752999842 12075944753029375
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 208 901550 901555 4194304 256 0 0 28 24 147712 0x7f39c020d300 0x7f38b4636ac0 12075944753052227 12075944753065922 12075944753316479 12075944753344320
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 210 901550 901555 4194304 256 0 0 24 24 149696 0x7f39c020da00 0x7f38b4636b00 12075944753366211 12075944753379838 12075944753509117 12075944753512723
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 212 901550 901555 4194304 256 0 0 24 24 152192 0x7f39c020d900 0x7f38b4636b40 12075944753541256 12075944753554557 12075944753781434 12075944753809364
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 214 901550 901555 4194304 256 0 0 24 24 154176 0x7f39c020d800 0x7f38b4636b80 12075944753842736 12075944753857754 12075944753984792 12075944753988196
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 901550 901555 4194304 256 0 0 20 24 155648 0x7f39c020d700 0x7f38b4636bc0 12075944754021478 12075944754035192 12075944754392148 12075944754424608
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 218 901550 901555 4194304 256 0 0 28 24 157632 0x7f39c020d600 0x7f38b4636c00 12075944754447961 12075944754461428 12075944754714865 12075944754743069
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 220 901550 901555 4194304 256 0 0 24 24 159616 0x7f39c020d500 0x7f38b4636c40 12075944754763878 12075944754778225 12075944754907663 12075944754911282
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 222 901550 901555 4194304 256 0 0 24 24 162368 0x7f39c020d400 0x7f38b4636c80 12075944754940416 12075944754953903 12075944755230540 12075944755258638
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 224 901550 901555 4194304 256 0 0 24 24 164608 0x7f39c020d300 0x7f38b4636cc0 12075944755291489 12075944755305739 12075944755434698 12075944755438672
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 901550 901555 4194304 256 0 0 20 24 166336 0x7f39c020da00 0x7f38b4636d00 12075944755465422 12075944755479977 12075944755881253 12075944755904177
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 228 901550 901555 4194304 256 0 0 28 24 168576 0x7f39c020d900 0x7f38b4636d40 12075944755926108 12075944755939493 12075944756196450 12075944756227017
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 230 901550 901555 4194304 256 0 0 24 24 170816 0x7f39c020d800 0x7f38b4636d80 12075944756249990 12075944756264130 12075944756393568 12075944756397093
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 232 901550 901555 4194304 256 0 0 24 24 174080 0x7f39c020d700 0x7f38b4636dc0 12075944756426488 12075944756439648 12075944756717725 12075944756745661
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 234 901550 901555 4194304 256 0 0 24 24 176576 0x7f39c020d600 0x7f38b4636e00 12075944756778302 12075944756791484 12075944756927003 12075944756930294
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 901550 901555 4194304 256 0 0 20 24 177792 0x7f39c020d500 0x7f38b4636e40 12075944756956934 12075944756971163 12075944757393078 12075944757426296
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 238 901550 901555 4194304 256 0 0 28 24 180288 0x7f39c020d400 0x7f38b4636e80 12075944757449459 12075944757462518 12075944757726035 12075944757754035
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 240 901550 901555 4194304 256 0 0 24 24 182784 0x7f39c020d300 0x7f38b4636ec0 12075944757776326 12075944757788434 12075944757924753 12075944757928139
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 242 901550 901555 4194304 256 0 0 24 24 186304 0x7f39c020da00 0x7f38b4636f00 12075944757957273 12075944757970673 12075944758283629 12075944758315699
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 244 901550 901555 4194304 256 0 0 24 24 189312 0x7f39c020d900 0x7f38b4636f40 12075944758350413 12075944758365069 12075944758516107 12075944758519708
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 901550 901555 4194304 256 0 0 20 24 190784 0x7f39c020d800 0x7f38b4636f80 12075944758547139 12075944758561227 12075944759077061 12075944759107651
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 248 901550 901555 4194304 256 0 0 28 24 193792 0x7f39c020d700 0x7f38b4636fc0 12075944759129511 12075944759143461 12075944759437378 12075944759464774
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 250 901550 901555 4194304 256 0 0 24 24 196800 0x7f39c020d600 0x7f38b4637000 12075944759486485 12075944759500417 12075944759655616 12075944759658925
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 252 901550 901555 4194304 256 0 0 24 24 201088 0x7f39c020d500 0x7f38b4637040 12075944759686847 12075944759700095 12075944760109851 12075944760139528
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 254 901550 901555 4194304 256 0 0 24 24 204608 0x7f39c020d400 0x7f38b4637080 12075944760172510 12075944760186970 12075944760400248 12075944760428085
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 901550 901555 4194304 256 0 0 20 24 206080 0x7f39c020d300 0x7f38b46370c0 12075944760448773 12075944760463128 12075944761072882 12075944761103340
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 258 901550 901555 4194304 256 0 0 28 24 209600 0x7f39c020da00 0x7f38b4637100 12075944761124880 12075944761138321 12075944761469358 12075944761497883
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 260 901550 901555 4194304 256 0 0 24 24 213120 0x7f39c020d900 0x7f38b4637140 12075944761520785 12075944761534797 12075944761712875 12075944761716650
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 262 901550 901555 4194304 256 0 0 24 24 218176 0x7f39c020d800 0x7f38b4637180 12075944761743509 12075944761756555 12075944762210790 12075944762241595
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 264 901550 901555 4194304 256 0 0 24 24 222208 0x7f39c020d700 0x7f38b46371c0 12075944762274626 12075944762289349 12075944762487907 12075944762515965
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 901550 901555 4194304 256 0 0 20 24 223936 0x7f39c020d600 0x7f38b4637200 12075944762537084 12075944762551107 12075944763253180 12075944763285535
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 268 901550 901555 4194304 256 0 0 28 24 227968 0x7f39c020d500 0x7f38b4637240 12075944763307646 12075944763321019 12075944763692215 12075944763721796
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 270 901550 901555 4194304 256 0 0 24 24 232000 0x7f39c020d400 0x7f38b4637280 12075944763744468 12075944763757975 12075944763960533 12075944763992299
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 272 901550 901555 4194304 256 0 0 24 24 237824 0x7f39c020d300 0x7f38b46372c0 12075944764016854 12075944764029972 12075944764554927 12075944764590841
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 274 901550 901555 4194304 256 0 0 24 24 242368 0x7f39c020da00 0x7f38b4637300 12075944764626527 12075944764641006 12075944764864204 12075944764893343
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 901550 901555 4194304 256 0 0 20 24 243584 0x7f39c020d900 0x7f38b4637340 12075944764915615 12075944764929643 12075944765726755 12075944765757249
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 278 901550 901555 4194304 256 0 0 28 24 248128 0x7f39c020d800 0x7f38b4637380 12075944765779971 12075944765793954 12075944766212030 12075944766241439
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 280 901550 901555 4194304 256 0 0 24 24 252672 0x7f39c020d700 0x7f38b46373c0 12075944766264151 12075944766277469 12075944766503227 12075944766527951
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 282 901550 901555 4194304 256 0 0 24 24 259264 0x7f39c020d600 0x7f38b4637400 12075944766551485 12075944766564507 12075944767160821 12075944767192085
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 284 901550 901555 4194304 256 0 0 24 24 264832 0x7f39c020d500 0x7f38b4637440 12075944767227030 12075944767241140 12075944767510737 12075944767538820
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 901550 901555 4194304 256 0 0 20 24 266304 0x7f39c020d400 0x7f38b4637480 12075944767560510 12075944767574576 12075944768559527 12075944768591907
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 288 901550 901555 4194304 256 0 0 28 24 271872 0x7f39c020d300 0x7f38b46374c0 12075944768614900 12075944768626886 12075944769157921 12075944769188776
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 290 901550 901555 4194304 256 0 0 24 24 277440 0x7f39c020da00 0x7f38b4637500 12075944769212700 12075944769226880 12075944769498557 12075944769527445
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 292 901550 901555 4194304 256 0 0 12 24 279936 0x7f39c020d900 0x7f38b4637540 12075944769550198 12075944769562877 12075944770300149 12075944770330588
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 294 901550 901555 4194304 256 0 0 24 24 286528 0x7f39c020d800 0x7f38b4637580 12075944770365122 12075944770379348 12075944770694705 12075944770723248
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 901550 901555 4194304 256 0 0 20 24 288000 0x7f39c020d700 0x7f38b46375c0 12075944770744277 12075944770758225 12075944771928773 12075944771963483
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 298 901550 901555 4194304 256 0 0 32 24 294592 0x7f39c020d600 0x7f38b4637600 12075944771988359 12075944772002692 12075944772615006 12075944772649277
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 300 901550 901555 4194304 256 0 0 24 24 301184 0x7f39c020d500 0x7f38b4637640 12075944772672300 12075944772686045 12075944773006362 12075944773039402
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 302 901550 901555 4194304 256 0 0 12 24 304960 0x7f39c020d400 0x7f38b4637680 12075944773063307 12075944773076761 12075944773953553 12075944773983647
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 304 901550 901555 4194304 256 0 0 24 24 313600 0x7f39c020d300 0x7f38b46376c0 12075944774029853 12075944774044112 12075944774454988 12075944774486111
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 901550 901555 4194304 256 0 0 20 24 314816 0x7f39c020da00 0x7f38b4637700 12075944774508873 12075944774523511 12075944776071979 12075944776148440
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 308 901550 901555 4194304 256 0 0 20 24 317568 0x7f39c020d900 0x7f38b4637740 12075944776172916 12075944776187497 12075944776979651 12075944777055085
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 310 901550 901555 4194304 256 0 0 12 24 320320 0x7f39c020d800 0x7f38b4637780 12075944777077507 12075944777092130 12075944777505887 12075944777576695
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 312 901550 901555 4194304 256 0 0 12 24 324096 0x7f39c020d700 0x7f38b46377c0 12075944777593726 12075944777608446 12075944778766037 12075944778838329
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 314 901550 901555 4194304 256 0 0 12 24 328896 0x7f39c020d600 0x7f38b4637800 12075944778876851 12075944778891636 12075944779676110 12075944779751306
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 901550 901555 4194304 256 0 0 20 24 330112 0x7f39c020d500 0x7f38b4637840 12075944779777655 12075944779792749 12075944782842805 12075944782920806
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 318 901550 901555 4194304 256 0 0 20 24 332864 0x7f39c020d400 0x7f38b4637880 12075944782945763 12075944782960404 12075944784501192 12075944784576333
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 320 901550 901555 4194304 256 0 0 12 24 335616 0x7f39c020d300 0x7f38b46378c0 12075944784601800 12075944784617031 12075944785405985 12075944785479482
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 322 901550 901555 4194304 256 0 0 12 24 339392 0x7f39c020da00 0x7f38b4637900 12075944785501442 12075944785515904 12075944787796046 12075944787870626
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 324 901550 901555 4194304 256 0 0 12 24 344192 0x7f39c020d900 0x7f38b4637940 12075944787905671 12075944787920045 12075944789455233 12075944789532173
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 901550 901555 4194304 256 0 0 20 24 345408 0x7f39c020d800 0x7f38b4637980 12075944789559113 12075944789574112 12075944795626064 12075944795698623
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 328 901550 901555 4194304 256 0 0 20 24 348160 0x7f39c020d700 0x7f38b46379c0 12075944795722307 12075944795736623 12075944798777559 12075944798850441
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 330 901550 901555 4194304 256 0 0 12 24 350912 0x7f39c020d600 0x7f38b4637a00 12075944798874506 12075944798889559 12075944800428586 12075944800507731
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 332 901550 901555 4194304 256 0 0 12 24 0 0x7f39c020d500 0x7f38b4637a40 12075944800532858 12075944800549705 12075944805075270 12075944805148536
@@ -1,168 +0,0 @@
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",0,0,0,200200,200200,33554432,256,0,0,4,32,4160,0x0,0x7f3043a04280,380449,380449,524288,4718592,680823,76291444,17230491852189,17229803716158,17230639935378,17230640050298
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,200200,200200,32768,256,0,0,12,24,13888,0x0,0x7f3043a23f80,33388,33388,512,8192,6035,679208,17230645228208,17230639935378,17230645362261,17230645367004
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,200200,200200,4194304,256,0,0,12,24,14336,0x7f304aaf0380,0x7f3043a23fc0,164997,164997,65536,917504,142337,15939976,17230645404843,17230645362261,17230645745301,17230645747704
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,200200,200200,4194304,256,0,0,16,24,15040,0x7f304aaf0200,0x7f3043a24000,310782,310782,65536,1114112,169402,18938872,17230645790383,17230645745301,17230646166581,17230646169192
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,200200,200200,4194304,256,0,0,16,24,15488,0x7f304aaf0080,0x7f3043a24040,309055,309055,65536,917504,138787,15597044,17230646205871,17230646166581,17230646586741,17230646589191
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,200200,200200,4194304,256,0,0,12,24,15936,0x7f304844df00,0x7f3043a24080,166664,166664,65536,1048576,158657,17789628,17230646626190,17230646586741,17230646911542,17230646913782
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,200200,200200,4194304,256,0,0,12,24,16384,0x7f304844dd80,0x7f3043a240c0,165207,165207,65536,983040,146870,16529420,17230646951031,17230646911542,17230647232022,17230647234284
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,200200,200200,4194304,256,0,0,12,24,17088,0x7f304844dc00,0x7f3043a24100,163382,163382,65536,1114112,164070,18310496,17230647281852,17230647232022,17230647550902,17230647553285
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,200200,200200,4194304,256,0,0,16,24,17792,0x7f304844da80,0x7f3043a24140,310746,310746,65536,1310720,195675,21954640,17230647589284,17230647550902,17230647959222,17230647961684
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,200200,200200,4194304,256,0,0,16,24,18496,0x7f304844d900,0x7f3043a24180,309955,309955,65536,1179648,178000,19980700,17230647996103,17230647959222,17230648379382,17230648381793
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,200200,200200,4194304,256,0,0,16,24,19200,0x7f304844d780,0x7f3043a241c0,164552,164552,65536,1245184,187310,20956568,17230648415772,17230648379382,17230648705623,17230648707924
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,200200,200200,4194304,256,0,0,16,24,19904,0x7f304844d600,0x7f3043a24200,164868,164868,65536,1245184,186472,20881924,17230648744363,17230648705623,17230649029783,17230649032455
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,200200,200200,4194304,256,0,0,12,24,20608,0x7f304aaf0480,0x7f3043a24240,164240,164240,65536,1245184,189435,21222580,17230649076614,17230649029783,17230649349303,17230649351576
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,200200,200200,4194304,256,0,0,16,24,21312,0x7f304aaf0300,0x7f3043a24280,309929,309929,65536,1441792,215034,24095384,17230649387685,17230649349303,17230649759863,17230649762185
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,200200,200200,4194304,256,0,0,16,24,22016,0x7f304aaf0180,0x7f3043a242c0,307647,307647,65536,1310720,200666,22434260,17230649797864,17230649759863,17230650170904,17230650173514
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,200200,200200,4194304,256,0,0,16,24,22720,0x7f304aaf0000,0x7f3043a24300,163586,163586,65536,1376256,207773,23238464,17230650209263,17230650170904,17230650504024,17230650506475
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,200200,200200,4194304,256,0,0,12,24,23424,0x7f304844de80,0x7f3043a24340,164942,164942,65536,1441792,216749,24287348,17230650541944,17230650504024,17230650826104,17230650827996
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,200200,200200,4194304,256,0,0,12,24,24128,0x7f304844dd00,0x7f3043a24380,164520,164520,65536,1310720,195726,21940208,17230650871035,17230650826104,17230651127224,17230651128918
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,200200,200200,4194304,256,0,0,16,24,24832,0x7f304844db80,0x7f3043a243c0,307882,307882,65536,1572864,234252,26307684,17230651165997,17230651127224,17230651504984,17230651506828
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,200200,200200,4194304,256,0,0,16,24,25536,0x7f304844da00,0x7f3043a24400,310896,310896,65536,1441792,208880,23368856,17230651542017,17230651504984,17230651887545,17230651889357
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,200200,200200,4194304,256,0,0,12,24,26240,0x7f304844d880,0x7f3043a24440,164810,164810,65536,1507328,224531,25131788,17230651924537,17230651887545,17230652179545,17230652181240
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,200200,200200,4194304,256,0,0,12,24,26944,0x7f304844d700,0x7f3043a24480,163294,163294,65536,1638400,245619,27507160,17230652216799,17230652179545,17230652471065,17230652472682
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,200200,200200,4194304,256,0,0,12,24,27648,0x7f304aaf0580,0x7f3043a244c0,163210,163210,65536,1441792,216004,24124144,17230652514850,17230652471065,17230652763225,17230652765074
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,200200,200200,4194304,256,0,0,16,24,28608,0x7f304aaf0400,0x7f3043a24500,307768,307768,65536,1703936,252732,28277064,17230652802083,17230652763225,17230653140985,17230653142663
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,200200,200200,4194304,256,0,0,16,24,29312,0x7f304aaf0280,0x7f3043a24540,304086,304086,65536,1572864,234321,26218088,17230653179082,17230653140985,17230653518746,17230653520613
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,200200,200200,4194304,256,0,0,12,24,30016,0x7f304aaf0100,0x7f3043a24580,162989,162989,65536,1638400,246650,27623476,17230653556662,17230653518746,17230653813146,17230653814835
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,200200,200200,4194304,256,0,0,8,24,30976,0x7f304844df80,0x7f3043a245c0,163674,163674,65536,1835008,273034,30556028,17230653850624,17230653813146,17230654106426,17230654108447
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,200200,200200,4194304,256,0,0,12,24,31680,0x7f304844de00,0x7f3043a24600,162781,162781,65536,1507328,227231,25455360,17230654151736,17230654106426,17230654405306,17230654407189
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,200200,200200,4194304,256,0,0,16,24,32640,0x7f304844dc80,0x7f3043a24640,303999,303999,65536,1835008,275944,30880412,17230654443658,17230654405306,17230654781466,17230654783359
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,200200,200200,4194304,256,0,0,12,24,33600,0x7f304844db00,0x7f3043a24680,305947,305947,65536,1703936,248084,27796728,17230654818368,17230654781466,17230655160027,17230655161799
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,200200,200200,4194304,256,0,0,12,24,34560,0x7f304844d980,0x7f3043a246c0,163816,163816,65536,1769472,263321,29449376,17230655196958,17230655160027,17230655450907,17230655452751
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,200200,200200,4194304,256,0,0,8,24,35520,0x7f304844d800,0x7f3043a24700,164381,164381,65536,2031616,310346,34842180,17230655488450,17230655450907,17230655744187,17230655745903
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,200200,200200,4194304,256,0,0,12,24,36224,0x7f304844d680,0x7f3043a24740,162393,162393,65536,1638400,246872,27689624,17230655788202,17230655744187,17230656034587,17230656036355
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,200200,200200,4194304,256,0,0,12,24,37184,0x7f304aaf0500,0x7f3043a24780,305063,305063,65536,1966080,288906,32364660,17230656072214,17230656034587,17230656417947,17230656419925
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,200200,200200,4194304,256,0,0,12,24,38144,0x7f304aaf0380,0x7f3043a247c0,304605,304605,65536,1835008,272048,30506216,17230656454504,17230656417947,17230656796988,17230656798675
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,200200,200200,4194304,256,0,0,12,24,39104,0x7f304aaf0200,0x7f3043a24800,164055,164055,65536,1900544,283345,31762032,17230656833994,17230656796988,17230657089468,17230657091257
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,200200,200200,4194304,256,0,0,8,24,40320,0x7f304aaf0080,0x7f3043a24840,163927,163927,65536,2228224,330805,36976876,17230657127006,17230657089468,17230657381468,17230657383129
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,200200,200200,4194304,256,0,0,12,24,41280,0x7f304844df00,0x7f3043a24880,163689,163689,65536,1703936,254761,28566444,17230657425918,17230657381468,17230657678908,17230657680561
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,200200,200200,4194304,256,0,0,12,24,42240,0x7f304844dd80,0x7f3043a248c0,306597,306597,65536,2097152,309252,34620448,17230657716940,17230657678908,17230658071068,17230658072750
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,200200,200200,4194304,256,0,0,12,24,43200,0x7f304844dc00,0x7f3043a24900,303101,303101,65536,1966080,284071,31845608,17230658110509,17230658071068,17230658459389,17230658461080
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,200200,200200,4194304,256,0,0,8,24,44160,0x7f304844da80,0x7f3043a24940,163274,163274,65536,2031616,303814,34025836,17230658497439,17230658459389,17230658753789,17230658755552
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,200200,200200,4194304,256,0,0,12,24,45376,0x7f304844d900,0x7f3043a24980,163078,163078,65536,2424832,362779,40615960,17230658790871,17230658753789,17230659053149,17230659054954
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,200200,200200,4194304,256,0,0,12,24,46336,0x7f304844d780,0x7f3043a249c0,162814,162814,65536,1835008,282713,31710248,17230659096182,17230659053149,17230659344669,17230659346466
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,200200,200200,4194304,256,0,0,12,24,47552,0x7f304844d600,0x7f3043a24a00,305186,305186,65536,2228224,330869,37059636,17230659383245,17230659344669,17230659723549,17230659725415
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,200200,200200,4194304,256,0,0,12,24,48512,0x7f304aaf0480,0x7f3043a24a40,303044,303044,65536,2097152,319154,35718512,17230659761174,17230659723549,17230660105309,17230660107065
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,200200,200200,4194304,256,0,0,8,24,49472,0x7f304aaf0300,0x7f3043a24a80,162398,162398,65536,2162688,318541,35680988,17230660143284,17230660105309,17230660399070,17230660400817
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,200200,200200,4194304,256,0,0,12,24,50688,0x7f304aaf0180,0x7f3043a24ac0,162390,162390,65536,2621440,387979,43293004,17230660436996,17230660399070,17230660692510,17230660694419
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,200200,200200,4194304,256,0,0,12,24,51648,0x7f304aaf0000,0x7f3043a24b00,162254,162254,65536,1966080,293781,32887184,17230660737358,17230660692510,17230660993950,17230660995671
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,200200,200200,4194304,256,0,0,12,24,52864,0x7f304844de80,0x7f3043a24b40,304381,304381,65536,2359296,362011,40537000,17230661032060,17230660993950,17230661376030,17230661377821
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,200200,200200,4194304,256,0,0,12,24,54080,0x7f304844dd00,0x7f3043a24b80,300824,300824,65536,2228224,340641,38086916,17230661413910,17230661376030,17230661758750,17230661760430
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,200200,200200,4194304,256,0,0,8,24,55296,0x7f304844db80,0x7f3043a24bc0,163739,163739,65536,2293760,340272,38150796,17230661796869,17230661758750,17230662052671,17230662054293
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,200200,200200,4194304,256,0,0,12,24,56768,0x7f304844da00,0x7f3043a24c00,163150,163150,65536,2752512,416212,46578968,17230662102681,17230662052671,17230662361471,17230662363224
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,200200,200200,4194304,256,0,0,12,24,57728,0x7f304844d880,0x7f3043a24c40,162519,162519,65536,2031616,302684,33874464,17230662406313,17230662361471,17230662656511,17230662658476
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,200200,200200,4194304,256,0,0,12,24,58944,0x7f304844d700,0x7f3043a24c80,301350,301350,65536,2490368,371291,41560636,17230662696145,17230662656511,17230663033311,17230663034976
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,200200,200200,4194304,256,0,0,12,24,60160,0x7f304aaf0580,0x7f3043a24cc0,301811,301811,65536,2359296,367035,41186144,17230663070665,17230663033311,17230663412511,17230663414456
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,200200,200200,4194304,256,0,0,8,24,61376,0x7f304aaf0400,0x7f3043a24d00,164426,164426,65536,2424832,366459,40976124,17230663449875,17230663412511,17230663704512,17230663706208
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,200200,200200,4194304,256,0,0,12,24,62848,0x7f304aaf0280,0x7f3043a24d40,169254,169254,65536,2949120,447367,50132076,17230663742167,17230663704512,17230664002432,17230664004220
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,200200,200200,4194304,256,0,0,12,24,63808,0x7f304aaf0100,0x7f3043a24d80,161622,161622,65536,2162688,321182,35976040,17230664047569,17230664002432,17230664304512,17230664306512
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,200200,200200,4194304,256,0,0,12,24,65024,0x7f304844df80,0x7f3043a24dc0,301543,301543,65536,2621440,394729,44272664,17230664341681,17230664304512,17230664684352,17230664686001
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,200200,200200,4194304,256,0,0,12,24,66240,0x7f304844de00,0x7f3043a24e00,300674,300674,65536,2490368,361140,40421676,17230664723490,17230664684352,17230665063232,17230665065011
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,200200,200200,4194304,256,0,0,8,24,67456,0x7f304844dc80,0x7f3043a24e40,163561,163561,65536,2555904,388626,43548832,17230665099380,17230665063232,17230665356673,17230665358453
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,200200,200200,4194304,256,0,0,12,24,68928,0x7f304844db00,0x7f3043a24e80,176658,176658,65536,3145728,467697,52363120,17230665395112,17230665356673,17230665664833,17230665666525
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,200200,200200,4194304,256,0,0,12,24,70144,0x7f304844d980,0x7f3043a24ec0,162061,162061,65536,2228224,332411,37227340,17230665708934,17230665664833,17230665959873,17230665961677
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,200200,200200,4194304,256,0,0,12,24,71616,0x7f304844d800,0x7f3043a24f00,301757,301757,65536,2752512,405992,45449776,17230665997696,17230665959873,17230666347393,17230666349206
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,200200,200200,4194304,256,0,0,12,24,72832,0x7f304844d680,0x7f3043a24f40,302163,302163,65536,2621440,394241,44213880,17230666384636,17230666347393,17230666728833,17230666730596
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,200200,200200,4194304,256,0,0,8,24,74048,0x7f304aaf0500,0x7f3043a24f80,163134,163134,65536,2686976,395671,44328660,17230666766365,17230666728833,17230667027234,17230667029048
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,200200,200200,4194304,256,0,0,12,24,75776,0x7f304aaf0380,0x7f3043a24fc0,183085,183085,65536,3342336,502790,56305908,17230667064927,17230667027234,17230667335874,17230667337880
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,200200,200200,4194304,256,0,0,12,24,76992,0x7f304aaf0200,0x7f3043a25000,162329,162329,65536,2359296,358568,40040196,17230667393358,17230667335874,17230667630914,17230667632782
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,200200,200200,4194304,256,0,0,12,24,78464,0x7f304aaf0080,0x7f3043a25040,302855,302855,65536,2883584,428430,47990568,17230667668321,17230667630914,17230668015554,17230668017351
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,200200,200200,4194304,256,0,0,12,24,79936,0x7f304844df00,0x7f3043a25080,302573,302573,65536,2686976,427643,47905088,17230668053640,17230668015554,17230668395394,17230668397261
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,200200,200200,4194304,256,0,0,8,24,81408,0x7f304844dd80,0x7f3043a250c0,163165,163165,65536,2818048,424049,47520680,17230668431830,17230668395394,17230668690435,17230668692053
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,200200,200200,4194304,256,0,0,12,24,83136,0x7f304844dc00,0x7f3043a25100,192377,192377,65536,3538944,530344,59415628,17230668727422,17230668690435,17230669004035,17230669005804
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,200200,200200,4194304,256,0,0,12,24,84352,0x7f304844da80,0x7f3043a25140,162189,162189,65536,2424832,359056,40180288,17230669048283,17230669004035,17230669299715,17230669301546
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,200200,200200,4194304,256,0,0,12,24,85824,0x7f304844d900,0x7f3043a25180,299148,299148,65536,3014656,466159,52162984,17230669335955,17230669299715,17230669681795,17230669683546
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,200200,200200,4194304,256,0,0,12,24,87296,0x7f304844d780,0x7f3043a251c0,299390,299390,65536,2818048,418846,46990864,17230669719155,17230669681795,17230670063235,17230670065055
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,200200,200200,4194304,256,0,0,12,24,88768,0x7f304844d600,0x7f3043a25200,162379,162379,65536,2949120,439976,49337992,17230670100845,17230670063235,17230670376196,17230670377997
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,200200,200200,4194304,256,0,0,12,24,90752,0x7f304aaf0480,0x7f3043a25240,203013,203013,65536,3735552,554541,62113364,17230670414786,17230670376196,17230670697796,17230670699488
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,200200,200200,4194304,256,0,0,12,24,91968,0x7f304aaf0300,0x7f3043a25280,161987,161987,65536,2555904,386413,43254120,17230670742367,17230670697796,17230670997476,17230670999210
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,200200,200200,4194304,256,0,0,12,24,93440,0x7f304aaf0180,0x7f3043a252c0,300535,300535,65536,3145728,469581,52538292,17230671036439,17230670997476,17230671375876,17230671377540
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,200200,200200,4194304,256,0,0,12,24,94912,0x7f304aaf0000,0x7f3043a25300,301427,301427,65536,2949120,433291,48543928,17230671414069,17230671375876,17230671755236,17230671756960
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,200200,200200,4194304,256,0,0,12,24,96384,0x7f304844de80,0x7f3043a25340,162561,162561,65536,3080192,460079,51475600,17230671791419,17230671755236,17230672054917,17230672056482
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,200200,200200,4194304,256,0,0,12,24,98368,0x7f304844dd00,0x7f3043a25380,212409,212409,65536,3932160,591570,66242416,17230672093141,17230672054917,17230672387877,17230672389493
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,200200,200200,4194304,256,0,0,12,24,99584,0x7f304844db80,0x7f3043a253c0,161719,161719,65536,2621440,389122,43596944,17230672431242,17230672387877,17230672688837,17230672690605
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,200200,200200,4194304,256,0,0,12,24,101312,0x7f304844da00,0x7f3043a25400,300379,300379,65536,3276800,488517,54738508,17230672727604,17230672688837,17230673072037,17230673073624
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,200200,200200,4194304,256,0,0,12,24,102784,0x7f304844d880,0x7f3043a25440,297883,297883,65536,3080192,449765,50356596,17230673108833,17230673072037,17230673450117,17230673451924
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,200200,200200,4194304,256,0,0,12,24,104256,0x7f304844d700,0x7f3043a25480,161493,161493,65536,3211264,477024,53370300,17230673486713,17230673450117,17230673745318,17230673746986
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,200200,200200,4194304,256,0,0,12,24,106240,0x7f304aaf0580,0x7f3043a254c0,220023,220023,65536,4128768,617828,69239336,17230673782235,17230673745318,17230674076518,17230674081927
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,200200,200200,4194304,256,0,0,12,24,107712,0x7f304aaf0400,0x7f3043a25500,161459,161459,65536,2752512,411465,46098152,17230674122916,17230674076518,17230674379718,17230674381509
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,200200,200200,4194304,256,0,0,16,24,109440,0x7f304aaf0280,0x7f3043a25540,298409,298409,65536,3407872,517724,57935876,17230674418868,17230674379718,17230674760678,17230674762419
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,200200,200200,4194304,256,0,0,16,24,111168,0x7f304aaf0100,0x7f3043a25580,299541,299541,65536,3211264,476616,53414416,17230674798338,17230674760678,17230675144838,17230675146528
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,200200,200200,4194304,256,0,0,8,24,112896,0x7f304844df80,0x7f3043a255c0,163815,163815,65536,3276800,497035,55670300,17230675182997,17230675144838,17230675439719,17230675441320
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,200200,200200,4194304,256,0,0,12,24,115136,0x7f304844de00,0x7f3043a25600,229685,229685,65536,4325376,657224,73555604,17230675476389,17230675439719,17230675776839,17230675778431
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,200200,200200,4194304,256,0,0,12,24,116608,0x7f304844dc80,0x7f3043a25640,163348,163348,65536,2818048,466414,52258272,17230675820340,17230675776839,17230676072039,17230676073653
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,200200,200200,4194304,256,0,0,16,24,118336,0x7f304844db00,0x7f3043a25680,297423,297423,65536,3538944,528267,59108136,17230676110572,17230676072039,17230676450759,17230676452353
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,200200,200200,4194304,256,0,0,16,24,120064,0x7f304844d980,0x7f3043a256c0,299630,299630,65536,3407872,501737,56223044,17230676487242,17230676450759,17230676832679,17230676834373
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,200200,200200,4194304,256,0,0,12,24,121792,0x7f304844d800,0x7f3043a25700,164756,164756,65536,3407872,509975,57161456,17230676869312,17230676832679,17230677127080,17230677128875
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,200200,200200,4194304,256,0,0,12,24,124032,0x7f304844d680,0x7f3043a25740,239809,239809,65536,4521984,679768,76194020,17230677164144,17230677127080,17230677470600,17230677472145
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,200200,200200,4194304,256,0,0,12,24,125504,0x7f304aaf0500,0x7f3043a25780,161248,161248,65536,3014656,453378,50786952,17230677514114,17230677470600,17230677764520,17230677766227
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,200200,200200,4194304,256,0,0,12,24,127488,0x7f304aaf0380,0x7f3043a257c0,298955,298955,65536,3801088,564090,63207388,17230677800826,17230677764520,17230678149640,17230678151547
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,200200,200200,4194304,256,0,0,12,24,129216,0x7f304aaf0200,0x7f3043a25800,299656,299656,65536,3670016,545992,61167132,17230678188766,17230678149640,17230678540841,17230678542636
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,200200,200200,4194304,256,0,0,12,24,130944,0x7f304aaf0080,0x7f3043a25840,172181,172181,65536,3670016,570741,63968428,17230678578805,17230678540841,17230678842761,17230678844518
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,200200,200200,4194304,256,0,0,12,24,133440,0x7f304844df00,0x7f3043a25880,259422,259422,65536,4915200,770619,86269040,17230678881027,17230678842761,17230679198601,17230679200469
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,200200,200200,4194304,256,0,0,12,24,134912,0x7f304844dd80,0x7f3043a258c0,162327,162327,65536,3145728,480589,53960940,17230679243087,17230679198601,17230679492841,17230679494691
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,200200,200200,4194304,256,0,0,12,24,136896,0x7f304844dc00,0x7f3043a25900,296872,296872,65536,4063232,606108,67854676,17230679531400,17230679492841,17230679871081,17230679872640
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,200200,200200,4194304,256,0,0,12,24,138880,0x7f304844da80,0x7f3043a25940,300515,300515,65536,3932160,598661,67125152,17230679908579,17230679871081,17230680252682,17230680254480
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,200200,200200,4194304,256,0,0,12,24,140864,0x7f304844d900,0x7f3043a25980,181020,181020,65536,3932160,593125,66408984,17230680289629,17230680252682,17230680562602,17230680564271
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,200200,200200,4194304,256,0,0,12,24,143616,0x7f304844d780,0x7f3043a259c0,281027,281027,65536,5308416,795368,89012436,17230680598680,17230680562602,17230680933002,17230680934611
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,200200,200200,4194304,256,0,0,12,24,145344,0x7f304844d600,0x7f3043a25a00,162936,162936,65536,3342336,497839,55836584,17230680978600,17230680933002,17230681227722,17230681229463
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,200200,200200,4194304,256,0,0,12,24,147584,0x7f304aaf0480,0x7f3043a25a40,295625,295625,65536,4325376,663755,74413072,17230681264482,17230681227722,17230681607082,17230681608843
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,200200,200200,4194304,256,0,0,12,24,149568,0x7f304aaf0300,0x7f3043a25a80,296196,296196,65536,4194304,659883,73927896,17230681644582,17230681607082,17230681992363,17230681993963
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,200200,200200,4194304,256,0,0,12,24,151552,0x7f304aaf0180,0x7f3043a25ac0,188119,188119,65536,4194304,620549,69584384,17230682029472,17230681992363,17230682309003,17230682310714
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,200200,200200,4194304,256,0,0,12,24,154304,0x7f304aaf0000,0x7f3043a25b00,300049,300049,65536,5701632,853908,95480540,17230682347393,17230682309003,17230682692683,17230682694384
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,200200,200200,4194304,256,0,0,12,24,156288,0x7f304844de80,0x7f3043a25b40,172721,172721,65536,3735552,567893,63563072,17230682737242,17230682692683,17230682999723,17230683001475
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,200200,200200,4194304,256,0,0,12,24,158784,0x7f304844dd00,0x7f3043a25b80,303224,303224,65536,4849664,748988,83987644,17230683036704,17230682999723,17230683386763,17230683388445
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,200200,200200,4194304,256,0,0,12,24,161024,0x7f304844db80,0x7f3043a25bc0,297249,297249,65536,4718592,733006,82116460,17230683423594,17230683386763,17230683773324,17230683775034
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,200200,200200,4194304,256,0,0,12,24,163264,0x7f304844da00,0x7f3043a25c00,206320,206320,65536,4718592,709591,79526156,17230683809714,17230683773324,17230684095884,17230684097576
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,200200,200200,4194304,256,0,0,12,24,166528,0x7f304844d880,0x7f3043a25c40,341017,341017,65536,6488064,976130,109319488,17230684132555,17230684095884,17230684502444,17230684549074
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,200200,200200,4194304,256,0,0,12,24,168512,0x7f304844d700,0x7f3043a25c80,185361,185361,65536,4128768,620699,69464476,17230684568933,17230684502444,17230684845964,17230684847625
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,200200,200200,4194304,256,0,0,12,24,171264,0x7f304aaf0580,0x7f3043a25cc0,298934,298934,65536,5373952,839012,93967904,17230684884214,17230684845964,17230685228045,17230685229855
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,200200,200200,4194304,256,0,0,12,24,173760,0x7f304aaf0400,0x7f3043a25d00,297658,297658,65536,5242880,827941,92748532,17230685266134,17230685228045,17230685611085,17230685612635
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,200200,200200,4194304,256,0,0,12,24,176256,0x7f304aaf0280,0x7f3043a25d40,225782,225782,65536,5242880,788154,88196292,17230685648704,17230685611085,17230685949805,17230685951706
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,200200,200200,4194304,256,0,0,12,24,179776,0x7f304aaf0100,0x7f3043a25d80,380606,380606,65536,7274496,1119811,125408736,17230685987655,17230685949805,17230686400525,17230686425383
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,200200,200200,4194304,256,0,0,12,24,182272,0x7f304844df80,0x7f3043a25dc0,211722,211722,65536,4915200,738025,82566040,17230686445972,17230686400525,17230686747565,17230686749344
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,200200,200200,4194304,256,0,0,12,24,185536,0x7f304844de00,0x7f3043a25e00,307320,307320,65536,6422528,1032859,115627544,17230686786353,17230686747565,17230687137966,17230687183222
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,200200,200200,4194304,256,0,0,12,24,188544,0x7f304844dc80,0x7f3043a25e40,312244,312244,65536,6291456,1020415,114243404,17230687194732,17230687137966,17230687561166,17230687605971
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,200200,200200,4194304,256,0,0,12,24,191552,0x7f304844db00,0x7f3043a25e80,266393,266393,65536,6291456,947568,106119276,17230687618091,17230687561166,17230687949326,17230687950952
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,200200,200200,4194304,256,0,0,12,24,195840,0x7f304844d980,0x7f3043a25ec0,462715,462715,65536,8847360,1337508,149786796,17230687986441,17230687949326,17230688435566,17230688480557
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,200200,200200,4194304,256,0,0,12,24,198592,0x7f304844d800,0x7f3043a25f00,242937,242937,65536,5701632,866738,97080748,17230688501227,17230688435566,17230688816527,17230688818288
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,200200,200200,4194304,256,0,0,12,24,202368,0x7f304844d680,0x7f3043a25f40,335015,335015,65536,7471104,1186058,132734668,17230688854437,17230688816527,17230689224687,17230689267066
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,200200,200200,4194304,256,0,0,12,24,205888,0x7f304aaf0500,0x7f3043a25f80,331471,331471,65536,7340032,1151742,128884656,17230689278556,17230689224687,17230689664847,17230689683735
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,200200,200200,4194304,256,0,0,12,24,209408,0x7f304aaf0380,0x7f3043a25fc0,309825,309825,65536,7340032,1115054,124938416,17230689701474,17230689664847,17230690056527,17230690059505
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,200200,200200,4194304,256,0,0,12,24,214464,0x7f304aaf0200,0x7f3043a26000,543503,543503,65536,10420224,1588316,177868940,17230690095644,17230690056527,17230690599248,17230690645039
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,200200,200200,4194304,256,0,0,12,24,217728,0x7f304aaf0080,0x7f3043a26040,271372,271372,65536,6488064,974536,109116672,17230690665948,17230690599248,17230690996208,17230690997919
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,200200,200200,4194304,256,0,0,12,24,222016,0x7f304844df00,0x7f3043a26080,365683,365683,65536,8519680,1376984,154240176,17230691035068,17230690996208,17230691425328,17230691467866
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,200200,200200,4194304,256,0,0,12,24,226048,0x7f304844dd80,0x7f3043a260c0,365976,365976,65536,8388608,1305082,146148728,17230691480616,17230691425328,17230691884369,17230691926394
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,200200,200200,4194304,256,0,0,12,24,230080,0x7f304844dc00,0x7f3043a26100,348124,348124,65536,8388608,1291298,144662364,17230691939354,17230691884369,17230692323889,17230692366332
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,200200,200200,4194304,256,0,0,12,24,235904,0x7f304844da80,0x7f3043a26140,623980,623980,65536,11993088,1836605,205591236,17230692378292,17230692323889,17230692935889,17230692977705
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,200200,200200,4194304,256,0,0,12,24,239424,0x7f304844d900,0x7f3043a26180,304951,304951,65536,7274496,1110533,124392372,17230692997505,17230692935889,17230693353169,17230693354805
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,200200,200200,4194304,256,0,0,12,24,244224,0x7f304844d780,0x7f3043a261c0,400586,400586,65536,9568256,1541178,172764392,17230693391124,17230693353169,17230693805970,17230693825372
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,200200,200200,4194304,256,0,0,12,24,248768,0x7f304844d600,0x7f3043a26200,392332,392332,65536,9437184,1529711,171376408,17230693845912,17230693805970,17230694257170,17230694303339
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,200200,200200,4194304,256,0,0,12,24,253312,0x7f304aaf0480,0x7f3043a26240,388146,388146,65536,9437184,1469648,164484344,17230694316019,17230694257170,17230694731090,17230694778807
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,200200,200200,4194304,256,0,0,8,24,255552,0x7f304aaf0300,0x7f3043a26280,719766,719766,65536,16056320,2303086,257967128,17230694790756,17230694731090,17230695417171,17230695459498
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,200200,200200,4194304,256,0,0,12,24,259840,0x7f304aaf0180,0x7f3043a262c0,364701,364701,65536,8847360,1382246,154853484,17230695479888,17230695417171,17230695872531,17230695915166
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,200200,200200,4194304,256,0,0,12,24,265664,0x7f304aaf0000,0x7f3043a26300,470110,470110,65536,11665408,1844660,206507712,17230695926416,17230695872531,17230696401011,17230696443062
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,200200,200200,4194304,256,0,0,12,24,271232,0x7f304844de80,0x7f3043a26340,471545,471545,65536,11468800,1851812,207409196,17230696455551,17230696401011,17230696928692,17230696970847
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,200200,200200,4194304,256,0,0,8,24,273216,0x7f304844dd00,0x7f3043a26380,483811,483811,65536,14090240,2021606,226338528,17230696982547,17230696928692,17230697458292,17230697501033
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,200200,200200,4194304,256,0,0,8,24,275712,0x7f304844db80,0x7f3043a263c0,879889,879889,65536,19202048,2753994,308599076,17230697512613,17230697458292,17230698241972,17230698286822
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,200200,200200,4194304,256,0,0,12,24,280768,0x7f304844da00,0x7f3043a26400,427708,427708,65536,10420224,1591607,178282556,17230698308131,17230698241972,17230698742933,17230698787318
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,200200,200200,4194304,256,0,0,12,24,287616,0x7f304844d880,0x7f3043a26440,549980,549980,65536,13762560,2197575,246241116,17230698799068,17230698742933,17230699326133,17230699368713
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,200200,200200,4194304,256,0,0,12,24,294208,0x7f304844d700,0x7f3043a26480,552478,552478,65536,13565952,2185166,244649428,17230699382012,17230699326133,17230699903573,17230699945657
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,200200,200200,4194304,256,0,0,8,24,296960,0x7f304aaf0580,0x7f3043a264c0,564914,564914,65536,15466496,2224895,249406804,17230699957527,17230699903573,17230700478614,17230700520701
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,200200,200200,4194304,256,0,0,8,24,299968,0x7f304aaf0400,0x7f3043a26500,1043124,1043124,65536,22347776,3216547,360080408,17230700532951,17230700478614,17230701364534,17230701406957
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,200200,200200,4194304,256,0,0,8,24,302720,0x7f304aaf0280,0x7f3043a26540,722212,722212,65536,20250624,2908543,325873304,17230701427787,17230701364534,17230702037015,17230702055460
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,200200,200200,4194304,256,0,0,12,24,305472,0x7f304aaf0100,0x7f3043a26580,723510,723510,65536,20447232,2936703,328893760,17230702073769,17230702036702,17230702718462,17230702767021
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,200200,200200,4194304,256,0,0,12,24,308224,0x7f304844df80,0x7f3043a265c0,723272,723272,65536,19595264,2818913,315632604,17230702781000,17230702718462,17230703413820,17230703459832
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,200200,200200,4194304,256,0,0,8,24,310976,0x7f304844de00,0x7f3043a26600,726348,726348,65536,20381696,2930925,328342788,17230703472271,17230703413820,17230704094780,17230704138993
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,200200,200200,4194304,256,0,0,8,24,313216,0x7f304844dc80,0x7f3043a26640,1369640,1369640,65536,31522816,4519909,506148692,17230704150533,17230704094780,17230705206300,17230705252483
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,200200,200200,4194304,256,0,0,8,24,315968,0x7f304844db00,0x7f3043a26680,1370938,1370938,65536,38993920,5592869,626095372,17230705271823,17230705206300,17230706304380,17230706371203
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,200200,200200,4194304,256,0,0,12,24,318720,0x7f304844d980,0x7f3043a266c0,1373390,1373390,65536,39124992,5610953,628252916,17230706384022,17230706304380,17230707461020,17230707528141
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,200200,200200,4194304,256,0,0,12,24,321472,0x7f304844d800,0x7f3043a26700,1372439,1372439,65536,38469632,5509836,617207136,17230707540731,17230707461020,17230708605660,17230708675150
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,200200,200200,4194304,256,0,0,8,24,324224,0x7f304844d680,0x7f3043a26740,1377380,1377380,65536,39059456,5596109,626891208,17230708687160,17230708605660,17230709732060,17230709797290
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,200200,200200,4194304,256,0,0,8,24,326464,0x7f304aaf0500,0x7f3043a26780,2663674,2663674,65536,60489728,8650049,968941056,17230709808880,17230709732060,17230711703260,17230711780507
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,200200,200200,4194304,256,0,0,8,24,329216,0x7f304aaf0380,0x7f3043a267c0,2671394,2671394,65536,77266944,11058204,1238333104,17230711799986,17230711703260,17230713656380,17230713724154
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,200200,200200,4194304,256,0,0,12,24,331968,0x7f304aaf0200,0x7f3043a26800,2670519,2670519,65536,77398016,11074576,1240054236,17230713736004,17230713656380,17230715655900,17230715729250
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,200200,200200,4194304,256,0,0,12,24,334720,0x7f304aaf0080,0x7f3043a26840,2669734,2669734,65536,76218368,10908447,1221550176,17230715742109,17230715655900,17230717653820,17230717718866
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,200200,200200,4194304,256,0,0,8,24,337472,0x7f304844df00,0x7f3043a26880,2674843,2674843,65536,77332480,11063591,1239190112,17230717730885,17230717653820,17230719594140,17230719666533
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,200200,200200,4194304,256,0,0,8,24,0,0x7f304844dd80,0x7f3043a268c0,5257525,5257525,65536,120258560,17185373,1925585988,17230719679693,17230719594140,17230723230300,17230723302965
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 200200 200200 33554432 256 0 0 4 32 4160 0x0 0x7f3043a04280 380449 380449 524288 4718592 680823 76291444 17230491852189 17229803716158 17230639935378 17230640050298
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 200200 200200 32768 256 0 0 12 24 13888 0x0 0x7f3043a23f80 33388 33388 512 8192 6035 679208 17230645228208 17230639935378 17230645362261 17230645367004
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 5 200200 200200 4194304 256 0 0 12 24 14336 0x7f304aaf0380 0x7f3043a23fc0 164997 164997 65536 917504 142337 15939976 17230645404843 17230645362261 17230645745301 17230645747704
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 200200 200200 4194304 256 0 0 16 24 15040 0x7f304aaf0200 0x7f3043a24000 310782 310782 65536 1114112 169402 18938872 17230645790383 17230645745301 17230646166581 17230646169192
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 11 200200 200200 4194304 256 0 0 16 24 15488 0x7f304aaf0080 0x7f3043a24040 309055 309055 65536 917504 138787 15597044 17230646205871 17230646166581 17230646586741 17230646589191
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 14 200200 200200 4194304 256 0 0 12 24 15936 0x7f304844df00 0x7f3043a24080 166664 166664 65536 1048576 158657 17789628 17230646626190 17230646586741 17230646911542 17230646913782
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 17 200200 200200 4194304 256 0 0 12 24 16384 0x7f304844dd80 0x7f3043a240c0 165207 165207 65536 983040 146870 16529420 17230646951031 17230646911542 17230647232022 17230647234284
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 20 200200 200200 4194304 256 0 0 12 24 17088 0x7f304844dc00 0x7f3043a24100 163382 163382 65536 1114112 164070 18310496 17230647281852 17230647232022 17230647550902 17230647553285
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 200200 200200 4194304 256 0 0 16 24 17792 0x7f304844da80 0x7f3043a24140 310746 310746 65536 1310720 195675 21954640 17230647589284 17230647550902 17230647959222 17230647961684
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 26 200200 200200 4194304 256 0 0 16 24 18496 0x7f304844d900 0x7f3043a24180 309955 309955 65536 1179648 178000 19980700 17230647996103 17230647959222 17230648379382 17230648381793
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 29 200200 200200 4194304 256 0 0 16 24 19200 0x7f304844d780 0x7f3043a241c0 164552 164552 65536 1245184 187310 20956568 17230648415772 17230648379382 17230648705623 17230648707924
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 32 200200 200200 4194304 256 0 0 16 24 19904 0x7f304844d600 0x7f3043a24200 164868 164868 65536 1245184 186472 20881924 17230648744363 17230648705623 17230649029783 17230649032455
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 35 200200 200200 4194304 256 0 0 12 24 20608 0x7f304aaf0480 0x7f3043a24240 164240 164240 65536 1245184 189435 21222580 17230649076614 17230649029783 17230649349303 17230649351576
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 200200 200200 4194304 256 0 0 16 24 21312 0x7f304aaf0300 0x7f3043a24280 309929 309929 65536 1441792 215034 24095384 17230649387685 17230649349303 17230649759863 17230649762185
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 41 200200 200200 4194304 256 0 0 16 24 22016 0x7f304aaf0180 0x7f3043a242c0 307647 307647 65536 1310720 200666 22434260 17230649797864 17230649759863 17230650170904 17230650173514
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 44 200200 200200 4194304 256 0 0 16 24 22720 0x7f304aaf0000 0x7f3043a24300 163586 163586 65536 1376256 207773 23238464 17230650209263 17230650170904 17230650504024 17230650506475
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 47 200200 200200 4194304 256 0 0 12 24 23424 0x7f304844de80 0x7f3043a24340 164942 164942 65536 1441792 216749 24287348 17230650541944 17230650504024 17230650826104 17230650827996
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 50 200200 200200 4194304 256 0 0 12 24 24128 0x7f304844dd00 0x7f3043a24380 164520 164520 65536 1310720 195726 21940208 17230650871035 17230650826104 17230651127224 17230651128918
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 200200 200200 4194304 256 0 0 16 24 24832 0x7f304844db80 0x7f3043a243c0 307882 307882 65536 1572864 234252 26307684 17230651165997 17230651127224 17230651504984 17230651506828
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 56 200200 200200 4194304 256 0 0 16 24 25536 0x7f304844da00 0x7f3043a24400 310896 310896 65536 1441792 208880 23368856 17230651542017 17230651504984 17230651887545 17230651889357
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 59 200200 200200 4194304 256 0 0 12 24 26240 0x7f304844d880 0x7f3043a24440 164810 164810 65536 1507328 224531 25131788 17230651924537 17230651887545 17230652179545 17230652181240
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 62 200200 200200 4194304 256 0 0 12 24 26944 0x7f304844d700 0x7f3043a24480 163294 163294 65536 1638400 245619 27507160 17230652216799 17230652179545 17230652471065 17230652472682
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 65 200200 200200 4194304 256 0 0 12 24 27648 0x7f304aaf0580 0x7f3043a244c0 163210 163210 65536 1441792 216004 24124144 17230652514850 17230652471065 17230652763225 17230652765074
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 200200 200200 4194304 256 0 0 16 24 28608 0x7f304aaf0400 0x7f3043a24500 307768 307768 65536 1703936 252732 28277064 17230652802083 17230652763225 17230653140985 17230653142663
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 71 200200 200200 4194304 256 0 0 16 24 29312 0x7f304aaf0280 0x7f3043a24540 304086 304086 65536 1572864 234321 26218088 17230653179082 17230653140985 17230653518746 17230653520613
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 74 200200 200200 4194304 256 0 0 12 24 30016 0x7f304aaf0100 0x7f3043a24580 162989 162989 65536 1638400 246650 27623476 17230653556662 17230653518746 17230653813146 17230653814835
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 77 200200 200200 4194304 256 0 0 8 24 30976 0x7f304844df80 0x7f3043a245c0 163674 163674 65536 1835008 273034 30556028 17230653850624 17230653813146 17230654106426 17230654108447
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 80 200200 200200 4194304 256 0 0 12 24 31680 0x7f304844de00 0x7f3043a24600 162781 162781 65536 1507328 227231 25455360 17230654151736 17230654106426 17230654405306 17230654407189
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 200200 200200 4194304 256 0 0 16 24 32640 0x7f304844dc80 0x7f3043a24640 303999 303999 65536 1835008 275944 30880412 17230654443658 17230654405306 17230654781466 17230654783359
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 86 200200 200200 4194304 256 0 0 12 24 33600 0x7f304844db00 0x7f3043a24680 305947 305947 65536 1703936 248084 27796728 17230654818368 17230654781466 17230655160027 17230655161799
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 89 200200 200200 4194304 256 0 0 12 24 34560 0x7f304844d980 0x7f3043a246c0 163816 163816 65536 1769472 263321 29449376 17230655196958 17230655160027 17230655450907 17230655452751
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 92 200200 200200 4194304 256 0 0 8 24 35520 0x7f304844d800 0x7f3043a24700 164381 164381 65536 2031616 310346 34842180 17230655488450 17230655450907 17230655744187 17230655745903
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 95 200200 200200 4194304 256 0 0 12 24 36224 0x7f304844d680 0x7f3043a24740 162393 162393 65536 1638400 246872 27689624 17230655788202 17230655744187 17230656034587 17230656036355
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 200200 200200 4194304 256 0 0 12 24 37184 0x7f304aaf0500 0x7f3043a24780 305063 305063 65536 1966080 288906 32364660 17230656072214 17230656034587 17230656417947 17230656419925
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 101 200200 200200 4194304 256 0 0 12 24 38144 0x7f304aaf0380 0x7f3043a247c0 304605 304605 65536 1835008 272048 30506216 17230656454504 17230656417947 17230656796988 17230656798675
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 104 200200 200200 4194304 256 0 0 12 24 39104 0x7f304aaf0200 0x7f3043a24800 164055 164055 65536 1900544 283345 31762032 17230656833994 17230656796988 17230657089468 17230657091257
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 107 200200 200200 4194304 256 0 0 8 24 40320 0x7f304aaf0080 0x7f3043a24840 163927 163927 65536 2228224 330805 36976876 17230657127006 17230657089468 17230657381468 17230657383129
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 110 200200 200200 4194304 256 0 0 12 24 41280 0x7f304844df00 0x7f3043a24880 163689 163689 65536 1703936 254761 28566444 17230657425918 17230657381468 17230657678908 17230657680561
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 200200 200200 4194304 256 0 0 12 24 42240 0x7f304844dd80 0x7f3043a248c0 306597 306597 65536 2097152 309252 34620448 17230657716940 17230657678908 17230658071068 17230658072750
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 116 200200 200200 4194304 256 0 0 12 24 43200 0x7f304844dc00 0x7f3043a24900 303101 303101 65536 1966080 284071 31845608 17230658110509 17230658071068 17230658459389 17230658461080
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 119 200200 200200 4194304 256 0 0 8 24 44160 0x7f304844da80 0x7f3043a24940 163274 163274 65536 2031616 303814 34025836 17230658497439 17230658459389 17230658753789 17230658755552
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 122 200200 200200 4194304 256 0 0 12 24 45376 0x7f304844d900 0x7f3043a24980 163078 163078 65536 2424832 362779 40615960 17230658790871 17230658753789 17230659053149 17230659054954
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 125 200200 200200 4194304 256 0 0 12 24 46336 0x7f304844d780 0x7f3043a249c0 162814 162814 65536 1835008 282713 31710248 17230659096182 17230659053149 17230659344669 17230659346466
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 200200 200200 4194304 256 0 0 12 24 47552 0x7f304844d600 0x7f3043a24a00 305186 305186 65536 2228224 330869 37059636 17230659383245 17230659344669 17230659723549 17230659725415
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 131 200200 200200 4194304 256 0 0 12 24 48512 0x7f304aaf0480 0x7f3043a24a40 303044 303044 65536 2097152 319154 35718512 17230659761174 17230659723549 17230660105309 17230660107065
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 134 200200 200200 4194304 256 0 0 8 24 49472 0x7f304aaf0300 0x7f3043a24a80 162398 162398 65536 2162688 318541 35680988 17230660143284 17230660105309 17230660399070 17230660400817
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 137 200200 200200 4194304 256 0 0 12 24 50688 0x7f304aaf0180 0x7f3043a24ac0 162390 162390 65536 2621440 387979 43293004 17230660436996 17230660399070 17230660692510 17230660694419
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 140 200200 200200 4194304 256 0 0 12 24 51648 0x7f304aaf0000 0x7f3043a24b00 162254 162254 65536 1966080 293781 32887184 17230660737358 17230660692510 17230660993950 17230660995671
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 200200 200200 4194304 256 0 0 12 24 52864 0x7f304844de80 0x7f3043a24b40 304381 304381 65536 2359296 362011 40537000 17230661032060 17230660993950 17230661376030 17230661377821
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 146 200200 200200 4194304 256 0 0 12 24 54080 0x7f304844dd00 0x7f3043a24b80 300824 300824 65536 2228224 340641 38086916 17230661413910 17230661376030 17230661758750 17230661760430
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 149 200200 200200 4194304 256 0 0 8 24 55296 0x7f304844db80 0x7f3043a24bc0 163739 163739 65536 2293760 340272 38150796 17230661796869 17230661758750 17230662052671 17230662054293
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 152 200200 200200 4194304 256 0 0 12 24 56768 0x7f304844da00 0x7f3043a24c00 163150 163150 65536 2752512 416212 46578968 17230662102681 17230662052671 17230662361471 17230662363224
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 155 200200 200200 4194304 256 0 0 12 24 57728 0x7f304844d880 0x7f3043a24c40 162519 162519 65536 2031616 302684 33874464 17230662406313 17230662361471 17230662656511 17230662658476
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 200200 200200 4194304 256 0 0 12 24 58944 0x7f304844d700 0x7f3043a24c80 301350 301350 65536 2490368 371291 41560636 17230662696145 17230662656511 17230663033311 17230663034976
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 161 200200 200200 4194304 256 0 0 12 24 60160 0x7f304aaf0580 0x7f3043a24cc0 301811 301811 65536 2359296 367035 41186144 17230663070665 17230663033311 17230663412511 17230663414456
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 164 200200 200200 4194304 256 0 0 8 24 61376 0x7f304aaf0400 0x7f3043a24d00 164426 164426 65536 2424832 366459 40976124 17230663449875 17230663412511 17230663704512 17230663706208
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 167 200200 200200 4194304 256 0 0 12 24 62848 0x7f304aaf0280 0x7f3043a24d40 169254 169254 65536 2949120 447367 50132076 17230663742167 17230663704512 17230664002432 17230664004220
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 170 200200 200200 4194304 256 0 0 12 24 63808 0x7f304aaf0100 0x7f3043a24d80 161622 161622 65536 2162688 321182 35976040 17230664047569 17230664002432 17230664304512 17230664306512
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 200200 200200 4194304 256 0 0 12 24 65024 0x7f304844df80 0x7f3043a24dc0 301543 301543 65536 2621440 394729 44272664 17230664341681 17230664304512 17230664684352 17230664686001
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 176 200200 200200 4194304 256 0 0 12 24 66240 0x7f304844de00 0x7f3043a24e00 300674 300674 65536 2490368 361140 40421676 17230664723490 17230664684352 17230665063232 17230665065011
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 179 200200 200200 4194304 256 0 0 8 24 67456 0x7f304844dc80 0x7f3043a24e40 163561 163561 65536 2555904 388626 43548832 17230665099380 17230665063232 17230665356673 17230665358453
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 182 200200 200200 4194304 256 0 0 12 24 68928 0x7f304844db00 0x7f3043a24e80 176658 176658 65536 3145728 467697 52363120 17230665395112 17230665356673 17230665664833 17230665666525
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 185 200200 200200 4194304 256 0 0 12 24 70144 0x7f304844d980 0x7f3043a24ec0 162061 162061 65536 2228224 332411 37227340 17230665708934 17230665664833 17230665959873 17230665961677
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 200200 200200 4194304 256 0 0 12 24 71616 0x7f304844d800 0x7f3043a24f00 301757 301757 65536 2752512 405992 45449776 17230665997696 17230665959873 17230666347393 17230666349206
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 191 200200 200200 4194304 256 0 0 12 24 72832 0x7f304844d680 0x7f3043a24f40 302163 302163 65536 2621440 394241 44213880 17230666384636 17230666347393 17230666728833 17230666730596
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 194 200200 200200 4194304 256 0 0 8 24 74048 0x7f304aaf0500 0x7f3043a24f80 163134 163134 65536 2686976 395671 44328660 17230666766365 17230666728833 17230667027234 17230667029048
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 197 200200 200200 4194304 256 0 0 12 24 75776 0x7f304aaf0380 0x7f3043a24fc0 183085 183085 65536 3342336 502790 56305908 17230667064927 17230667027234 17230667335874 17230667337880
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 200 200200 200200 4194304 256 0 0 12 24 76992 0x7f304aaf0200 0x7f3043a25000 162329 162329 65536 2359296 358568 40040196 17230667393358 17230667335874 17230667630914 17230667632782
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 200200 200200 4194304 256 0 0 12 24 78464 0x7f304aaf0080 0x7f3043a25040 302855 302855 65536 2883584 428430 47990568 17230667668321 17230667630914 17230668015554 17230668017351
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 206 200200 200200 4194304 256 0 0 12 24 79936 0x7f304844df00 0x7f3043a25080 302573 302573 65536 2686976 427643 47905088 17230668053640 17230668015554 17230668395394 17230668397261
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 209 200200 200200 4194304 256 0 0 8 24 81408 0x7f304844dd80 0x7f3043a250c0 163165 163165 65536 2818048 424049 47520680 17230668431830 17230668395394 17230668690435 17230668692053
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 212 200200 200200 4194304 256 0 0 12 24 83136 0x7f304844dc00 0x7f3043a25100 192377 192377 65536 3538944 530344 59415628 17230668727422 17230668690435 17230669004035 17230669005804
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 215 200200 200200 4194304 256 0 0 12 24 84352 0x7f304844da80 0x7f3043a25140 162189 162189 65536 2424832 359056 40180288 17230669048283 17230669004035 17230669299715 17230669301546
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 200200 200200 4194304 256 0 0 12 24 85824 0x7f304844d900 0x7f3043a25180 299148 299148 65536 3014656 466159 52162984 17230669335955 17230669299715 17230669681795 17230669683546
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 221 200200 200200 4194304 256 0 0 12 24 87296 0x7f304844d780 0x7f3043a251c0 299390 299390 65536 2818048 418846 46990864 17230669719155 17230669681795 17230670063235 17230670065055
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 224 200200 200200 4194304 256 0 0 12 24 88768 0x7f304844d600 0x7f3043a25200 162379 162379 65536 2949120 439976 49337992 17230670100845 17230670063235 17230670376196 17230670377997
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 227 200200 200200 4194304 256 0 0 12 24 90752 0x7f304aaf0480 0x7f3043a25240 203013 203013 65536 3735552 554541 62113364 17230670414786 17230670376196 17230670697796 17230670699488
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 230 200200 200200 4194304 256 0 0 12 24 91968 0x7f304aaf0300 0x7f3043a25280 161987 161987 65536 2555904 386413 43254120 17230670742367 17230670697796 17230670997476 17230670999210
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 200200 200200 4194304 256 0 0 12 24 93440 0x7f304aaf0180 0x7f3043a252c0 300535 300535 65536 3145728 469581 52538292 17230671036439 17230670997476 17230671375876 17230671377540
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 236 200200 200200 4194304 256 0 0 12 24 94912 0x7f304aaf0000 0x7f3043a25300 301427 301427 65536 2949120 433291 48543928 17230671414069 17230671375876 17230671755236 17230671756960
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 239 200200 200200 4194304 256 0 0 12 24 96384 0x7f304844de80 0x7f3043a25340 162561 162561 65536 3080192 460079 51475600 17230671791419 17230671755236 17230672054917 17230672056482
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 242 200200 200200 4194304 256 0 0 12 24 98368 0x7f304844dd00 0x7f3043a25380 212409 212409 65536 3932160 591570 66242416 17230672093141 17230672054917 17230672387877 17230672389493
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 245 200200 200200 4194304 256 0 0 12 24 99584 0x7f304844db80 0x7f3043a253c0 161719 161719 65536 2621440 389122 43596944 17230672431242 17230672387877 17230672688837 17230672690605
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 200200 200200 4194304 256 0 0 12 24 101312 0x7f304844da00 0x7f3043a25400 300379 300379 65536 3276800 488517 54738508 17230672727604 17230672688837 17230673072037 17230673073624
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 251 200200 200200 4194304 256 0 0 12 24 102784 0x7f304844d880 0x7f3043a25440 297883 297883 65536 3080192 449765 50356596 17230673108833 17230673072037 17230673450117 17230673451924
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 254 200200 200200 4194304 256 0 0 12 24 104256 0x7f304844d700 0x7f3043a25480 161493 161493 65536 3211264 477024 53370300 17230673486713 17230673450117 17230673745318 17230673746986
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 257 200200 200200 4194304 256 0 0 12 24 106240 0x7f304aaf0580 0x7f3043a254c0 220023 220023 65536 4128768 617828 69239336 17230673782235 17230673745318 17230674076518 17230674081927
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 260 200200 200200 4194304 256 0 0 12 24 107712 0x7f304aaf0400 0x7f3043a25500 161459 161459 65536 2752512 411465 46098152 17230674122916 17230674076518 17230674379718 17230674381509
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 200200 200200 4194304 256 0 0 16 24 109440 0x7f304aaf0280 0x7f3043a25540 298409 298409 65536 3407872 517724 57935876 17230674418868 17230674379718 17230674760678 17230674762419
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 266 200200 200200 4194304 256 0 0 16 24 111168 0x7f304aaf0100 0x7f3043a25580 299541 299541 65536 3211264 476616 53414416 17230674798338 17230674760678 17230675144838 17230675146528
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 269 200200 200200 4194304 256 0 0 8 24 112896 0x7f304844df80 0x7f3043a255c0 163815 163815 65536 3276800 497035 55670300 17230675182997 17230675144838 17230675439719 17230675441320
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 272 200200 200200 4194304 256 0 0 12 24 115136 0x7f304844de00 0x7f3043a25600 229685 229685 65536 4325376 657224 73555604 17230675476389 17230675439719 17230675776839 17230675778431
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 275 200200 200200 4194304 256 0 0 12 24 116608 0x7f304844dc80 0x7f3043a25640 163348 163348 65536 2818048 466414 52258272 17230675820340 17230675776839 17230676072039 17230676073653
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 200200 200200 4194304 256 0 0 16 24 118336 0x7f304844db00 0x7f3043a25680 297423 297423 65536 3538944 528267 59108136 17230676110572 17230676072039 17230676450759 17230676452353
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 281 200200 200200 4194304 256 0 0 16 24 120064 0x7f304844d980 0x7f3043a256c0 299630 299630 65536 3407872 501737 56223044 17230676487242 17230676450759 17230676832679 17230676834373
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 284 200200 200200 4194304 256 0 0 12 24 121792 0x7f304844d800 0x7f3043a25700 164756 164756 65536 3407872 509975 57161456 17230676869312 17230676832679 17230677127080 17230677128875
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 287 200200 200200 4194304 256 0 0 12 24 124032 0x7f304844d680 0x7f3043a25740 239809 239809 65536 4521984 679768 76194020 17230677164144 17230677127080 17230677470600 17230677472145
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 290 200200 200200 4194304 256 0 0 12 24 125504 0x7f304aaf0500 0x7f3043a25780 161248 161248 65536 3014656 453378 50786952 17230677514114 17230677470600 17230677764520 17230677766227
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 200200 200200 4194304 256 0 0 12 24 127488 0x7f304aaf0380 0x7f3043a257c0 298955 298955 65536 3801088 564090 63207388 17230677800826 17230677764520 17230678149640 17230678151547
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 296 200200 200200 4194304 256 0 0 12 24 129216 0x7f304aaf0200 0x7f3043a25800 299656 299656 65536 3670016 545992 61167132 17230678188766 17230678149640 17230678540841 17230678542636
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 299 200200 200200 4194304 256 0 0 12 24 130944 0x7f304aaf0080 0x7f3043a25840 172181 172181 65536 3670016 570741 63968428 17230678578805 17230678540841 17230678842761 17230678844518
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 302 200200 200200 4194304 256 0 0 12 24 133440 0x7f304844df00 0x7f3043a25880 259422 259422 65536 4915200 770619 86269040 17230678881027 17230678842761 17230679198601 17230679200469
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 305 200200 200200 4194304 256 0 0 12 24 134912 0x7f304844dd80 0x7f3043a258c0 162327 162327 65536 3145728 480589 53960940 17230679243087 17230679198601 17230679492841 17230679494691
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 200200 200200 4194304 256 0 0 12 24 136896 0x7f304844dc00 0x7f3043a25900 296872 296872 65536 4063232 606108 67854676 17230679531400 17230679492841 17230679871081 17230679872640
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 311 200200 200200 4194304 256 0 0 12 24 138880 0x7f304844da80 0x7f3043a25940 300515 300515 65536 3932160 598661 67125152 17230679908579 17230679871081 17230680252682 17230680254480
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 314 200200 200200 4194304 256 0 0 12 24 140864 0x7f304844d900 0x7f3043a25980 181020 181020 65536 3932160 593125 66408984 17230680289629 17230680252682 17230680562602 17230680564271
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 317 200200 200200 4194304 256 0 0 12 24 143616 0x7f304844d780 0x7f3043a259c0 281027 281027 65536 5308416 795368 89012436 17230680598680 17230680562602 17230680933002 17230680934611
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 320 200200 200200 4194304 256 0 0 12 24 145344 0x7f304844d600 0x7f3043a25a00 162936 162936 65536 3342336 497839 55836584 17230680978600 17230680933002 17230681227722 17230681229463
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 200200 200200 4194304 256 0 0 12 24 147584 0x7f304aaf0480 0x7f3043a25a40 295625 295625 65536 4325376 663755 74413072 17230681264482 17230681227722 17230681607082 17230681608843
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 326 200200 200200 4194304 256 0 0 12 24 149568 0x7f304aaf0300 0x7f3043a25a80 296196 296196 65536 4194304 659883 73927896 17230681644582 17230681607082 17230681992363 17230681993963
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 329 200200 200200 4194304 256 0 0 12 24 151552 0x7f304aaf0180 0x7f3043a25ac0 188119 188119 65536 4194304 620549 69584384 17230682029472 17230681992363 17230682309003 17230682310714
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 332 200200 200200 4194304 256 0 0 12 24 154304 0x7f304aaf0000 0x7f3043a25b00 300049 300049 65536 5701632 853908 95480540 17230682347393 17230682309003 17230682692683 17230682694384
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 335 200200 200200 4194304 256 0 0 12 24 156288 0x7f304844de80 0x7f3043a25b40 172721 172721 65536 3735552 567893 63563072 17230682737242 17230682692683 17230682999723 17230683001475
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 200200 200200 4194304 256 0 0 12 24 158784 0x7f304844dd00 0x7f3043a25b80 303224 303224 65536 4849664 748988 83987644 17230683036704 17230682999723 17230683386763 17230683388445
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 341 200200 200200 4194304 256 0 0 12 24 161024 0x7f304844db80 0x7f3043a25bc0 297249 297249 65536 4718592 733006 82116460 17230683423594 17230683386763 17230683773324 17230683775034
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 344 200200 200200 4194304 256 0 0 12 24 163264 0x7f304844da00 0x7f3043a25c00 206320 206320 65536 4718592 709591 79526156 17230683809714 17230683773324 17230684095884 17230684097576
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 347 200200 200200 4194304 256 0 0 12 24 166528 0x7f304844d880 0x7f3043a25c40 341017 341017 65536 6488064 976130 109319488 17230684132555 17230684095884 17230684502444 17230684549074
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 350 200200 200200 4194304 256 0 0 12 24 168512 0x7f304844d700 0x7f3043a25c80 185361 185361 65536 4128768 620699 69464476 17230684568933 17230684502444 17230684845964 17230684847625
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 200200 200200 4194304 256 0 0 12 24 171264 0x7f304aaf0580 0x7f3043a25cc0 298934 298934 65536 5373952 839012 93967904 17230684884214 17230684845964 17230685228045 17230685229855
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 356 200200 200200 4194304 256 0 0 12 24 173760 0x7f304aaf0400 0x7f3043a25d00 297658 297658 65536 5242880 827941 92748532 17230685266134 17230685228045 17230685611085 17230685612635
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 359 200200 200200 4194304 256 0 0 12 24 176256 0x7f304aaf0280 0x7f3043a25d40 225782 225782 65536 5242880 788154 88196292 17230685648704 17230685611085 17230685949805 17230685951706
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 362 200200 200200 4194304 256 0 0 12 24 179776 0x7f304aaf0100 0x7f3043a25d80 380606 380606 65536 7274496 1119811 125408736 17230685987655 17230685949805 17230686400525 17230686425383
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 365 200200 200200 4194304 256 0 0 12 24 182272 0x7f304844df80 0x7f3043a25dc0 211722 211722 65536 4915200 738025 82566040 17230686445972 17230686400525 17230686747565 17230686749344
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 200200 200200 4194304 256 0 0 12 24 185536 0x7f304844de00 0x7f3043a25e00 307320 307320 65536 6422528 1032859 115627544 17230686786353 17230686747565 17230687137966 17230687183222
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 371 200200 200200 4194304 256 0 0 12 24 188544 0x7f304844dc80 0x7f3043a25e40 312244 312244 65536 6291456 1020415 114243404 17230687194732 17230687137966 17230687561166 17230687605971
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 374 200200 200200 4194304 256 0 0 12 24 191552 0x7f304844db00 0x7f3043a25e80 266393 266393 65536 6291456 947568 106119276 17230687618091 17230687561166 17230687949326 17230687950952
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 377 200200 200200 4194304 256 0 0 12 24 195840 0x7f304844d980 0x7f3043a25ec0 462715 462715 65536 8847360 1337508 149786796 17230687986441 17230687949326 17230688435566 17230688480557
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 380 200200 200200 4194304 256 0 0 12 24 198592 0x7f304844d800 0x7f3043a25f00 242937 242937 65536 5701632 866738 97080748 17230688501227 17230688435566 17230688816527 17230688818288
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 200200 200200 4194304 256 0 0 12 24 202368 0x7f304844d680 0x7f3043a25f40 335015 335015 65536 7471104 1186058 132734668 17230688854437 17230688816527 17230689224687 17230689267066
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 386 200200 200200 4194304 256 0 0 12 24 205888 0x7f304aaf0500 0x7f3043a25f80 331471 331471 65536 7340032 1151742 128884656 17230689278556 17230689224687 17230689664847 17230689683735
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 389 200200 200200 4194304 256 0 0 12 24 209408 0x7f304aaf0380 0x7f3043a25fc0 309825 309825 65536 7340032 1115054 124938416 17230689701474 17230689664847 17230690056527 17230690059505
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 392 200200 200200 4194304 256 0 0 12 24 214464 0x7f304aaf0200 0x7f3043a26000 543503 543503 65536 10420224 1588316 177868940 17230690095644 17230690056527 17230690599248 17230690645039
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 395 200200 200200 4194304 256 0 0 12 24 217728 0x7f304aaf0080 0x7f3043a26040 271372 271372 65536 6488064 974536 109116672 17230690665948 17230690599248 17230690996208 17230690997919
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 200200 200200 4194304 256 0 0 12 24 222016 0x7f304844df00 0x7f3043a26080 365683 365683 65536 8519680 1376984 154240176 17230691035068 17230690996208 17230691425328 17230691467866
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 401 200200 200200 4194304 256 0 0 12 24 226048 0x7f304844dd80 0x7f3043a260c0 365976 365976 65536 8388608 1305082 146148728 17230691480616 17230691425328 17230691884369 17230691926394
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 404 200200 200200 4194304 256 0 0 12 24 230080 0x7f304844dc00 0x7f3043a26100 348124 348124 65536 8388608 1291298 144662364 17230691939354 17230691884369 17230692323889 17230692366332
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 407 200200 200200 4194304 256 0 0 12 24 235904 0x7f304844da80 0x7f3043a26140 623980 623980 65536 11993088 1836605 205591236 17230692378292 17230692323889 17230692935889 17230692977705
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 410 200200 200200 4194304 256 0 0 12 24 239424 0x7f304844d900 0x7f3043a26180 304951 304951 65536 7274496 1110533 124392372 17230692997505 17230692935889 17230693353169 17230693354805
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 200200 200200 4194304 256 0 0 12 24 244224 0x7f304844d780 0x7f3043a261c0 400586 400586 65536 9568256 1541178 172764392 17230693391124 17230693353169 17230693805970 17230693825372
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 416 200200 200200 4194304 256 0 0 12 24 248768 0x7f304844d600 0x7f3043a26200 392332 392332 65536 9437184 1529711 171376408 17230693845912 17230693805970 17230694257170 17230694303339
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 419 200200 200200 4194304 256 0 0 12 24 253312 0x7f304aaf0480 0x7f3043a26240 388146 388146 65536 9437184 1469648 164484344 17230694316019 17230694257170 17230694731090 17230694778807
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 422 200200 200200 4194304 256 0 0 8 24 255552 0x7f304aaf0300 0x7f3043a26280 719766 719766 65536 16056320 2303086 257967128 17230694790756 17230694731090 17230695417171 17230695459498
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 425 200200 200200 4194304 256 0 0 12 24 259840 0x7f304aaf0180 0x7f3043a262c0 364701 364701 65536 8847360 1382246 154853484 17230695479888 17230695417171 17230695872531 17230695915166
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 200200 200200 4194304 256 0 0 12 24 265664 0x7f304aaf0000 0x7f3043a26300 470110 470110 65536 11665408 1844660 206507712 17230695926416 17230695872531 17230696401011 17230696443062
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 431 200200 200200 4194304 256 0 0 12 24 271232 0x7f304844de80 0x7f3043a26340 471545 471545 65536 11468800 1851812 207409196 17230696455551 17230696401011 17230696928692 17230696970847
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 434 200200 200200 4194304 256 0 0 8 24 273216 0x7f304844dd00 0x7f3043a26380 483811 483811 65536 14090240 2021606 226338528 17230696982547 17230696928692 17230697458292 17230697501033
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 437 200200 200200 4194304 256 0 0 8 24 275712 0x7f304844db80 0x7f3043a263c0 879889 879889 65536 19202048 2753994 308599076 17230697512613 17230697458292 17230698241972 17230698286822
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 440 200200 200200 4194304 256 0 0 12 24 280768 0x7f304844da00 0x7f3043a26400 427708 427708 65536 10420224 1591607 178282556 17230698308131 17230698241972 17230698742933 17230698787318
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 200200 200200 4194304 256 0 0 12 24 287616 0x7f304844d880 0x7f3043a26440 549980 549980 65536 13762560 2197575 246241116 17230698799068 17230698742933 17230699326133 17230699368713
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 446 200200 200200 4194304 256 0 0 12 24 294208 0x7f304844d700 0x7f3043a26480 552478 552478 65536 13565952 2185166 244649428 17230699382012 17230699326133 17230699903573 17230699945657
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 449 200200 200200 4194304 256 0 0 8 24 296960 0x7f304aaf0580 0x7f3043a264c0 564914 564914 65536 15466496 2224895 249406804 17230699957527 17230699903573 17230700478614 17230700520701
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 452 200200 200200 4194304 256 0 0 8 24 299968 0x7f304aaf0400 0x7f3043a26500 1043124 1043124 65536 22347776 3216547 360080408 17230700532951 17230700478614 17230701364534 17230701406957
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 455 200200 200200 4194304 256 0 0 8 24 302720 0x7f304aaf0280 0x7f3043a26540 722212 722212 65536 20250624 2908543 325873304 17230701427787 17230701364534 17230702037015 17230702055460
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 200200 200200 4194304 256 0 0 12 24 305472 0x7f304aaf0100 0x7f3043a26580 723510 723510 65536 20447232 2936703 328893760 17230702073769 17230702036702 17230702718462 17230702767021
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 461 200200 200200 4194304 256 0 0 12 24 308224 0x7f304844df80 0x7f3043a265c0 723272 723272 65536 19595264 2818913 315632604 17230702781000 17230702718462 17230703413820 17230703459832
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 464 200200 200200 4194304 256 0 0 8 24 310976 0x7f304844de00 0x7f3043a26600 726348 726348 65536 20381696 2930925 328342788 17230703472271 17230703413820 17230704094780 17230704138993
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 467 200200 200200 4194304 256 0 0 8 24 313216 0x7f304844dc80 0x7f3043a26640 1369640 1369640 65536 31522816 4519909 506148692 17230704150533 17230704094780 17230705206300 17230705252483
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 470 200200 200200 4194304 256 0 0 8 24 315968 0x7f304844db00 0x7f3043a26680 1370938 1370938 65536 38993920 5592869 626095372 17230705271823 17230705206300 17230706304380 17230706371203
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 200200 200200 4194304 256 0 0 12 24 318720 0x7f304844d980 0x7f3043a266c0 1373390 1373390 65536 39124992 5610953 628252916 17230706384022 17230706304380 17230707461020 17230707528141
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 476 200200 200200 4194304 256 0 0 12 24 321472 0x7f304844d800 0x7f3043a26700 1372439 1372439 65536 38469632 5509836 617207136 17230707540731 17230707461020 17230708605660 17230708675150
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 479 200200 200200 4194304 256 0 0 8 24 324224 0x7f304844d680 0x7f3043a26740 1377380 1377380 65536 39059456 5596109 626891208 17230708687160 17230708605660 17230709732060 17230709797290
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 482 200200 200200 4194304 256 0 0 8 24 326464 0x7f304aaf0500 0x7f3043a26780 2663674 2663674 65536 60489728 8650049 968941056 17230709808880 17230709732060 17230711703260 17230711780507
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 485 200200 200200 4194304 256 0 0 8 24 329216 0x7f304aaf0380 0x7f3043a267c0 2671394 2671394 65536 77266944 11058204 1238333104 17230711799986 17230711703260 17230713656380 17230713724154
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 200200 200200 4194304 256 0 0 12 24 331968 0x7f304aaf0200 0x7f3043a26800 2670519 2670519 65536 77398016 11074576 1240054236 17230713736004 17230713656380 17230715655900 17230715729250
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 491 200200 200200 4194304 256 0 0 12 24 334720 0x7f304aaf0080 0x7f3043a26840 2669734 2669734 65536 76218368 10908447 1221550176 17230715742109 17230715655900 17230717653820 17230717718866
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 494 200200 200200 4194304 256 0 0 8 24 337472 0x7f304844df00 0x7f3043a26880 2674843 2674843 65536 77332480 11063591 1239190112 17230717730885 17230717653820 17230719594140 17230719666533
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 497 200200 200200 4194304 256 0 0 8 24 0 0x7f304844dd80 0x7f3043a268c0 5257525 5257525 65536 120258560 17185373 1925585988 17230719679693 17230719594140 17230723230300 17230723302965
@@ -1,168 +0,0 @@
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",0,0,0,202048,202048,33554432,256,0,0,4,32,4160,0x0,0x7ff18ec04280,0,0,0,17249839171366,17249136551505,17249986734818,17249986848227
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,202048,202048,32768,256,0,0,12,24,13888,0x0,0x7ff18ec23f80,0,0,0,17249992035347,17249986734818,17249992162336,17249992165533
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,202048,202048,4194304,256,0,0,12,24,14336,0x7ff191cc5380,0x7ff18ec23fc0,0,0,0,17249992202162,17249992162336,17249992490176,17249992492374
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,202048,202048,4194304,256,0,0,16,24,15040,0x7ff191cc5200,0x7ff18ec24000,0,0,0,17249992529443,17249992490176,17249992890816,17249992893283
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,202048,202048,4194304,256,0,0,16,24,15488,0x7ff191cc5080,0x7ff18ec24040,0,0,0,17249992925242,17249992890816,17249993283296,17249993285693
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,202048,202048,4194304,256,0,0,12,24,15936,0x7ff18f697f00,0x7ff18ec24080,0,0,0,17249993318942,17249993283296,17249993592096,17249993594354
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,202048,202048,4194304,256,0,0,12,24,16384,0x7ff18f697d80,0x7ff18ec240c0,0,0,0,17249993626764,17249993592096,17249993899296,17249993901626
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,202048,202048,4194304,256,0,0,12,24,17088,0x7ff18f697c00,0x7ff18ec24100,0,0,0,17249993945465,17249993899296,17249994219616,17249994222037
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,202048,202048,4194304,256,0,0,16,24,17792,0x7ff18f697a80,0x7ff18ec24140,0,0,0,17249994253437,17249994219616,17249994622656,17249994624857
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,202048,202048,4194304,256,0,0,16,24,18496,0x7ff18f697900,0x7ff18ec24180,0,0,0,17249994656146,17249994622656,17249995018016,17249995020296
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,202048,202048,4194304,256,0,0,16,24,19200,0x7ff18f697780,0x7ff18ec241c0,0,0,0,17249995050875,17249995018016,17249995336416,17249995338617
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,202048,202048,4194304,256,0,0,16,24,19904,0x7ff18f697600,0x7ff18ec24200,0,0,0,17249995371007,17249995336416,17249995641696,17249995643839
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,202048,202048,4194304,256,0,0,12,24,20608,0x7ff191cc5480,0x7ff18ec24240,0,0,0,17249995684388,17249995641696,17249995948896,17249995951081
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,202048,202048,4194304,256,0,0,16,24,21312,0x7ff191cc5300,0x7ff18ec24280,0,0,0,17249995984580,17249995948896,17249996340096,17249996342321
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,202048,202048,4194304,256,0,0,16,24,22016,0x7ff191cc5180,0x7ff18ec242c0,0,0,0,17249996375400,17249996340096,17249996730176,17249996732560
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,202048,202048,4194304,256,0,0,16,24,22720,0x7ff191cc5000,0x7ff18ec24300,0,0,0,17249996765329,17249996730176,17249997031296,17249997033652
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,202048,202048,4194304,256,0,0,12,24,23424,0x7ff18f697e80,0x7ff18ec24340,0,0,0,17249997066421,17249997031296,17249997337696,17249997339894
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,202048,202048,4194304,256,0,0,12,24,24128,0x7ff18f697d00,0x7ff18ec24380,0,0,0,17249997378473,17249997337696,17249997638976,17249997641146
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,202048,202048,4194304,256,0,0,16,24,24832,0x7ff18f697b80,0x7ff18ec243c0,0,0,0,17249997672505,17249997638976,17249998031456,17249998033625
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,202048,202048,4194304,256,0,0,16,24,25536,0x7ff18f697a00,0x7ff18ec24400,0,0,0,17249998065784,17249998031456,17249998447456,17249998450024
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,202048,202048,4194304,256,0,0,12,24,26240,0x7ff18f697880,0x7ff18ec24440,0,0,0,17249998484223,17249998447456,17249998752096,17249998753776
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,202048,202048,4194304,256,0,0,12,24,26944,0x7ff18f697700,0x7ff18ec24480,0,0,0,17249998785525,17249998752096,17249999030976,17249999032658
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,202048,202048,4194304,256,0,0,12,24,27648,0x7ff191cc5580,0x7ff18ec244c0,0,0,0,17249999072127,17249999030976,17249999307936,17249999309711
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,202048,202048,4194304,256,0,0,16,24,28608,0x7ff191cc5400,0x7ff18ec24500,0,0,0,17249999342300,17249999307936,17249999674816,17249999676431
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,202048,202048,4194304,256,0,0,16,24,29312,0x7ff191cc5280,0x7ff18ec24540,0,0,0,17249999709210,17249999674816,17250000041376,17250000043121
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,202048,202048,4194304,256,0,0,12,24,30016,0x7ff191cc5100,0x7ff18ec24580,0,0,0,17250000075610,17250000041376,17250000318336,17250000320053
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,202048,202048,4194304,256,0,0,8,24,30976,0x7ff18f697f80,0x7ff18ec245c0,0,0,0,17250000352962,17250000318336,17250000600416,17250000602016
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,202048,202048,4194304,256,0,0,12,24,31680,0x7ff18f697e00,0x7ff18ec24600,0,0,0,17250000641455,17250000600416,17250000878336,17250000879978
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,202048,202048,4194304,256,0,0,16,24,32640,0x7ff18f697c80,0x7ff18ec24640,0,0,0,17250000911847,17250000878336,17250001241376,17250001243018
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,202048,202048,4194304,256,0,0,12,24,33600,0x7ff18f697b00,0x7ff18ec24680,0,0,0,17250001275378,17250001241376,17250001608096,17250001609689
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,202048,202048,4194304,256,0,0,12,24,34560,0x7ff18f697980,0x7ff18ec246c0,0,0,0,17250001641878,17250001608096,17250001890816,17250001892581
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,202048,202048,4194304,256,0,0,8,24,35520,0x7ff18f697800,0x7ff18ec24700,0,0,0,17250001924570,17250001890816,17250002170176,17250002171953
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,202048,202048,4194304,256,0,0,12,24,36224,0x7ff18f697680,0x7ff18ec24740,0,0,0,17250002211702,17250002170176,17250002451776,17250002453386
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,202048,202048,4194304,256,0,0,12,24,37184,0x7ff191cc5500,0x7ff18ec24780,0,0,0,17250002485335,17250002451776,17250002819296,17250002821006
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,202048,202048,4194304,256,0,0,12,24,38144,0x7ff191cc5380,0x7ff18ec247c0,0,0,0,17250002853395,17250002819296,17250003191616,17250003193166
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,202048,202048,4194304,256,0,0,12,24,39104,0x7ff191cc5200,0x7ff18ec24800,0,0,0,17250003225635,17250003191616,17250003470016,17250003471708
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,202048,202048,4194304,256,0,0,8,24,40320,0x7ff191cc5080,0x7ff18ec24840,0,0,0,17250003504508,17250003470016,17250003748416,17250003750151
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,202048,202048,4194304,256,0,0,12,24,41280,0x7ff18f697f00,0x7ff18ec24880,0,0,0,17250003790240,17250003748416,17250004027616,17250004029204
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,202048,202048,4194304,256,0,0,12,24,42240,0x7ff18f697d80,0x7ff18ec248c0,0,0,0,17250004060783,17250004027616,17250004393376,17250004395214
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,202048,202048,4194304,256,0,0,12,24,43200,0x7ff18f697c00,0x7ff18ec24900,0,0,0,17250004427603,17250004393376,17250004762656,17250004764364
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,202048,202048,4194304,256,0,0,8,24,44160,0x7ff18f697a80,0x7ff18ec24940,0,0,0,17250004795883,17250004762656,17250005042335,17250005043946
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,202048,202048,4194304,256,0,0,12,24,45376,0x7ff18f697900,0x7ff18ec24980,0,0,0,17250005076675,17250005042335,17250005337855,17250005339478
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,202048,202048,4194304,256,0,0,12,24,46336,0x7ff18f697780,0x7ff18ec249c0,0,0,0,17250005378017,17250005337855,17250005618335,17250005620071
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,202048,202048,4194304,256,0,0,12,24,47552,0x7ff18f697600,0x7ff18ec24a00,0,0,0,17250005651960,17250005618335,17250005981375,17250005982891
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,202048,202048,4194304,256,0,0,12,24,48512,0x7ff191cc5480,0x7ff18ec24a40,0,0,0,17250006015180,17250005981375,17250006356095,17250006357801
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,202048,202048,4194304,256,0,0,8,24,49472,0x7ff191cc5300,0x7ff18ec24a80,0,0,0,17250006390150,17250006356095,17250006636415,17250006638083
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,202048,202048,4194304,256,0,0,12,24,50688,0x7ff191cc5180,0x7ff18ec24ac0,0,0,0,17250006670163,17250006636415,17250006915295,17250006916826
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,202048,202048,4194304,256,0,0,12,24,51648,0x7ff191cc5000,0x7ff18ec24b00,0,0,0,17250006956305,17250006915295,17250007192095,17250007193868
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,202048,202048,4194304,256,0,0,12,24,52864,0x7ff18f697e80,0x7ff18ec24b40,0,0,0,17250007225608,17250007192095,17250007560255,17250007561868
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,202048,202048,4194304,256,0,0,12,24,54080,0x7ff18f697d00,0x7ff18ec24b80,0,0,0,17250007593328,17250007560255,17250007930335,17250007931788
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,202048,202048,4194304,256,0,0,8,24,55296,0x7ff18f697b80,0x7ff18ec24bc0,0,0,0,17250007962958,17250007930335,17250008210175,17250008211931
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,202048,202048,4194304,256,0,0,12,24,56768,0x7ff18f697a00,0x7ff18ec24c00,0,0,0,17250008243900,17250008210175,17250008490175,17250008491643
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,202048,202048,4194304,256,0,0,12,24,57728,0x7ff18f697880,0x7ff18ec24c40,0,0,0,17250008529862,17250008490175,17250008767295,17250008768846
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,202048,202048,4194304,256,0,0,12,24,58944,0x7ff18f697700,0x7ff18ec24c80,0,0,0,17250008801015,17250008767295,17250009133535,17250009135316
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,202048,202048,4194304,256,0,0,12,24,60160,0x7ff191cc5580,0x7ff18ec24cc0,0,0,0,17250009167525,17250009133535,17250009497215,17250009498826
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,202048,202048,4194304,256,0,0,8,24,61376,0x7ff191cc5400,0x7ff18ec24d00,0,0,0,17250009530285,17250009497215,17250009774495,17250009776119
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,202048,202048,4194304,256,0,0,12,24,62848,0x7ff191cc5280,0x7ff18ec24d40,0,0,0,17250009807728,17250009774495,17250010056095,17250010057781
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,202048,202048,4194304,256,0,0,12,24,63808,0x7ff191cc5100,0x7ff18ec24d80,0,0,0,17250010101420,17250010056095,17250010349855,17250010351743
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,202048,202048,4194304,256,0,0,12,24,65024,0x7ff18f697f80,0x7ff18ec24dc0,0,0,0,17250010383852,17250010349855,17250010719135,17250010720863
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,202048,202048,4194304,256,0,0,12,24,66240,0x7ff18f697e00,0x7ff18ec24e00,0,0,0,17250010753092,17250010719135,17250011085695,17250011087233
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,202048,202048,4194304,256,0,0,8,24,67456,0x7ff18f697c80,0x7ff18ec24e40,0,0,0,17250011118952,17250011085695,17250011364895,17250011366506
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,202048,202048,4194304,256,0,0,12,24,68928,0x7ff18f697b00,0x7ff18ec24e80,0,0,0,17250011399495,17250011364895,17250011654815,17250011656398
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,202048,202048,4194304,256,0,0,12,24,70144,0x7ff18f697980,0x7ff18ec24ec0,0,0,0,17250011696437,17250011654815,17250011933375,17250011934980
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,202048,202048,4194304,256,0,0,12,24,71616,0x7ff18f697800,0x7ff18ec24f00,0,0,0,17250011966369,17250011933375,17250012302175,17250012303850
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,202048,202048,4194304,256,0,0,12,24,72832,0x7ff18f697680,0x7ff18ec24f40,0,0,0,17250012335749,17250012302175,17250012672255,17250012673930
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,202048,202048,4194304,256,0,0,8,24,74048,0x7ff191cc5500,0x7ff18ec24f80,0,0,0,17250012706059,17250012672255,17250012951775,17250012953383
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,202048,202048,4194304,256,0,0,12,24,75776,0x7ff191cc5380,0x7ff18ec24fc0,0,0,0,17250012985682,17250012951775,17250013246175,17250013247735
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,202048,202048,4194304,256,0,0,12,24,76992,0x7ff191cc5200,0x7ff18ec25000,0,0,0,17250013287404,17250013246175,17250013525855,17250013527607
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,202048,202048,4194304,256,0,0,12,24,78464,0x7ff191cc5080,0x7ff18ec25040,0,0,0,17250013559916,17250013525855,17250013894495,17250013896277
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,202048,202048,4194304,256,0,0,12,24,79936,0x7ff18f697f00,0x7ff18ec25080,0,0,0,17250013928766,17250013894495,17250014259935,17250014261747
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,202048,202048,4194304,256,0,0,8,24,81408,0x7ff18f697d80,0x7ff18ec250c0,0,0,0,17250014294877,17250014259935,17250014546815,17250014548540
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,202048,202048,4194304,256,0,0,12,24,83136,0x7ff18f697c00,0x7ff18ec25100,0,0,0,17250014579829,17250014546815,17250014845535,17250014847142
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,202048,202048,4194304,256,0,0,12,24,84352,0x7ff18f697a80,0x7ff18ec25140,0,0,0,17250014896760,17250014845535,17250015126495,17250015128384
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,202048,202048,4194304,256,0,0,12,24,85824,0x7ff18f697900,0x7ff18ec25180,0,0,0,17250015159803,17250015126495,17250015490655,17250015492484
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,202048,202048,4194304,256,0,0,12,24,87296,0x7ff18f697780,0x7ff18ec251c0,0,0,0,17250015524194,17250015490655,17250015853535,17250015855125
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,202048,202048,4194304,256,0,0,12,24,88768,0x7ff18f697600,0x7ff18ec25200,0,0,0,17250015886674,17250015853535,17250016132735,17250016134397
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,202048,202048,4194304,256,0,0,12,24,90752,0x7ff191cc5480,0x7ff18ec25240,0,0,0,17250016166106,17250016132735,17250016434495,17250016436389
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,202048,202048,4194304,256,0,0,12,24,91968,0x7ff191cc5300,0x7ff18ec25280,0,0,0,17250016474598,17250016434495,17250016717855,17250016719451
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,202048,202048,4194304,256,0,0,12,24,93440,0x7ff191cc5180,0x7ff18ec252c0,0,0,0,17250016750651,17250016717855,17250017083295,17250017084962
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,202048,202048,4194304,256,0,0,12,24,94912,0x7ff191cc5000,0x7ff18ec25300,0,0,0,17250017116261,17250017083295,17250017446015,17250017447732
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,202048,202048,4194304,256,0,0,12,24,96384,0x7ff18f697e80,0x7ff18ec25340,0,0,0,17250017478501,17250017446015,17250017726655,17250017728224
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,202048,202048,4194304,256,0,0,12,24,98368,0x7ff18f697d00,0x7ff18ec25380,0,0,0,17250017759794,17250017726655,17250018036255,17250018037846
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,202048,202048,4194304,256,0,0,12,24,99584,0x7ff18f697b80,0x7ff18ec253c0,0,0,0,17250018084125,17250018036255,17250018316575,17250018318209
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,202048,202048,4194304,256,0,0,12,24,101312,0x7ff18f697a00,0x7ff18ec25400,0,0,0,17250018349828,17250018316575,17250018687295,17250018688969
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,202048,202048,4194304,256,0,0,12,24,102784,0x7ff18f697880,0x7ff18ec25440,0,0,0,17250018720298,17250018687295,17250019051935,17250019053609
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,202048,202048,4194304,256,0,0,12,24,104256,0x7ff18f697700,0x7ff18ec25480,0,0,0,17250019085488,17250019051935,17250019332415,17250019333961
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,202048,202048,4194304,256,0,0,12,24,106240,0x7ff191cc5580,0x7ff18ec254c0,0,0,0,17250019365160,17250019332415,17250019646975,17250019648723
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,202048,202048,4194304,256,0,0,12,24,107712,0x7ff191cc5400,0x7ff18ec25500,0,0,0,17250019688752,17250019646975,17250019934495,17250019936085
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,202048,202048,4194304,256,0,0,16,24,109440,0x7ff191cc5280,0x7ff18ec25540,0,0,0,17250019968774,17250019934495,17250020298655,17250020300345
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,202048,202048,4194304,256,0,0,16,24,111168,0x7ff191cc5100,0x7ff18ec25580,0,0,0,17250020331954,17250020298655,17250020663935,17250020665595
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,202048,202048,4194304,256,0,0,8,24,112896,0x7ff18f697f80,0x7ff18ec255c0,0,0,0,17250020697724,17250020663935,17250020945215,17250020946938
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,202048,202048,4194304,256,0,0,12,24,115136,0x7ff18f697e00,0x7ff18ec25600,0,0,0,17250020979117,17250020945215,17250021271135,17250021272729
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,202048,202048,4194304,256,0,0,12,24,116608,0x7ff18f697c80,0x7ff18ec25640,0,0,0,17250021311788,17250021271135,17250021549535,17250021551161
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,202048,202048,4194304,256,0,0,16,24,118336,0x7ff18f697b00,0x7ff18ec25680,0,0,0,17250021582920,17250021549535,17250021914495,17250021916101
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,202048,202048,4194304,256,0,0,16,24,120064,0x7ff18f697980,0x7ff18ec256c0,0,0,0,17250021947220,17250021914495,17250022285375,17250022287171
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,202048,202048,4194304,256,0,0,12,24,121792,0x7ff18f697800,0x7ff18ec25700,0,0,0,17250022319060,17250022285375,17250022580095,17250022581813
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,202048,202048,4194304,256,0,0,12,24,124032,0x7ff18f697680,0x7ff18ec25740,0,0,0,17250022614103,17250022580095,17250022913215,17250022914864
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,202048,202048,4194304,256,0,0,12,24,125504,0x7ff191cc5500,0x7ff18ec25780,0,0,0,17250022954783,17250022913215,17250023191614,17250023193277
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,202048,202048,4194304,256,0,0,12,24,127488,0x7ff191cc5380,0x7ff18ec257c0,0,0,0,17250023225146,17250023191614,17250023556254,17250023557967
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,202048,202048,4194304,256,0,0,12,24,129216,0x7ff191cc5200,0x7ff18ec25800,0,0,0,17250023589986,17250023556254,17250023921854,17250023923477
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,202048,202048,4194304,256,0,0,12,24,130944,0x7ff191cc5080,0x7ff18ec25840,0,0,0,17250023954797,17250023921854,17250024207294,17250024208840
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,202048,202048,4194304,256,0,0,12,24,133440,0x7ff18f697f00,0x7ff18ec25880,0,0,0,17250024241219,17250024207294,17250024551614,17250024553261
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,202048,202048,4194304,256,0,0,12,24,134912,0x7ff18f697d80,0x7ff18ec258c0,0,0,0,17250024592319,17250024551614,17250024830014,17250024831703
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,202048,202048,4194304,256,0,0,12,24,136896,0x7ff18f697c00,0x7ff18ec25900,0,0,0,17250024863352,17250024830014,17250025201534,17250025203253
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,202048,202048,4194304,256,0,0,12,24,138880,0x7ff18f697a80,0x7ff18ec25940,0,0,0,17250025235412,17250025201534,17250025565054,17250025566733
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,202048,202048,4194304,256,0,0,12,24,140864,0x7ff18f697900,0x7ff18ec25980,0,0,0,17250025597652,17250025565054,17250025855294,17250025856936
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,202048,202048,4194304,256,0,0,12,24,143616,0x7ff18f697780,0x7ff18ec259c0,0,0,0,17250025887595,17250025855294,17250026214494,17250026216556
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,202048,202048,4194304,256,0,0,12,24,145344,0x7ff18f697600,0x7ff18ec25a00,0,0,0,17250026256775,17250026214494,17250026506334,17250026507828
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,202048,202048,4194304,256,0,0,12,24,147584,0x7ff191cc5480,0x7ff18ec25a40,0,0,0,17250026539807,17250026506334,17250026873214,17250026874788
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,202048,202048,4194304,256,0,0,12,24,149568,0x7ff191cc5300,0x7ff18ec25a80,0,0,0,17250026907227,17250026873214,17250027240094,17250027241838
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,202048,202048,4194304,256,0,0,12,24,151552,0x7ff191cc5180,0x7ff18ec25ac0,0,0,0,17250027273827,17250027240094,17250027535774,17250027537420
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,202048,202048,4194304,256,0,0,12,24,154304,0x7ff191cc5000,0x7ff18ec25b00,0,0,0,17250027569779,17250027535774,17250027901694,17250027903350
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,202048,202048,4194304,256,0,0,12,24,156288,0x7ff18f697e80,0x7ff18ec25b40,0,0,0,17250027941739,17250027901694,17250028187614,17250028189313
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,202048,202048,4194304,256,0,0,12,24,158784,0x7ff18f697d00,0x7ff18ec25b80,0,0,0,17250028221292,17250028187614,17250028557054,17250028558593
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,202048,202048,4194304,256,0,0,12,24,161024,0x7ff18f697b80,0x7ff18ec25bc0,0,0,0,17250028590722,17250028557054,17250028925854,17250028927573
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,202048,202048,4194304,256,0,0,12,24,163264,0x7ff18f697a00,0x7ff18ec25c00,0,0,0,17250028959012,17250028925854,17250029236574,17250029238184
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,202048,202048,4194304,256,0,0,12,24,166528,0x7ff18f697880,0x7ff18ec25c40,0,0,0,17250029268973,17250029236574,17250029633054,17250029652533
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,202048,202048,4194304,256,0,0,12,24,168512,0x7ff18f697700,0x7ff18ec25c80,0,0,0,17250029673472,17250029633054,17250029936894,17250029938475
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,202048,202048,4194304,256,0,0,12,24,171264,0x7ff191cc5580,0x7ff18ec25cc0,0,0,0,17250029970014,17250029936894,17250030314654,17250030316675
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,202048,202048,4194304,256,0,0,12,24,173760,0x7ff191cc5400,0x7ff18ec25d00,0,0,0,17250030349674,17250030314654,17250030686334,17250030687945
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,202048,202048,4194304,256,0,0,12,24,176256,0x7ff191cc5280,0x7ff18ec25d40,0,0,0,17250030719524,17250030686334,17250031006654,17250031008336
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,202048,202048,4194304,256,0,0,12,24,179776,0x7ff191cc5100,0x7ff18ec25d80,0,0,0,17250031039776,17250031006654,17250031422814,17250031467844
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,202048,202048,4194304,256,0,0,12,24,182272,0x7ff18f697f80,0x7ff18ec25dc0,0,0,0,17250031486953,17250031422814,17250031773534,17250031775126
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,202048,202048,4194304,256,0,0,12,24,185536,0x7ff18f697e00,0x7ff18ec25e00,0,0,0,17250031806945,17250031773534,17250032149214,17250032193484
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,202048,202048,4194304,256,0,0,12,24,188544,0x7ff18f697c80,0x7ff18ec25e40,0,0,0,17250032205894,17250032149214,17250032559294,17250032580324
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,202048,202048,4194304,256,0,0,12,24,191552,0x7ff18f697b00,0x7ff18ec25e80,0,0,0,17250032592394,17250032559294,17250032921054,17250032922615
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,202048,202048,4194304,256,0,0,12,24,195840,0x7ff18f697980,0x7ff18ec25ec0,0,0,0,17250032953794,17250032921054,17250033390334,17250033407822
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,202048,202048,4194304,256,0,0,12,24,198592,0x7ff18f697800,0x7ff18ec25f00,0,0,0,17250033430201,17250033390334,17250033725534,17250033727103
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,202048,202048,4194304,256,0,0,12,24,202368,0x7ff18f697680,0x7ff18ec25f40,0,0,0,17250033757882,17250033725534,17250034120574,17250034142802
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,202048,202048,4194304,256,0,0,12,24,205888,0x7ff191cc5500,0x7ff18ec25f80,0,0,0,17250034155271,17250034120574,17250034525374,17250034544491
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,202048,202048,4194304,256,0,0,12,24,209408,0x7ff191cc5380,0x7ff18ec25fc0,0,0,0,17250034558791,17250034525374,17250034900734,17250034902381
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,202048,202048,4194304,256,0,0,12,24,214464,0x7ff191cc5200,0x7ff18ec26000,0,0,0,17250034934360,17250034900734,17250035418814,17250035436097
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,202048,202048,4194304,256,0,0,12,24,217728,0x7ff191cc5080,0x7ff18ec26040,0,0,0,17250035459876,17250035418814,17250035779614,17250035781328
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,202048,202048,4194304,256,0,0,12,24,222016,0x7ff18f697f00,0x7ff18ec26080,0,0,0,17250035812857,17250035779614,17250036195294,17250036212556
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,202048,202048,4194304,256,0,0,12,24,226048,0x7ff18f697d80,0x7ff18ec260c0,0,0,0,17250036228766,17250036195294,17250036619454,17250036636225
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,202048,202048,4194304,256,0,0,12,24,230080,0x7ff18f697c00,0x7ff18ec26100,0,0,0,17250036652734,17250036619454,17250037019454,17250037036564
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,202048,202048,4194304,256,0,0,12,24,235904,0x7ff18f697a80,0x7ff18ec26140,0,0,0,17250037053704,17250037019454,17250037591774,17250037608549
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,202048,202048,4194304,256,0,0,12,24,239424,0x7ff18f697900,0x7ff18ec26180,0,0,0,17250037632138,17250037591774,17250037970174,17250037971779
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,202048,202048,4194304,256,0,0,12,24,244224,0x7ff18f697780,0x7ff18ec261c0,0,0,0,17250038003048,17250037970174,17250038413854,17250038437536
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,202048,202048,4194304,256,0,0,12,24,248768,0x7ff18f697600,0x7ff18ec26200,0,0,0,17250038449936,17250038413854,17250038858174,17250038899884
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,202048,202048,4194304,256,0,0,12,24,253312,0x7ff191cc5480,0x7ff18ec26240,0,0,0,17250038912234,17250038858174,17250039306814,17250039348802
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,202048,202048,4194304,256,0,0,8,24,255552,0x7ff191cc5300,0x7ff18ec26280,0,0,0,17250039360151,17250039306814,17250039972254,17250040014014
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,202048,202048,4194304,256,0,0,12,24,259840,0x7ff191cc5180,0x7ff18ec262c0,0,0,0,17250040033743,17250039972254,17250040410174,17250040451192
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,202048,202048,4194304,256,0,0,12,24,265664,0x7ff191cc5000,0x7ff18ec26300,0,0,0,17250040463092,17250040410174,17250040921534,17250040939109
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,202048,202048,4194304,256,0,0,12,24,271232,0x7ff18f697e80,0x7ff18ec26340,0,0,0,17250040955688,17250040921534,17250041414493,17250041432345
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,202048,202048,4194304,256,0,0,8,24,273216,0x7ff18f697d00,0x7ff18ec26380,0,0,0,17250041446965,17250041414493,17250041898653,17250041915732
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,202048,202048,4194304,256,0,0,8,24,275712,0x7ff18f697b80,0x7ff18ec263c0,0,0,0,17250041932422,17250041898653,17250042638493,17250042658702
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,202048,202048,4194304,256,0,0,12,24,280768,0x7ff18f697a00,0x7ff18ec26400,0,0,0,17250042680402,17250042638493,17250043099933,17250043116590
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,202048,202048,4194304,256,0,0,12,24,287616,0x7ff18f697880,0x7ff18ec26440,0,0,0,17250043133570,17250043099933,17250043638013,17250043655575
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,202048,202048,4194304,256,0,0,12,24,294208,0x7ff18f697700,0x7ff18ec26480,0,0,0,17250043673655,17250043638013,17250044174333,17250044190921
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,202048,202048,4194304,256,0,0,8,24,296960,0x7ff191cc5580,0x7ff18ec264c0,0,0,0,17250044208160,17250044174333,17250044708573,17250044725657
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,202048,202048,4194304,256,0,0,8,24,299968,0x7ff191cc5400,0x7ff18ec26500,0,0,0,17250044742886,17250044708573,17250045554653,17250045571234
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,202048,202048,4194304,256,0,0,8,24,302720,0x7ff191cc5280,0x7ff18ec26540,0,0,0,17250045596103,17250045554653,17250046189533,17250046207366
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,202048,202048,4194304,256,0,0,12,24,305472,0x7ff191cc5100,0x7ff18ec26580,0,0,0,17250046224526,17250046189533,17250046845533,17250046887638
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,202048,202048,4194304,256,0,0,12,24,308224,0x7ff18f697f80,0x7ff18ec265c0,0,0,0,17250046898758,17250046845533,17250047524413,17250047565400
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,202048,202048,4194304,256,0,0,8,24,310976,0x7ff18f697e00,0x7ff18ec26600,0,0,0,17250047576870,17250047524413,17250048188573,17250048229422
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,202048,202048,4194304,256,0,0,8,24,313216,0x7ff18f697c80,0x7ff18ec26640,0,0,0,17250048241772,17250048188573,17250049274973,17250049293424
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,202048,202048,4194304,256,0,0,8,24,315968,0x7ff18f697b00,0x7ff18ec26680,0,0,0,17250049316833,17250049274646,17250050317046,17250050366595
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,202048,202048,4194304,256,0,0,12,24,318720,0x7ff18f697980,0x7ff18ec266c0,0,0,0,17250050378434,17250050317046,17250051428724,17250051494854
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,202048,202048,4194304,256,0,0,12,24,321472,0x7ff18f697800,0x7ff18ec26700,0,0,0,17250051508774,17250051428724,17250052565523,17250052630134
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,202048,202048,4194304,256,0,0,8,24,324224,0x7ff18f697680,0x7ff18ec26740,0,0,0,17250052642423,17250052565523,17250053675442,17250053739184
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,202048,202048,4194304,256,0,0,8,24,326464,0x7ff191cc5500,0x7ff18ec26780,0,0,0,17250053751213,17250053675442,17250055621521,17250055669142
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,202048,202048,4194304,256,0,0,8,24,329216,0x7ff191cc5380,0x7ff18ec267c0,0,0,0,17250055689131,17250055621521,17250057523920,17250057565091
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,202048,202048,4194304,256,0,0,12,24,331968,0x7ff191cc5200,0x7ff18ec26800,0,0,0,17250057576921,17250057523920,17250059480878,17250059554457
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,202048,202048,4194304,256,0,0,12,24,334720,0x7ff191cc5080,0x7ff18ec26840,0,0,0,17250059567397,17250059480878,17250061463757,17250061506085
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,202048,202048,4194304,256,0,0,8,24,337472,0x7ff18f697f00,0x7ff18ec26880,0,0,0,17250061518804,17250061463757,17250063371595,17250063418413
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,202048,202048,4194304,256,0,0,8,24,0,0x7ff18f697d80,0x7ff18ec268c0,0,0,0,17250063432183,17250063371595,17250066969673,17250067038855
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 202048 202048 33554432 256 0 0 4 32 4160 0x0 0x7ff18ec04280 0 0 0 17249839171366 17249136551505 17249986734818 17249986848227
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 202048 202048 32768 256 0 0 12 24 13888 0x0 0x7ff18ec23f80 0 0 0 17249992035347 17249986734818 17249992162336 17249992165533
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 5 202048 202048 4194304 256 0 0 12 24 14336 0x7ff191cc5380 0x7ff18ec23fc0 0 0 0 17249992202162 17249992162336 17249992490176 17249992492374
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 202048 202048 4194304 256 0 0 16 24 15040 0x7ff191cc5200 0x7ff18ec24000 0 0 0 17249992529443 17249992490176 17249992890816 17249992893283
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 11 202048 202048 4194304 256 0 0 16 24 15488 0x7ff191cc5080 0x7ff18ec24040 0 0 0 17249992925242 17249992890816 17249993283296 17249993285693
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 14 202048 202048 4194304 256 0 0 12 24 15936 0x7ff18f697f00 0x7ff18ec24080 0 0 0 17249993318942 17249993283296 17249993592096 17249993594354
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 17 202048 202048 4194304 256 0 0 12 24 16384 0x7ff18f697d80 0x7ff18ec240c0 0 0 0 17249993626764 17249993592096 17249993899296 17249993901626
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 20 202048 202048 4194304 256 0 0 12 24 17088 0x7ff18f697c00 0x7ff18ec24100 0 0 0 17249993945465 17249993899296 17249994219616 17249994222037
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 202048 202048 4194304 256 0 0 16 24 17792 0x7ff18f697a80 0x7ff18ec24140 0 0 0 17249994253437 17249994219616 17249994622656 17249994624857
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 26 202048 202048 4194304 256 0 0 16 24 18496 0x7ff18f697900 0x7ff18ec24180 0 0 0 17249994656146 17249994622656 17249995018016 17249995020296
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 29 202048 202048 4194304 256 0 0 16 24 19200 0x7ff18f697780 0x7ff18ec241c0 0 0 0 17249995050875 17249995018016 17249995336416 17249995338617
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 32 202048 202048 4194304 256 0 0 16 24 19904 0x7ff18f697600 0x7ff18ec24200 0 0 0 17249995371007 17249995336416 17249995641696 17249995643839
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 35 202048 202048 4194304 256 0 0 12 24 20608 0x7ff191cc5480 0x7ff18ec24240 0 0 0 17249995684388 17249995641696 17249995948896 17249995951081
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 202048 202048 4194304 256 0 0 16 24 21312 0x7ff191cc5300 0x7ff18ec24280 0 0 0 17249995984580 17249995948896 17249996340096 17249996342321
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 41 202048 202048 4194304 256 0 0 16 24 22016 0x7ff191cc5180 0x7ff18ec242c0 0 0 0 17249996375400 17249996340096 17249996730176 17249996732560
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 44 202048 202048 4194304 256 0 0 16 24 22720 0x7ff191cc5000 0x7ff18ec24300 0 0 0 17249996765329 17249996730176 17249997031296 17249997033652
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 47 202048 202048 4194304 256 0 0 12 24 23424 0x7ff18f697e80 0x7ff18ec24340 0 0 0 17249997066421 17249997031296 17249997337696 17249997339894
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 50 202048 202048 4194304 256 0 0 12 24 24128 0x7ff18f697d00 0x7ff18ec24380 0 0 0 17249997378473 17249997337696 17249997638976 17249997641146
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 202048 202048 4194304 256 0 0 16 24 24832 0x7ff18f697b80 0x7ff18ec243c0 0 0 0 17249997672505 17249997638976 17249998031456 17249998033625
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 56 202048 202048 4194304 256 0 0 16 24 25536 0x7ff18f697a00 0x7ff18ec24400 0 0 0 17249998065784 17249998031456 17249998447456 17249998450024
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 59 202048 202048 4194304 256 0 0 12 24 26240 0x7ff18f697880 0x7ff18ec24440 0 0 0 17249998484223 17249998447456 17249998752096 17249998753776
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 62 202048 202048 4194304 256 0 0 12 24 26944 0x7ff18f697700 0x7ff18ec24480 0 0 0 17249998785525 17249998752096 17249999030976 17249999032658
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 65 202048 202048 4194304 256 0 0 12 24 27648 0x7ff191cc5580 0x7ff18ec244c0 0 0 0 17249999072127 17249999030976 17249999307936 17249999309711
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 202048 202048 4194304 256 0 0 16 24 28608 0x7ff191cc5400 0x7ff18ec24500 0 0 0 17249999342300 17249999307936 17249999674816 17249999676431
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 71 202048 202048 4194304 256 0 0 16 24 29312 0x7ff191cc5280 0x7ff18ec24540 0 0 0 17249999709210 17249999674816 17250000041376 17250000043121
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 74 202048 202048 4194304 256 0 0 12 24 30016 0x7ff191cc5100 0x7ff18ec24580 0 0 0 17250000075610 17250000041376 17250000318336 17250000320053
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 77 202048 202048 4194304 256 0 0 8 24 30976 0x7ff18f697f80 0x7ff18ec245c0 0 0 0 17250000352962 17250000318336 17250000600416 17250000602016
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 80 202048 202048 4194304 256 0 0 12 24 31680 0x7ff18f697e00 0x7ff18ec24600 0 0 0 17250000641455 17250000600416 17250000878336 17250000879978
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 202048 202048 4194304 256 0 0 16 24 32640 0x7ff18f697c80 0x7ff18ec24640 0 0 0 17250000911847 17250000878336 17250001241376 17250001243018
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 86 202048 202048 4194304 256 0 0 12 24 33600 0x7ff18f697b00 0x7ff18ec24680 0 0 0 17250001275378 17250001241376 17250001608096 17250001609689
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 89 202048 202048 4194304 256 0 0 12 24 34560 0x7ff18f697980 0x7ff18ec246c0 0 0 0 17250001641878 17250001608096 17250001890816 17250001892581
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 92 202048 202048 4194304 256 0 0 8 24 35520 0x7ff18f697800 0x7ff18ec24700 0 0 0 17250001924570 17250001890816 17250002170176 17250002171953
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 95 202048 202048 4194304 256 0 0 12 24 36224 0x7ff18f697680 0x7ff18ec24740 0 0 0 17250002211702 17250002170176 17250002451776 17250002453386
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 202048 202048 4194304 256 0 0 12 24 37184 0x7ff191cc5500 0x7ff18ec24780 0 0 0 17250002485335 17250002451776 17250002819296 17250002821006
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 101 202048 202048 4194304 256 0 0 12 24 38144 0x7ff191cc5380 0x7ff18ec247c0 0 0 0 17250002853395 17250002819296 17250003191616 17250003193166
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 104 202048 202048 4194304 256 0 0 12 24 39104 0x7ff191cc5200 0x7ff18ec24800 0 0 0 17250003225635 17250003191616 17250003470016 17250003471708
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 107 202048 202048 4194304 256 0 0 8 24 40320 0x7ff191cc5080 0x7ff18ec24840 0 0 0 17250003504508 17250003470016 17250003748416 17250003750151
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 110 202048 202048 4194304 256 0 0 12 24 41280 0x7ff18f697f00 0x7ff18ec24880 0 0 0 17250003790240 17250003748416 17250004027616 17250004029204
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 202048 202048 4194304 256 0 0 12 24 42240 0x7ff18f697d80 0x7ff18ec248c0 0 0 0 17250004060783 17250004027616 17250004393376 17250004395214
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 116 202048 202048 4194304 256 0 0 12 24 43200 0x7ff18f697c00 0x7ff18ec24900 0 0 0 17250004427603 17250004393376 17250004762656 17250004764364
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 119 202048 202048 4194304 256 0 0 8 24 44160 0x7ff18f697a80 0x7ff18ec24940 0 0 0 17250004795883 17250004762656 17250005042335 17250005043946
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 122 202048 202048 4194304 256 0 0 12 24 45376 0x7ff18f697900 0x7ff18ec24980 0 0 0 17250005076675 17250005042335 17250005337855 17250005339478
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 125 202048 202048 4194304 256 0 0 12 24 46336 0x7ff18f697780 0x7ff18ec249c0 0 0 0 17250005378017 17250005337855 17250005618335 17250005620071
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 202048 202048 4194304 256 0 0 12 24 47552 0x7ff18f697600 0x7ff18ec24a00 0 0 0 17250005651960 17250005618335 17250005981375 17250005982891
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 131 202048 202048 4194304 256 0 0 12 24 48512 0x7ff191cc5480 0x7ff18ec24a40 0 0 0 17250006015180 17250005981375 17250006356095 17250006357801
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 134 202048 202048 4194304 256 0 0 8 24 49472 0x7ff191cc5300 0x7ff18ec24a80 0 0 0 17250006390150 17250006356095 17250006636415 17250006638083
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 137 202048 202048 4194304 256 0 0 12 24 50688 0x7ff191cc5180 0x7ff18ec24ac0 0 0 0 17250006670163 17250006636415 17250006915295 17250006916826
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 140 202048 202048 4194304 256 0 0 12 24 51648 0x7ff191cc5000 0x7ff18ec24b00 0 0 0 17250006956305 17250006915295 17250007192095 17250007193868
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 202048 202048 4194304 256 0 0 12 24 52864 0x7ff18f697e80 0x7ff18ec24b40 0 0 0 17250007225608 17250007192095 17250007560255 17250007561868
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 146 202048 202048 4194304 256 0 0 12 24 54080 0x7ff18f697d00 0x7ff18ec24b80 0 0 0 17250007593328 17250007560255 17250007930335 17250007931788
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 149 202048 202048 4194304 256 0 0 8 24 55296 0x7ff18f697b80 0x7ff18ec24bc0 0 0 0 17250007962958 17250007930335 17250008210175 17250008211931
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 152 202048 202048 4194304 256 0 0 12 24 56768 0x7ff18f697a00 0x7ff18ec24c00 0 0 0 17250008243900 17250008210175 17250008490175 17250008491643
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 155 202048 202048 4194304 256 0 0 12 24 57728 0x7ff18f697880 0x7ff18ec24c40 0 0 0 17250008529862 17250008490175 17250008767295 17250008768846
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 202048 202048 4194304 256 0 0 12 24 58944 0x7ff18f697700 0x7ff18ec24c80 0 0 0 17250008801015 17250008767295 17250009133535 17250009135316
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 161 202048 202048 4194304 256 0 0 12 24 60160 0x7ff191cc5580 0x7ff18ec24cc0 0 0 0 17250009167525 17250009133535 17250009497215 17250009498826
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 164 202048 202048 4194304 256 0 0 8 24 61376 0x7ff191cc5400 0x7ff18ec24d00 0 0 0 17250009530285 17250009497215 17250009774495 17250009776119
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 167 202048 202048 4194304 256 0 0 12 24 62848 0x7ff191cc5280 0x7ff18ec24d40 0 0 0 17250009807728 17250009774495 17250010056095 17250010057781
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 170 202048 202048 4194304 256 0 0 12 24 63808 0x7ff191cc5100 0x7ff18ec24d80 0 0 0 17250010101420 17250010056095 17250010349855 17250010351743
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 202048 202048 4194304 256 0 0 12 24 65024 0x7ff18f697f80 0x7ff18ec24dc0 0 0 0 17250010383852 17250010349855 17250010719135 17250010720863
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 176 202048 202048 4194304 256 0 0 12 24 66240 0x7ff18f697e00 0x7ff18ec24e00 0 0 0 17250010753092 17250010719135 17250011085695 17250011087233
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 179 202048 202048 4194304 256 0 0 8 24 67456 0x7ff18f697c80 0x7ff18ec24e40 0 0 0 17250011118952 17250011085695 17250011364895 17250011366506
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 182 202048 202048 4194304 256 0 0 12 24 68928 0x7ff18f697b00 0x7ff18ec24e80 0 0 0 17250011399495 17250011364895 17250011654815 17250011656398
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 185 202048 202048 4194304 256 0 0 12 24 70144 0x7ff18f697980 0x7ff18ec24ec0 0 0 0 17250011696437 17250011654815 17250011933375 17250011934980
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 202048 202048 4194304 256 0 0 12 24 71616 0x7ff18f697800 0x7ff18ec24f00 0 0 0 17250011966369 17250011933375 17250012302175 17250012303850
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 191 202048 202048 4194304 256 0 0 12 24 72832 0x7ff18f697680 0x7ff18ec24f40 0 0 0 17250012335749 17250012302175 17250012672255 17250012673930
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 194 202048 202048 4194304 256 0 0 8 24 74048 0x7ff191cc5500 0x7ff18ec24f80 0 0 0 17250012706059 17250012672255 17250012951775 17250012953383
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 197 202048 202048 4194304 256 0 0 12 24 75776 0x7ff191cc5380 0x7ff18ec24fc0 0 0 0 17250012985682 17250012951775 17250013246175 17250013247735
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 200 202048 202048 4194304 256 0 0 12 24 76992 0x7ff191cc5200 0x7ff18ec25000 0 0 0 17250013287404 17250013246175 17250013525855 17250013527607
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 202048 202048 4194304 256 0 0 12 24 78464 0x7ff191cc5080 0x7ff18ec25040 0 0 0 17250013559916 17250013525855 17250013894495 17250013896277
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 206 202048 202048 4194304 256 0 0 12 24 79936 0x7ff18f697f00 0x7ff18ec25080 0 0 0 17250013928766 17250013894495 17250014259935 17250014261747
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 209 202048 202048 4194304 256 0 0 8 24 81408 0x7ff18f697d80 0x7ff18ec250c0 0 0 0 17250014294877 17250014259935 17250014546815 17250014548540
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 212 202048 202048 4194304 256 0 0 12 24 83136 0x7ff18f697c00 0x7ff18ec25100 0 0 0 17250014579829 17250014546815 17250014845535 17250014847142
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 215 202048 202048 4194304 256 0 0 12 24 84352 0x7ff18f697a80 0x7ff18ec25140 0 0 0 17250014896760 17250014845535 17250015126495 17250015128384
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 202048 202048 4194304 256 0 0 12 24 85824 0x7ff18f697900 0x7ff18ec25180 0 0 0 17250015159803 17250015126495 17250015490655 17250015492484
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 221 202048 202048 4194304 256 0 0 12 24 87296 0x7ff18f697780 0x7ff18ec251c0 0 0 0 17250015524194 17250015490655 17250015853535 17250015855125
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 224 202048 202048 4194304 256 0 0 12 24 88768 0x7ff18f697600 0x7ff18ec25200 0 0 0 17250015886674 17250015853535 17250016132735 17250016134397
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 227 202048 202048 4194304 256 0 0 12 24 90752 0x7ff191cc5480 0x7ff18ec25240 0 0 0 17250016166106 17250016132735 17250016434495 17250016436389
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 230 202048 202048 4194304 256 0 0 12 24 91968 0x7ff191cc5300 0x7ff18ec25280 0 0 0 17250016474598 17250016434495 17250016717855 17250016719451
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 202048 202048 4194304 256 0 0 12 24 93440 0x7ff191cc5180 0x7ff18ec252c0 0 0 0 17250016750651 17250016717855 17250017083295 17250017084962
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 236 202048 202048 4194304 256 0 0 12 24 94912 0x7ff191cc5000 0x7ff18ec25300 0 0 0 17250017116261 17250017083295 17250017446015 17250017447732
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 239 202048 202048 4194304 256 0 0 12 24 96384 0x7ff18f697e80 0x7ff18ec25340 0 0 0 17250017478501 17250017446015 17250017726655 17250017728224
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 242 202048 202048 4194304 256 0 0 12 24 98368 0x7ff18f697d00 0x7ff18ec25380 0 0 0 17250017759794 17250017726655 17250018036255 17250018037846
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 245 202048 202048 4194304 256 0 0 12 24 99584 0x7ff18f697b80 0x7ff18ec253c0 0 0 0 17250018084125 17250018036255 17250018316575 17250018318209
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 202048 202048 4194304 256 0 0 12 24 101312 0x7ff18f697a00 0x7ff18ec25400 0 0 0 17250018349828 17250018316575 17250018687295 17250018688969
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 251 202048 202048 4194304 256 0 0 12 24 102784 0x7ff18f697880 0x7ff18ec25440 0 0 0 17250018720298 17250018687295 17250019051935 17250019053609
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 254 202048 202048 4194304 256 0 0 12 24 104256 0x7ff18f697700 0x7ff18ec25480 0 0 0 17250019085488 17250019051935 17250019332415 17250019333961
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 257 202048 202048 4194304 256 0 0 12 24 106240 0x7ff191cc5580 0x7ff18ec254c0 0 0 0 17250019365160 17250019332415 17250019646975 17250019648723
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 260 202048 202048 4194304 256 0 0 12 24 107712 0x7ff191cc5400 0x7ff18ec25500 0 0 0 17250019688752 17250019646975 17250019934495 17250019936085
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 202048 202048 4194304 256 0 0 16 24 109440 0x7ff191cc5280 0x7ff18ec25540 0 0 0 17250019968774 17250019934495 17250020298655 17250020300345
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 266 202048 202048 4194304 256 0 0 16 24 111168 0x7ff191cc5100 0x7ff18ec25580 0 0 0 17250020331954 17250020298655 17250020663935 17250020665595
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 269 202048 202048 4194304 256 0 0 8 24 112896 0x7ff18f697f80 0x7ff18ec255c0 0 0 0 17250020697724 17250020663935 17250020945215 17250020946938
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 272 202048 202048 4194304 256 0 0 12 24 115136 0x7ff18f697e00 0x7ff18ec25600 0 0 0 17250020979117 17250020945215 17250021271135 17250021272729
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 275 202048 202048 4194304 256 0 0 12 24 116608 0x7ff18f697c80 0x7ff18ec25640 0 0 0 17250021311788 17250021271135 17250021549535 17250021551161
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 202048 202048 4194304 256 0 0 16 24 118336 0x7ff18f697b00 0x7ff18ec25680 0 0 0 17250021582920 17250021549535 17250021914495 17250021916101
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 281 202048 202048 4194304 256 0 0 16 24 120064 0x7ff18f697980 0x7ff18ec256c0 0 0 0 17250021947220 17250021914495 17250022285375 17250022287171
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 284 202048 202048 4194304 256 0 0 12 24 121792 0x7ff18f697800 0x7ff18ec25700 0 0 0 17250022319060 17250022285375 17250022580095 17250022581813
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 287 202048 202048 4194304 256 0 0 12 24 124032 0x7ff18f697680 0x7ff18ec25740 0 0 0 17250022614103 17250022580095 17250022913215 17250022914864
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 290 202048 202048 4194304 256 0 0 12 24 125504 0x7ff191cc5500 0x7ff18ec25780 0 0 0 17250022954783 17250022913215 17250023191614 17250023193277
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 202048 202048 4194304 256 0 0 12 24 127488 0x7ff191cc5380 0x7ff18ec257c0 0 0 0 17250023225146 17250023191614 17250023556254 17250023557967
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 296 202048 202048 4194304 256 0 0 12 24 129216 0x7ff191cc5200 0x7ff18ec25800 0 0 0 17250023589986 17250023556254 17250023921854 17250023923477
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 299 202048 202048 4194304 256 0 0 12 24 130944 0x7ff191cc5080 0x7ff18ec25840 0 0 0 17250023954797 17250023921854 17250024207294 17250024208840
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 302 202048 202048 4194304 256 0 0 12 24 133440 0x7ff18f697f00 0x7ff18ec25880 0 0 0 17250024241219 17250024207294 17250024551614 17250024553261
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 305 202048 202048 4194304 256 0 0 12 24 134912 0x7ff18f697d80 0x7ff18ec258c0 0 0 0 17250024592319 17250024551614 17250024830014 17250024831703
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 202048 202048 4194304 256 0 0 12 24 136896 0x7ff18f697c00 0x7ff18ec25900 0 0 0 17250024863352 17250024830014 17250025201534 17250025203253
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 311 202048 202048 4194304 256 0 0 12 24 138880 0x7ff18f697a80 0x7ff18ec25940 0 0 0 17250025235412 17250025201534 17250025565054 17250025566733
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 314 202048 202048 4194304 256 0 0 12 24 140864 0x7ff18f697900 0x7ff18ec25980 0 0 0 17250025597652 17250025565054 17250025855294 17250025856936
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 317 202048 202048 4194304 256 0 0 12 24 143616 0x7ff18f697780 0x7ff18ec259c0 0 0 0 17250025887595 17250025855294 17250026214494 17250026216556
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 320 202048 202048 4194304 256 0 0 12 24 145344 0x7ff18f697600 0x7ff18ec25a00 0 0 0 17250026256775 17250026214494 17250026506334 17250026507828
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 202048 202048 4194304 256 0 0 12 24 147584 0x7ff191cc5480 0x7ff18ec25a40 0 0 0 17250026539807 17250026506334 17250026873214 17250026874788
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 326 202048 202048 4194304 256 0 0 12 24 149568 0x7ff191cc5300 0x7ff18ec25a80 0 0 0 17250026907227 17250026873214 17250027240094 17250027241838
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 329 202048 202048 4194304 256 0 0 12 24 151552 0x7ff191cc5180 0x7ff18ec25ac0 0 0 0 17250027273827 17250027240094 17250027535774 17250027537420
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 332 202048 202048 4194304 256 0 0 12 24 154304 0x7ff191cc5000 0x7ff18ec25b00 0 0 0 17250027569779 17250027535774 17250027901694 17250027903350
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 335 202048 202048 4194304 256 0 0 12 24 156288 0x7ff18f697e80 0x7ff18ec25b40 0 0 0 17250027941739 17250027901694 17250028187614 17250028189313
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 202048 202048 4194304 256 0 0 12 24 158784 0x7ff18f697d00 0x7ff18ec25b80 0 0 0 17250028221292 17250028187614 17250028557054 17250028558593
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 341 202048 202048 4194304 256 0 0 12 24 161024 0x7ff18f697b80 0x7ff18ec25bc0 0 0 0 17250028590722 17250028557054 17250028925854 17250028927573
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 344 202048 202048 4194304 256 0 0 12 24 163264 0x7ff18f697a00 0x7ff18ec25c00 0 0 0 17250028959012 17250028925854 17250029236574 17250029238184
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 347 202048 202048 4194304 256 0 0 12 24 166528 0x7ff18f697880 0x7ff18ec25c40 0 0 0 17250029268973 17250029236574 17250029633054 17250029652533
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 350 202048 202048 4194304 256 0 0 12 24 168512 0x7ff18f697700 0x7ff18ec25c80 0 0 0 17250029673472 17250029633054 17250029936894 17250029938475
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 202048 202048 4194304 256 0 0 12 24 171264 0x7ff191cc5580 0x7ff18ec25cc0 0 0 0 17250029970014 17250029936894 17250030314654 17250030316675
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 356 202048 202048 4194304 256 0 0 12 24 173760 0x7ff191cc5400 0x7ff18ec25d00 0 0 0 17250030349674 17250030314654 17250030686334 17250030687945
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 359 202048 202048 4194304 256 0 0 12 24 176256 0x7ff191cc5280 0x7ff18ec25d40 0 0 0 17250030719524 17250030686334 17250031006654 17250031008336
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 362 202048 202048 4194304 256 0 0 12 24 179776 0x7ff191cc5100 0x7ff18ec25d80 0 0 0 17250031039776 17250031006654 17250031422814 17250031467844
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 365 202048 202048 4194304 256 0 0 12 24 182272 0x7ff18f697f80 0x7ff18ec25dc0 0 0 0 17250031486953 17250031422814 17250031773534 17250031775126
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 202048 202048 4194304 256 0 0 12 24 185536 0x7ff18f697e00 0x7ff18ec25e00 0 0 0 17250031806945 17250031773534 17250032149214 17250032193484
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 371 202048 202048 4194304 256 0 0 12 24 188544 0x7ff18f697c80 0x7ff18ec25e40 0 0 0 17250032205894 17250032149214 17250032559294 17250032580324
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 374 202048 202048 4194304 256 0 0 12 24 191552 0x7ff18f697b00 0x7ff18ec25e80 0 0 0 17250032592394 17250032559294 17250032921054 17250032922615
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 377 202048 202048 4194304 256 0 0 12 24 195840 0x7ff18f697980 0x7ff18ec25ec0 0 0 0 17250032953794 17250032921054 17250033390334 17250033407822
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 380 202048 202048 4194304 256 0 0 12 24 198592 0x7ff18f697800 0x7ff18ec25f00 0 0 0 17250033430201 17250033390334 17250033725534 17250033727103
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 202048 202048 4194304 256 0 0 12 24 202368 0x7ff18f697680 0x7ff18ec25f40 0 0 0 17250033757882 17250033725534 17250034120574 17250034142802
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 386 202048 202048 4194304 256 0 0 12 24 205888 0x7ff191cc5500 0x7ff18ec25f80 0 0 0 17250034155271 17250034120574 17250034525374 17250034544491
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 389 202048 202048 4194304 256 0 0 12 24 209408 0x7ff191cc5380 0x7ff18ec25fc0 0 0 0 17250034558791 17250034525374 17250034900734 17250034902381
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 392 202048 202048 4194304 256 0 0 12 24 214464 0x7ff191cc5200 0x7ff18ec26000 0 0 0 17250034934360 17250034900734 17250035418814 17250035436097
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 395 202048 202048 4194304 256 0 0 12 24 217728 0x7ff191cc5080 0x7ff18ec26040 0 0 0 17250035459876 17250035418814 17250035779614 17250035781328
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 202048 202048 4194304 256 0 0 12 24 222016 0x7ff18f697f00 0x7ff18ec26080 0 0 0 17250035812857 17250035779614 17250036195294 17250036212556
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 401 202048 202048 4194304 256 0 0 12 24 226048 0x7ff18f697d80 0x7ff18ec260c0 0 0 0 17250036228766 17250036195294 17250036619454 17250036636225
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 404 202048 202048 4194304 256 0 0 12 24 230080 0x7ff18f697c00 0x7ff18ec26100 0 0 0 17250036652734 17250036619454 17250037019454 17250037036564
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 407 202048 202048 4194304 256 0 0 12 24 235904 0x7ff18f697a80 0x7ff18ec26140 0 0 0 17250037053704 17250037019454 17250037591774 17250037608549
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 410 202048 202048 4194304 256 0 0 12 24 239424 0x7ff18f697900 0x7ff18ec26180 0 0 0 17250037632138 17250037591774 17250037970174 17250037971779
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 202048 202048 4194304 256 0 0 12 24 244224 0x7ff18f697780 0x7ff18ec261c0 0 0 0 17250038003048 17250037970174 17250038413854 17250038437536
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 416 202048 202048 4194304 256 0 0 12 24 248768 0x7ff18f697600 0x7ff18ec26200 0 0 0 17250038449936 17250038413854 17250038858174 17250038899884
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 419 202048 202048 4194304 256 0 0 12 24 253312 0x7ff191cc5480 0x7ff18ec26240 0 0 0 17250038912234 17250038858174 17250039306814 17250039348802
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 422 202048 202048 4194304 256 0 0 8 24 255552 0x7ff191cc5300 0x7ff18ec26280 0 0 0 17250039360151 17250039306814 17250039972254 17250040014014
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 425 202048 202048 4194304 256 0 0 12 24 259840 0x7ff191cc5180 0x7ff18ec262c0 0 0 0 17250040033743 17250039972254 17250040410174 17250040451192
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 202048 202048 4194304 256 0 0 12 24 265664 0x7ff191cc5000 0x7ff18ec26300 0 0 0 17250040463092 17250040410174 17250040921534 17250040939109
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 431 202048 202048 4194304 256 0 0 12 24 271232 0x7ff18f697e80 0x7ff18ec26340 0 0 0 17250040955688 17250040921534 17250041414493 17250041432345
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 434 202048 202048 4194304 256 0 0 8 24 273216 0x7ff18f697d00 0x7ff18ec26380 0 0 0 17250041446965 17250041414493 17250041898653 17250041915732
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 437 202048 202048 4194304 256 0 0 8 24 275712 0x7ff18f697b80 0x7ff18ec263c0 0 0 0 17250041932422 17250041898653 17250042638493 17250042658702
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 440 202048 202048 4194304 256 0 0 12 24 280768 0x7ff18f697a00 0x7ff18ec26400 0 0 0 17250042680402 17250042638493 17250043099933 17250043116590
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 202048 202048 4194304 256 0 0 12 24 287616 0x7ff18f697880 0x7ff18ec26440 0 0 0 17250043133570 17250043099933 17250043638013 17250043655575
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 446 202048 202048 4194304 256 0 0 12 24 294208 0x7ff18f697700 0x7ff18ec26480 0 0 0 17250043673655 17250043638013 17250044174333 17250044190921
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 449 202048 202048 4194304 256 0 0 8 24 296960 0x7ff191cc5580 0x7ff18ec264c0 0 0 0 17250044208160 17250044174333 17250044708573 17250044725657
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 452 202048 202048 4194304 256 0 0 8 24 299968 0x7ff191cc5400 0x7ff18ec26500 0 0 0 17250044742886 17250044708573 17250045554653 17250045571234
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 455 202048 202048 4194304 256 0 0 8 24 302720 0x7ff191cc5280 0x7ff18ec26540 0 0 0 17250045596103 17250045554653 17250046189533 17250046207366
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 202048 202048 4194304 256 0 0 12 24 305472 0x7ff191cc5100 0x7ff18ec26580 0 0 0 17250046224526 17250046189533 17250046845533 17250046887638
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 461 202048 202048 4194304 256 0 0 12 24 308224 0x7ff18f697f80 0x7ff18ec265c0 0 0 0 17250046898758 17250046845533 17250047524413 17250047565400
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 464 202048 202048 4194304 256 0 0 8 24 310976 0x7ff18f697e00 0x7ff18ec26600 0 0 0 17250047576870 17250047524413 17250048188573 17250048229422
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 467 202048 202048 4194304 256 0 0 8 24 313216 0x7ff18f697c80 0x7ff18ec26640 0 0 0 17250048241772 17250048188573 17250049274973 17250049293424
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 470 202048 202048 4194304 256 0 0 8 24 315968 0x7ff18f697b00 0x7ff18ec26680 0 0 0 17250049316833 17250049274646 17250050317046 17250050366595
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 202048 202048 4194304 256 0 0 12 24 318720 0x7ff18f697980 0x7ff18ec266c0 0 0 0 17250050378434 17250050317046 17250051428724 17250051494854
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 476 202048 202048 4194304 256 0 0 12 24 321472 0x7ff18f697800 0x7ff18ec26700 0 0 0 17250051508774 17250051428724 17250052565523 17250052630134
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 479 202048 202048 4194304 256 0 0 8 24 324224 0x7ff18f697680 0x7ff18ec26740 0 0 0 17250052642423 17250052565523 17250053675442 17250053739184
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 482 202048 202048 4194304 256 0 0 8 24 326464 0x7ff191cc5500 0x7ff18ec26780 0 0 0 17250053751213 17250053675442 17250055621521 17250055669142
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 485 202048 202048 4194304 256 0 0 8 24 329216 0x7ff191cc5380 0x7ff18ec267c0 0 0 0 17250055689131 17250055621521 17250057523920 17250057565091
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 202048 202048 4194304 256 0 0 12 24 331968 0x7ff191cc5200 0x7ff18ec26800 0 0 0 17250057576921 17250057523920 17250059480878 17250059554457
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 491 202048 202048 4194304 256 0 0 12 24 334720 0x7ff191cc5080 0x7ff18ec26840 0 0 0 17250059567397 17250059480878 17250061463757 17250061506085
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 494 202048 202048 4194304 256 0 0 8 24 337472 0x7ff18f697f00 0x7ff18ec26880 0 0 0 17250061518804 17250061463757 17250063371595 17250063418413
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 497 202048 202048 4194304 256 0 0 8 24 0 0x7ff18f697d80 0x7ff18ec268c0 0 0 0 17250063432183 17250063371595 17250066969673 17250067038855
@@ -1,168 +0,0 @@
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",0,0,0,199978,199978,33554432,256,0,0,4,32,4160,0x0,0x7fe1d2a04280,3670016,3040452,340321896,17229574411755,17224026851585,17229723837237,17229723948727
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,199978,199978,32768,256,0,0,12,24,13888,0x0,0x7fe1d2a23f80,512,97598,10948992,17229729109777,17229723837237,17229729235641,17229729240263
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,199978,199978,4194304,256,0,0,12,24,14336,0x7fe1d5a50380,0x7fe1d2a23fc0,65536,619714,69394784,17229729274252,17229729235641,17229729595641,17229729597774
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,199978,199978,4194304,256,0,0,16,24,15040,0x7fe1d5a50200,0x7fe1d2a24000,65536,650318,72879808,17229729633863,17229729595641,17229729997881,17229729999983
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,199978,199978,4194304,256,0,0,16,24,15488,0x7fe1d5a50080,0x7fe1d2a24040,65536,660540,73841616,17229730033752,17229729997881,17229730405402,17229730407522
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,199978,199978,4194304,256,0,0,12,24,15936,0x7fe1d32edf00,0x7fe1d2a24080,65536,651524,72958416,17229730439761,17229730405402,17229730712282,17229730714413
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,199978,199978,4194304,256,0,0,12,24,16384,0x7fe1d32edd80,0x7fe1d2a240c0,65536,621762,69629072,17229730746023,17229730712282,17229731016282,17229731018485
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,199978,199978,4194304,256,0,0,12,24,17088,0x7fe1d32edc00,0x7fe1d2a24100,131072,658036,73785048,17229731061514,17229731016282,17229731318682,17229731320617
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,199978,199978,4194304,256,0,0,16,24,17792,0x7fe1d32eda80,0x7fe1d2a24140,131072,692714,77624960,17229731352936,17229731318682,17229731705403,17229731707457
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,199978,199978,4194304,256,0,0,16,24,18496,0x7fe1d32ed900,0x7fe1d2a24180,65536,657794,73816888,17229731738516,17229731705403,17229732092283,17229732094766
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,199978,199978,4194304,256,0,0,16,24,19200,0x7fe1d32ed780,0x7fe1d2a241c0,131072,696868,78111816,17229732125465,17229732092283,17229732405083,17229732407348
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,199978,199978,4194304,256,0,0,16,24,19904,0x7fe1d32ed600,0x7fe1d2a24200,131072,688984,77089720,17229732439337,17229732405083,17229732705243,17229732707560
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,199978,199978,4194304,256,0,0,12,24,20608,0x7fe1d5a50480,0x7fe1d2a24240,131072,697572,78205352,17229732747848,17229732705243,17229733005084,17229733007491
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,199978,199978,4194304,256,0,0,16,24,21312,0x7fe1d5a50300,0x7fe1d2a24280,131072,699686,78315120,17229733039281,17229733005084,17229733392284,17229733394351
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,199978,199978,4194304,256,0,0,16,24,22016,0x7fe1d5a50180,0x7fe1d2a242c0,65536,661136,74060040,17229733425900,17229733392284,17229733781084,17229733783221
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,199978,199978,4194304,256,0,0,16,24,22720,0x7fe1d5a50000,0x7fe1d2a24300,131072,692774,77575808,17229733814700,17229733781084,17229734081405,17229734103252
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,199978,199978,4194304,256,0,0,12,24,23424,0x7fe1d32ede80,0x7fe1d2a24340,131072,696002,77982304,17229734116062,17229734081405,17229734400765,17229734403004
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,199978,199978,4194304,256,0,0,12,24,24128,0x7fe1d32edd00,0x7fe1d2a24380,131072,694870,77780424,17229734442153,17229734400765,17229734703485,17229734705525
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,199978,199978,4194304,256,0,0,16,24,24832,0x7fe1d32edb80,0x7fe1d2a243c0,131072,693142,77612224,17229734737245,17229734703485,17229735078845,17229735080325
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,199978,199978,4194304,256,0,0,16,24,25536,0x7fe1d32eda00,0x7fe1d2a24400,65536,632122,70739888,17229735111904,17229735078845,17229735442526,17229735444085
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,199978,199978,4194304,256,0,0,12,24,26240,0x7fe1d32ed880,0x7fe1d2a24440,131072,696514,78115888,17229735474235,17229735442526,17229735713406,17229735714958
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,199978,199978,4194304,256,0,0,12,24,26944,0x7fe1d32ed700,0x7fe1d2a24480,131072,697122,78073464,17229735745907,17229735713406,17229735988926,17229735990371
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,199978,199978,4194304,256,0,0,12,24,27648,0x7fe1d5a50580,0x7fe1d2a244c0,131072,656260,73458768,17229736028670,17229735988926,17229736267966,17229736269463
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,199978,199978,4194304,256,0,0,16,24,28608,0x7fe1d5a50400,0x7fe1d2a24500,131072,694092,77729424,17229736300782,17229736267966,17229736628127,17229736629553
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,199978,199978,4194304,256,0,0,16,24,29312,0x7fe1d5a50280,0x7fe1d2a24540,65536,653480,73120032,17229736661042,17229736628127,17229736987807,17229736989253
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,199978,199978,4194304,256,0,0,12,24,30016,0x7fe1d5a50100,0x7fe1d2a24580,131072,651654,72963520,17229737021073,17229736987807,17229737259327,17229737260826
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,199978,199978,4194304,256,0,0,8,24,30976,0x7fe1d32edf80,0x7fe1d2a245c0,131072,676638,75862016,17229737292915,17229737259327,17229737536287,17229737537729
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,199978,199978,4194304,256,0,0,12,24,31680,0x7fe1d32ede00,0x7fe1d2a24600,131072,697408,78157968,17229737575827,17229737536287,17229737809728,17229737811211
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,199978,199978,4194304,256,0,0,16,24,32640,0x7fe1d32edc80,0x7fe1d2a24640,131072,651490,72953896,17229737842360,17229737809728,17229738171808,17229738173581
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,199978,199978,4194304,256,0,0,12,24,33600,0x7fe1d32edb00,0x7fe1d2a24680,65536,647570,72530616,17229738204170,17229738171808,17229738538688,17229738540131
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,199978,199978,4194304,256,0,0,12,24,34560,0x7fe1d32ed980,0x7fe1d2a246c0,131072,695336,77882328,17229738570871,17229738538688,17229738812928,17229738814384
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,199978,199978,4194304,256,0,0,8,24,35520,0x7fe1d32ed800,0x7fe1d2a24700,131072,692392,77567480,17229738845563,17229738812928,17229739087329,17229739088797
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,199978,199978,4194304,256,0,0,12,24,36224,0x7fe1d32ed680,0x7fe1d2a24740,131072,686996,77028992,17229739127145,17229739087329,17229739365409,17229739366779
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,199978,199978,4194304,256,0,0,12,24,37184,0x7fe1d5a50500,0x7fe1d2a24780,131072,650852,72891072,17229739397518,17229739365409,17229739726209,17229739727719
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,199978,199978,4194304,256,0,0,12,24,38144,0x7fe1d5a50380,0x7fe1d2a247c0,65536,652532,73094752,17229739759308,17229739726209,17229740085089,17229740086490
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,199978,199978,4194304,256,0,0,12,24,39104,0x7fe1d5a50200,0x7fe1d2a24800,131072,688218,77136928,17229740117329,17229740085089,17229740358210,17229740359662
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,199978,199978,4194304,256,0,0,8,24,40320,0x7fe1d5a50080,0x7fe1d2a24840,131072,689854,77240728,17229740391301,17229740358210,17229740630690,17229740632135
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,199978,199978,4194304,256,0,0,12,24,41280,0x7fe1d32edf00,0x7fe1d2a24880,131072,698612,78183104,17229740670384,17229740630690,17229740907970,17229740909567
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,199978,199978,4194304,256,0,0,12,24,42240,0x7fe1d32edd80,0x7fe1d2a248c0,131072,688732,77205936,17229740939887,17229740907970,17229741283490,17229741285027
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,199978,199978,4194304,256,0,0,12,24,43200,0x7fe1d32edc00,0x7fe1d2a24900,65536,643360,72084848,17229741316056,17229741283490,17229741644931,17229741646397
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,199978,199978,4194304,256,0,0,8,24,44160,0x7fe1d32eda80,0x7fe1d2a24940,131072,694312,77835328,17229741677187,17229741644931,17229741917571,17229741919010
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,199978,199978,4194304,256,0,0,12,24,45376,0x7fe1d32ed900,0x7fe1d2a24980,131072,690512,77344248,17229741949439,17229741917571,17229742203331,17229742204862
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,199978,199978,4194304,256,0,0,12,24,46336,0x7fe1d32ed780,0x7fe1d2a249c0,131072,694344,77807592,17229742242981,17229742203331,17229742487171,17229742488715
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,199978,199978,4194304,256,0,0,12,24,47552,0x7fe1d32ed600,0x7fe1d2a24a00,131072,699456,78338704,17229742520354,17229742487171,17229742848132,17229742849545
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,199978,199978,4194304,256,0,0,12,24,48512,0x7fe1d5a50480,0x7fe1d2a24a40,65536,655170,73448704,17229742881104,17229742848132,17229743205252,17229743206795
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,199978,199978,4194304,256,0,0,8,24,49472,0x7fe1d5a50300,0x7fe1d2a24a80,131072,657420,73669896,17229743238224,17229743205252,17229743478372,17229743479828
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,199978,199978,4194304,256,0,0,12,24,50688,0x7fe1d5a50180,0x7fe1d2a24ac0,131072,655534,73262024,17229743511727,17229743478372,17229743749092,17229743750621
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,199978,199978,4194304,256,0,0,12,24,51648,0x7fe1d5a50000,0x7fe1d2a24b00,131072,653462,73291488,17229743789280,17229743749092,17229744033732,17229744035243
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,199978,199978,4194304,256,0,0,12,24,52864,0x7fe1d32ede80,0x7fe1d2a24b40,131072,701236,78512344,17229744067372,17229744033732,17229744392773,17229744394223
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,199978,199978,4194304,256,0,0,12,24,54080,0x7fe1d32edd00,0x7fe1d2a24b80,65536,651740,72963632,17229744425492,17229744392773,17229744750853,17229744752374
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,199978,199978,4194304,256,0,0,8,24,55296,0x7fe1d32edb80,0x7fe1d2a24bc0,131072,690970,77444424,17229744783923,17229744750853,17229745023333,17229745024756
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,199978,199978,4194304,256,0,0,12,24,56768,0x7fe1d32eda00,0x7fe1d2a24c00,131072,691894,77577944,17229745055765,17229745023333,17229745297893,17229745299439
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,199978,199978,4194304,256,0,0,12,24,57728,0x7fe1d32ed880,0x7fe1d2a24c40,131072,690332,77267912,17229745337298,17229745297893,17229745570854,17229745572301
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,199978,199978,4194304,256,0,0,12,24,58944,0x7fe1d32ed700,0x7fe1d2a24c80,131072,650030,72785448,17229745603361,17229745570854,17229745930054,17229745931472
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,199978,199978,4194304,256,0,0,12,24,60160,0x7fe1d5a50580,0x7fe1d2a24cc0,65536,648214,72658440,17229745962451,17229745930054,17229746297734,17229746299172
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,199978,199978,4194304,256,0,0,8,24,61376,0x7fe1d5a50400,0x7fe1d2a24d00,131072,694088,77665712,17229746330791,17229746297734,17229746577095,17229746578664
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,199978,199978,4194304,256,0,0,12,24,62848,0x7fe1d5a50280,0x7fe1d2a24d40,131072,697236,78081184,17229746610213,17229746577095,17229746857575,17229746859106
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,199978,199978,4194304,256,0,0,12,24,63808,0x7fe1d5a50100,0x7fe1d2a24d80,131072,691432,77482472,17229746898285,17229746857575,17229747131335,17229747132849
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,199978,199978,4194304,256,0,0,12,24,65024,0x7fe1d32edf80,0x7fe1d2a24dc0,131072,647160,72396728,17229747164348,17229747131335,17229747487815,17229747489279
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,199978,199978,4194304,256,0,0,12,24,66240,0x7fe1d32ede00,0x7fe1d2a24e00,65536,622286,69678184,17229747520279,17229747487815,17229747845416,17229747846890
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,199978,199978,4194304,256,0,0,8,24,67456,0x7fe1d32edc80,0x7fe1d2a24e40,131072,695708,77973768,17229747877299,17229747845416,17229748117896,17229748119392
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,199978,199978,4194304,256,0,0,12,24,68928,0x7fe1d32edb00,0x7fe1d2a24e80,131072,692924,77692848,17229748150211,17229748117896,17229748399336,17229748400855
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,199978,199978,4194304,256,0,0,12,24,70144,0x7fe1d32ed980,0x7fe1d2a24ec0,131072,654402,73185312,17229748438944,17229748399336,17229748673896,17229748675347
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,199978,199978,4194304,256,0,0,12,24,71616,0x7fe1d32ed800,0x7fe1d2a24f00,131072,703178,78741424,17229748706376,17229748673896,17229749034696,17229749036317
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,199978,199978,4194304,256,0,0,12,24,72832,0x7fe1d32ed680,0x7fe1d2a24f40,65536,658376,73762752,17229749067076,17229749034696,17229749395497,17229749396898
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,199978,199978,4194304,256,0,0,8,24,74048,0x7fe1d5a50500,0x7fe1d2a24f80,131072,654188,73164320,17229749427517,17229749395497,17229749672617,17229749674240
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,199978,199978,4194304,256,0,0,12,24,75776,0x7fe1d5a50380,0x7fe1d2a24fc0,131072,651998,73052896,17229749704559,17229749672617,17229749960617,17229749962062
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,199978,199978,4194304,256,0,0,12,24,76992,0x7fe1d5a50200,0x7fe1d2a25000,131072,693448,77708360,17229750000561,17229749960617,17229750248297,17229750250064
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,199978,199978,4194304,256,0,0,12,24,78464,0x7fe1d5a50080,0x7fe1d2a25040,131072,698358,78132256,17229750280964,17229750248297,17229750610698,17229750612285
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,199978,199978,4194304,256,0,0,12,24,79936,0x7fe1d32edf00,0x7fe1d2a25080,65536,656022,73489312,17229750644654,17229750610698,17229750969258,17229750970705
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,199978,199978,4194304,256,0,0,8,24,81408,0x7fe1d32edd80,0x7fe1d2a250c0,131072,687656,77075208,17229751001264,17229750969258,17229751241418,17229751242788
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,199978,199978,4194304,256,0,0,12,24,83136,0x7fe1d32edc00,0x7fe1d2a25100,131072,694816,77855688,17229751273967,17229751241418,17229751536618,17229751538090
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,199978,199978,4194304,256,0,0,12,24,84352,0x7fe1d32eda80,0x7fe1d2a25140,131072,723126,80993576,17229751588728,17229751536618,17229751815979,17229751817492
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,199978,199978,4194304,256,0,0,12,24,85824,0x7fe1d32ed900,0x7fe1d2a25180,131072,695490,77934520,17229751847561,17229751815979,17229752179179,17229752180572
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,199978,199978,4194304,256,0,0,12,24,87296,0x7fe1d32ed780,0x7fe1d2a251c0,65536,665304,74530984,17229752211071,17229752179179,17229752545099,17229752546532
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,199978,199978,4194304,256,0,0,12,24,88768,0x7fe1d32ed600,0x7fe1d2a25200,131072,690002,77289808,17229752577211,17229752545099,17229752817419,17229752818915
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,199978,199978,4194304,256,0,0,12,24,90752,0x7fe1d5a50480,0x7fe1d2a25240,131072,690972,77398064,17229752849594,17229752817419,17229753116460,17229753117937
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,199978,199978,4194304,256,0,0,12,24,91968,0x7fe1d5a50300,0x7fe1d2a25280,131072,693782,77700432,17229753155996,17229753116460,17229753389900,17229753391319
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,199978,199978,4194304,256,0,0,12,24,93440,0x7fe1d5a50180,0x7fe1d2a252c0,131072,680758,76218616,17229753421929,17229753389900,17229753751180,17229753752650
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,199978,199978,4194304,256,0,0,12,24,94912,0x7fe1d5a50000,0x7fe1d2a25300,65536,658788,73721336,17229753785469,17229753751180,17229754117581,17229754119130
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,199978,199978,4194304,256,0,0,12,24,96384,0x7fe1d32ede80,0x7fe1d2a25340,131072,691942,77554056,17229754150369,17229754117581,17229754396941,17229754398312
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,199978,199978,4194304,256,0,0,12,24,98368,0x7fe1d32edd00,0x7fe1d2a25380,131072,688758,77187880,17229754428951,17229754396941,17229754705101,17229754706604
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,199978,199978,4194304,256,0,0,12,24,99584,0x7fe1d32edb80,0x7fe1d2a253c0,131072,691104,77372464,17229754744113,17229754705101,17229754981261,17229754982856
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,199978,199978,4194304,256,0,0,12,24,101312,0x7fe1d32eda00,0x7fe1d2a25400,131072,649638,72733736,17229755013586,17229754981261,17229755348461,17229755349957
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,199978,199978,4194304,256,0,0,12,24,102784,0x7fe1d32ed880,0x7fe1d2a25440,65536,657900,73651048,17229755380396,17229755348461,17229755711502,17229755713037
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,199978,199978,4194304,256,0,0,12,24,104256,0x7fe1d32ed700,0x7fe1d2a25480,131072,703028,78742840,17229755743076,17229755711502,17229755987502,17229755988979
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,199978,199978,4194304,256,0,0,12,24,106240,0x7fe1d5a50580,0x7fe1d2a254c0,131072,653618,73344056,17229756019558,17229755987502,17229756298382,17229756299841
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,199978,199978,4194304,256,0,0,12,24,107712,0x7fe1d5a50400,0x7fe1d2a25500,131072,642784,71979936,17229756337770,17229756298382,17229756577262,17229756578843
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,199978,199978,4194304,256,0,0,16,24,109440,0x7fe1d5a50280,0x7fe1d2a25540,131072,711360,79613480,17229756610223,17229756577262,17229756935823,17229756937314
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,199978,199978,4194304,256,0,0,16,24,111168,0x7fe1d5a50100,0x7fe1d2a25580,65536,648064,72613816,17229756968403,17229756935823,17229757294703,17229757296194
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,199978,199978,4194304,256,0,0,8,24,112896,0x7fe1d32edf80,0x7fe1d2a255c0,131072,695014,77748400,17229757326353,17229757294703,17229757569903,17229757571307
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,199978,199978,4194304,256,0,0,12,24,115136,0x7fe1d32ede00,0x7fe1d2a25600,131072,686958,77029112,17229757601606,17229757569903,17229757889104,17229757890628
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,199978,199978,4194304,256,0,0,12,24,116608,0x7fe1d32edc80,0x7fe1d2a25640,131072,692630,77680104,17229757928397,17229757889104,17229758166704,17229758168340
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,199978,199978,4194304,256,0,0,16,24,118336,0x7fe1d32edb00,0x7fe1d2a25680,131072,694774,77900120,17229758198560,17229758166704,17229758539504,17229758541150
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,199978,199978,4194304,256,0,0,16,24,120064,0x7fe1d32ed980,0x7fe1d2a256c0,65536,648832,72663616,17229758571899,17229758539504,17229758897104,17229758898601
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,199978,199978,4194304,256,0,0,12,24,121792,0x7fe1d32ed800,0x7fe1d2a25700,131072,699648,78385872,17229758929200,17229758897104,17229759172305,17229759173773
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,199978,199978,4194304,256,0,0,12,24,124032,0x7fe1d32ed680,0x7fe1d2a25740,131072,688894,77158496,17229759204292,17229759172305,17229759493265,17229759494544
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,199978,199978,4194304,256,0,0,12,24,125504,0x7fe1d5a50500,0x7fe1d2a25780,131072,702652,78755024,17229759532313,17229759493265,17229759764625,17229759766167
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,199978,199978,4194304,256,0,0,12,24,127488,0x7fe1d5a50380,0x7fe1d2a257c0,131072,693964,77733776,17229759797796,17229759764625,17229760121425,17229760122967
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,199978,199978,4194304,256,0,0,12,24,129216,0x7fe1d5a50200,0x7fe1d2a25800,65536,662076,74109832,17229760154256,17229760121425,17229760479986,17229760481618
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,199978,199978,4194304,256,0,0,12,24,130944,0x7fe1d5a50080,0x7fe1d2a25840,131072,648944,72639784,17229760513127,17229760479986,17229760758226,17229760759580
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,199978,199978,4194304,256,0,0,12,24,133440,0x7fe1d32edf00,0x7fe1d2a25880,131072,655580,73383176,17229760790439,17229760758226,17229761090866,17229761092411
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,199978,199978,4194304,256,0,0,12,24,134912,0x7fe1d32edd80,0x7fe1d2a258c0,131072,1029228,115501488,17229761131190,17229761090866,17229761370866,17229761372383
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,199978,199978,4194304,256,0,0,12,24,136896,0x7fe1d32edc00,0x7fe1d2a25900,131072,658768,73737024,17229761402583,17229761370866,17229761733427,17229761735133
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,199978,199978,4194304,256,0,0,12,24,138880,0x7fe1d32eda80,0x7fe1d2a25940,65536,656608,73354024,17229761765903,17229761733427,17229762091347,17229762093114
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,199978,199978,4194304,256,0,0,12,24,140864,0x7fe1d32ed900,0x7fe1d2a25980,131072,699878,78359344,17229762123673,17229762091347,17229762381267,17229762382796
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,199978,199978,4194304,256,0,0,12,24,143616,0x7fe1d32ed780,0x7fe1d2a259c0,131072,692510,77546800,17229762412755,17229762381267,17229762728307,17229762729827
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,199978,199978,4194304,256,0,0,12,24,145344,0x7fe1d32ed600,0x7fe1d2a25a00,131072,1031390,115541096,17229762768226,17229762728307,17229763002868,17229763004429
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,199978,199978,4194304,256,0,0,12,24,147584,0x7fe1d5a50480,0x7fe1d2a25a40,131072,689014,77238960,17229763034908,17229763002868,17229763366388,17229763367859
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,199978,199978,4194304,256,0,0,12,24,149568,0x7fe1d5a50300,0x7fe1d2a25a80,65536,647862,72664936,17229763399298,17229763366388,17229763727508,17229763729040
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,199978,199978,4194304,256,0,0,12,24,151552,0x7fe1d5a50180,0x7fe1d2a25ac0,131072,677972,75915208,17229763759869,17229763727508,17229764018068,17229764019522
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,199978,199978,4194304,256,0,0,12,24,154304,0x7fe1d5a50000,0x7fe1d2a25b00,131072,655158,73297080,17229764050841,17229764018068,17229764385269,17229764386732
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,199978,199978,4194304,256,0,0,12,24,156288,0x7fe1d32ede80,0x7fe1d2a25b40,131072,979438,109780136,17229764425461,17229764385269,17229764667829,17229764669154
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,199978,199978,4194304,256,0,0,12,24,158784,0x7fe1d32edd00,0x7fe1d2a25b80,131072,749656,83895672,17229764699523,17229764667829,17229765031509,17229765033024
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,199978,199978,4194304,256,0,0,12,24,161024,0x7fe1d32edb80,0x7fe1d2a25bc0,65536,655836,73380776,17229765063114,17229765031509,17229765395029,17229765396425
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,199978,199978,4194304,256,0,0,12,24,163264,0x7fe1d32eda00,0x7fe1d2a25c00,131072,654092,73285872,17229765426734,17229765395029,17229765695830,17229765697276
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,199978,199978,4194304,256,0,0,12,24,166528,0x7fe1d32ed880,0x7fe1d2a25c40,131072,653258,73084176,17229765727446,17229765695830,17229766083030,17229766106585
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,199978,199978,4194304,256,0,0,12,24,168512,0x7fe1d32ed700,0x7fe1d2a25c80,131072,1029692,115221856,17229766125805,17229766083030,17229766389110,17229766390578
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,199978,199978,4194304,256,0,0,12,24,171264,0x7fe1d5a50580,0x7fe1d2a25cc0,131072,657502,73618456,17229766420967,17229766389110,17229766752471,17229766753848
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,199978,199978,4194304,256,0,0,12,24,173760,0x7fe1d5a50400,0x7fe1d2a25d00,65536,660430,73873128,17229766784717,17229766752471,17229767121431,17229767122838
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,199978,199978,4194304,256,0,0,12,24,176256,0x7fe1d5a50280,0x7fe1d2a25d40,131072,674432,75572384,17229767153587,17229767121431,17229767444471,17229767445949
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,199978,199978,4194304,256,0,0,12,24,179776,0x7fe1d5a50100,0x7fe1d2a25d80,131072,673906,75441072,17229767476208,17229767444471,17229767861431,17229767881467
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,199978,199978,4194304,256,0,0,12,24,182272,0x7fe1d32edf80,0x7fe1d2a25dc0,131072,981800,109942344,17229767901777,17229767861431,17229768177272,17229768178769
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,199978,199978,4194304,256,0,0,12,24,185536,0x7fe1d32ede00,0x7fe1d2a25e00,131072,690758,77372432,17229768210099,17229768177272,17229768550712,17229768570789
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,199978,199978,4194304,256,0,0,12,24,188544,0x7fe1d32edc80,0x7fe1d2a25e40,65536,659946,73901008,17229768583418,17229768550712,17229768932632,17229768949579
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,199978,199978,4194304,256,0,0,12,24,191552,0x7fe1d32edb00,0x7fe1d2a25e80,131072,658782,73851224,17229768965188,17229768932632,17229769278873,17229769280260
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,199978,199978,4194304,256,0,0,12,24,195840,0x7fe1d32ed980,0x7fe1d2a25ec0,131072,647704,72567408,17229769310839,17229769278873,17229769742073,17229769759407
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,199978,199978,4194304,256,0,0,12,24,198592,0x7fe1d32ed800,0x7fe1d2a25f00,131072,1028044,115064712,17229769784646,17229769742073,17229770080313,17229770081958
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,199978,199978,4194304,256,0,0,12,24,202368,0x7fe1d32ed680,0x7fe1d2a25f40,131072,973238,108984216,17229770112147,17229770080313,17229770470714,17229770487457
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,199978,199978,4194304,256,0,0,12,24,205888,0x7fe1d5a50500,0x7fe1d2a25f80,65536,655288,73453328,17229770503197,17229770470714,17229770867834,17229770885196
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,199978,199978,4194304,256,0,0,12,24,209408,0x7fe1d5a50380,0x7fe1d2a25fc0,131072,667030,74750376,17229770900176,17229770867834,17229771239994,17229771241506
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,199978,199978,4194304,256,0,0,12,24,214464,0x7fe1d5a50200,0x7fe1d2a26000,131072,652270,73091720,17229771272126,17229771239994,17229771752635,17229771770542
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,199978,199978,4194304,256,0,0,12,24,217728,0x7fe1d5a50080,0x7fe1d2a26040,131072,1037286,115977064,17229771793031,17229771752635,17229772110555,17229772111913
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,199978,199978,4194304,256,0,0,12,24,222016,0x7fe1d32edf00,0x7fe1d2a26080,131072,1048210,117580344,17229772143032,17229772110555,17229772520155,17229772536881
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,199978,199978,4194304,256,0,0,12,24,226048,0x7fe1d32edd80,0x7fe1d2a260c0,65536,654894,73366432,17229772553831,17229772520155,17229772935195,17229772952460
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,199978,199978,4194304,256,0,0,12,24,230080,0x7fe1d32edc00,0x7fe1d2a26100,131072,665448,74556000,17229772967760,17229772935195,17229773332156,17229773349379
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,199978,199978,4194304,256,0,0,12,24,235904,0x7fe1d32eda80,0x7fe1d2a26140,131072,698602,78228816,17229773365059,17229773332156,17229773902716,17229773919264
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,199978,199978,4194304,256,0,0,12,24,239424,0x7fe1d32ed900,0x7fe1d2a26180,131072,1025572,114815784,17229773941983,17229773902716,17229774272957,17229774274564
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,199978,199978,4194304,256,0,0,12,24,244224,0x7fe1d32ed780,0x7fe1d2a261c0,131072,991698,110841088,17229774305373,17229774272957,17229774711837,17229774757221
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,199978,199978,4194304,256,0,0,12,24,248768,0x7fe1d32ed600,0x7fe1d2a26200,65536,653126,73159768,17229774768521,17229774711837,17229775173277,17229775214729
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,199978,199978,4194304,256,0,0,12,24,253312,0x7fe1d5a50480,0x7fe1d2a26240,131072,658424,73694912,17229775226108,17229775173277,17229775619358,17229775660587
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,199978,199978,4194304,256,0,0,8,24,255552,0x7fe1d5a50300,0x7fe1d2a26280,131072,1030754,115550160,17229775671386,17229775619358,17229776292158,17229776334988
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,199978,199978,4194304,256,0,0,12,24,259840,0x7fe1d5a50180,0x7fe1d2a262c0,131072,1020390,114365104,17229776353308,17229776292158,17229776725118,17229776766297
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,199978,199978,4194304,256,0,0,12,24,265664,0x7fe1d5a50000,0x7fe1d2a26300,131072,981720,109672360,17229776777566,17229776725118,17229777231999,17229777272883
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,199978,199978,4194304,256,0,0,12,24,271232,0x7fe1d32ede80,0x7fe1d2a26340,65536,655876,73487520,17229777284863,17229777231999,17229777738879,17229777756560
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,199978,199978,4194304,256,0,0,8,24,273216,0x7fe1d32edd00,0x7fe1d2a26380,131072,986122,110432168,17229777771220,17229777738879,17229778220800,17229778265086
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,199978,199978,4194304,256,0,0,8,24,275712,0x7fe1d32edb80,0x7fe1d2a263c0,131072,1020804,114724544,17229778275936,17229778220800,17229778994560,17229779037965
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,199978,199978,4194304,256,0,0,12,24,280768,0x7fe1d32eda00,0x7fe1d2a26400,131072,989890,110757368,17229779057215,17229778994560,17229779476801,17229779518252
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,199978,199978,4194304,256,0,0,12,24,287616,0x7fe1d32ed880,0x7fe1d2a26440,131072,1037604,115958456,17229779529302,17229779476801,17229780033761,17229780075157
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,199978,199978,4194304,256,0,0,12,24,294208,0x7fe1d32ed700,0x7fe1d2a26480,65536,691110,77414008,17229780087117,17229780033761,17229780589762,17229780631282
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,199978,199978,4194304,256,0,0,8,24,296960,0x7fe1d5a50580,0x7fe1d2a264c0,131072,954500,107156008,17229780642192,17229780589762,17229781143682,17229781184837
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,199978,199978,4194304,256,0,0,8,24,299968,0x7fe1d5a50400,0x7fe1d2a26500,131072,1035532,116290400,17229781195507,17229781143682,17229782010563,17229782052583
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,199978,199978,4194304,256,0,0,8,24,302720,0x7fe1d5a50280,0x7fe1d2a26540,131072,1023712,114670064,17229782071263,17229782010563,17229782673763,17229782717285
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,199978,199978,4194304,256,0,0,12,24,305472,0x7fe1d5a50100,0x7fe1d2a26580,131072,1033124,115602776,17229782727805,17229782673763,17229783348644,17229783389767
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,199978,199978,4194304,256,0,0,12,24,308224,0x7fe1d32edf80,0x7fe1d2a265c0,65536,657370,73591752,17229783401007,17229783348644,17229784018724,17229784059619
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,199978,199978,4194304,256,0,0,8,24,310976,0x7fe1d32ede00,0x7fe1d2a26600,131072,1032580,115708432,17229784070059,17229784018724,17229784680005,17229784720851
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,199978,199978,4194304,256,0,0,8,24,313216,0x7fe1d32edc80,0x7fe1d2a26640,131072,1031196,115863144,17229784731231,17229784680005,17229785763846,17229785804932
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,199978,199978,4194304,256,0,0,8,24,315968,0x7fe1d32edb00,0x7fe1d2a26680,131072,1029072,115054072,17229785826221,17229785763563,17229786832523,17229786881313
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,199978,199978,4194304,256,0,0,12,24,318720,0x7fe1d32ed980,0x7fe1d2a266c0,131072,1021276,114635952,17229786892063,17229786832523,17229787935563,17229787999693
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,199978,199978,4194304,256,0,0,12,24,321472,0x7fe1d32ed800,0x7fe1d2a26700,65536,644584,72135416,17229788010422,17229787935563,17229789061643,17229789125802
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,199978,199978,4194304,256,0,0,8,24,324224,0x7fe1d32ed680,0x7fe1d2a26740,131072,1018932,114366704,17229789136902,17229789061643,17229790164363,17229790229782
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,199978,199978,4194304,256,0,0,8,24,326464,0x7fe1d5a50500,0x7fe1d2a26780,131072,1015630,113809128,17229790241082,17229790164363,17229792113804,17229792177919
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,199978,199978,4194304,256,0,0,8,24,329216,0x7fe1d5a50380,0x7fe1d2a267c0,131072,1078016,120535456,17229792196739,17229792113804,17229794026604,17229794104317
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,199978,199978,4194304,256,0,0,12,24,331968,0x7fe1d5a50200,0x7fe1d2a26800,131072,1024624,114585728,17229794115877,17229794026604,17229796022125,17229796096693
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,199978,199978,4194304,256,0,0,12,24,334720,0x7fe1d5a50080,0x7fe1d2a26840,65536,655984,73357232,17229796107923,17229796022125,17229798001485,17229798066830
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,199978,199978,4194304,256,0,0,8,24,337472,0x7fe1d32edf00,0x7fe1d2a26880,131072,1062814,119048120,17229798084779,17229798001485,17229800099086,17229800169393
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,199978,199978,4194304,256,0,0,8,24,0,0x7fe1d32edd80,0x7fe1d2a268c0,131072,1025300,114902272,17229800180823,17229800099086,17229803715887,17229803767726
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 199978 199978 33554432 256 0 0 4 32 4160 0x0 0x7fe1d2a04280 3670016 3040452 340321896 17229574411755 17224026851585 17229723837237 17229723948727
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 199978 199978 32768 256 0 0 12 24 13888 0x0 0x7fe1d2a23f80 512 97598 10948992 17229729109777 17229723837237 17229729235641 17229729240263
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 5 199978 199978 4194304 256 0 0 12 24 14336 0x7fe1d5a50380 0x7fe1d2a23fc0 65536 619714 69394784 17229729274252 17229729235641 17229729595641 17229729597774
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 199978 199978 4194304 256 0 0 16 24 15040 0x7fe1d5a50200 0x7fe1d2a24000 65536 650318 72879808 17229729633863 17229729595641 17229729997881 17229729999983
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 11 199978 199978 4194304 256 0 0 16 24 15488 0x7fe1d5a50080 0x7fe1d2a24040 65536 660540 73841616 17229730033752 17229729997881 17229730405402 17229730407522
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 14 199978 199978 4194304 256 0 0 12 24 15936 0x7fe1d32edf00 0x7fe1d2a24080 65536 651524 72958416 17229730439761 17229730405402 17229730712282 17229730714413
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 17 199978 199978 4194304 256 0 0 12 24 16384 0x7fe1d32edd80 0x7fe1d2a240c0 65536 621762 69629072 17229730746023 17229730712282 17229731016282 17229731018485
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 20 199978 199978 4194304 256 0 0 12 24 17088 0x7fe1d32edc00 0x7fe1d2a24100 131072 658036 73785048 17229731061514 17229731016282 17229731318682 17229731320617
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 199978 199978 4194304 256 0 0 16 24 17792 0x7fe1d32eda80 0x7fe1d2a24140 131072 692714 77624960 17229731352936 17229731318682 17229731705403 17229731707457
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 26 199978 199978 4194304 256 0 0 16 24 18496 0x7fe1d32ed900 0x7fe1d2a24180 65536 657794 73816888 17229731738516 17229731705403 17229732092283 17229732094766
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 29 199978 199978 4194304 256 0 0 16 24 19200 0x7fe1d32ed780 0x7fe1d2a241c0 131072 696868 78111816 17229732125465 17229732092283 17229732405083 17229732407348
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 32 199978 199978 4194304 256 0 0 16 24 19904 0x7fe1d32ed600 0x7fe1d2a24200 131072 688984 77089720 17229732439337 17229732405083 17229732705243 17229732707560
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 35 199978 199978 4194304 256 0 0 12 24 20608 0x7fe1d5a50480 0x7fe1d2a24240 131072 697572 78205352 17229732747848 17229732705243 17229733005084 17229733007491
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 199978 199978 4194304 256 0 0 16 24 21312 0x7fe1d5a50300 0x7fe1d2a24280 131072 699686 78315120 17229733039281 17229733005084 17229733392284 17229733394351
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 41 199978 199978 4194304 256 0 0 16 24 22016 0x7fe1d5a50180 0x7fe1d2a242c0 65536 661136 74060040 17229733425900 17229733392284 17229733781084 17229733783221
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 44 199978 199978 4194304 256 0 0 16 24 22720 0x7fe1d5a50000 0x7fe1d2a24300 131072 692774 77575808 17229733814700 17229733781084 17229734081405 17229734103252
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 47 199978 199978 4194304 256 0 0 12 24 23424 0x7fe1d32ede80 0x7fe1d2a24340 131072 696002 77982304 17229734116062 17229734081405 17229734400765 17229734403004
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 50 199978 199978 4194304 256 0 0 12 24 24128 0x7fe1d32edd00 0x7fe1d2a24380 131072 694870 77780424 17229734442153 17229734400765 17229734703485 17229734705525
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 199978 199978 4194304 256 0 0 16 24 24832 0x7fe1d32edb80 0x7fe1d2a243c0 131072 693142 77612224 17229734737245 17229734703485 17229735078845 17229735080325
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 56 199978 199978 4194304 256 0 0 16 24 25536 0x7fe1d32eda00 0x7fe1d2a24400 65536 632122 70739888 17229735111904 17229735078845 17229735442526 17229735444085
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 59 199978 199978 4194304 256 0 0 12 24 26240 0x7fe1d32ed880 0x7fe1d2a24440 131072 696514 78115888 17229735474235 17229735442526 17229735713406 17229735714958
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 62 199978 199978 4194304 256 0 0 12 24 26944 0x7fe1d32ed700 0x7fe1d2a24480 131072 697122 78073464 17229735745907 17229735713406 17229735988926 17229735990371
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 65 199978 199978 4194304 256 0 0 12 24 27648 0x7fe1d5a50580 0x7fe1d2a244c0 131072 656260 73458768 17229736028670 17229735988926 17229736267966 17229736269463
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 199978 199978 4194304 256 0 0 16 24 28608 0x7fe1d5a50400 0x7fe1d2a24500 131072 694092 77729424 17229736300782 17229736267966 17229736628127 17229736629553
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 71 199978 199978 4194304 256 0 0 16 24 29312 0x7fe1d5a50280 0x7fe1d2a24540 65536 653480 73120032 17229736661042 17229736628127 17229736987807 17229736989253
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 74 199978 199978 4194304 256 0 0 12 24 30016 0x7fe1d5a50100 0x7fe1d2a24580 131072 651654 72963520 17229737021073 17229736987807 17229737259327 17229737260826
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 77 199978 199978 4194304 256 0 0 8 24 30976 0x7fe1d32edf80 0x7fe1d2a245c0 131072 676638 75862016 17229737292915 17229737259327 17229737536287 17229737537729
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 80 199978 199978 4194304 256 0 0 12 24 31680 0x7fe1d32ede00 0x7fe1d2a24600 131072 697408 78157968 17229737575827 17229737536287 17229737809728 17229737811211
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 199978 199978 4194304 256 0 0 16 24 32640 0x7fe1d32edc80 0x7fe1d2a24640 131072 651490 72953896 17229737842360 17229737809728 17229738171808 17229738173581
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 86 199978 199978 4194304 256 0 0 12 24 33600 0x7fe1d32edb00 0x7fe1d2a24680 65536 647570 72530616 17229738204170 17229738171808 17229738538688 17229738540131
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 89 199978 199978 4194304 256 0 0 12 24 34560 0x7fe1d32ed980 0x7fe1d2a246c0 131072 695336 77882328 17229738570871 17229738538688 17229738812928 17229738814384
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 92 199978 199978 4194304 256 0 0 8 24 35520 0x7fe1d32ed800 0x7fe1d2a24700 131072 692392 77567480 17229738845563 17229738812928 17229739087329 17229739088797
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 95 199978 199978 4194304 256 0 0 12 24 36224 0x7fe1d32ed680 0x7fe1d2a24740 131072 686996 77028992 17229739127145 17229739087329 17229739365409 17229739366779
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 199978 199978 4194304 256 0 0 12 24 37184 0x7fe1d5a50500 0x7fe1d2a24780 131072 650852 72891072 17229739397518 17229739365409 17229739726209 17229739727719
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 101 199978 199978 4194304 256 0 0 12 24 38144 0x7fe1d5a50380 0x7fe1d2a247c0 65536 652532 73094752 17229739759308 17229739726209 17229740085089 17229740086490
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 104 199978 199978 4194304 256 0 0 12 24 39104 0x7fe1d5a50200 0x7fe1d2a24800 131072 688218 77136928 17229740117329 17229740085089 17229740358210 17229740359662
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 107 199978 199978 4194304 256 0 0 8 24 40320 0x7fe1d5a50080 0x7fe1d2a24840 131072 689854 77240728 17229740391301 17229740358210 17229740630690 17229740632135
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 110 199978 199978 4194304 256 0 0 12 24 41280 0x7fe1d32edf00 0x7fe1d2a24880 131072 698612 78183104 17229740670384 17229740630690 17229740907970 17229740909567
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 199978 199978 4194304 256 0 0 12 24 42240 0x7fe1d32edd80 0x7fe1d2a248c0 131072 688732 77205936 17229740939887 17229740907970 17229741283490 17229741285027
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 116 199978 199978 4194304 256 0 0 12 24 43200 0x7fe1d32edc00 0x7fe1d2a24900 65536 643360 72084848 17229741316056 17229741283490 17229741644931 17229741646397
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 119 199978 199978 4194304 256 0 0 8 24 44160 0x7fe1d32eda80 0x7fe1d2a24940 131072 694312 77835328 17229741677187 17229741644931 17229741917571 17229741919010
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 122 199978 199978 4194304 256 0 0 12 24 45376 0x7fe1d32ed900 0x7fe1d2a24980 131072 690512 77344248 17229741949439 17229741917571 17229742203331 17229742204862
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 125 199978 199978 4194304 256 0 0 12 24 46336 0x7fe1d32ed780 0x7fe1d2a249c0 131072 694344 77807592 17229742242981 17229742203331 17229742487171 17229742488715
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 199978 199978 4194304 256 0 0 12 24 47552 0x7fe1d32ed600 0x7fe1d2a24a00 131072 699456 78338704 17229742520354 17229742487171 17229742848132 17229742849545
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 131 199978 199978 4194304 256 0 0 12 24 48512 0x7fe1d5a50480 0x7fe1d2a24a40 65536 655170 73448704 17229742881104 17229742848132 17229743205252 17229743206795
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 134 199978 199978 4194304 256 0 0 8 24 49472 0x7fe1d5a50300 0x7fe1d2a24a80 131072 657420 73669896 17229743238224 17229743205252 17229743478372 17229743479828
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 137 199978 199978 4194304 256 0 0 12 24 50688 0x7fe1d5a50180 0x7fe1d2a24ac0 131072 655534 73262024 17229743511727 17229743478372 17229743749092 17229743750621
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 140 199978 199978 4194304 256 0 0 12 24 51648 0x7fe1d5a50000 0x7fe1d2a24b00 131072 653462 73291488 17229743789280 17229743749092 17229744033732 17229744035243
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 199978 199978 4194304 256 0 0 12 24 52864 0x7fe1d32ede80 0x7fe1d2a24b40 131072 701236 78512344 17229744067372 17229744033732 17229744392773 17229744394223
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 146 199978 199978 4194304 256 0 0 12 24 54080 0x7fe1d32edd00 0x7fe1d2a24b80 65536 651740 72963632 17229744425492 17229744392773 17229744750853 17229744752374
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 149 199978 199978 4194304 256 0 0 8 24 55296 0x7fe1d32edb80 0x7fe1d2a24bc0 131072 690970 77444424 17229744783923 17229744750853 17229745023333 17229745024756
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 152 199978 199978 4194304 256 0 0 12 24 56768 0x7fe1d32eda00 0x7fe1d2a24c00 131072 691894 77577944 17229745055765 17229745023333 17229745297893 17229745299439
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 155 199978 199978 4194304 256 0 0 12 24 57728 0x7fe1d32ed880 0x7fe1d2a24c40 131072 690332 77267912 17229745337298 17229745297893 17229745570854 17229745572301
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 199978 199978 4194304 256 0 0 12 24 58944 0x7fe1d32ed700 0x7fe1d2a24c80 131072 650030 72785448 17229745603361 17229745570854 17229745930054 17229745931472
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 161 199978 199978 4194304 256 0 0 12 24 60160 0x7fe1d5a50580 0x7fe1d2a24cc0 65536 648214 72658440 17229745962451 17229745930054 17229746297734 17229746299172
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 164 199978 199978 4194304 256 0 0 8 24 61376 0x7fe1d5a50400 0x7fe1d2a24d00 131072 694088 77665712 17229746330791 17229746297734 17229746577095 17229746578664
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 167 199978 199978 4194304 256 0 0 12 24 62848 0x7fe1d5a50280 0x7fe1d2a24d40 131072 697236 78081184 17229746610213 17229746577095 17229746857575 17229746859106
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 170 199978 199978 4194304 256 0 0 12 24 63808 0x7fe1d5a50100 0x7fe1d2a24d80 131072 691432 77482472 17229746898285 17229746857575 17229747131335 17229747132849
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 199978 199978 4194304 256 0 0 12 24 65024 0x7fe1d32edf80 0x7fe1d2a24dc0 131072 647160 72396728 17229747164348 17229747131335 17229747487815 17229747489279
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 176 199978 199978 4194304 256 0 0 12 24 66240 0x7fe1d32ede00 0x7fe1d2a24e00 65536 622286 69678184 17229747520279 17229747487815 17229747845416 17229747846890
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 179 199978 199978 4194304 256 0 0 8 24 67456 0x7fe1d32edc80 0x7fe1d2a24e40 131072 695708 77973768 17229747877299 17229747845416 17229748117896 17229748119392
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 182 199978 199978 4194304 256 0 0 12 24 68928 0x7fe1d32edb00 0x7fe1d2a24e80 131072 692924 77692848 17229748150211 17229748117896 17229748399336 17229748400855
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 185 199978 199978 4194304 256 0 0 12 24 70144 0x7fe1d32ed980 0x7fe1d2a24ec0 131072 654402 73185312 17229748438944 17229748399336 17229748673896 17229748675347
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 199978 199978 4194304 256 0 0 12 24 71616 0x7fe1d32ed800 0x7fe1d2a24f00 131072 703178 78741424 17229748706376 17229748673896 17229749034696 17229749036317
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 191 199978 199978 4194304 256 0 0 12 24 72832 0x7fe1d32ed680 0x7fe1d2a24f40 65536 658376 73762752 17229749067076 17229749034696 17229749395497 17229749396898
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 194 199978 199978 4194304 256 0 0 8 24 74048 0x7fe1d5a50500 0x7fe1d2a24f80 131072 654188 73164320 17229749427517 17229749395497 17229749672617 17229749674240
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 197 199978 199978 4194304 256 0 0 12 24 75776 0x7fe1d5a50380 0x7fe1d2a24fc0 131072 651998 73052896 17229749704559 17229749672617 17229749960617 17229749962062
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 200 199978 199978 4194304 256 0 0 12 24 76992 0x7fe1d5a50200 0x7fe1d2a25000 131072 693448 77708360 17229750000561 17229749960617 17229750248297 17229750250064
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 199978 199978 4194304 256 0 0 12 24 78464 0x7fe1d5a50080 0x7fe1d2a25040 131072 698358 78132256 17229750280964 17229750248297 17229750610698 17229750612285
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 206 199978 199978 4194304 256 0 0 12 24 79936 0x7fe1d32edf00 0x7fe1d2a25080 65536 656022 73489312 17229750644654 17229750610698 17229750969258 17229750970705
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 209 199978 199978 4194304 256 0 0 8 24 81408 0x7fe1d32edd80 0x7fe1d2a250c0 131072 687656 77075208 17229751001264 17229750969258 17229751241418 17229751242788
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 212 199978 199978 4194304 256 0 0 12 24 83136 0x7fe1d32edc00 0x7fe1d2a25100 131072 694816 77855688 17229751273967 17229751241418 17229751536618 17229751538090
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 215 199978 199978 4194304 256 0 0 12 24 84352 0x7fe1d32eda80 0x7fe1d2a25140 131072 723126 80993576 17229751588728 17229751536618 17229751815979 17229751817492
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 199978 199978 4194304 256 0 0 12 24 85824 0x7fe1d32ed900 0x7fe1d2a25180 131072 695490 77934520 17229751847561 17229751815979 17229752179179 17229752180572
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 221 199978 199978 4194304 256 0 0 12 24 87296 0x7fe1d32ed780 0x7fe1d2a251c0 65536 665304 74530984 17229752211071 17229752179179 17229752545099 17229752546532
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 224 199978 199978 4194304 256 0 0 12 24 88768 0x7fe1d32ed600 0x7fe1d2a25200 131072 690002 77289808 17229752577211 17229752545099 17229752817419 17229752818915
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 227 199978 199978 4194304 256 0 0 12 24 90752 0x7fe1d5a50480 0x7fe1d2a25240 131072 690972 77398064 17229752849594 17229752817419 17229753116460 17229753117937
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 230 199978 199978 4194304 256 0 0 12 24 91968 0x7fe1d5a50300 0x7fe1d2a25280 131072 693782 77700432 17229753155996 17229753116460 17229753389900 17229753391319
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 199978 199978 4194304 256 0 0 12 24 93440 0x7fe1d5a50180 0x7fe1d2a252c0 131072 680758 76218616 17229753421929 17229753389900 17229753751180 17229753752650
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 236 199978 199978 4194304 256 0 0 12 24 94912 0x7fe1d5a50000 0x7fe1d2a25300 65536 658788 73721336 17229753785469 17229753751180 17229754117581 17229754119130
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 239 199978 199978 4194304 256 0 0 12 24 96384 0x7fe1d32ede80 0x7fe1d2a25340 131072 691942 77554056 17229754150369 17229754117581 17229754396941 17229754398312
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 242 199978 199978 4194304 256 0 0 12 24 98368 0x7fe1d32edd00 0x7fe1d2a25380 131072 688758 77187880 17229754428951 17229754396941 17229754705101 17229754706604
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 245 199978 199978 4194304 256 0 0 12 24 99584 0x7fe1d32edb80 0x7fe1d2a253c0 131072 691104 77372464 17229754744113 17229754705101 17229754981261 17229754982856
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 199978 199978 4194304 256 0 0 12 24 101312 0x7fe1d32eda00 0x7fe1d2a25400 131072 649638 72733736 17229755013586 17229754981261 17229755348461 17229755349957
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 251 199978 199978 4194304 256 0 0 12 24 102784 0x7fe1d32ed880 0x7fe1d2a25440 65536 657900 73651048 17229755380396 17229755348461 17229755711502 17229755713037
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 254 199978 199978 4194304 256 0 0 12 24 104256 0x7fe1d32ed700 0x7fe1d2a25480 131072 703028 78742840 17229755743076 17229755711502 17229755987502 17229755988979
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 257 199978 199978 4194304 256 0 0 12 24 106240 0x7fe1d5a50580 0x7fe1d2a254c0 131072 653618 73344056 17229756019558 17229755987502 17229756298382 17229756299841
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 260 199978 199978 4194304 256 0 0 12 24 107712 0x7fe1d5a50400 0x7fe1d2a25500 131072 642784 71979936 17229756337770 17229756298382 17229756577262 17229756578843
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 199978 199978 4194304 256 0 0 16 24 109440 0x7fe1d5a50280 0x7fe1d2a25540 131072 711360 79613480 17229756610223 17229756577262 17229756935823 17229756937314
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 266 199978 199978 4194304 256 0 0 16 24 111168 0x7fe1d5a50100 0x7fe1d2a25580 65536 648064 72613816 17229756968403 17229756935823 17229757294703 17229757296194
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 269 199978 199978 4194304 256 0 0 8 24 112896 0x7fe1d32edf80 0x7fe1d2a255c0 131072 695014 77748400 17229757326353 17229757294703 17229757569903 17229757571307
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 272 199978 199978 4194304 256 0 0 12 24 115136 0x7fe1d32ede00 0x7fe1d2a25600 131072 686958 77029112 17229757601606 17229757569903 17229757889104 17229757890628
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 275 199978 199978 4194304 256 0 0 12 24 116608 0x7fe1d32edc80 0x7fe1d2a25640 131072 692630 77680104 17229757928397 17229757889104 17229758166704 17229758168340
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 199978 199978 4194304 256 0 0 16 24 118336 0x7fe1d32edb00 0x7fe1d2a25680 131072 694774 77900120 17229758198560 17229758166704 17229758539504 17229758541150
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 281 199978 199978 4194304 256 0 0 16 24 120064 0x7fe1d32ed980 0x7fe1d2a256c0 65536 648832 72663616 17229758571899 17229758539504 17229758897104 17229758898601
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 284 199978 199978 4194304 256 0 0 12 24 121792 0x7fe1d32ed800 0x7fe1d2a25700 131072 699648 78385872 17229758929200 17229758897104 17229759172305 17229759173773
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 287 199978 199978 4194304 256 0 0 12 24 124032 0x7fe1d32ed680 0x7fe1d2a25740 131072 688894 77158496 17229759204292 17229759172305 17229759493265 17229759494544
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 290 199978 199978 4194304 256 0 0 12 24 125504 0x7fe1d5a50500 0x7fe1d2a25780 131072 702652 78755024 17229759532313 17229759493265 17229759764625 17229759766167
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 199978 199978 4194304 256 0 0 12 24 127488 0x7fe1d5a50380 0x7fe1d2a257c0 131072 693964 77733776 17229759797796 17229759764625 17229760121425 17229760122967
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 296 199978 199978 4194304 256 0 0 12 24 129216 0x7fe1d5a50200 0x7fe1d2a25800 65536 662076 74109832 17229760154256 17229760121425 17229760479986 17229760481618
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 299 199978 199978 4194304 256 0 0 12 24 130944 0x7fe1d5a50080 0x7fe1d2a25840 131072 648944 72639784 17229760513127 17229760479986 17229760758226 17229760759580
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 302 199978 199978 4194304 256 0 0 12 24 133440 0x7fe1d32edf00 0x7fe1d2a25880 131072 655580 73383176 17229760790439 17229760758226 17229761090866 17229761092411
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 305 199978 199978 4194304 256 0 0 12 24 134912 0x7fe1d32edd80 0x7fe1d2a258c0 131072 1029228 115501488 17229761131190 17229761090866 17229761370866 17229761372383
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 199978 199978 4194304 256 0 0 12 24 136896 0x7fe1d32edc00 0x7fe1d2a25900 131072 658768 73737024 17229761402583 17229761370866 17229761733427 17229761735133
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 311 199978 199978 4194304 256 0 0 12 24 138880 0x7fe1d32eda80 0x7fe1d2a25940 65536 656608 73354024 17229761765903 17229761733427 17229762091347 17229762093114
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 314 199978 199978 4194304 256 0 0 12 24 140864 0x7fe1d32ed900 0x7fe1d2a25980 131072 699878 78359344 17229762123673 17229762091347 17229762381267 17229762382796
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 317 199978 199978 4194304 256 0 0 12 24 143616 0x7fe1d32ed780 0x7fe1d2a259c0 131072 692510 77546800 17229762412755 17229762381267 17229762728307 17229762729827
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 320 199978 199978 4194304 256 0 0 12 24 145344 0x7fe1d32ed600 0x7fe1d2a25a00 131072 1031390 115541096 17229762768226 17229762728307 17229763002868 17229763004429
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 199978 199978 4194304 256 0 0 12 24 147584 0x7fe1d5a50480 0x7fe1d2a25a40 131072 689014 77238960 17229763034908 17229763002868 17229763366388 17229763367859
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 326 199978 199978 4194304 256 0 0 12 24 149568 0x7fe1d5a50300 0x7fe1d2a25a80 65536 647862 72664936 17229763399298 17229763366388 17229763727508 17229763729040
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 329 199978 199978 4194304 256 0 0 12 24 151552 0x7fe1d5a50180 0x7fe1d2a25ac0 131072 677972 75915208 17229763759869 17229763727508 17229764018068 17229764019522
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 332 199978 199978 4194304 256 0 0 12 24 154304 0x7fe1d5a50000 0x7fe1d2a25b00 131072 655158 73297080 17229764050841 17229764018068 17229764385269 17229764386732
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 335 199978 199978 4194304 256 0 0 12 24 156288 0x7fe1d32ede80 0x7fe1d2a25b40 131072 979438 109780136 17229764425461 17229764385269 17229764667829 17229764669154
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 199978 199978 4194304 256 0 0 12 24 158784 0x7fe1d32edd00 0x7fe1d2a25b80 131072 749656 83895672 17229764699523 17229764667829 17229765031509 17229765033024
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 341 199978 199978 4194304 256 0 0 12 24 161024 0x7fe1d32edb80 0x7fe1d2a25bc0 65536 655836 73380776 17229765063114 17229765031509 17229765395029 17229765396425
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 344 199978 199978 4194304 256 0 0 12 24 163264 0x7fe1d32eda00 0x7fe1d2a25c00 131072 654092 73285872 17229765426734 17229765395029 17229765695830 17229765697276
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 347 199978 199978 4194304 256 0 0 12 24 166528 0x7fe1d32ed880 0x7fe1d2a25c40 131072 653258 73084176 17229765727446 17229765695830 17229766083030 17229766106585
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 350 199978 199978 4194304 256 0 0 12 24 168512 0x7fe1d32ed700 0x7fe1d2a25c80 131072 1029692 115221856 17229766125805 17229766083030 17229766389110 17229766390578
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 199978 199978 4194304 256 0 0 12 24 171264 0x7fe1d5a50580 0x7fe1d2a25cc0 131072 657502 73618456 17229766420967 17229766389110 17229766752471 17229766753848
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 356 199978 199978 4194304 256 0 0 12 24 173760 0x7fe1d5a50400 0x7fe1d2a25d00 65536 660430 73873128 17229766784717 17229766752471 17229767121431 17229767122838
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 359 199978 199978 4194304 256 0 0 12 24 176256 0x7fe1d5a50280 0x7fe1d2a25d40 131072 674432 75572384 17229767153587 17229767121431 17229767444471 17229767445949
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 362 199978 199978 4194304 256 0 0 12 24 179776 0x7fe1d5a50100 0x7fe1d2a25d80 131072 673906 75441072 17229767476208 17229767444471 17229767861431 17229767881467
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 365 199978 199978 4194304 256 0 0 12 24 182272 0x7fe1d32edf80 0x7fe1d2a25dc0 131072 981800 109942344 17229767901777 17229767861431 17229768177272 17229768178769
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 199978 199978 4194304 256 0 0 12 24 185536 0x7fe1d32ede00 0x7fe1d2a25e00 131072 690758 77372432 17229768210099 17229768177272 17229768550712 17229768570789
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 371 199978 199978 4194304 256 0 0 12 24 188544 0x7fe1d32edc80 0x7fe1d2a25e40 65536 659946 73901008 17229768583418 17229768550712 17229768932632 17229768949579
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 374 199978 199978 4194304 256 0 0 12 24 191552 0x7fe1d32edb00 0x7fe1d2a25e80 131072 658782 73851224 17229768965188 17229768932632 17229769278873 17229769280260
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 377 199978 199978 4194304 256 0 0 12 24 195840 0x7fe1d32ed980 0x7fe1d2a25ec0 131072 647704 72567408 17229769310839 17229769278873 17229769742073 17229769759407
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 380 199978 199978 4194304 256 0 0 12 24 198592 0x7fe1d32ed800 0x7fe1d2a25f00 131072 1028044 115064712 17229769784646 17229769742073 17229770080313 17229770081958
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 199978 199978 4194304 256 0 0 12 24 202368 0x7fe1d32ed680 0x7fe1d2a25f40 131072 973238 108984216 17229770112147 17229770080313 17229770470714 17229770487457
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 386 199978 199978 4194304 256 0 0 12 24 205888 0x7fe1d5a50500 0x7fe1d2a25f80 65536 655288 73453328 17229770503197 17229770470714 17229770867834 17229770885196
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 389 199978 199978 4194304 256 0 0 12 24 209408 0x7fe1d5a50380 0x7fe1d2a25fc0 131072 667030 74750376 17229770900176 17229770867834 17229771239994 17229771241506
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 392 199978 199978 4194304 256 0 0 12 24 214464 0x7fe1d5a50200 0x7fe1d2a26000 131072 652270 73091720 17229771272126 17229771239994 17229771752635 17229771770542
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 395 199978 199978 4194304 256 0 0 12 24 217728 0x7fe1d5a50080 0x7fe1d2a26040 131072 1037286 115977064 17229771793031 17229771752635 17229772110555 17229772111913
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 199978 199978 4194304 256 0 0 12 24 222016 0x7fe1d32edf00 0x7fe1d2a26080 131072 1048210 117580344 17229772143032 17229772110555 17229772520155 17229772536881
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 401 199978 199978 4194304 256 0 0 12 24 226048 0x7fe1d32edd80 0x7fe1d2a260c0 65536 654894 73366432 17229772553831 17229772520155 17229772935195 17229772952460
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 404 199978 199978 4194304 256 0 0 12 24 230080 0x7fe1d32edc00 0x7fe1d2a26100 131072 665448 74556000 17229772967760 17229772935195 17229773332156 17229773349379
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 407 199978 199978 4194304 256 0 0 12 24 235904 0x7fe1d32eda80 0x7fe1d2a26140 131072 698602 78228816 17229773365059 17229773332156 17229773902716 17229773919264
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 410 199978 199978 4194304 256 0 0 12 24 239424 0x7fe1d32ed900 0x7fe1d2a26180 131072 1025572 114815784 17229773941983 17229773902716 17229774272957 17229774274564
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 199978 199978 4194304 256 0 0 12 24 244224 0x7fe1d32ed780 0x7fe1d2a261c0 131072 991698 110841088 17229774305373 17229774272957 17229774711837 17229774757221
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 416 199978 199978 4194304 256 0 0 12 24 248768 0x7fe1d32ed600 0x7fe1d2a26200 65536 653126 73159768 17229774768521 17229774711837 17229775173277 17229775214729
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 419 199978 199978 4194304 256 0 0 12 24 253312 0x7fe1d5a50480 0x7fe1d2a26240 131072 658424 73694912 17229775226108 17229775173277 17229775619358 17229775660587
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 422 199978 199978 4194304 256 0 0 8 24 255552 0x7fe1d5a50300 0x7fe1d2a26280 131072 1030754 115550160 17229775671386 17229775619358 17229776292158 17229776334988
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 425 199978 199978 4194304 256 0 0 12 24 259840 0x7fe1d5a50180 0x7fe1d2a262c0 131072 1020390 114365104 17229776353308 17229776292158 17229776725118 17229776766297
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 199978 199978 4194304 256 0 0 12 24 265664 0x7fe1d5a50000 0x7fe1d2a26300 131072 981720 109672360 17229776777566 17229776725118 17229777231999 17229777272883
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 431 199978 199978 4194304 256 0 0 12 24 271232 0x7fe1d32ede80 0x7fe1d2a26340 65536 655876 73487520 17229777284863 17229777231999 17229777738879 17229777756560
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 434 199978 199978 4194304 256 0 0 8 24 273216 0x7fe1d32edd00 0x7fe1d2a26380 131072 986122 110432168 17229777771220 17229777738879 17229778220800 17229778265086
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 437 199978 199978 4194304 256 0 0 8 24 275712 0x7fe1d32edb80 0x7fe1d2a263c0 131072 1020804 114724544 17229778275936 17229778220800 17229778994560 17229779037965
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 440 199978 199978 4194304 256 0 0 12 24 280768 0x7fe1d32eda00 0x7fe1d2a26400 131072 989890 110757368 17229779057215 17229778994560 17229779476801 17229779518252
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 199978 199978 4194304 256 0 0 12 24 287616 0x7fe1d32ed880 0x7fe1d2a26440 131072 1037604 115958456 17229779529302 17229779476801 17229780033761 17229780075157
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 446 199978 199978 4194304 256 0 0 12 24 294208 0x7fe1d32ed700 0x7fe1d2a26480 65536 691110 77414008 17229780087117 17229780033761 17229780589762 17229780631282
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 449 199978 199978 4194304 256 0 0 8 24 296960 0x7fe1d5a50580 0x7fe1d2a264c0 131072 954500 107156008 17229780642192 17229780589762 17229781143682 17229781184837
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 452 199978 199978 4194304 256 0 0 8 24 299968 0x7fe1d5a50400 0x7fe1d2a26500 131072 1035532 116290400 17229781195507 17229781143682 17229782010563 17229782052583
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 455 199978 199978 4194304 256 0 0 8 24 302720 0x7fe1d5a50280 0x7fe1d2a26540 131072 1023712 114670064 17229782071263 17229782010563 17229782673763 17229782717285
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 199978 199978 4194304 256 0 0 12 24 305472 0x7fe1d5a50100 0x7fe1d2a26580 131072 1033124 115602776 17229782727805 17229782673763 17229783348644 17229783389767
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 461 199978 199978 4194304 256 0 0 12 24 308224 0x7fe1d32edf80 0x7fe1d2a265c0 65536 657370 73591752 17229783401007 17229783348644 17229784018724 17229784059619
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 464 199978 199978 4194304 256 0 0 8 24 310976 0x7fe1d32ede00 0x7fe1d2a26600 131072 1032580 115708432 17229784070059 17229784018724 17229784680005 17229784720851
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 467 199978 199978 4194304 256 0 0 8 24 313216 0x7fe1d32edc80 0x7fe1d2a26640 131072 1031196 115863144 17229784731231 17229784680005 17229785763846 17229785804932
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 470 199978 199978 4194304 256 0 0 8 24 315968 0x7fe1d32edb00 0x7fe1d2a26680 131072 1029072 115054072 17229785826221 17229785763563 17229786832523 17229786881313
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 199978 199978 4194304 256 0 0 12 24 318720 0x7fe1d32ed980 0x7fe1d2a266c0 131072 1021276 114635952 17229786892063 17229786832523 17229787935563 17229787999693
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 476 199978 199978 4194304 256 0 0 12 24 321472 0x7fe1d32ed800 0x7fe1d2a26700 65536 644584 72135416 17229788010422 17229787935563 17229789061643 17229789125802
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 479 199978 199978 4194304 256 0 0 8 24 324224 0x7fe1d32ed680 0x7fe1d2a26740 131072 1018932 114366704 17229789136902 17229789061643 17229790164363 17229790229782
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 482 199978 199978 4194304 256 0 0 8 24 326464 0x7fe1d5a50500 0x7fe1d2a26780 131072 1015630 113809128 17229790241082 17229790164363 17229792113804 17229792177919
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 485 199978 199978 4194304 256 0 0 8 24 329216 0x7fe1d5a50380 0x7fe1d2a267c0 131072 1078016 120535456 17229792196739 17229792113804 17229794026604 17229794104317
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 199978 199978 4194304 256 0 0 12 24 331968 0x7fe1d5a50200 0x7fe1d2a26800 131072 1024624 114585728 17229794115877 17229794026604 17229796022125 17229796096693
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 491 199978 199978 4194304 256 0 0 12 24 334720 0x7fe1d5a50080 0x7fe1d2a26840 65536 655984 73357232 17229796107923 17229796022125 17229798001485 17229798066830
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 494 199978 199978 4194304 256 0 0 8 24 337472 0x7fe1d32edf00 0x7fe1d2a26880 131072 1062814 119048120 17229798084779 17229798001485 17229800099086 17229800169393
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 497 199978 199978 4194304 256 0 0 8 24 0 0x7fe1d32edd80 0x7fe1d2a268c0 131072 1025300 114902272 17229800180823 17229800099086 17229803715887 17229803767726
@@ -1,168 +0,0 @@
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",0,0,0,201826,201826,33554432,256,0,0,4,32,4160,0x0,0x7f4602604280,524288,5464894,612004276,17248909572510,17246651988621,17249056201395,17249056314154
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,201826,201826,32768,256,0,0,12,24,13888,0x0,0x7f4602623f80,4096,40146,4496804,17249061450266,17249056201395,17249061580271,17249061585092
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,201826,201826,4194304,256,0,0,12,24,14336,0x7f4605631380,0x7f4602623fc0,524288,10522350,1178437788,17249061620532,17249061580271,17249061951471,17249061954023
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,201826,201826,4194304,256,0,0,16,24,15040,0x7f4605631200,0x7f4602624000,524288,11578892,1296802392,17249061992232,17249061951471,17249062370671,17249062373351
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,201826,201826,4194304,256,0,0,16,24,15488,0x7f4605631080,0x7f4602624040,524288,11405389,1277385548,17249062407200,17249062370671,17249062778990,17249062781460
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,201826,201826,4194304,256,0,0,12,24,15936,0x7f4602ecdf00,0x7f4602624080,524288,10771586,1206422972,17249062814199,17249062778990,17249063093230,17249063095452
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,201826,201826,4194304,256,0,0,12,24,16384,0x7f4602ecdd80,0x7f46026240c0,524288,11089437,1241966076,17249063128461,17249063093230,17249063406030,17249063408703
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,201826,201826,4194304,256,0,0,12,24,17088,0x7f4602ecdc00,0x7f4602624100,524288,11133938,1247027944,17249063451652,17249063406030,17249063714830,17249063717215
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,201826,201826,4194304,256,0,0,16,24,17792,0x7f4602ecda80,0x7f4602624140,524288,11642591,1303946964,17249063750054,17249063714830,17249064114510,17249064116854
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,201826,201826,4194304,256,0,0,16,24,18496,0x7f4602ecd900,0x7f4602624180,524288,11447045,1282049568,17249064148813,17249064114510,17249064509550,17249064512013
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,201826,201826,4194304,256,0,0,16,24,19200,0x7f4602ecd780,0x7f46026241c0,524288,11168649,1250871884,17249064543053,17249064509550,17249064835629,17249064838055
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,201826,201826,4194304,256,0,0,16,24,19904,0x7f4602ecd600,0x7f4602624200,524288,10950607,1226508936,17249064870714,17249064835629,17249065143789,17249065146276
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,201826,201826,4194304,256,0,0,12,24,20608,0x7f4605631480,0x7f4602624240,524288,10792735,1208822680,17249065185875,17249065143789,17249065459309,17249065461728
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,201826,201826,4194304,256,0,0,16,24,21312,0x7f4605631300,0x7f4602624280,524288,11465287,1284133820,17249065493057,17249065459309,17249065855789,17249065858167
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,201826,201826,4194304,256,0,0,16,24,22016,0x7f4605631180,0x7f46026242c0,524288,11659215,1305790300,17249065891436,17249065855789,17249066251949,17249066254886
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,201826,201826,4194304,256,0,0,16,24,22720,0x7f4605631000,0x7f4602624300,524288,10964963,1228053184,17249066286326,17249066251949,17249066569229,17249066570968
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,201826,201826,4194304,256,0,0,12,24,23424,0x7f4602ecde80,0x7f4602624340,524288,11017684,1233964396,17249066602867,17249066569229,17249066850348,17249066852110
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,201826,201826,4194304,256,0,0,12,24,24128,0x7f4602ecdd00,0x7f4602624380,524288,11130003,1246512824,17249066890149,17249066850348,17249067133708,17249067135723
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,201826,201826,4194304,256,0,0,16,24,24832,0x7f4602ecdb80,0x7f46026243c0,524288,11495331,1287446064,17249067167882,17249067133708,17249067502348,17249067504053
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,201826,201826,4194304,256,0,0,16,24,25536,0x7f4602ecda00,0x7f4602624400,524288,11451355,1282520548,17249067535012,17249067502348,17249067875948,17249067877823
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,201826,201826,4194304,256,0,0,12,24,26240,0x7f4602ecd880,0x7f4602624440,524288,10933782,1224605228,17249067908822,17249067875948,17249068156748,17249068158535
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,201826,201826,4194304,256,0,0,12,24,26944,0x7f4602ecd700,0x7f4602624480,524288,10923690,1223447784,17249068189744,17249068156748,17249068439788,17249068441357
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,201826,201826,4194304,256,0,0,12,24,27648,0x7f4605631580,0x7f46026244c0,524288,11208563,1255339608,17249068479546,17249068439788,17249068719628,17249068721470
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,201826,201826,4194304,256,0,0,16,24,28608,0x7f4605631400,0x7f4602624500,524288,11482302,1285994588,17249068752419,17249068719628,17249069089067,17249069090770
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,201826,201826,4194304,256,0,0,16,24,29312,0x7f4605631280,0x7f4602624540,524288,11497488,1287726600,17249069122629,17249069089067,17249069455947,17249069457760
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,201826,201826,4194304,256,0,0,12,24,30016,0x7f4605631100,0x7f4602624580,524288,10905647,1221488772,17249069488969,17249069455947,17249069735467,17249069737342
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,201826,201826,4194304,256,0,0,8,24,30976,0x7f4602ecdf80,0x7f46026245c0,524288,10621894,1189720976,17249069769461,17249069735467,17249070014827,17249070016595
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,201826,201826,4194304,256,0,0,12,24,31680,0x7f4602ecde00,0x7f4602624600,524288,11236993,1258495348,17249070054104,17249070014827,17249070302027,17249070303937
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,201826,201826,4194304,256,0,0,16,24,32640,0x7f4602ecdc80,0x7f4602624640,524288,11382138,1274744988,17249070335636,17249070302027,17249070675307,17249070677047
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,201826,201826,4194304,256,0,0,12,24,33600,0x7f4602ecdb00,0x7f4602624680,524288,11522714,1290547584,17249070708346,17249070675307,17249071043466,17249071045357
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,201826,201826,4194304,256,0,0,12,24,34560,0x7f4602ecd980,0x7f46026246c0,524288,10645747,1192311064,17249071077096,17249071043466,17249071323146,17249071324950
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,201826,201826,4194304,256,0,0,8,24,35520,0x7f4602ecd800,0x7f4602624700,524288,10269042,1150120568,17249071356779,17249071323146,17249071606506,17249071608332
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,201826,201826,4194304,256,0,0,12,24,36224,0x7f4602ecd680,0x7f4602624740,524288,10943920,1225716428,17249071647101,17249071606506,17249071886026,17249071887855
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,201826,201826,4194304,256,0,0,12,24,37184,0x7f4605631500,0x7f4602624780,524288,11582338,1297211008,17249071919414,17249071886026,17249072255306,17249072257145
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,201826,201826,4194304,256,0,0,12,24,38144,0x7f4605631380,0x7f46026247c0,524288,11250668,1260006372,17249072289144,17249072255306,17249072621546,17249072623375
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,201826,201826,4194304,256,0,0,12,24,39104,0x7f4605631200,0x7f4602624800,524288,10404206,1165173604,17249072655764,17249072621546,17249072902186,17249072903937
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,201826,201826,4194304,256,0,0,8,24,40320,0x7f4605631080,0x7f4602624840,524288,10004092,1120444592,17249072936126,17249072902186,17249073184585,17249073186140
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,201826,201826,4194304,256,0,0,12,24,41280,0x7f4602ecdf00,0x7f4602624880,524288,10541861,1180706896,17249073224349,17249073184585,17249073474665,17249073476512
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,201826,201826,4194304,256,0,0,12,24,42240,0x7f4602ecdd80,0x7f46026248c0,524288,11396323,1276349876,17249073507581,17249073474665,17249073844105,17249073845932
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,201826,201826,4194304,256,0,0,12,24,43200,0x7f4602ecdc00,0x7f4602624900,524288,11404589,1277290352,17249073877281,17249073844105,17249074213705,17249074215592
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,201826,201826,4194304,256,0,0,8,24,44160,0x7f4602ecda80,0x7f4602624940,524288,10704374,1198881756,17249074248151,17249074213705,17249074499625,17249074501624
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,201826,201826,4194304,256,0,0,12,24,45376,0x7f4602ecd900,0x7f4602624980,524288,9721293,1088773068,17249074532843,17249074499625,17249074792105,17249074793946
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,201826,201826,4194304,256,0,0,12,24,46336,0x7f4602ecd780,0x7f46026249c0,524288,10790063,1208467776,17249074832015,17249074792105,17249075071945,17249075073659
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,201826,201826,4194304,256,0,0,12,24,47552,0x7f4602ecd600,0x7f4602624a00,524288,11227370,1257455960,17249075104888,17249075071945,17249075437544,17249075439119
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,201826,201826,4194304,256,0,0,12,24,48512,0x7f4605631480,0x7f4602624a40,524288,11400305,1276832952,17249075472218,17249075437544,17249075804104,17249075805949
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,201826,201826,4194304,256,0,0,8,24,49472,0x7f4605631300,0x7f4602624a80,524288,10036111,1123975644,17249075837598,17249075804104,17249076085704,17249076087551
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,201826,201826,4194304,256,0,0,12,24,50688,0x7f4605631180,0x7f4602624ac0,524288,9048223,1013362100,17249076120561,17249076085704,17249076369864,17249076371724
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,201826,201826,4194304,256,0,0,12,24,51648,0x7f4605631000,0x7f4602624b00,524288,10287369,1152178888,17249076410253,17249076369864,17249076650344,17249076652246
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,201826,201826,4194304,256,0,0,12,24,52864,0x7f4602ecde80,0x7f4602624b40,524288,11434914,1280706904,17249076683795,17249076650344,17249077017864,17249077019726
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,201826,201826,4194304,256,0,0,12,24,54080,0x7f4602ecdd00,0x7f4602624b80,524288,11202466,1254663004,17249077051085,17249077017864,17249077384103,17249077385866
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,201826,201826,4194304,256,0,0,8,24,55296,0x7f4602ecdb80,0x7f4602624bc0,524288,10453953,1170846980,17249077417756,17249077384103,17249077664743,17249077666609
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,201826,201826,4194304,256,0,0,12,24,56768,0x7f4602ecda00,0x7f4602624c00,524288,7801717,873825412,17249077698378,17249077664743,17249077946023,17249077947941
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,201826,201826,4194304,256,0,0,12,24,57728,0x7f4602ecd880,0x7f4602624c40,524288,10397669,1164527280,17249077986230,17249077946023,17249078234183,17249078236203
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,201826,201826,4194304,256,0,0,12,24,58944,0x7f4602ecd700,0x7f4602624c80,524288,11346280,1270750740,17249078268413,17249078234183,17249078603303,17249078605133
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,201826,201826,4194304,256,0,0,12,24,60160,0x7f4605631580,0x7f4602624cc0,524288,11296973,1265244932,17249078637073,17249078603303,17249078968103,17249078969914
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,201826,201826,4194304,256,0,0,8,24,61376,0x7f4605631400,0x7f4602624d00,524288,10186663,1140847984,17249079001653,17249078968103,17249079256103,17249079257946
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,201826,201826,4194304,256,0,0,12,24,62848,0x7f4605631280,0x7f4602624d40,524288,6299202,705534860,17249079289485,17249079256103,17249079544102,17249079545928
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,201826,201826,4194304,256,0,0,12,24,63808,0x7f4605631100,0x7f4602624d80,524288,10306115,1154216752,17249079584987,17249079544102,17249079825222,17249079826930
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,201826,201826,4194304,256,0,0,12,24,65024,0x7f4602ecdf80,0x7f4602624dc0,524288,11320974,1267941288,17249079860670,17249079825222,17249080188742,17249080190611
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,201826,201826,4194304,256,0,0,12,24,66240,0x7f4602ecde00,0x7f4602624e00,524288,11174915,1251552308,17249080222540,17249080188742,17249080551302,17249080553011
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,201826,201826,4194304,256,0,0,8,24,67456,0x7f4602ecdc80,0x7f4602624e40,524288,10032926,1123807416,17249080584350,17249080551302,17249080834182,17249080836003
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,201826,201826,4194304,256,0,0,12,24,68928,0x7f4602ecdb00,0x7f4602624e80,524288,5939571,665209840,17249080867792,17249080834182,17249081126982,17249081128785
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,201826,201826,4194304,256,0,0,12,24,70144,0x7f4602ecd980,0x7f4602624ec0,524288,10002538,1120236792,17249081167994,17249081126982,17249081410822,17249081412558
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,201826,201826,4194304,256,0,0,12,24,71616,0x7f4602ecd800,0x7f4602624f00,524288,11313475,1267114736,17249081443487,17249081410822,17249081779621,17249081781538
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,201826,201826,4194304,256,0,0,12,24,72832,0x7f4602ecd680,0x7f4602624f40,524288,11321778,1267977588,17249081812997,17249081779621,17249082160581,17249082162637
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,201826,201826,4194304,256,0,0,8,24,74048,0x7f4605631500,0x7f4602624f80,524288,9799168,1097478780,17249082195516,17249082160581,17249082446341,17249082448030
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,201826,201826,4194304,256,0,0,12,24,75776,0x7f4605631380,0x7f4602624fc0,524288,4828539,540720016,17249082480129,17249082446341,17249082741381,17249082743192
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,201826,201826,4194304,256,0,0,12,24,76992,0x7f4605631200,0x7f4602625000,524288,10032332,1123587020,17249082782161,17249082741381,17249083020741,17249083022494
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,201826,201826,4194304,256,0,0,12,24,78464,0x7f4605631080,0x7f4602625040,524288,11270953,1262352036,17249083053713,17249083020741,17249083385381,17249083387184
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,201826,201826,4194304,256,0,0,12,24,79936,0x7f4602ecdf00,0x7f4602625080,524288,11212773,1255821212,17249083420474,17249083385381,17249083754500,17249083756185
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,201826,201826,4194304,256,0,0,8,24,81408,0x7f4602ecdd80,0x7f46026250c0,524288,9705000,1086944608,17249083787354,17249083754500,17249084033060,17249084034807
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,201826,201826,4194304,256,0,0,12,24,83136,0x7f4602ecdc00,0x7f4602625100,524288,4162468,466124840,17249084066606,17249084033060,17249084337220,17249084338969
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,201826,201826,4194304,256,0,0,12,24,84352,0x7f4602ecda80,0x7f4602625140,524288,10335929,1157575312,17249084388388,17249084337220,17249084622980,17249084624851
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,201826,201826,4194304,256,0,0,12,24,85824,0x7f4602ecd900,0x7f4602625180,524288,11233967,1258191336,17249084656620,17249084622980,17249084993540,17249084995271
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,201826,201826,4194304,256,0,0,12,24,87296,0x7f4602ecd780,0x7f46026251c0,524288,11251050,1260098316,17249085028350,17249084993540,17249085366500,17249085368301
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,201826,201826,4194304,256,0,0,12,24,88768,0x7f4602ecd600,0x7f4602625200,524288,9538965,1068265724,17249085399630,17249085366500,17249085652420,17249085654144
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,201826,201826,4194304,256,0,0,12,24,90752,0x7f4605631480,0x7f4602625240,524288,3845273,430654356,17249085685043,17249085652420,17249085959139,17249085960945
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,201826,201826,4194304,256,0,0,12,24,91968,0x7f4605631300,0x7f4602625280,524288,10008285,1120830452,17249085999104,17249085959139,17249086252419,17249086254167
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,201826,201826,4194304,256,0,0,12,24,93440,0x7f4605631180,0x7f46026252c0,524288,11252972,1260290656,17249086286167,17249086252419,17249086627299,17249086629157
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,201826,201826,4194304,256,0,0,12,24,94912,0x7f4605631000,0x7f4602625300,524288,11158331,1249669316,17249086660906,17249086627299,17249086995139,17249086996727
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,201826,201826,4194304,256,0,0,12,24,96384,0x7f4602ecde80,0x7f4602625340,524288,9243940,1035263396,17249087028197,17249086995139,17249087277539,17249087279290
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,201826,201826,4194304,256,0,0,12,24,98368,0x7f4602ecdd00,0x7f4602625380,524288,3443146,385588200,17249087310249,17249087277539,17249087588579,17249087590411
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,201826,201826,4194304,256,0,0,12,24,99584,0x7f4602ecdb80,0x7f46026253c0,524288,10134374,1135033728,17249087630020,17249087588579,17249087871138,17249087872844
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,201826,201826,4194304,256,0,0,12,24,101312,0x7f4602ecda00,0x7f4602625400,524288,11046720,1237212236,17249087903913,17249087871138,17249088247938,17249088249714
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,201826,201826,4194304,256,0,0,12,24,102784,0x7f4602ecd880,0x7f4602625440,524288,10920083,1223044816,17249088282163,17249088247938,17249088618498,17249088620344
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,201826,201826,4194304,256,0,0,12,24,104256,0x7f4602ecd700,0x7f4602625480,524288,8582309,961181868,17249088651703,17249088618498,17249088899458,17249088901096
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,201826,201826,4194304,256,0,0,12,24,106240,0x7f4605631580,0x7f46026254c0,524288,3122904,349835864,17249088933465,17249088899458,17249089218338,17249089220047
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,201826,201826,4194304,256,0,0,12,24,107712,0x7f4605631400,0x7f4602625500,524288,9868636,1105316592,17249089258846,17249089218338,17249089499298,17249089501280
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,201826,201826,4194304,256,0,0,16,24,109440,0x7f4605631280,0x7f4602625540,524288,11187215,1252945108,17249089532399,17249089499298,17249089865858,17249089867700
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,201826,201826,4194304,256,0,0,16,24,111168,0x7f4605631100,0x7f4602625580,524288,11040859,1236549844,17249089899859,17249089865858,17249090233057,17249090235200
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,201826,201826,4194304,256,0,0,8,24,112896,0x7f4602ecdf80,0x7f46026255c0,524288,8028115,899129052,17249090267589,17249090233057,17249090522337,17249090524072
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,201826,201826,4194304,256,0,0,12,24,115136,0x7f4602ecde00,0x7f4602625600,524288,3185703,356881392,17249090555771,17249090522337,17249090847937,17249090849633
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,201826,201826,4194304,256,0,0,12,24,116608,0x7f4602ecdc80,0x7f4602625640,524288,9764110,1093612004,17249090888642,17249090847937,17249091137697,17249091139615
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,201826,201826,4194304,256,0,0,16,24,118336,0x7f4602ecdb00,0x7f4602625680,524288,11086681,1241687688,17249091172475,17249091137697,17249091506977,17249091508716
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,201826,201826,4194304,256,0,0,16,24,120064,0x7f4602ecd980,0x7f46026256c0,524288,11124997,1246003592,17249091540555,17249091506977,17249091874177,17249091876036
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,201826,201826,4194304,256,0,0,12,24,121792,0x7f4602ecd800,0x7f4602625700,524288,6979797,781683324,17249091906875,17249091874177,17249092159776,17249092161558
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,201826,201826,4194304,256,0,0,12,24,124032,0x7f4602ecd680,0x7f4602625740,524288,2948249,330122264,17249092193187,17249092159776,17249092489856,17249092491609
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,201826,201826,4194304,256,0,0,12,24,125504,0x7f4605631500,0x7f4602625780,524288,9305908,1042190668,17249092530598,17249092489856,17249092776736,17249092778591
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,201826,201826,4194304,256,0,0,12,24,127488,0x7f4605631380,0x7f46026257c0,524288,11098917,1243041032,17249092810010,17249092776736,17249093142176,17249093144011
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,201826,201826,4194304,256,0,0,12,24,129216,0x7f4605631200,0x7f4602625800,524288,11071627,1239980140,17249093176170,17249093142176,17249093509376,17249093511261
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,201826,201826,4194304,256,0,0,12,24,130944,0x7f4605631080,0x7f4602625840,524288,6089493,682020720,17249093542171,17249093509376,17249093794976,17249093796864
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,201826,201826,4194304,256,0,0,12,24,133440,0x7f4602ecdf00,0x7f4602625880,524288,2894059,324121484,17249093828013,17249093794976,17249094140735,17249094142844
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,201826,201826,4194304,256,0,0,12,24,134912,0x7f4602ecdd80,0x7f46026258c0,524288,8512209,953353332,17249094182543,17249094140735,17249094425855,17249094427837
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,201826,201826,4194304,256,0,0,12,24,136896,0x7f4602ecdc00,0x7f4602625900,524288,10978651,1229581608,17249094458766,17249094425855,17249094791135,17249094792987
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,201826,201826,4194304,256,0,0,12,24,138880,0x7f4602ecda80,0x7f4602625940,524288,10906645,1221515196,17249094824236,17249094791135,17249095156735,17249095158407
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,201826,201826,4194304,256,0,0,12,24,140864,0x7f4602ecd900,0x7f4602625980,524288,4755457,532632748,17249095190246,17249095156735,17249095448895,17249095450799
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,201826,201826,4194304,256,0,0,12,24,143616,0x7f4602ecd780,0x7f46026259c0,524288,2911910,326066296,17249095482518,17249095448895,17249095802335,17249095804180
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,201826,201826,4194304,256,0,0,12,24,145344,0x7f4602ecd600,0x7f4602625a00,524288,7554098,846090704,17249095843169,17249095802335,17249096083615,17249096085372
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,201826,201826,4194304,256,0,0,12,24,147584,0x7f4605631480,0x7f4602625a40,524288,10902436,1221079596,17249096116781,17249096083615,17249096451134,17249096453002
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,201826,201826,4194304,256,0,0,12,24,149568,0x7f4605631300,0x7f4602625a80,524288,10960057,1227459496,17249096484662,17249096451134,17249096819454,17249096821322
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,201826,201826,4194304,256,0,0,12,24,151552,0x7f4605631180,0x7f4602625ac0,524288,3787791,424203884,17249096852582,17249096819454,17249097120254,17249097122154
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,201826,201826,4194304,256,0,0,12,24,154304,0x7f4605631000,0x7f4602625b00,524288,2869819,321305616,17249097154004,17249097120254,17249097488094,17249097489875
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,201826,201826,4194304,256,0,0,12,24,156288,0x7f4602ecde80,0x7f4602625b40,524288,5537835,620264428,17249097527434,17249097488094,17249097776574,17249097778367
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,201826,201826,4194304,256,0,0,12,24,158784,0x7f4602ecdd00,0x7f4602625b80,524288,10613095,1188637584,17249097808806,17249097776574,17249098143614,17249098145657
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,201826,201826,4194304,256,0,0,12,24,161024,0x7f4602ecdb80,0x7f4602625bc0,524288,10845487,1214681496,17249098177776,17249098143614,17249098516893,17249098518727
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,201826,201826,4194304,256,0,0,12,24,163264,0x7f4602ecda00,0x7f4602625c00,524288,3722360,416921828,17249098549736,17249098516893,17249098825053,17249098827038
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,201826,201826,4194304,256,0,0,12,24,166528,0x7f4602ecd880,0x7f4602625c40,524288,2897139,324286488,17249098857858,17249098825053,17249099215293,17249099237347
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,201826,201826,4194304,256,0,0,12,24,168512,0x7f4602ecd700,0x7f4602625c80,524288,3984490,446214564,17249099257707,17249099215293,17249099525373,17249099527140
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,201826,201826,4194304,256,0,0,12,24,171264,0x7f4605631580,0x7f4602625cc0,524288,10074109,1128246912,17249099558349,17249099525373,17249099900573,17249099902419
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,201826,201826,4194304,256,0,0,12,24,173760,0x7f4605631400,0x7f4602625d00,524288,9640308,1079704068,17249099934919,17249099900573,17249100276733,17249100278609
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,201826,201826,4194304,256,0,0,12,24,176256,0x7f4605631280,0x7f4602625d40,524288,2959344,331403356,17249100309838,17249100276733,17249100602492,17249100604240
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,201826,201826,4194304,256,0,0,12,24,179776,0x7f4605631100,0x7f4602625d80,524288,2866389,320940448,17249100635960,17249100602492,17249101021532,17249101039489
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,201826,201826,4194304,256,0,0,12,24,182272,0x7f4602ecdf80,0x7f4602625dc0,524288,3112985,348649996,17249101063018,17249101021532,17249101348732,17249101350480
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,201826,201826,4194304,256,0,0,12,24,185536,0x7f4602ecde00,0x7f4602625e00,524288,8284910,927913576,17249101382199,17249101348732,17249101726652,17249101744380
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,201826,201826,4194304,256,0,0,12,24,188544,0x7f4602ecdc80,0x7f4602625e40,524288,7699433,862352220,17249101759819,17249101726652,17249102111932,17249102133309
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,201826,201826,4194304,256,0,0,12,24,191552,0x7f4602ecdb00,0x7f4602625e80,524288,2833549,317367264,17249102146209,17249102111932,17249102479131,17249102480840
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,201826,201826,4194304,256,0,0,12,24,195840,0x7f4602ecd980,0x7f4602625ec0,524288,2860681,320387212,17249102512209,17249102479131,17249102950331,17249102969597
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,201826,201826,4194304,256,0,0,12,24,198592,0x7f4602ecd800,0x7f4602625f00,524288,2798688,313451972,17249102990996,17249102950331,17249103291131,17249103292848
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,201826,201826,4194304,256,0,0,12,24,202368,0x7f4602ecd680,0x7f4602625f40,524288,6936537,776835180,17249103323687,17249103291131,17249103692411,17249103710297
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,201826,201826,4194304,256,0,0,12,24,205888,0x7f4605631500,0x7f4602625f80,524288,6674983,747584524,17249103726246,17249103692411,17249104091131,17249104108486
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,201826,201826,4194304,256,0,0,12,24,209408,0x7f4605631380,0x7f4602625fc0,524288,2853917,319694768,17249104124965,17249104091131,17249104469371,17249104471526
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,201826,201826,4194304,256,0,0,12,24,214464,0x7f4605631200,0x7f4602626000,524288,2933155,328509384,17249104504965,17249104469371,17249104991450,17249105008892
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,201826,201826,4194304,256,0,0,12,24,217728,0x7f4605631080,0x7f4602626040,524288,2828172,316734688,17249105032371,17249104991450,17249105355450,17249105357182
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,201826,201826,4194304,256,0,0,12,24,222016,0x7f4602ecdf00,0x7f4602626080,524288,5953377,666786396,17249105390681,17249105355450,17249105770810,17249105788110
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,201826,201826,4194304,256,0,0,12,24,226048,0x7f4602ecdd80,0x7f46026260c0,524288,5077998,568701260,17249105805380,17249105770810,17249106193370,17249106211759
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,201826,201826,4194304,256,0,0,12,24,230080,0x7f4602ecdc00,0x7f4602626100,524288,2778853,311209532,17249106226989,17249106193370,17249106603770,17249106646447
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,201826,201826,4194304,256,0,0,12,24,235904,0x7f4602ecda80,0x7f4602626140,524288,2905589,325403568,17249106659267,17249106603770,17249107207929,17249107250171
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,201826,201826,4194304,256,0,0,12,24,239424,0x7f4602ecd900,0x7f4602626180,524288,2757233,308845420,17249107270111,17249107207929,17249107614969,17249107616761
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,201826,201826,4194304,256,0,0,12,24,244224,0x7f4602ecd780,0x7f46026261c0,524288,5264884,589635128,17249107649130,17249107614969,17249108058009,17249108076499
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,201826,201826,4194304,256,0,0,12,24,248768,0x7f4602ecd600,0x7f4602626200,524288,3185236,356761576,17249108091369,17249108058009,17249108493849,17249108510847
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,201826,201826,4194304,256,0,0,12,24,253312,0x7f4605631480,0x7f4602626240,524288,2730254,305778696,17249108527587,17249108493849,17249108922168,17249108939076
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,201826,201826,4194304,256,0,0,8,24,255552,0x7f4605631300,0x7f4602626280,524288,2379427,266485184,17249108956565,17249108922168,17249109566488,17249109583329
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,201826,201826,4194304,256,0,0,12,24,259840,0x7f4605631180,0x7f46026262c0,524288,2731630,305925384,17249109608408,17249109566488,17249109982488,17249109998847
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,201826,201826,4194304,256,0,0,12,24,265664,0x7f4605631000,0x7f4602626300,524288,3371281,377530148,17249110015397,17249109982488,17249110482968,17249110503344
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,201826,201826,4194304,256,0,0,12,24,271232,0x7f4602ecde80,0x7f4602626340,524288,3566902,399510052,17249110516973,17249110482968,17249110979287,17249110996290
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,201826,201826,4194304,256,0,0,8,24,273216,0x7f4602ecdd00,0x7f4602626380,524288,2409085,269846780,17249111013160,17249110979287,17249111468407,17249111485817
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,201826,201826,4194304,256,0,0,8,24,275712,0x7f4602ecdb80,0x7f46026263c0,524288,2384099,266982020,17249111502227,17249111468407,17249112220407,17249112237417
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,201826,201826,4194304,256,0,0,12,24,280768,0x7f4602ecda00,0x7f4602626400,524288,2653983,297219544,17249112261306,17249112220407,17249112681847,17249112698484
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,201826,201826,4194304,256,0,0,12,24,287616,0x7f4602ecd880,0x7f4602626440,524288,3455484,387000588,17249112715134,17249112681847,17249113223126,17249113240020
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,201826,201826,4194304,256,0,0,12,24,294208,0x7f4602ecd700,0x7f4602626480,524288,3349610,375135196,17249113257529,17249113223126,17249113764086,17249113782325
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,201826,201826,4194304,256,0,0,8,24,296960,0x7f4605631580,0x7f46026264c0,524288,2391568,267848524,17249113797165,17249113764086,17249114304886,17249114323011
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,201826,201826,4194304,256,0,0,8,24,299968,0x7f4605631400,0x7f4602626500,524288,2395734,268311072,17249114339820,17249114304886,17249115158965,17249115181307
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,201826,201826,4194304,256,0,0,8,24,302720,0x7f4605631280,0x7f4602626540,524288,2396866,268412932,17249115200707,17249115158965,17249115805205,17249115822320
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,201826,201826,4194304,256,0,0,12,24,305472,0x7f4605631100,0x7f4602626580,524288,2600738,291307888,17249115839690,17249115805205,17249116462325,17249116481172
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,201826,201826,4194304,256,0,0,12,24,308224,0x7f4602ecdf80,0x7f46026265c0,524288,2616855,293107100,17249116498462,17249116462325,17249117117205,17249117134615
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,201826,201826,4194304,256,0,0,8,24,310976,0x7f4602ecde00,0x7f4602626600,524288,2405162,269361008,17249117151334,17249117117205,17249117762964,17249117780437
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,201826,201826,4194304,256,0,0,8,24,313216,0x7f4602ecdc80,0x7f4602626640,524288,2419136,270944456,17249117796607,17249117762799,17249118823599,17249118869908
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,201826,201826,4194304,256,0,0,8,24,315968,0x7f4602ecdb00,0x7f4602626680,524288,2442546,273553904,17249118890617,17249118823599,17249119906957,17249119954289
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,201826,201826,4194304,256,0,0,12,24,318720,0x7f4602ecd980,0x7f46026266c0,524288,2600709,291284960,17249119965408,17249119906957,17249121016716,17249121055609
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,201826,201826,4194304,256,0,0,12,24,321472,0x7f4602ecd800,0x7f4602626700,524288,2591423,290216036,17249121067449,17249121016716,17249122109195,17249122175659
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,201826,201826,4194304,256,0,0,8,24,324224,0x7f4602ecd680,0x7f4602626740,524288,2426293,271693344,17249122187259,17249122109195,17249123215754,17249123256420
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,201826,201826,4194304,256,0,0,8,24,326464,0x7f4605631500,0x7f4602626780,524288,2460495,275535664,17249123267940,17249123215754,17249125126792,17249125167788
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,201826,201826,4194304,256,0,0,8,24,329216,0x7f4605631380,0x7f46026267c0,524288,2456342,275073060,17249125187048,17249125126792,17249127023111,17249127088467
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,201826,201826,4194304,256,0,0,12,24,331968,0x7f4605631200,0x7f4602626800,524288,2624766,294024028,17249127100496,17249127023111,17249129005669,17249129072943
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,201826,201826,4194304,256,0,0,12,24,334720,0x7f4605631080,0x7f4602626840,524288,2613384,292643220,17249129083973,17249129005669,17249130992708,17249131063310
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,201826,201826,4194304,256,0,0,8,24,337472,0x7f4602ecdf00,0x7f4602626880,524288,2465829,276165604,17249131075829,17249130992708,17249132932706,17249133005247
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,201826,201826,4194304,256,0,0,8,24,0,0x7f4602ecdd80,0x7f46026268c0,524288,2472715,276887956,17249133017057,17249132932706,17249136551263,17249136623859
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 201826 201826 33554432 256 0 0 4 32 4160 0x0 0x7f4602604280 524288 5464894 612004276 17248909572510 17246651988621 17249056201395 17249056314154
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 201826 201826 32768 256 0 0 12 24 13888 0x0 0x7f4602623f80 4096 40146 4496804 17249061450266 17249056201395 17249061580271 17249061585092
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 5 201826 201826 4194304 256 0 0 12 24 14336 0x7f4605631380 0x7f4602623fc0 524288 10522350 1178437788 17249061620532 17249061580271 17249061951471 17249061954023
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 201826 201826 4194304 256 0 0 16 24 15040 0x7f4605631200 0x7f4602624000 524288 11578892 1296802392 17249061992232 17249061951471 17249062370671 17249062373351
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 11 201826 201826 4194304 256 0 0 16 24 15488 0x7f4605631080 0x7f4602624040 524288 11405389 1277385548 17249062407200 17249062370671 17249062778990 17249062781460
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 14 201826 201826 4194304 256 0 0 12 24 15936 0x7f4602ecdf00 0x7f4602624080 524288 10771586 1206422972 17249062814199 17249062778990 17249063093230 17249063095452
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 17 201826 201826 4194304 256 0 0 12 24 16384 0x7f4602ecdd80 0x7f46026240c0 524288 11089437 1241966076 17249063128461 17249063093230 17249063406030 17249063408703
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 20 201826 201826 4194304 256 0 0 12 24 17088 0x7f4602ecdc00 0x7f4602624100 524288 11133938 1247027944 17249063451652 17249063406030 17249063714830 17249063717215
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 201826 201826 4194304 256 0 0 16 24 17792 0x7f4602ecda80 0x7f4602624140 524288 11642591 1303946964 17249063750054 17249063714830 17249064114510 17249064116854
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 26 201826 201826 4194304 256 0 0 16 24 18496 0x7f4602ecd900 0x7f4602624180 524288 11447045 1282049568 17249064148813 17249064114510 17249064509550 17249064512013
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 29 201826 201826 4194304 256 0 0 16 24 19200 0x7f4602ecd780 0x7f46026241c0 524288 11168649 1250871884 17249064543053 17249064509550 17249064835629 17249064838055
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 32 201826 201826 4194304 256 0 0 16 24 19904 0x7f4602ecd600 0x7f4602624200 524288 10950607 1226508936 17249064870714 17249064835629 17249065143789 17249065146276
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 35 201826 201826 4194304 256 0 0 12 24 20608 0x7f4605631480 0x7f4602624240 524288 10792735 1208822680 17249065185875 17249065143789 17249065459309 17249065461728
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 201826 201826 4194304 256 0 0 16 24 21312 0x7f4605631300 0x7f4602624280 524288 11465287 1284133820 17249065493057 17249065459309 17249065855789 17249065858167
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 41 201826 201826 4194304 256 0 0 16 24 22016 0x7f4605631180 0x7f46026242c0 524288 11659215 1305790300 17249065891436 17249065855789 17249066251949 17249066254886
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 44 201826 201826 4194304 256 0 0 16 24 22720 0x7f4605631000 0x7f4602624300 524288 10964963 1228053184 17249066286326 17249066251949 17249066569229 17249066570968
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 47 201826 201826 4194304 256 0 0 12 24 23424 0x7f4602ecde80 0x7f4602624340 524288 11017684 1233964396 17249066602867 17249066569229 17249066850348 17249066852110
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 50 201826 201826 4194304 256 0 0 12 24 24128 0x7f4602ecdd00 0x7f4602624380 524288 11130003 1246512824 17249066890149 17249066850348 17249067133708 17249067135723
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 201826 201826 4194304 256 0 0 16 24 24832 0x7f4602ecdb80 0x7f46026243c0 524288 11495331 1287446064 17249067167882 17249067133708 17249067502348 17249067504053
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 56 201826 201826 4194304 256 0 0 16 24 25536 0x7f4602ecda00 0x7f4602624400 524288 11451355 1282520548 17249067535012 17249067502348 17249067875948 17249067877823
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 59 201826 201826 4194304 256 0 0 12 24 26240 0x7f4602ecd880 0x7f4602624440 524288 10933782 1224605228 17249067908822 17249067875948 17249068156748 17249068158535
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 62 201826 201826 4194304 256 0 0 12 24 26944 0x7f4602ecd700 0x7f4602624480 524288 10923690 1223447784 17249068189744 17249068156748 17249068439788 17249068441357
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 65 201826 201826 4194304 256 0 0 12 24 27648 0x7f4605631580 0x7f46026244c0 524288 11208563 1255339608 17249068479546 17249068439788 17249068719628 17249068721470
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 201826 201826 4194304 256 0 0 16 24 28608 0x7f4605631400 0x7f4602624500 524288 11482302 1285994588 17249068752419 17249068719628 17249069089067 17249069090770
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 71 201826 201826 4194304 256 0 0 16 24 29312 0x7f4605631280 0x7f4602624540 524288 11497488 1287726600 17249069122629 17249069089067 17249069455947 17249069457760
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 74 201826 201826 4194304 256 0 0 12 24 30016 0x7f4605631100 0x7f4602624580 524288 10905647 1221488772 17249069488969 17249069455947 17249069735467 17249069737342
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 77 201826 201826 4194304 256 0 0 8 24 30976 0x7f4602ecdf80 0x7f46026245c0 524288 10621894 1189720976 17249069769461 17249069735467 17249070014827 17249070016595
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 80 201826 201826 4194304 256 0 0 12 24 31680 0x7f4602ecde00 0x7f4602624600 524288 11236993 1258495348 17249070054104 17249070014827 17249070302027 17249070303937
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 201826 201826 4194304 256 0 0 16 24 32640 0x7f4602ecdc80 0x7f4602624640 524288 11382138 1274744988 17249070335636 17249070302027 17249070675307 17249070677047
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 86 201826 201826 4194304 256 0 0 12 24 33600 0x7f4602ecdb00 0x7f4602624680 524288 11522714 1290547584 17249070708346 17249070675307 17249071043466 17249071045357
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 89 201826 201826 4194304 256 0 0 12 24 34560 0x7f4602ecd980 0x7f46026246c0 524288 10645747 1192311064 17249071077096 17249071043466 17249071323146 17249071324950
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 92 201826 201826 4194304 256 0 0 8 24 35520 0x7f4602ecd800 0x7f4602624700 524288 10269042 1150120568 17249071356779 17249071323146 17249071606506 17249071608332
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 95 201826 201826 4194304 256 0 0 12 24 36224 0x7f4602ecd680 0x7f4602624740 524288 10943920 1225716428 17249071647101 17249071606506 17249071886026 17249071887855
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 201826 201826 4194304 256 0 0 12 24 37184 0x7f4605631500 0x7f4602624780 524288 11582338 1297211008 17249071919414 17249071886026 17249072255306 17249072257145
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 101 201826 201826 4194304 256 0 0 12 24 38144 0x7f4605631380 0x7f46026247c0 524288 11250668 1260006372 17249072289144 17249072255306 17249072621546 17249072623375
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 104 201826 201826 4194304 256 0 0 12 24 39104 0x7f4605631200 0x7f4602624800 524288 10404206 1165173604 17249072655764 17249072621546 17249072902186 17249072903937
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 107 201826 201826 4194304 256 0 0 8 24 40320 0x7f4605631080 0x7f4602624840 524288 10004092 1120444592 17249072936126 17249072902186 17249073184585 17249073186140
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 110 201826 201826 4194304 256 0 0 12 24 41280 0x7f4602ecdf00 0x7f4602624880 524288 10541861 1180706896 17249073224349 17249073184585 17249073474665 17249073476512
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 201826 201826 4194304 256 0 0 12 24 42240 0x7f4602ecdd80 0x7f46026248c0 524288 11396323 1276349876 17249073507581 17249073474665 17249073844105 17249073845932
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 116 201826 201826 4194304 256 0 0 12 24 43200 0x7f4602ecdc00 0x7f4602624900 524288 11404589 1277290352 17249073877281 17249073844105 17249074213705 17249074215592
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 119 201826 201826 4194304 256 0 0 8 24 44160 0x7f4602ecda80 0x7f4602624940 524288 10704374 1198881756 17249074248151 17249074213705 17249074499625 17249074501624
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 122 201826 201826 4194304 256 0 0 12 24 45376 0x7f4602ecd900 0x7f4602624980 524288 9721293 1088773068 17249074532843 17249074499625 17249074792105 17249074793946
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 125 201826 201826 4194304 256 0 0 12 24 46336 0x7f4602ecd780 0x7f46026249c0 524288 10790063 1208467776 17249074832015 17249074792105 17249075071945 17249075073659
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 201826 201826 4194304 256 0 0 12 24 47552 0x7f4602ecd600 0x7f4602624a00 524288 11227370 1257455960 17249075104888 17249075071945 17249075437544 17249075439119
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 131 201826 201826 4194304 256 0 0 12 24 48512 0x7f4605631480 0x7f4602624a40 524288 11400305 1276832952 17249075472218 17249075437544 17249075804104 17249075805949
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 134 201826 201826 4194304 256 0 0 8 24 49472 0x7f4605631300 0x7f4602624a80 524288 10036111 1123975644 17249075837598 17249075804104 17249076085704 17249076087551
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 137 201826 201826 4194304 256 0 0 12 24 50688 0x7f4605631180 0x7f4602624ac0 524288 9048223 1013362100 17249076120561 17249076085704 17249076369864 17249076371724
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 140 201826 201826 4194304 256 0 0 12 24 51648 0x7f4605631000 0x7f4602624b00 524288 10287369 1152178888 17249076410253 17249076369864 17249076650344 17249076652246
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 201826 201826 4194304 256 0 0 12 24 52864 0x7f4602ecde80 0x7f4602624b40 524288 11434914 1280706904 17249076683795 17249076650344 17249077017864 17249077019726
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 146 201826 201826 4194304 256 0 0 12 24 54080 0x7f4602ecdd00 0x7f4602624b80 524288 11202466 1254663004 17249077051085 17249077017864 17249077384103 17249077385866
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 149 201826 201826 4194304 256 0 0 8 24 55296 0x7f4602ecdb80 0x7f4602624bc0 524288 10453953 1170846980 17249077417756 17249077384103 17249077664743 17249077666609
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 152 201826 201826 4194304 256 0 0 12 24 56768 0x7f4602ecda00 0x7f4602624c00 524288 7801717 873825412 17249077698378 17249077664743 17249077946023 17249077947941
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 155 201826 201826 4194304 256 0 0 12 24 57728 0x7f4602ecd880 0x7f4602624c40 524288 10397669 1164527280 17249077986230 17249077946023 17249078234183 17249078236203
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 201826 201826 4194304 256 0 0 12 24 58944 0x7f4602ecd700 0x7f4602624c80 524288 11346280 1270750740 17249078268413 17249078234183 17249078603303 17249078605133
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 161 201826 201826 4194304 256 0 0 12 24 60160 0x7f4605631580 0x7f4602624cc0 524288 11296973 1265244932 17249078637073 17249078603303 17249078968103 17249078969914
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 164 201826 201826 4194304 256 0 0 8 24 61376 0x7f4605631400 0x7f4602624d00 524288 10186663 1140847984 17249079001653 17249078968103 17249079256103 17249079257946
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 167 201826 201826 4194304 256 0 0 12 24 62848 0x7f4605631280 0x7f4602624d40 524288 6299202 705534860 17249079289485 17249079256103 17249079544102 17249079545928
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 170 201826 201826 4194304 256 0 0 12 24 63808 0x7f4605631100 0x7f4602624d80 524288 10306115 1154216752 17249079584987 17249079544102 17249079825222 17249079826930
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 201826 201826 4194304 256 0 0 12 24 65024 0x7f4602ecdf80 0x7f4602624dc0 524288 11320974 1267941288 17249079860670 17249079825222 17249080188742 17249080190611
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 176 201826 201826 4194304 256 0 0 12 24 66240 0x7f4602ecde00 0x7f4602624e00 524288 11174915 1251552308 17249080222540 17249080188742 17249080551302 17249080553011
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 179 201826 201826 4194304 256 0 0 8 24 67456 0x7f4602ecdc80 0x7f4602624e40 524288 10032926 1123807416 17249080584350 17249080551302 17249080834182 17249080836003
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 182 201826 201826 4194304 256 0 0 12 24 68928 0x7f4602ecdb00 0x7f4602624e80 524288 5939571 665209840 17249080867792 17249080834182 17249081126982 17249081128785
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 185 201826 201826 4194304 256 0 0 12 24 70144 0x7f4602ecd980 0x7f4602624ec0 524288 10002538 1120236792 17249081167994 17249081126982 17249081410822 17249081412558
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 201826 201826 4194304 256 0 0 12 24 71616 0x7f4602ecd800 0x7f4602624f00 524288 11313475 1267114736 17249081443487 17249081410822 17249081779621 17249081781538
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 191 201826 201826 4194304 256 0 0 12 24 72832 0x7f4602ecd680 0x7f4602624f40 524288 11321778 1267977588 17249081812997 17249081779621 17249082160581 17249082162637
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 194 201826 201826 4194304 256 0 0 8 24 74048 0x7f4605631500 0x7f4602624f80 524288 9799168 1097478780 17249082195516 17249082160581 17249082446341 17249082448030
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 197 201826 201826 4194304 256 0 0 12 24 75776 0x7f4605631380 0x7f4602624fc0 524288 4828539 540720016 17249082480129 17249082446341 17249082741381 17249082743192
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 200 201826 201826 4194304 256 0 0 12 24 76992 0x7f4605631200 0x7f4602625000 524288 10032332 1123587020 17249082782161 17249082741381 17249083020741 17249083022494
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 201826 201826 4194304 256 0 0 12 24 78464 0x7f4605631080 0x7f4602625040 524288 11270953 1262352036 17249083053713 17249083020741 17249083385381 17249083387184
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 206 201826 201826 4194304 256 0 0 12 24 79936 0x7f4602ecdf00 0x7f4602625080 524288 11212773 1255821212 17249083420474 17249083385381 17249083754500 17249083756185
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 209 201826 201826 4194304 256 0 0 8 24 81408 0x7f4602ecdd80 0x7f46026250c0 524288 9705000 1086944608 17249083787354 17249083754500 17249084033060 17249084034807
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 212 201826 201826 4194304 256 0 0 12 24 83136 0x7f4602ecdc00 0x7f4602625100 524288 4162468 466124840 17249084066606 17249084033060 17249084337220 17249084338969
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 215 201826 201826 4194304 256 0 0 12 24 84352 0x7f4602ecda80 0x7f4602625140 524288 10335929 1157575312 17249084388388 17249084337220 17249084622980 17249084624851
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 201826 201826 4194304 256 0 0 12 24 85824 0x7f4602ecd900 0x7f4602625180 524288 11233967 1258191336 17249084656620 17249084622980 17249084993540 17249084995271
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 221 201826 201826 4194304 256 0 0 12 24 87296 0x7f4602ecd780 0x7f46026251c0 524288 11251050 1260098316 17249085028350 17249084993540 17249085366500 17249085368301
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 224 201826 201826 4194304 256 0 0 12 24 88768 0x7f4602ecd600 0x7f4602625200 524288 9538965 1068265724 17249085399630 17249085366500 17249085652420 17249085654144
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 227 201826 201826 4194304 256 0 0 12 24 90752 0x7f4605631480 0x7f4602625240 524288 3845273 430654356 17249085685043 17249085652420 17249085959139 17249085960945
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 230 201826 201826 4194304 256 0 0 12 24 91968 0x7f4605631300 0x7f4602625280 524288 10008285 1120830452 17249085999104 17249085959139 17249086252419 17249086254167
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 201826 201826 4194304 256 0 0 12 24 93440 0x7f4605631180 0x7f46026252c0 524288 11252972 1260290656 17249086286167 17249086252419 17249086627299 17249086629157
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 236 201826 201826 4194304 256 0 0 12 24 94912 0x7f4605631000 0x7f4602625300 524288 11158331 1249669316 17249086660906 17249086627299 17249086995139 17249086996727
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 239 201826 201826 4194304 256 0 0 12 24 96384 0x7f4602ecde80 0x7f4602625340 524288 9243940 1035263396 17249087028197 17249086995139 17249087277539 17249087279290
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 242 201826 201826 4194304 256 0 0 12 24 98368 0x7f4602ecdd00 0x7f4602625380 524288 3443146 385588200 17249087310249 17249087277539 17249087588579 17249087590411
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 245 201826 201826 4194304 256 0 0 12 24 99584 0x7f4602ecdb80 0x7f46026253c0 524288 10134374 1135033728 17249087630020 17249087588579 17249087871138 17249087872844
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 201826 201826 4194304 256 0 0 12 24 101312 0x7f4602ecda00 0x7f4602625400 524288 11046720 1237212236 17249087903913 17249087871138 17249088247938 17249088249714
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 251 201826 201826 4194304 256 0 0 12 24 102784 0x7f4602ecd880 0x7f4602625440 524288 10920083 1223044816 17249088282163 17249088247938 17249088618498 17249088620344
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 254 201826 201826 4194304 256 0 0 12 24 104256 0x7f4602ecd700 0x7f4602625480 524288 8582309 961181868 17249088651703 17249088618498 17249088899458 17249088901096
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 257 201826 201826 4194304 256 0 0 12 24 106240 0x7f4605631580 0x7f46026254c0 524288 3122904 349835864 17249088933465 17249088899458 17249089218338 17249089220047
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 260 201826 201826 4194304 256 0 0 12 24 107712 0x7f4605631400 0x7f4602625500 524288 9868636 1105316592 17249089258846 17249089218338 17249089499298 17249089501280
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 201826 201826 4194304 256 0 0 16 24 109440 0x7f4605631280 0x7f4602625540 524288 11187215 1252945108 17249089532399 17249089499298 17249089865858 17249089867700
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 266 201826 201826 4194304 256 0 0 16 24 111168 0x7f4605631100 0x7f4602625580 524288 11040859 1236549844 17249089899859 17249089865858 17249090233057 17249090235200
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 269 201826 201826 4194304 256 0 0 8 24 112896 0x7f4602ecdf80 0x7f46026255c0 524288 8028115 899129052 17249090267589 17249090233057 17249090522337 17249090524072
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 272 201826 201826 4194304 256 0 0 12 24 115136 0x7f4602ecde00 0x7f4602625600 524288 3185703 356881392 17249090555771 17249090522337 17249090847937 17249090849633
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 275 201826 201826 4194304 256 0 0 12 24 116608 0x7f4602ecdc80 0x7f4602625640 524288 9764110 1093612004 17249090888642 17249090847937 17249091137697 17249091139615
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 201826 201826 4194304 256 0 0 16 24 118336 0x7f4602ecdb00 0x7f4602625680 524288 11086681 1241687688 17249091172475 17249091137697 17249091506977 17249091508716
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 281 201826 201826 4194304 256 0 0 16 24 120064 0x7f4602ecd980 0x7f46026256c0 524288 11124997 1246003592 17249091540555 17249091506977 17249091874177 17249091876036
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 284 201826 201826 4194304 256 0 0 12 24 121792 0x7f4602ecd800 0x7f4602625700 524288 6979797 781683324 17249091906875 17249091874177 17249092159776 17249092161558
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 287 201826 201826 4194304 256 0 0 12 24 124032 0x7f4602ecd680 0x7f4602625740 524288 2948249 330122264 17249092193187 17249092159776 17249092489856 17249092491609
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 290 201826 201826 4194304 256 0 0 12 24 125504 0x7f4605631500 0x7f4602625780 524288 9305908 1042190668 17249092530598 17249092489856 17249092776736 17249092778591
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 201826 201826 4194304 256 0 0 12 24 127488 0x7f4605631380 0x7f46026257c0 524288 11098917 1243041032 17249092810010 17249092776736 17249093142176 17249093144011
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 296 201826 201826 4194304 256 0 0 12 24 129216 0x7f4605631200 0x7f4602625800 524288 11071627 1239980140 17249093176170 17249093142176 17249093509376 17249093511261
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 299 201826 201826 4194304 256 0 0 12 24 130944 0x7f4605631080 0x7f4602625840 524288 6089493 682020720 17249093542171 17249093509376 17249093794976 17249093796864
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 302 201826 201826 4194304 256 0 0 12 24 133440 0x7f4602ecdf00 0x7f4602625880 524288 2894059 324121484 17249093828013 17249093794976 17249094140735 17249094142844
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 305 201826 201826 4194304 256 0 0 12 24 134912 0x7f4602ecdd80 0x7f46026258c0 524288 8512209 953353332 17249094182543 17249094140735 17249094425855 17249094427837
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 201826 201826 4194304 256 0 0 12 24 136896 0x7f4602ecdc00 0x7f4602625900 524288 10978651 1229581608 17249094458766 17249094425855 17249094791135 17249094792987
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 311 201826 201826 4194304 256 0 0 12 24 138880 0x7f4602ecda80 0x7f4602625940 524288 10906645 1221515196 17249094824236 17249094791135 17249095156735 17249095158407
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 314 201826 201826 4194304 256 0 0 12 24 140864 0x7f4602ecd900 0x7f4602625980 524288 4755457 532632748 17249095190246 17249095156735 17249095448895 17249095450799
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 317 201826 201826 4194304 256 0 0 12 24 143616 0x7f4602ecd780 0x7f46026259c0 524288 2911910 326066296 17249095482518 17249095448895 17249095802335 17249095804180
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 320 201826 201826 4194304 256 0 0 12 24 145344 0x7f4602ecd600 0x7f4602625a00 524288 7554098 846090704 17249095843169 17249095802335 17249096083615 17249096085372
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 201826 201826 4194304 256 0 0 12 24 147584 0x7f4605631480 0x7f4602625a40 524288 10902436 1221079596 17249096116781 17249096083615 17249096451134 17249096453002
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 326 201826 201826 4194304 256 0 0 12 24 149568 0x7f4605631300 0x7f4602625a80 524288 10960057 1227459496 17249096484662 17249096451134 17249096819454 17249096821322
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 329 201826 201826 4194304 256 0 0 12 24 151552 0x7f4605631180 0x7f4602625ac0 524288 3787791 424203884 17249096852582 17249096819454 17249097120254 17249097122154
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 332 201826 201826 4194304 256 0 0 12 24 154304 0x7f4605631000 0x7f4602625b00 524288 2869819 321305616 17249097154004 17249097120254 17249097488094 17249097489875
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 335 201826 201826 4194304 256 0 0 12 24 156288 0x7f4602ecde80 0x7f4602625b40 524288 5537835 620264428 17249097527434 17249097488094 17249097776574 17249097778367
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 201826 201826 4194304 256 0 0 12 24 158784 0x7f4602ecdd00 0x7f4602625b80 524288 10613095 1188637584 17249097808806 17249097776574 17249098143614 17249098145657
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 341 201826 201826 4194304 256 0 0 12 24 161024 0x7f4602ecdb80 0x7f4602625bc0 524288 10845487 1214681496 17249098177776 17249098143614 17249098516893 17249098518727
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 344 201826 201826 4194304 256 0 0 12 24 163264 0x7f4602ecda00 0x7f4602625c00 524288 3722360 416921828 17249098549736 17249098516893 17249098825053 17249098827038
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 347 201826 201826 4194304 256 0 0 12 24 166528 0x7f4602ecd880 0x7f4602625c40 524288 2897139 324286488 17249098857858 17249098825053 17249099215293 17249099237347
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 350 201826 201826 4194304 256 0 0 12 24 168512 0x7f4602ecd700 0x7f4602625c80 524288 3984490 446214564 17249099257707 17249099215293 17249099525373 17249099527140
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 201826 201826 4194304 256 0 0 12 24 171264 0x7f4605631580 0x7f4602625cc0 524288 10074109 1128246912 17249099558349 17249099525373 17249099900573 17249099902419
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 356 201826 201826 4194304 256 0 0 12 24 173760 0x7f4605631400 0x7f4602625d00 524288 9640308 1079704068 17249099934919 17249099900573 17249100276733 17249100278609
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 359 201826 201826 4194304 256 0 0 12 24 176256 0x7f4605631280 0x7f4602625d40 524288 2959344 331403356 17249100309838 17249100276733 17249100602492 17249100604240
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 362 201826 201826 4194304 256 0 0 12 24 179776 0x7f4605631100 0x7f4602625d80 524288 2866389 320940448 17249100635960 17249100602492 17249101021532 17249101039489
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 365 201826 201826 4194304 256 0 0 12 24 182272 0x7f4602ecdf80 0x7f4602625dc0 524288 3112985 348649996 17249101063018 17249101021532 17249101348732 17249101350480
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 201826 201826 4194304 256 0 0 12 24 185536 0x7f4602ecde00 0x7f4602625e00 524288 8284910 927913576 17249101382199 17249101348732 17249101726652 17249101744380
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 371 201826 201826 4194304 256 0 0 12 24 188544 0x7f4602ecdc80 0x7f4602625e40 524288 7699433 862352220 17249101759819 17249101726652 17249102111932 17249102133309
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 374 201826 201826 4194304 256 0 0 12 24 191552 0x7f4602ecdb00 0x7f4602625e80 524288 2833549 317367264 17249102146209 17249102111932 17249102479131 17249102480840
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 377 201826 201826 4194304 256 0 0 12 24 195840 0x7f4602ecd980 0x7f4602625ec0 524288 2860681 320387212 17249102512209 17249102479131 17249102950331 17249102969597
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 380 201826 201826 4194304 256 0 0 12 24 198592 0x7f4602ecd800 0x7f4602625f00 524288 2798688 313451972 17249102990996 17249102950331 17249103291131 17249103292848
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 201826 201826 4194304 256 0 0 12 24 202368 0x7f4602ecd680 0x7f4602625f40 524288 6936537 776835180 17249103323687 17249103291131 17249103692411 17249103710297
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 386 201826 201826 4194304 256 0 0 12 24 205888 0x7f4605631500 0x7f4602625f80 524288 6674983 747584524 17249103726246 17249103692411 17249104091131 17249104108486
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 389 201826 201826 4194304 256 0 0 12 24 209408 0x7f4605631380 0x7f4602625fc0 524288 2853917 319694768 17249104124965 17249104091131 17249104469371 17249104471526
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 392 201826 201826 4194304 256 0 0 12 24 214464 0x7f4605631200 0x7f4602626000 524288 2933155 328509384 17249104504965 17249104469371 17249104991450 17249105008892
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 395 201826 201826 4194304 256 0 0 12 24 217728 0x7f4605631080 0x7f4602626040 524288 2828172 316734688 17249105032371 17249104991450 17249105355450 17249105357182
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 201826 201826 4194304 256 0 0 12 24 222016 0x7f4602ecdf00 0x7f4602626080 524288 5953377 666786396 17249105390681 17249105355450 17249105770810 17249105788110
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 401 201826 201826 4194304 256 0 0 12 24 226048 0x7f4602ecdd80 0x7f46026260c0 524288 5077998 568701260 17249105805380 17249105770810 17249106193370 17249106211759
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 404 201826 201826 4194304 256 0 0 12 24 230080 0x7f4602ecdc00 0x7f4602626100 524288 2778853 311209532 17249106226989 17249106193370 17249106603770 17249106646447
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 407 201826 201826 4194304 256 0 0 12 24 235904 0x7f4602ecda80 0x7f4602626140 524288 2905589 325403568 17249106659267 17249106603770 17249107207929 17249107250171
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 410 201826 201826 4194304 256 0 0 12 24 239424 0x7f4602ecd900 0x7f4602626180 524288 2757233 308845420 17249107270111 17249107207929 17249107614969 17249107616761
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 201826 201826 4194304 256 0 0 12 24 244224 0x7f4602ecd780 0x7f46026261c0 524288 5264884 589635128 17249107649130 17249107614969 17249108058009 17249108076499
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 416 201826 201826 4194304 256 0 0 12 24 248768 0x7f4602ecd600 0x7f4602626200 524288 3185236 356761576 17249108091369 17249108058009 17249108493849 17249108510847
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 419 201826 201826 4194304 256 0 0 12 24 253312 0x7f4605631480 0x7f4602626240 524288 2730254 305778696 17249108527587 17249108493849 17249108922168 17249108939076
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 422 201826 201826 4194304 256 0 0 8 24 255552 0x7f4605631300 0x7f4602626280 524288 2379427 266485184 17249108956565 17249108922168 17249109566488 17249109583329
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 425 201826 201826 4194304 256 0 0 12 24 259840 0x7f4605631180 0x7f46026262c0 524288 2731630 305925384 17249109608408 17249109566488 17249109982488 17249109998847
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 201826 201826 4194304 256 0 0 12 24 265664 0x7f4605631000 0x7f4602626300 524288 3371281 377530148 17249110015397 17249109982488 17249110482968 17249110503344
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 431 201826 201826 4194304 256 0 0 12 24 271232 0x7f4602ecde80 0x7f4602626340 524288 3566902 399510052 17249110516973 17249110482968 17249110979287 17249110996290
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 434 201826 201826 4194304 256 0 0 8 24 273216 0x7f4602ecdd00 0x7f4602626380 524288 2409085 269846780 17249111013160 17249110979287 17249111468407 17249111485817
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 437 201826 201826 4194304 256 0 0 8 24 275712 0x7f4602ecdb80 0x7f46026263c0 524288 2384099 266982020 17249111502227 17249111468407 17249112220407 17249112237417
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 440 201826 201826 4194304 256 0 0 12 24 280768 0x7f4602ecda00 0x7f4602626400 524288 2653983 297219544 17249112261306 17249112220407 17249112681847 17249112698484
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 201826 201826 4194304 256 0 0 12 24 287616 0x7f4602ecd880 0x7f4602626440 524288 3455484 387000588 17249112715134 17249112681847 17249113223126 17249113240020
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 446 201826 201826 4194304 256 0 0 12 24 294208 0x7f4602ecd700 0x7f4602626480 524288 3349610 375135196 17249113257529 17249113223126 17249113764086 17249113782325
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 449 201826 201826 4194304 256 0 0 8 24 296960 0x7f4605631580 0x7f46026264c0 524288 2391568 267848524 17249113797165 17249113764086 17249114304886 17249114323011
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 452 201826 201826 4194304 256 0 0 8 24 299968 0x7f4605631400 0x7f4602626500 524288 2395734 268311072 17249114339820 17249114304886 17249115158965 17249115181307
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 455 201826 201826 4194304 256 0 0 8 24 302720 0x7f4605631280 0x7f4602626540 524288 2396866 268412932 17249115200707 17249115158965 17249115805205 17249115822320
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 201826 201826 4194304 256 0 0 12 24 305472 0x7f4605631100 0x7f4602626580 524288 2600738 291307888 17249115839690 17249115805205 17249116462325 17249116481172
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 461 201826 201826 4194304 256 0 0 12 24 308224 0x7f4602ecdf80 0x7f46026265c0 524288 2616855 293107100 17249116498462 17249116462325 17249117117205 17249117134615
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 464 201826 201826 4194304 256 0 0 8 24 310976 0x7f4602ecde00 0x7f4602626600 524288 2405162 269361008 17249117151334 17249117117205 17249117762964 17249117780437
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 467 201826 201826 4194304 256 0 0 8 24 313216 0x7f4602ecdc80 0x7f4602626640 524288 2419136 270944456 17249117796607 17249117762799 17249118823599 17249118869908
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 470 201826 201826 4194304 256 0 0 8 24 315968 0x7f4602ecdb00 0x7f4602626680 524288 2442546 273553904 17249118890617 17249118823599 17249119906957 17249119954289
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 201826 201826 4194304 256 0 0 12 24 318720 0x7f4602ecd980 0x7f46026266c0 524288 2600709 291284960 17249119965408 17249119906957 17249121016716 17249121055609
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 476 201826 201826 4194304 256 0 0 12 24 321472 0x7f4602ecd800 0x7f4602626700 524288 2591423 290216036 17249121067449 17249121016716 17249122109195 17249122175659
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 479 201826 201826 4194304 256 0 0 8 24 324224 0x7f4602ecd680 0x7f4602626740 524288 2426293 271693344 17249122187259 17249122109195 17249123215754 17249123256420
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 482 201826 201826 4194304 256 0 0 8 24 326464 0x7f4605631500 0x7f4602626780 524288 2460495 275535664 17249123267940 17249123215754 17249125126792 17249125167788
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 485 201826 201826 4194304 256 0 0 8 24 329216 0x7f4605631380 0x7f46026267c0 524288 2456342 275073060 17249125187048 17249125126792 17249127023111 17249127088467
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 201826 201826 4194304 256 0 0 12 24 331968 0x7f4605631200 0x7f4602626800 524288 2624766 294024028 17249127100496 17249127023111 17249129005669 17249129072943
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 491 201826 201826 4194304 256 0 0 12 24 334720 0x7f4605631080 0x7f4602626840 524288 2613384 292643220 17249129083973 17249129005669 17249130992708 17249131063310
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 494 201826 201826 4194304 256 0 0 8 24 337472 0x7f4602ecdf00 0x7f4602626880 524288 2465829 276165604 17249131075829 17249130992708 17249132932706 17249133005247
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 497 201826 201826 4194304 256 0 0 8 24 0 0x7f4602ecdd80 0x7f46026268c0 524288 2472715 276887956 17249133017057 17249132932706 17249136551263 17249136623859
@@ -1,168 +0,0 @@
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",0,0,0,200422,200422,33554432,256,0,0,4,32,4160,0x0,0x7f294c004280,381872,381872,8673,3054984,524288,239943240,2968704,0,976030444,17231436888452,17230723230837,17231579793472,17231579902522
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,200422,200422,32768,256,0,0,12,24,13888,0x0,0x7f294c023f80,33766,33766,29849,270136,512,1763704,170161,0,7068488,17231585064932,17231579793472,17231585197473,17231585201818
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,200422,200422,4194304,256,0,0,12,24,14336,0x7f295a882380,0x7f294c023fc0,163877,163877,13443,1311024,65536,79496243,1203897,0,319710652,17231585245607,17231585197473,17231585576993,17231585579388
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,200422,200422,4194304,256,0,0,16,24,15040,0x7f295a882200,0x7f294c024000,309221,309221,24795,2473776,65536,221112383,2370366,0,886177260,17231585625207,17231585576993,17231585993313,17231585995657
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,200422,200422,4194304,256,0,0,16,24,15488,0x7f295a882080,0x7f294c024040,307144,307144,24038,2457160,65536,218953150,2353946,0,877541124,17231586036396,17231585993313,17231586415073,17231586417365
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,200422,200422,4194304,256,0,0,12,24,15936,0x7f2958223f00,0x7f294c024080,165125,165125,13541,1321008,65536,80331027,1217298,0,323050652,17231586459154,17231586415073,17231586742913,17231586744947
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,200422,200422,4194304,256,0,0,12,24,16384,0x7f2958223d80,0x7f294c0240c0,164436,164436,13859,1315496,65536,81809694,1211739,0,328968920,17231586785745,17231586742913,17231587063873,17231587066248
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,200422,200422,4194304,256,0,0,12,24,17088,0x7f2958223c00,0x7f294c024100,162547,162547,14650,1300384,65536,107612950,1202849,0,432179420,17231587119646,17231587063873,17231587392514,17231587394499
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,200422,200422,4194304,256,0,0,16,24,17792,0x7f2958223a80,0x7f294c024140,308062,308062,24341,2464504,65536,227032297,2356917,0,909856952,17231587434528,17231587392514,17231587815554,17231587817578
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,200422,200422,4194304,256,0,0,16,24,18496,0x7f2958223900,0x7f294c024180,308317,308317,21847,2466544,65536,215408232,2361613,0,863361936,17231587857637,17231587815554,17231588224994,17231588227147
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,200422,200422,4194304,256,0,0,16,24,19200,0x7f2958223780,0x7f294c0241c0,164058,164058,14214,1312472,65536,97433328,1213034,0,391459520,17231588267185,17231588224994,17231588544514,17231588546578
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,200422,200422,4194304,256,0,0,16,24,19904,0x7f2958223600,0x7f294c024200,164954,164954,15216,1319640,65536,98077723,1216678,0,394039584,17231588587457,17231588544514,17231588866754,17231588868799
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,200422,200422,4194304,256,0,0,12,24,20608,0x7f295a882480,0x7f294c024240,165083,165083,14806,1320672,65536,97692985,1212773,0,392499764,17231588920308,17231588866754,17231589199234,17231589201420
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,200422,200422,4194304,256,0,0,16,24,21312,0x7f295a882300,0x7f294c024280,309005,309005,23386,2472048,65536,225034621,2365908,0,901866704,17231589243559,17231589199234,17231589609154,17231589611309
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,200422,200422,4194304,256,0,0,16,24,22016,0x7f295a882180,0x7f294c0242c0,310724,310724,23158,2485800,65536,224653867,2376621,0,900342636,17231589653138,17231589609154,17231590019074,17231590021018
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,200422,200422,4194304,256,0,0,16,24,22720,0x7f295a882000,0x7f294c024300,164123,164123,14808,1312992,65536,101701650,1209561,0,408533388,17231590062177,17231590019074,17231590384514,17231590387098
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,200422,200422,4194304,256,0,0,12,24,23424,0x7f2958223e80,0x7f294c024340,163637,163637,15174,1309104,65536,106839113,1207738,0,429080056,17231590427667,17231590384514,17231590714434,17231590716609
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,200422,200422,4194304,256,0,0,12,24,24128,0x7f2958223d00,0x7f294c024380,163099,163099,14664,1304800,65536,91319689,1198689,0,366999856,17231590765488,17231590714434,17231591010435,17231591012051
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,200422,200422,4194304,256,0,0,16,24,24832,0x7f2958223b80,0x7f294c0243c0,307817,307817,24146,2462544,65536,229129382,2360185,0,918245276,17231591057580,17231591010435,17231591396995,17231591398661
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,200422,200422,4194304,256,0,0,16,24,25536,0x7f2958223a00,0x7f294c024400,305737,305737,21777,2445904,65536,217415872,2343908,0,871395244,17231591441640,17231591396995,17231591776035,17231591777621
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,200422,200422,4194304,256,0,0,12,24,26240,0x7f2958223880,0x7f294c024440,163247,163247,15202,1305984,65536,109852515,1206631,0,441132548,17231591819060,17231591776035,17231592071875,17231592073333
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,200422,200422,4194304,256,0,0,12,24,26944,0x7f2958223700,0x7f294c024480,162662,162662,15207,1301304,65536,102837429,1200475,0,413070920,17231592114142,17231592071875,17231592365635,17231592367205
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,200422,200422,4194304,256,0,0,12,24,27648,0x7f295a882580,0x7f294c0244c0,162145,162145,14706,1297168,65536,107149336,1200389,0,430329788,17231592415963,17231592365635,17231592665955,17231592667437
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,200422,200422,4194304,256,0,0,16,24,28608,0x7f295a882400,0x7f294c024500,308856,308856,23626,2470856,65536,228595292,2371593,0,916111848,17231592711085,17231592665955,17231593046275,17231593047786
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,200422,200422,4194304,256,0,0,16,24,29312,0x7f295a882280,0x7f294c024540,307216,307216,22341,2457736,65536,207196865,2342818,0,830515600,17231593089375,17231593046275,17231593425955,17231593427526
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,200422,200422,4194304,256,0,0,12,24,30016,0x7f295a882100,0x7f294c024580,162343,162343,15353,1298752,65536,103342321,1198061,0,415102664,17231593470395,17231593425955,17231593716195,17231593717608
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,200422,200422,4194304,256,0,0,8,24,30976,0x7f2958223f80,0x7f294c0245c0,162866,162866,14483,1302936,65536,94786539,1201256,0,380874720,17231593759567,17231593716195,17231594010595,17231594012110
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,200422,200422,4194304,256,0,0,12,24,31680,0x7f2958223e00,0x7f294c024600,162029,162029,15104,1296240,65536,105582930,1196527,0,424051160,17231594059839,17231594010595,17231594313635,17231594315072
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,200422,200422,4194304,256,0,0,16,24,32640,0x7f2958223c80,0x7f294c024640,306910,306910,23609,2455288,65536,229553078,2355095,0,919942424,17231594356191,17231594313635,17231594697156,17231594698652
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,200422,200422,4194304,256,0,0,12,24,33600,0x7f2958223b00,0x7f294c024680,305252,305252,22643,2442024,65536,213084391,2338703,0,854068168,17231594741760,17231594697156,17231595075236,17231595076681
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,200422,200422,4194304,256,0,0,12,24,34560,0x7f2958223980,0x7f294c0246c0,162890,162890,14183,1303128,65536,85698342,1200153,0,344523460,17231595118270,17231595075236,17231595366596,17231595367983
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,200422,200422,4194304,256,0,0,8,24,35520,0x7f2958223800,0x7f294c024700,164288,164288,14176,1314312,65536,91200453,1211620,0,366528608,17231595409292,17231595366596,17231595660356,17231595661895
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,200422,200422,4194304,256,0,0,12,24,36224,0x7f2958223680,0x7f294c024740,162839,162839,14675,1302720,65536,102534285,1204287,0,411859796,17231595710134,17231595660356,17231595949796,17231595951618
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,200422,200422,4194304,256,0,0,12,24,37184,0x7f295a882500,0x7f294c024780,304190,304190,23800,2433528,65536,226421577,2329273,0,907417372,17231595996936,17231595949796,17231596329636,17231596331027
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,200422,200422,4194304,256,0,0,12,24,38144,0x7f295a882380,0x7f294c0247c0,302779,302779,19946,2422240,65536,205794436,2317590,0,824906896,17231596372246,17231596329636,17231596704516,17231596706087
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,200422,200422,4194304,256,0,0,12,24,39104,0x7f295a882200,0x7f294c024800,162251,162251,14774,1298016,65536,98660632,1195466,0,396366100,17231596747916,17231596704516,17231597003716,17231597005299
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,200422,200422,4194304,256,0,0,8,24,40320,0x7f295a882080,0x7f294c024840,162639,162639,15081,1301120,65536,87838870,1198578,0,353080104,17231597047598,17231597003716,17231597297156,17231597298491
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,200422,200422,4194304,256,0,0,12,24,41280,0x7f2958223f00,0x7f294c024880,162727,162727,14452,1301824,65536,92389806,1197277,0,371284192,17231597347480,17231597297156,17231597589956,17231597591533
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,200422,200422,4194304,256,0,0,12,24,42240,0x7f2958223d80,0x7f294c0248c0,303688,303688,23462,2429512,65536,220687632,2330210,0,884480148,17231597636752,17231597589956,17231597988996,17231597990502
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,200422,200422,4194304,256,0,0,12,24,43200,0x7f2958223c00,0x7f294c024900,304756,304756,22321,2438056,65536,221955429,2339543,0,889553340,17231598032641,17231597988996,17231598379397,17231598380842
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,200422,200422,4194304,256,0,0,8,24,44160,0x7f2958223a80,0x7f294c024940,161744,161744,14549,1293960,65536,98750628,1195926,0,396726624,17231598421111,17231598379397,17231598673317,17231598674804
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,200422,200422,4194304,256,0,0,12,24,45376,0x7f2958223900,0x7f294c024980,161777,161777,15104,1294224,65536,93410086,1193329,0,375364484,17231598715953,17231598673317,17231598972197,17231598973686
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,200422,200422,4194304,256,0,0,12,24,46336,0x7f2958223780,0x7f294c0249c0,161120,161120,14500,1288968,65536,91373618,1189571,0,367223492,17231599022744,17231598972197,17231599271877,17231599273407
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,200422,200422,4194304,256,0,0,12,24,47552,0x7f2958223600,0x7f294c024a00,305987,305987,23560,2447904,65536,220391244,2339617,0,883293508,17231599316616,17231599271877,17231599652677,17231599654177
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,200422,200422,4194304,256,0,0,12,24,48512,0x7f295a882480,0x7f294c024a40,301093,301093,20606,2408752,65536,210894164,2306493,0,845307420,17231599695966,17231599652677,17231600030597,17231600032097
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,200422,200422,4194304,256,0,0,8,24,49472,0x7f295a882300,0x7f294c024a80,161205,161205,14431,1289648,65536,90390244,1189161,0,363292440,17231600073316,17231600030597,17231600319877,17231600321489
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,200422,200422,4194304,256,0,0,12,24,50688,0x7f295a882180,0x7f294c024ac0,162294,162294,15781,1298360,65536,97445347,1193747,0,391518464,17231600362838,17231600319877,17231600610757,17231600612181
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,200422,200422,4194304,256,0,0,12,24,51648,0x7f295a882000,0x7f294c024b00,161088,161088,14473,1288712,65536,94475788,1190067,0,379633068,17231600661650,17231600610757,17231600904197,17231600905593
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,200422,200422,4194304,256,0,0,12,24,52864,0x7f2958223e80,0x7f294c024b40,304126,304126,22967,2433016,65536,226482642,2329813,0,907658944,17231600948132,17231600904197,17231601283877,17231601285243
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,200422,200422,4194304,256,0,0,12,24,54080,0x7f2958223d00,0x7f294c024b80,304104,304104,22147,2432840,65536,218872393,2331005,0,877218824,17231601325622,17231601283877,17231601665157,17231601666713
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,200422,200422,4194304,256,0,0,8,24,55296,0x7f2958223b80,0x7f294c024bc0,162364,162364,14608,1298920,65536,95645801,1199488,0,384310828,17231601707732,17231601665157,17231601955718,17231601957175
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,200422,200422,4194304,256,0,0,12,24,56768,0x7f2958223a00,0x7f294c024c00,163018,163018,16069,1304152,65536,100216849,1199878,0,402602280,17231601998094,17231601955718,17231602257478,17231602258967
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,200422,200422,4194304,256,0,0,12,24,57728,0x7f2958223880,0x7f294c024c40,163398,163398,14437,1307192,65536,92974555,1200034,0,373624384,17231602307476,17231602257478,17231602556838,17231602558659
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,200422,200422,4194304,256,0,0,12,24,58944,0x7f2958223700,0x7f294c024c80,301484,301484,22946,2411880,65536,218241043,2310822,0,874697144,17231602599168,17231602556838,17231602933958,17231602935359
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,200422,200422,4194304,256,0,0,12,24,60160,0x7f295a882580,0x7f294c024cc0,302080,302080,21992,2416648,65536,208457380,2310551,0,835556576,17231602977017,17231602933958,17231603312198,17231603313688
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,200422,200422,4194304,256,0,0,8,24,61376,0x7f295a882400,0x7f294c024d00,162616,162616,14151,1300936,65536,97078684,1203996,0,390037504,17231603355847,17231603312198,17231603601958,17231603603221
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,200422,200422,4194304,256,0,0,12,24,62848,0x7f295a882280,0x7f294c024d40,168245,168245,16265,1345968,65536,106217653,1246019,0,426604060,17231603644549,17231603601958,17231603900038,17231603901552
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,200422,200422,4194304,256,0,0,12,24,63808,0x7f295a882100,0x7f294c024d80,162123,162123,14654,1296992,65536,101757316,1196478,0,408750416,17231603949961,17231603900038,17231604188198,17231604189745
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,200422,200422,4194304,256,0,0,12,24,65024,0x7f2958223f80,0x7f294c024dc0,301055,301055,22656,2408448,65536,218438797,2306041,0,875488532,17231604234873,17231604188198,17231604581638,17231604583104
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,200422,200422,4194304,256,0,0,12,24,66240,0x7f2958223e00,0x7f294c024e00,298868,298868,20801,2390952,65536,208158295,2286319,0,834367380,17231604624193,17231604581638,17231604964838,17231604966294
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,200422,200422,4194304,256,0,0,8,24,67456,0x7f2958223c80,0x7f294c024e40,164029,164029,14480,1312240,65536,92710114,1207982,0,372567164,17231605005893,17231604964838,17231605256678,17231605258176
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,200422,200422,4194304,256,0,0,12,24,68928,0x7f2958223b00,0x7f294c024e80,176594,176594,16215,1412760,65536,108118199,1308234,0,434208944,17231605298755,17231605256678,17231605556839,17231605558298
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,200422,200422,4194304,256,0,0,12,24,70144,0x7f2958223980,0x7f294c024ec0,160574,160574,14856,1284600,65536,90026451,1183697,0,361837972,17231605606966,17231605556839,17231605857159,17231605858560
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,200422,200422,4194304,256,0,0,12,24,71616,0x7f2958223800,0x7f294c024f00,303013,303013,23334,2424112,65536,221957468,2322322,0,889561760,17231605900158,17231605857159,17231606234919,17231606236539
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,200422,200422,4194304,256,0,0,12,24,72832,0x7f2958223680,0x7f294c024f40,300754,300754,21679,2406040,65536,219022988,2305582,0,877821012,17231606278738,17231606234919,17231606617319,17231606618759
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,200422,200422,4194304,256,0,0,8,24,74048,0x7f295a882500,0x7f294c024f80,160819,160819,14584,1286560,65536,89771526,1187721,0,360821756,17231606659708,17231606617319,17231606906919,17231606908431
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,200422,200422,4194304,256,0,0,12,24,75776,0x7f295a882380,0x7f294c024fc0,181071,181071,16859,1448576,65536,112869436,1345061,0,453220084,17231606949150,17231606906919,17231607210919,17231607212403
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,200422,200422,4194304,256,0,0,12,24,76992,0x7f295a882200,0x7f294c025000,160683,160683,14647,1285472,65536,100795857,1187139,0,404909652,17231607272191,17231607210919,17231607502919,17231607504525
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,200422,200422,4194304,256,0,0,12,24,78464,0x7f295a882080,0x7f294c025040,301757,301757,23351,2414064,65536,217891782,2311532,0,873298764,17231607552224,17231607502919,17231607887079,17231607888715
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,200422,200422,4194304,256,0,0,12,24,79936,0x7f2958223f00,0x7f294c025080,300565,300565,22021,2404528,65536,213486591,2298636,0,855675624,17231607929804,17231607887079,17231608270919,17231608272454
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,200422,200422,4194304,256,0,0,8,24,81408,0x7f2958223d80,0x7f294c0250c0,162815,162815,15202,1302528,65536,94875261,1202603,0,381225248,17231608313853,17231608270919,17231608564039,17231608565586
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,200422,200422,4194304,256,0,0,12,24,83136,0x7f2958223c00,0x7f294c025100,190365,190365,17465,1522928,65536,127640821,1424804,0,512306844,17231608606595,17231608564039,17231608876359,17231608877858
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,200422,200422,4194304,256,0,0,12,24,84352,0x7f2958223a80,0x7f294c025140,161176,161176,14444,1289416,65536,93567046,1190218,0,375998292,17231608926297,17231608876359,17231609172520,17231609173970
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,200422,200422,4194304,256,0,0,12,24,85824,0x7f2958223900,0x7f294c025180,303654,303654,24097,2429240,65536,222235612,2325778,0,890679232,17231609218419,17231609172520,17231609564040,17231609565659
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,200422,200422,4194304,256,0,0,12,24,87296,0x7f2958223780,0x7f294c0251c0,299116,299116,22401,2392936,65536,211163536,2293811,0,846382728,17231609607558,17231609564040,17231609941640,17231609943099
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,200422,200422,4194304,256,0,0,12,24,88768,0x7f2958223600,0x7f294c025200,163309,163309,15891,1306480,65536,96334904,1199470,0,387066280,17231609983598,17231609941640,17231610244520,17231610246011
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,200422,200422,4194304,256,0,0,12,24,90752,0x7f295a882480,0x7f294c025240,200492,200492,18059,1603944,65536,129800226,1500390,0,520943684,17231610287420,17231610244520,17231610569640,17231610571252
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,200422,200422,4194304,256,0,0,12,24,91968,0x7f295a882300,0x7f294c025280,162244,162244,15514,1297960,65536,93538361,1192686,0,375877232,17231610619871,17231610569640,17231610868520,17231610869844
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,200422,200422,4194304,256,0,0,12,24,93440,0x7f295a882180,0x7f294c0252c0,301762,301762,23044,2414104,65536,216926542,2303429,0,869438460,17231610915023,17231610868520,17231611253960,17231611255464
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,200422,200422,4194304,256,0,0,12,24,94912,0x7f295a882000,0x7f294c025300,299453,299453,20078,2395632,65536,203593527,2292485,0,816108980,17231611297982,17231611253960,17231611630760,17231611632223
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,200422,200422,4194304,256,0,0,12,24,96384,0x7f2958223e80,0x7f294c025340,161891,161891,15198,1295136,65536,97968461,1196395,0,393604328,17231611673732,17231611630760,17231611927880,17231611929345
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,200422,200422,4194304,256,0,0,12,24,98368,0x7f2958223d00,0x7f294c025380,211095,211095,18817,1688768,65536,124430395,1573317,0,499467664,17231611969644,17231611927880,17231612256680,17231612258076
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,200422,200422,4194304,256,0,0,12,24,99584,0x7f2958223b80,0x7f294c0253c0,161023,161023,14706,1288192,65536,89859098,1190262,0,361171344,17231612306345,17231612256680,17231612553640,17231612555048
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,200422,200422,4194304,256,0,0,12,24,101312,0x7f2958223a00,0x7f294c025400,299799,299799,23068,2398400,65536,217978625,2298970,0,873648940,17231612595717,17231612553640,17231612935881,17231612937458
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,200422,200422,4194304,256,0,0,12,24,102784,0x7f2958223880,0x7f294c025440,297931,297931,20593,2383456,65536,208733186,2276747,0,836665732,17231612977937,17231612935881,17231613312521,17231613314078
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,200422,200422,4194304,256,0,0,12,24,104256,0x7f2958223700,0x7f294c025480,162085,162085,16597,1296688,65536,99237539,1186965,0,398681308,17231613354017,17231613312521,17231613605641,17231613607050
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,200422,200422,4194304,256,0,0,12,24,106240,0x7f295a882580,0x7f294c0254c0,219424,219424,19592,1755400,65536,138081562,1643017,0,554077112,17231613648159,17231613605641,17231613947081,17231613948560
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,200422,200422,4194304,256,0,0,12,24,107712,0x7f295a882400,0x7f294c025500,160993,160993,14458,1287952,65536,90929804,1188426,0,365460640,17231613996809,17231613947081,17231614247241,17231614248812
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,200422,200422,4194304,256,0,0,16,24,109440,0x7f295a882280,0x7f294c025540,297705,297705,21606,2381648,65536,208310328,2276299,0,834973552,17231614294091,17231614247241,17231614627721,17231614629302
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,200422,200422,4194304,256,0,0,16,24,111168,0x7f295a882100,0x7f294c025580,298417,298417,20312,2387344,65536,207052009,2283088,0,829938276,17231614670921,17231614627721,17231615005321,17231615006822
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,200422,200422,4194304,256,0,0,8,24,112896,0x7f2958223f80,0x7f294c0255c0,162670,162670,15369,1301368,65536,102240218,1200080,0,410699996,17231615048431,17231615005321,17231615302601,17231615304094
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,200422,200422,4194304,256,0,0,12,24,115136,0x7f2958223e00,0x7f294c025600,229540,229540,19857,1836328,65536,147306050,1721496,0,590967192,17231615344683,17231615302601,17231615638601,17231615639985
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,200422,200422,4194304,256,0,0,12,24,116608,0x7f2958223c80,0x7f294c025640,162102,162102,15943,1296824,65536,95372929,1190358,0,383224800,17231615687453,17231615638601,17231615931401,17231615932817
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,200422,200422,4194304,256,0,0,16,24,118336,0x7f2958223b00,0x7f294c025680,299345,299345,22472,2394768,65536,211891866,2292097,0,849299196,17231615978446,17231615931401,17231616315082,17231616316836
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,200422,200422,4194304,256,0,0,16,24,120064,0x7f2958223980,0x7f294c0256c0,298015,298015,20239,2384128,65536,206770921,2273589,0,828815864,17231616357715,17231616315082,17231616692362,17231616693966
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,200422,200422,4194304,256,0,0,12,24,121792,0x7f2958223800,0x7f294c025700,163980,163980,16065,1311848,65536,102137658,1207572,0,410281616,17231616735305,17231616692362,17231616989642,17231616991188
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,200422,200422,4194304,256,0,0,12,24,124032,0x7f2958223680,0x7f294c025740,239995,239995,19904,1919968,65536,148735996,1809358,0,596691264,17231617031657,17231616989642,17231617335562,17231617337189
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,200422,200422,4194304,256,0,0,12,24,125504,0x7f295a882500,0x7f294c025780,162264,162264,15604,1298120,65536,101478602,1191938,0,407641108,17231617385988,17231617335562,17231617635082,17231617636491
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,200422,200422,4194304,256,0,0,12,24,127488,0x7f295a882380,0x7f294c0257c0,296689,296689,20183,2373520,65536,207851829,2269995,0,833140292,17231617681250,17231617635082,17231618023242,17231618024760
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,200422,200422,4194304,256,0,0,12,24,129216,0x7f295a882200,0x7f294c025800,297534,297534,20071,2380280,65536,210291710,2275068,0,842898884,17231618067049,17231618023242,17231618409962,17231618411480
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,200422,200422,4194304,256,0,0,12,24,130944,0x7f295a882080,0x7f294c025840,169609,169609,15948,1356880,65536,103993311,1254775,0,417721568,17231618454409,17231618409962,17231618708042,17231618709582
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,200422,200422,4194304,256,0,0,12,24,133440,0x7f2958223f00,0x7f294c025880,258710,258710,21329,2069688,65536,181336855,1955134,0,727094360,17231618753921,17231618708042,17231619065802,17231619067322
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,200422,200422,4194304,256,0,0,12,24,134912,0x7f2958223d80,0x7f294c0258c0,161949,161949,17038,1295600,65536,99162329,1183969,0,398379272,17231619117481,17231619065802,17231619360362,17231619362094
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,200422,200422,4194304,256,0,0,12,24,136896,0x7f2958223c00,0x7f294c025900,296914,296914,20762,2375320,65536,207273288,2273821,0,830834512,17231619403113,17231619360362,17231619743402,17231619744954
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,200422,200422,4194304,256,0,0,12,24,138880,0x7f2958223a80,0x7f294c025940,297449,297449,20956,2379600,65536,214007620,2271210,0,857762528,17231619786493,17231619743402,17231620122923,17231620124414
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,200422,200422,4194304,256,0,0,12,24,140864,0x7f2958223900,0x7f294c025980,177732,177732,16586,1421864,65536,111952432,1320538,0,449550432,17231620164802,17231620122923,17231620426123,17231620427605
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,200422,200422,4194304,256,0,0,12,24,143616,0x7f2958223780,0x7f294c0259c0,279200,279200,22168,2233608,65536,200179956,2126518,0,802461908,17231620468884,17231620426123,17231620793323,17231620794805
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,200422,200422,4194304,256,0,0,12,24,145344,0x7f2958223600,0x7f294c025a00,162170,162170,15687,1297368,65536,99669919,1194945,0,400414004,17231620843374,17231620793323,17231621091403,17231621092897
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,200422,200422,4194304,256,0,0,12,24,147584,0x7f295a882480,0x7f294c025a40,293819,293819,20319,2350560,65536,205299412,2251239,0,822932500,17231621137226,17231621091403,17231621473963,17231621475397
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,200422,200422,4194304,256,0,0,12,24,149568,0x7f295a882300,0x7f294c025a80,295370,295370,20525,2362968,65536,209878742,2257967,0,841250948,17231621518336,17231621473963,17231621854443,17231621855877
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,200422,200422,4194304,256,0,0,12,24,151552,0x7f295a882180,0x7f294c025ac0,186634,186634,17661,1493080,65536,109340791,1382012,0,439111956,17231621896716,17231621854443,17231622167883,17231622169448
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,200422,200422,4194304,256,0,0,12,24,154304,0x7f295a882000,0x7f294c025b00,299341,299341,22984,2394736,65536,200769001,2287059,0,804830740,17231622210747,17231622167883,17231622550923,17231622552358
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,200422,200422,4194304,256,0,0,12,24,156288,0x7f2958223e80,0x7f294c025b40,171560,171560,16562,1372488,65536,103736801,1268941,0,416699940,17231622600427,17231622550923,17231622851243,17231622852750
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,200422,200422,4194304,256,0,0,12,24,158784,0x7f2958223d00,0x7f294c025b80,296654,296654,19621,2373240,65536,185843027,2263227,0,745118084,17231622893479,17231622851243,17231623231243,17231623232619
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,200422,200422,4194304,256,0,0,12,24,161024,0x7f2958223b80,0x7f294c025bc0,296141,296141,20019,2369136,65536,200900158,2261354,0,805356028,17231623273688,17231623231243,17231623611404,17231623612949
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,200422,200422,4194304,256,0,0,12,24,163264,0x7f2958223a00,0x7f294c025c00,205397,205397,18078,1643184,65536,128144857,1530767,0,514324964,17231623652688,17231623611404,17231623932044,17231623933490
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,200422,200422,4194304,256,0,0,12,24,166528,0x7f2958223880,0x7f294c025c40,339666,339666,25004,2717336,65536,240492471,2608449,0,963724140,17231623973549,17231623932044,17231624337324,17231624380198
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,200422,200422,4194304,256,0,0,12,24,168512,0x7f2958223700,0x7f294c025c80,183456,183456,16786,1467656,65536,104208680,1361092,0,418582216,17231624398528,17231624337324,17231624672684,17231624674130
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,200422,200422,4194304,256,0,0,12,24,171264,0x7f295a882580,0x7f294c025cc0,295239,295239,18697,2361920,65536,164466383,2237031,0,659627484,17231624715079,17231624672684,17231625054444,17231625055970
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,200422,200422,4194304,256,0,0,12,24,173760,0x7f295a882400,0x7f294c025d00,295772,295772,20762,2366184,65536,196869949,2258497,0,789226500,17231625097169,17231625054444,17231625435404,17231625436859
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,200422,200422,4194304,256,0,0,12,24,176256,0x7f295a882280,0x7f294c025d40,225282,225282,19480,1802264,65536,145542428,1695158,0,583922244,17231625477358,17231625435404,17231625770124,17231625771560
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,200422,200422,4194304,256,0,0,12,24,179776,0x7f295a882100,0x7f294c025d80,379656,379656,26922,3037256,65536,280209836,2929653,0,1122589780,17231625812829,17231625770124,17231626199884,17231626223518
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,200422,200422,4194304,256,0,0,12,24,182272,0x7f2958223f80,0x7f294c025dc0,210469,210469,18571,1683760,65536,133685792,1577480,0,536494544,17231626250577,17231626199884,17231626538924,17231626540340
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,200422,200422,4194304,256,0,0,12,24,185536,0x7f2958223e00,0x7f294c025e00,303172,303172,22112,2425384,65536,191823665,2305203,0,769052816,17231626580688,17231626538924,17231626933164,17231626935539
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,200422,200422,4194304,256,0,0,12,24,188544,0x7f2958223c80,0x7f294c025e40,307442,307442,22485,2459544,65536,176953968,2332701,0,709577508,17231626974578,17231626933164,17231627331405,17231627333718
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,200422,200422,4194304,256,0,0,12,24,191552,0x7f2958223b00,0x7f294c025e80,266294,266294,21926,2130360,65536,180065375,2018223,0,722023816,17231627372797,17231627331405,17231627692845,17231627694478
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,200422,200422,4194304,256,0,0,12,24,195840,0x7f2958223980,0x7f294c025ec0,460636,460636,31321,3685096,65536,346846106,3577428,0,1389144048,17231627734717,17231627692845,17231628177805,17231628195495
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,200422,200422,4194304,256,0,0,12,24,198592,0x7f2958223800,0x7f294c025f00,244610,244610,20263,1956888,65536,151009413,1844672,0,605798556,17231628227354,17231628177805,17231628526125,17231628527686
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,200422,200422,4194304,256,0,0,12,24,202368,0x7f2958223680,0x7f294c025f40,334198,334198,22628,2673592,65536,213497531,2558930,0,855765908,17231628568385,17231628526125,17231628932845,17231628947655
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,200422,200422,4194304,256,0,0,12,24,205888,0x7f295a882500,0x7f294c025f80,330180,330180,22761,2641448,65536,210071669,2521111,0,842056988,17231628975584,17231628932845,17231629346765,17231629361293
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,200422,200422,4194304,256,0,0,12,24,209408,0x7f295a882380,0x7f294c025fc0,305389,305389,23176,2443120,65536,218513807,2340306,0,875811112,17231629387873,17231629346765,17231629737965,17231629739543
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,200422,200422,4194304,256,0,0,12,24,214464,0x7f295a882200,0x7f294c026000,541966,541966,35270,4335736,65536,412537177,4224256,0,1651912024,17231629779832,17231629737965,17231630273325,17231630287808
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,200422,200422,4194304,256,0,0,12,24,217728,0x7f295a882080,0x7f294c026040,273069,273069,21327,2184560,65536,171320182,2075622,0,687039236,17231630323797,17231630273325,17231630643565,17231630645059
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,200422,200422,4194304,256,0,0,12,24,222016,0x7f2958223f00,0x7f294c026080,363323,363323,28653,2906592,65536,247955699,2796665,0,993603528,17231630686228,17231630643565,17231631071566,17231631113446
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,200422,200422,4194304,256,0,0,12,24,226048,0x7f2958223d80,0x7f294c0260c0,365450,365450,27686,2923608,65536,256753072,2817239,0,1028783604,17231631122856,17231631071566,17231631521646,17231631563344
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,200422,200422,4194304,256,0,0,12,24,230080,0x7f2958223c00,0x7f294c026100,347119,347119,25241,2776960,65536,248017257,2666784,0,993835092,17231631573494,17231631521646,17231631953006,17231631994052
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,200422,200422,4194304,256,0,0,12,24,235904,0x7f2958223a80,0x7f294c026140,624722,624722,40660,4997784,65536,473810578,4875511,0,1897002308,17231632004202,17231631953006,17231632559246,17231632600426
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,200422,200422,4194304,256,0,0,12,24,239424,0x7f2958223900,0x7f294c026180,302147,302147,22621,2417184,65536,211567813,2315765,0,848034748,17231632618725,17231632559246,17231632971726,17231632973296
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,200422,200422,4194304,256,0,0,12,24,244224,0x7f2958223780,0x7f294c0261c0,397576,397576,27872,3180616,65536,273852920,3068198,0,1097194364,17231633014045,17231632971726,17231633419246,17231633460683
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,200422,200422,4194304,256,0,0,12,24,248768,0x7f2958223600,0x7f294c026200,389877,389877,27191,3119024,65536,294496227,3021203,0,1179756088,17231633470072,17231633419246,17231633884686,17231633902211
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,200422,200422,4194304,256,0,0,12,24,253312,0x7f295a882480,0x7f294c026240,387204,387204,27520,3097640,65536,290449581,2990639,0,1163591664,17231633926980,17231633884686,17231634322926,17231634369898
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,200422,200422,4194304,256,0,0,8,24,255552,0x7f295a882300,0x7f294c026280,716980,716980,43862,5735848,65536,550929702,5630413,0,2205458468,17231634380888,17231634322926,17231635004047,17231635047210
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,200422,200422,4194304,256,0,0,12,24,259840,0x7f295a882180,0x7f294c0262c0,364380,364380,26166,2915048,65536,257305393,2804173,0,1030985812,17231635066309,17231635004047,17231635448687,17231635491298
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,200422,200422,4194304,256,0,0,12,24,265664,0x7f295a882000,0x7f294c026300,469213,469213,31164,3753712,65536,353538872,3646434,0,1415942712,17231635501767,17231635448687,17231635971727,17231636012804
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,200422,200422,4194304,256,0,0,12,24,271232,0x7f2958223e80,0x7f294c026340,472782,472782,32208,3782264,65536,350692765,3674988,0,1404554008,17231636023083,17231635971727,17231636494287,17231636535000
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,200422,200422,4194304,256,0,0,8,24,273216,0x7f2958223d00,0x7f294c026380,483410,483410,33165,3867288,65536,356741343,3755658,0,1428705704,17231636545169,17231636494287,17231637010127,17231637050746
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,200422,200422,4194304,256,0,0,8,24,275712,0x7f2958223b80,0x7f294c0263c0,879208,879208,52783,7033672,65536,683750772,6923919,0,2736744260,17231637061125,17231637010127,17231637786927,17231637828775
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,200422,200422,4194304,256,0,0,12,24,280768,0x7f2958223a00,0x7f294c026400,425745,425745,29144,3405968,65536,319495457,3301280,0,1279750752,17231637847614,17231637786927,17231638272848,17231638317091
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,200422,200422,4194304,256,0,0,12,24,287616,0x7f2958223880,0x7f294c026440,548289,548289,35218,4386320,65536,414758485,4286026,0,1660820752,17231638328781,17231638272848,17231638847888,17231638891636
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,200422,200422,4194304,256,0,0,12,24,294208,0x7f2958223700,0x7f294c026480,550983,550983,35718,4407872,65536,406158858,4298525,0,1626419400,17231638901696,17231638847888,17231639418448,17231639459870
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,200422,200422,4194304,256,0,0,8,24,296960,0x7f295a882580,0x7f294c0264c0,562022,562022,36282,4496184,65536,424763207,4387586,0,1700795720,17231639469750,17231639418448,17231639984528,17231640025425
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,200422,200422,4194304,256,0,0,8,24,299968,0x7f295a882400,0x7f294c026500,1042215,1042215,61270,8337728,65536,817003442,8220806,0,3269755936,17231640035765,17231639984528,17231640867408,17231640911091
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,200422,200422,4194304,256,0,0,8,24,302720,0x7f295a882280,0x7f294c026540,722641,722641,44551,5781136,65536,545394791,5656491,0,2183322012,17231640929850,17231640867408,17231641536528,17231641577063
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,200422,200422,4194304,256,0,0,12,24,305472,0x7f295a882100,0x7f294c026580,723095,723095,44448,5784768,65536,552455064,5673853,0,2211561192,17231641587173,17231641536528,17231642221969,17231642266534
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,200422,200422,4194304,256,0,0,12,24,308224,0x7f2958223f80,0x7f294c0265c0,721259,721259,43987,5770080,65536,548760037,5661350,0,2196780064,17231642277424,17231642221816,17231642907256,17231642958655
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,200422,200422,4194304,256,0,0,8,24,310976,0x7f2958223e00,0x7f294c026600,726630,726630,44644,5813048,65536,555561140,5697271,0,2223985996,17231642969215,17231642907256,17231643588214,17231643631587
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,200422,200422,4194304,256,0,0,8,24,313216,0x7f2958223c80,0x7f294c026640,1367304,1367304,77501,10938440,65536,1067749919,10822414,0,4272741176,17231643642027,17231643588214,17231644680054,17231644723038
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,200422,200422,4194304,256,0,0,8,24,315968,0x7f2958223b00,0x7f294c026680,1371228,1371228,77375,10969832,65536,1082524152,10849956,0,4331838720,17231644744147,17231644680054,17231645780534,17231645844557
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,200422,200422,4194304,256,0,0,12,24,318720,0x7f2958223980,0x7f294c0266c0,1372315,1372315,77166,10978528,65536,1074250970,10862144,0,4298744480,17231645855407,17231645780534,17231646920534,17231646986267
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,200422,200422,4194304,256,0,0,12,24,321472,0x7f2958223800,0x7f294c026700,1371465,1371465,77029,10971728,65536,1079868798,10849505,0,4321216184,17231646996746,17231646920534,17231648061174,17231648127126
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,200422,200422,4194304,256,0,0,8,24,324224,0x7f2958223680,0x7f294c026740,1377412,1377412,77862,11019304,65536,1067129407,10891598,0,4270259980,17231648136856,17231648061174,17231649191414,17231649257825
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,200422,200422,4194304,256,0,0,8,24,326464,0x7f295a882500,0x7f294c026780,2664265,2664265,142063,21314128,65536,2119458099,21183122,0,8479574076,17231649267665,17231649191414,17231651150614,17231651226242
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,200422,200422,4194304,256,0,0,8,24,329216,0x7f295a882380,0x7f294c0267c0,2669748,2669748,143521,21357992,65536,2133181962,21231914,0,8534468992,17231651245222,17231651150614,17231653089654,17231653156420
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,200422,200422,4194304,256,0,0,12,24,331968,0x7f295a882200,0x7f294c026800,2671224,2671224,142967,21369800,65536,2131474553,21239023,0,8527638892,17231653167080,17231653089654,17231655078614,17231655150156
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,200422,200422,4194304,256,0,0,12,24,334720,0x7f295a882080,0x7f294c026840,2668850,2668850,142948,21350808,65536,2125485042,21234779,0,8503680176,17231655160816,17231655078614,17231657070614,17231657135542
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,200422,200422,4194304,256,0,0,8,24,337472,0x7f2958223f00,0x7f294c026880,2674558,2674558,142583,21396472,65536,2127696938,21262653,0,8512530040,17231657146272,17231657070614,17231659003254,17231659074779
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,200422,200422,4194304,256,0,0,8,24,0,0x7f2958223d80,0x7f294c0268c0,5256982,5256982,274055,42055864,65536,4232667833,41931017,0,16932412712,17231659085669,17231659003254,17231662631094,17231662703371
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 200422 200422 33554432 256 0 0 4 32 4160 0x0 0x7f294c004280 381872 381872 8673 3054984 524288 239943240 2968704 0 976030444 17231436888452 17230723230837 17231579793472 17231579902522
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 200422 200422 32768 256 0 0 12 24 13888 0x0 0x7f294c023f80 33766 33766 29849 270136 512 1763704 170161 0 7068488 17231585064932 17231579793472 17231585197473 17231585201818
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 5 200422 200422 4194304 256 0 0 12 24 14336 0x7f295a882380 0x7f294c023fc0 163877 163877 13443 1311024 65536 79496243 1203897 0 319710652 17231585245607 17231585197473 17231585576993 17231585579388
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 200422 200422 4194304 256 0 0 16 24 15040 0x7f295a882200 0x7f294c024000 309221 309221 24795 2473776 65536 221112383 2370366 0 886177260 17231585625207 17231585576993 17231585993313 17231585995657
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 11 200422 200422 4194304 256 0 0 16 24 15488 0x7f295a882080 0x7f294c024040 307144 307144 24038 2457160 65536 218953150 2353946 0 877541124 17231586036396 17231585993313 17231586415073 17231586417365
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 14 200422 200422 4194304 256 0 0 12 24 15936 0x7f2958223f00 0x7f294c024080 165125 165125 13541 1321008 65536 80331027 1217298 0 323050652 17231586459154 17231586415073 17231586742913 17231586744947
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 17 200422 200422 4194304 256 0 0 12 24 16384 0x7f2958223d80 0x7f294c0240c0 164436 164436 13859 1315496 65536 81809694 1211739 0 328968920 17231586785745 17231586742913 17231587063873 17231587066248
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 20 200422 200422 4194304 256 0 0 12 24 17088 0x7f2958223c00 0x7f294c024100 162547 162547 14650 1300384 65536 107612950 1202849 0 432179420 17231587119646 17231587063873 17231587392514 17231587394499
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 200422 200422 4194304 256 0 0 16 24 17792 0x7f2958223a80 0x7f294c024140 308062 308062 24341 2464504 65536 227032297 2356917 0 909856952 17231587434528 17231587392514 17231587815554 17231587817578
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 26 200422 200422 4194304 256 0 0 16 24 18496 0x7f2958223900 0x7f294c024180 308317 308317 21847 2466544 65536 215408232 2361613 0 863361936 17231587857637 17231587815554 17231588224994 17231588227147
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 29 200422 200422 4194304 256 0 0 16 24 19200 0x7f2958223780 0x7f294c0241c0 164058 164058 14214 1312472 65536 97433328 1213034 0 391459520 17231588267185 17231588224994 17231588544514 17231588546578
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 32 200422 200422 4194304 256 0 0 16 24 19904 0x7f2958223600 0x7f294c024200 164954 164954 15216 1319640 65536 98077723 1216678 0 394039584 17231588587457 17231588544514 17231588866754 17231588868799
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 35 200422 200422 4194304 256 0 0 12 24 20608 0x7f295a882480 0x7f294c024240 165083 165083 14806 1320672 65536 97692985 1212773 0 392499764 17231588920308 17231588866754 17231589199234 17231589201420
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 200422 200422 4194304 256 0 0 16 24 21312 0x7f295a882300 0x7f294c024280 309005 309005 23386 2472048 65536 225034621 2365908 0 901866704 17231589243559 17231589199234 17231589609154 17231589611309
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 41 200422 200422 4194304 256 0 0 16 24 22016 0x7f295a882180 0x7f294c0242c0 310724 310724 23158 2485800 65536 224653867 2376621 0 900342636 17231589653138 17231589609154 17231590019074 17231590021018
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 44 200422 200422 4194304 256 0 0 16 24 22720 0x7f295a882000 0x7f294c024300 164123 164123 14808 1312992 65536 101701650 1209561 0 408533388 17231590062177 17231590019074 17231590384514 17231590387098
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 47 200422 200422 4194304 256 0 0 12 24 23424 0x7f2958223e80 0x7f294c024340 163637 163637 15174 1309104 65536 106839113 1207738 0 429080056 17231590427667 17231590384514 17231590714434 17231590716609
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 50 200422 200422 4194304 256 0 0 12 24 24128 0x7f2958223d00 0x7f294c024380 163099 163099 14664 1304800 65536 91319689 1198689 0 366999856 17231590765488 17231590714434 17231591010435 17231591012051
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 200422 200422 4194304 256 0 0 16 24 24832 0x7f2958223b80 0x7f294c0243c0 307817 307817 24146 2462544 65536 229129382 2360185 0 918245276 17231591057580 17231591010435 17231591396995 17231591398661
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 56 200422 200422 4194304 256 0 0 16 24 25536 0x7f2958223a00 0x7f294c024400 305737 305737 21777 2445904 65536 217415872 2343908 0 871395244 17231591441640 17231591396995 17231591776035 17231591777621
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 59 200422 200422 4194304 256 0 0 12 24 26240 0x7f2958223880 0x7f294c024440 163247 163247 15202 1305984 65536 109852515 1206631 0 441132548 17231591819060 17231591776035 17231592071875 17231592073333
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 62 200422 200422 4194304 256 0 0 12 24 26944 0x7f2958223700 0x7f294c024480 162662 162662 15207 1301304 65536 102837429 1200475 0 413070920 17231592114142 17231592071875 17231592365635 17231592367205
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 65 200422 200422 4194304 256 0 0 12 24 27648 0x7f295a882580 0x7f294c0244c0 162145 162145 14706 1297168 65536 107149336 1200389 0 430329788 17231592415963 17231592365635 17231592665955 17231592667437
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 200422 200422 4194304 256 0 0 16 24 28608 0x7f295a882400 0x7f294c024500 308856 308856 23626 2470856 65536 228595292 2371593 0 916111848 17231592711085 17231592665955 17231593046275 17231593047786
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 71 200422 200422 4194304 256 0 0 16 24 29312 0x7f295a882280 0x7f294c024540 307216 307216 22341 2457736 65536 207196865 2342818 0 830515600 17231593089375 17231593046275 17231593425955 17231593427526
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 74 200422 200422 4194304 256 0 0 12 24 30016 0x7f295a882100 0x7f294c024580 162343 162343 15353 1298752 65536 103342321 1198061 0 415102664 17231593470395 17231593425955 17231593716195 17231593717608
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 77 200422 200422 4194304 256 0 0 8 24 30976 0x7f2958223f80 0x7f294c0245c0 162866 162866 14483 1302936 65536 94786539 1201256 0 380874720 17231593759567 17231593716195 17231594010595 17231594012110
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 80 200422 200422 4194304 256 0 0 12 24 31680 0x7f2958223e00 0x7f294c024600 162029 162029 15104 1296240 65536 105582930 1196527 0 424051160 17231594059839 17231594010595 17231594313635 17231594315072
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 200422 200422 4194304 256 0 0 16 24 32640 0x7f2958223c80 0x7f294c024640 306910 306910 23609 2455288 65536 229553078 2355095 0 919942424 17231594356191 17231594313635 17231594697156 17231594698652
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 86 200422 200422 4194304 256 0 0 12 24 33600 0x7f2958223b00 0x7f294c024680 305252 305252 22643 2442024 65536 213084391 2338703 0 854068168 17231594741760 17231594697156 17231595075236 17231595076681
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 89 200422 200422 4194304 256 0 0 12 24 34560 0x7f2958223980 0x7f294c0246c0 162890 162890 14183 1303128 65536 85698342 1200153 0 344523460 17231595118270 17231595075236 17231595366596 17231595367983
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 92 200422 200422 4194304 256 0 0 8 24 35520 0x7f2958223800 0x7f294c024700 164288 164288 14176 1314312 65536 91200453 1211620 0 366528608 17231595409292 17231595366596 17231595660356 17231595661895
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 95 200422 200422 4194304 256 0 0 12 24 36224 0x7f2958223680 0x7f294c024740 162839 162839 14675 1302720 65536 102534285 1204287 0 411859796 17231595710134 17231595660356 17231595949796 17231595951618
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 200422 200422 4194304 256 0 0 12 24 37184 0x7f295a882500 0x7f294c024780 304190 304190 23800 2433528 65536 226421577 2329273 0 907417372 17231595996936 17231595949796 17231596329636 17231596331027
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 101 200422 200422 4194304 256 0 0 12 24 38144 0x7f295a882380 0x7f294c0247c0 302779 302779 19946 2422240 65536 205794436 2317590 0 824906896 17231596372246 17231596329636 17231596704516 17231596706087
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 104 200422 200422 4194304 256 0 0 12 24 39104 0x7f295a882200 0x7f294c024800 162251 162251 14774 1298016 65536 98660632 1195466 0 396366100 17231596747916 17231596704516 17231597003716 17231597005299
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 107 200422 200422 4194304 256 0 0 8 24 40320 0x7f295a882080 0x7f294c024840 162639 162639 15081 1301120 65536 87838870 1198578 0 353080104 17231597047598 17231597003716 17231597297156 17231597298491
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 110 200422 200422 4194304 256 0 0 12 24 41280 0x7f2958223f00 0x7f294c024880 162727 162727 14452 1301824 65536 92389806 1197277 0 371284192 17231597347480 17231597297156 17231597589956 17231597591533
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 200422 200422 4194304 256 0 0 12 24 42240 0x7f2958223d80 0x7f294c0248c0 303688 303688 23462 2429512 65536 220687632 2330210 0 884480148 17231597636752 17231597589956 17231597988996 17231597990502
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 116 200422 200422 4194304 256 0 0 12 24 43200 0x7f2958223c00 0x7f294c024900 304756 304756 22321 2438056 65536 221955429 2339543 0 889553340 17231598032641 17231597988996 17231598379397 17231598380842
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 119 200422 200422 4194304 256 0 0 8 24 44160 0x7f2958223a80 0x7f294c024940 161744 161744 14549 1293960 65536 98750628 1195926 0 396726624 17231598421111 17231598379397 17231598673317 17231598674804
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 122 200422 200422 4194304 256 0 0 12 24 45376 0x7f2958223900 0x7f294c024980 161777 161777 15104 1294224 65536 93410086 1193329 0 375364484 17231598715953 17231598673317 17231598972197 17231598973686
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 125 200422 200422 4194304 256 0 0 12 24 46336 0x7f2958223780 0x7f294c0249c0 161120 161120 14500 1288968 65536 91373618 1189571 0 367223492 17231599022744 17231598972197 17231599271877 17231599273407
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 200422 200422 4194304 256 0 0 12 24 47552 0x7f2958223600 0x7f294c024a00 305987 305987 23560 2447904 65536 220391244 2339617 0 883293508 17231599316616 17231599271877 17231599652677 17231599654177
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 131 200422 200422 4194304 256 0 0 12 24 48512 0x7f295a882480 0x7f294c024a40 301093 301093 20606 2408752 65536 210894164 2306493 0 845307420 17231599695966 17231599652677 17231600030597 17231600032097
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 134 200422 200422 4194304 256 0 0 8 24 49472 0x7f295a882300 0x7f294c024a80 161205 161205 14431 1289648 65536 90390244 1189161 0 363292440 17231600073316 17231600030597 17231600319877 17231600321489
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 137 200422 200422 4194304 256 0 0 12 24 50688 0x7f295a882180 0x7f294c024ac0 162294 162294 15781 1298360 65536 97445347 1193747 0 391518464 17231600362838 17231600319877 17231600610757 17231600612181
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 140 200422 200422 4194304 256 0 0 12 24 51648 0x7f295a882000 0x7f294c024b00 161088 161088 14473 1288712 65536 94475788 1190067 0 379633068 17231600661650 17231600610757 17231600904197 17231600905593
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 200422 200422 4194304 256 0 0 12 24 52864 0x7f2958223e80 0x7f294c024b40 304126 304126 22967 2433016 65536 226482642 2329813 0 907658944 17231600948132 17231600904197 17231601283877 17231601285243
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 146 200422 200422 4194304 256 0 0 12 24 54080 0x7f2958223d00 0x7f294c024b80 304104 304104 22147 2432840 65536 218872393 2331005 0 877218824 17231601325622 17231601283877 17231601665157 17231601666713
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 149 200422 200422 4194304 256 0 0 8 24 55296 0x7f2958223b80 0x7f294c024bc0 162364 162364 14608 1298920 65536 95645801 1199488 0 384310828 17231601707732 17231601665157 17231601955718 17231601957175
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 152 200422 200422 4194304 256 0 0 12 24 56768 0x7f2958223a00 0x7f294c024c00 163018 163018 16069 1304152 65536 100216849 1199878 0 402602280 17231601998094 17231601955718 17231602257478 17231602258967
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 155 200422 200422 4194304 256 0 0 12 24 57728 0x7f2958223880 0x7f294c024c40 163398 163398 14437 1307192 65536 92974555 1200034 0 373624384 17231602307476 17231602257478 17231602556838 17231602558659
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 200422 200422 4194304 256 0 0 12 24 58944 0x7f2958223700 0x7f294c024c80 301484 301484 22946 2411880 65536 218241043 2310822 0 874697144 17231602599168 17231602556838 17231602933958 17231602935359
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 161 200422 200422 4194304 256 0 0 12 24 60160 0x7f295a882580 0x7f294c024cc0 302080 302080 21992 2416648 65536 208457380 2310551 0 835556576 17231602977017 17231602933958 17231603312198 17231603313688
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 164 200422 200422 4194304 256 0 0 8 24 61376 0x7f295a882400 0x7f294c024d00 162616 162616 14151 1300936 65536 97078684 1203996 0 390037504 17231603355847 17231603312198 17231603601958 17231603603221
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 167 200422 200422 4194304 256 0 0 12 24 62848 0x7f295a882280 0x7f294c024d40 168245 168245 16265 1345968 65536 106217653 1246019 0 426604060 17231603644549 17231603601958 17231603900038 17231603901552
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 170 200422 200422 4194304 256 0 0 12 24 63808 0x7f295a882100 0x7f294c024d80 162123 162123 14654 1296992 65536 101757316 1196478 0 408750416 17231603949961 17231603900038 17231604188198 17231604189745
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 200422 200422 4194304 256 0 0 12 24 65024 0x7f2958223f80 0x7f294c024dc0 301055 301055 22656 2408448 65536 218438797 2306041 0 875488532 17231604234873 17231604188198 17231604581638 17231604583104
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 176 200422 200422 4194304 256 0 0 12 24 66240 0x7f2958223e00 0x7f294c024e00 298868 298868 20801 2390952 65536 208158295 2286319 0 834367380 17231604624193 17231604581638 17231604964838 17231604966294
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 179 200422 200422 4194304 256 0 0 8 24 67456 0x7f2958223c80 0x7f294c024e40 164029 164029 14480 1312240 65536 92710114 1207982 0 372567164 17231605005893 17231604964838 17231605256678 17231605258176
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 182 200422 200422 4194304 256 0 0 12 24 68928 0x7f2958223b00 0x7f294c024e80 176594 176594 16215 1412760 65536 108118199 1308234 0 434208944 17231605298755 17231605256678 17231605556839 17231605558298
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 185 200422 200422 4194304 256 0 0 12 24 70144 0x7f2958223980 0x7f294c024ec0 160574 160574 14856 1284600 65536 90026451 1183697 0 361837972 17231605606966 17231605556839 17231605857159 17231605858560
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 200422 200422 4194304 256 0 0 12 24 71616 0x7f2958223800 0x7f294c024f00 303013 303013 23334 2424112 65536 221957468 2322322 0 889561760 17231605900158 17231605857159 17231606234919 17231606236539
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 191 200422 200422 4194304 256 0 0 12 24 72832 0x7f2958223680 0x7f294c024f40 300754 300754 21679 2406040 65536 219022988 2305582 0 877821012 17231606278738 17231606234919 17231606617319 17231606618759
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 194 200422 200422 4194304 256 0 0 8 24 74048 0x7f295a882500 0x7f294c024f80 160819 160819 14584 1286560 65536 89771526 1187721 0 360821756 17231606659708 17231606617319 17231606906919 17231606908431
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 197 200422 200422 4194304 256 0 0 12 24 75776 0x7f295a882380 0x7f294c024fc0 181071 181071 16859 1448576 65536 112869436 1345061 0 453220084 17231606949150 17231606906919 17231607210919 17231607212403
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 200 200422 200422 4194304 256 0 0 12 24 76992 0x7f295a882200 0x7f294c025000 160683 160683 14647 1285472 65536 100795857 1187139 0 404909652 17231607272191 17231607210919 17231607502919 17231607504525
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 200422 200422 4194304 256 0 0 12 24 78464 0x7f295a882080 0x7f294c025040 301757 301757 23351 2414064 65536 217891782 2311532 0 873298764 17231607552224 17231607502919 17231607887079 17231607888715
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 206 200422 200422 4194304 256 0 0 12 24 79936 0x7f2958223f00 0x7f294c025080 300565 300565 22021 2404528 65536 213486591 2298636 0 855675624 17231607929804 17231607887079 17231608270919 17231608272454
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 209 200422 200422 4194304 256 0 0 8 24 81408 0x7f2958223d80 0x7f294c0250c0 162815 162815 15202 1302528 65536 94875261 1202603 0 381225248 17231608313853 17231608270919 17231608564039 17231608565586
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 212 200422 200422 4194304 256 0 0 12 24 83136 0x7f2958223c00 0x7f294c025100 190365 190365 17465 1522928 65536 127640821 1424804 0 512306844 17231608606595 17231608564039 17231608876359 17231608877858
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 215 200422 200422 4194304 256 0 0 12 24 84352 0x7f2958223a80 0x7f294c025140 161176 161176 14444 1289416 65536 93567046 1190218 0 375998292 17231608926297 17231608876359 17231609172520 17231609173970
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 200422 200422 4194304 256 0 0 12 24 85824 0x7f2958223900 0x7f294c025180 303654 303654 24097 2429240 65536 222235612 2325778 0 890679232 17231609218419 17231609172520 17231609564040 17231609565659
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 221 200422 200422 4194304 256 0 0 12 24 87296 0x7f2958223780 0x7f294c0251c0 299116 299116 22401 2392936 65536 211163536 2293811 0 846382728 17231609607558 17231609564040 17231609941640 17231609943099
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 224 200422 200422 4194304 256 0 0 12 24 88768 0x7f2958223600 0x7f294c025200 163309 163309 15891 1306480 65536 96334904 1199470 0 387066280 17231609983598 17231609941640 17231610244520 17231610246011
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 227 200422 200422 4194304 256 0 0 12 24 90752 0x7f295a882480 0x7f294c025240 200492 200492 18059 1603944 65536 129800226 1500390 0 520943684 17231610287420 17231610244520 17231610569640 17231610571252
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 230 200422 200422 4194304 256 0 0 12 24 91968 0x7f295a882300 0x7f294c025280 162244 162244 15514 1297960 65536 93538361 1192686 0 375877232 17231610619871 17231610569640 17231610868520 17231610869844
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 200422 200422 4194304 256 0 0 12 24 93440 0x7f295a882180 0x7f294c0252c0 301762 301762 23044 2414104 65536 216926542 2303429 0 869438460 17231610915023 17231610868520 17231611253960 17231611255464
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 236 200422 200422 4194304 256 0 0 12 24 94912 0x7f295a882000 0x7f294c025300 299453 299453 20078 2395632 65536 203593527 2292485 0 816108980 17231611297982 17231611253960 17231611630760 17231611632223
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 239 200422 200422 4194304 256 0 0 12 24 96384 0x7f2958223e80 0x7f294c025340 161891 161891 15198 1295136 65536 97968461 1196395 0 393604328 17231611673732 17231611630760 17231611927880 17231611929345
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 242 200422 200422 4194304 256 0 0 12 24 98368 0x7f2958223d00 0x7f294c025380 211095 211095 18817 1688768 65536 124430395 1573317 0 499467664 17231611969644 17231611927880 17231612256680 17231612258076
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 245 200422 200422 4194304 256 0 0 12 24 99584 0x7f2958223b80 0x7f294c0253c0 161023 161023 14706 1288192 65536 89859098 1190262 0 361171344 17231612306345 17231612256680 17231612553640 17231612555048
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 200422 200422 4194304 256 0 0 12 24 101312 0x7f2958223a00 0x7f294c025400 299799 299799 23068 2398400 65536 217978625 2298970 0 873648940 17231612595717 17231612553640 17231612935881 17231612937458
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 251 200422 200422 4194304 256 0 0 12 24 102784 0x7f2958223880 0x7f294c025440 297931 297931 20593 2383456 65536 208733186 2276747 0 836665732 17231612977937 17231612935881 17231613312521 17231613314078
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 254 200422 200422 4194304 256 0 0 12 24 104256 0x7f2958223700 0x7f294c025480 162085 162085 16597 1296688 65536 99237539 1186965 0 398681308 17231613354017 17231613312521 17231613605641 17231613607050
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 257 200422 200422 4194304 256 0 0 12 24 106240 0x7f295a882580 0x7f294c0254c0 219424 219424 19592 1755400 65536 138081562 1643017 0 554077112 17231613648159 17231613605641 17231613947081 17231613948560
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 260 200422 200422 4194304 256 0 0 12 24 107712 0x7f295a882400 0x7f294c025500 160993 160993 14458 1287952 65536 90929804 1188426 0 365460640 17231613996809 17231613947081 17231614247241 17231614248812
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 200422 200422 4194304 256 0 0 16 24 109440 0x7f295a882280 0x7f294c025540 297705 297705 21606 2381648 65536 208310328 2276299 0 834973552 17231614294091 17231614247241 17231614627721 17231614629302
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 266 200422 200422 4194304 256 0 0 16 24 111168 0x7f295a882100 0x7f294c025580 298417 298417 20312 2387344 65536 207052009 2283088 0 829938276 17231614670921 17231614627721 17231615005321 17231615006822
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 269 200422 200422 4194304 256 0 0 8 24 112896 0x7f2958223f80 0x7f294c0255c0 162670 162670 15369 1301368 65536 102240218 1200080 0 410699996 17231615048431 17231615005321 17231615302601 17231615304094
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 272 200422 200422 4194304 256 0 0 12 24 115136 0x7f2958223e00 0x7f294c025600 229540 229540 19857 1836328 65536 147306050 1721496 0 590967192 17231615344683 17231615302601 17231615638601 17231615639985
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 275 200422 200422 4194304 256 0 0 12 24 116608 0x7f2958223c80 0x7f294c025640 162102 162102 15943 1296824 65536 95372929 1190358 0 383224800 17231615687453 17231615638601 17231615931401 17231615932817
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 200422 200422 4194304 256 0 0 16 24 118336 0x7f2958223b00 0x7f294c025680 299345 299345 22472 2394768 65536 211891866 2292097 0 849299196 17231615978446 17231615931401 17231616315082 17231616316836
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 281 200422 200422 4194304 256 0 0 16 24 120064 0x7f2958223980 0x7f294c0256c0 298015 298015 20239 2384128 65536 206770921 2273589 0 828815864 17231616357715 17231616315082 17231616692362 17231616693966
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 284 200422 200422 4194304 256 0 0 12 24 121792 0x7f2958223800 0x7f294c025700 163980 163980 16065 1311848 65536 102137658 1207572 0 410281616 17231616735305 17231616692362 17231616989642 17231616991188
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 287 200422 200422 4194304 256 0 0 12 24 124032 0x7f2958223680 0x7f294c025740 239995 239995 19904 1919968 65536 148735996 1809358 0 596691264 17231617031657 17231616989642 17231617335562 17231617337189
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 290 200422 200422 4194304 256 0 0 12 24 125504 0x7f295a882500 0x7f294c025780 162264 162264 15604 1298120 65536 101478602 1191938 0 407641108 17231617385988 17231617335562 17231617635082 17231617636491
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 200422 200422 4194304 256 0 0 12 24 127488 0x7f295a882380 0x7f294c0257c0 296689 296689 20183 2373520 65536 207851829 2269995 0 833140292 17231617681250 17231617635082 17231618023242 17231618024760
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 296 200422 200422 4194304 256 0 0 12 24 129216 0x7f295a882200 0x7f294c025800 297534 297534 20071 2380280 65536 210291710 2275068 0 842898884 17231618067049 17231618023242 17231618409962 17231618411480
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 299 200422 200422 4194304 256 0 0 12 24 130944 0x7f295a882080 0x7f294c025840 169609 169609 15948 1356880 65536 103993311 1254775 0 417721568 17231618454409 17231618409962 17231618708042 17231618709582
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 302 200422 200422 4194304 256 0 0 12 24 133440 0x7f2958223f00 0x7f294c025880 258710 258710 21329 2069688 65536 181336855 1955134 0 727094360 17231618753921 17231618708042 17231619065802 17231619067322
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 305 200422 200422 4194304 256 0 0 12 24 134912 0x7f2958223d80 0x7f294c0258c0 161949 161949 17038 1295600 65536 99162329 1183969 0 398379272 17231619117481 17231619065802 17231619360362 17231619362094
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 200422 200422 4194304 256 0 0 12 24 136896 0x7f2958223c00 0x7f294c025900 296914 296914 20762 2375320 65536 207273288 2273821 0 830834512 17231619403113 17231619360362 17231619743402 17231619744954
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 311 200422 200422 4194304 256 0 0 12 24 138880 0x7f2958223a80 0x7f294c025940 297449 297449 20956 2379600 65536 214007620 2271210 0 857762528 17231619786493 17231619743402 17231620122923 17231620124414
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 314 200422 200422 4194304 256 0 0 12 24 140864 0x7f2958223900 0x7f294c025980 177732 177732 16586 1421864 65536 111952432 1320538 0 449550432 17231620164802 17231620122923 17231620426123 17231620427605
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 317 200422 200422 4194304 256 0 0 12 24 143616 0x7f2958223780 0x7f294c0259c0 279200 279200 22168 2233608 65536 200179956 2126518 0 802461908 17231620468884 17231620426123 17231620793323 17231620794805
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 320 200422 200422 4194304 256 0 0 12 24 145344 0x7f2958223600 0x7f294c025a00 162170 162170 15687 1297368 65536 99669919 1194945 0 400414004 17231620843374 17231620793323 17231621091403 17231621092897
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 200422 200422 4194304 256 0 0 12 24 147584 0x7f295a882480 0x7f294c025a40 293819 293819 20319 2350560 65536 205299412 2251239 0 822932500 17231621137226 17231621091403 17231621473963 17231621475397
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 326 200422 200422 4194304 256 0 0 12 24 149568 0x7f295a882300 0x7f294c025a80 295370 295370 20525 2362968 65536 209878742 2257967 0 841250948 17231621518336 17231621473963 17231621854443 17231621855877
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 329 200422 200422 4194304 256 0 0 12 24 151552 0x7f295a882180 0x7f294c025ac0 186634 186634 17661 1493080 65536 109340791 1382012 0 439111956 17231621896716 17231621854443 17231622167883 17231622169448
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 332 200422 200422 4194304 256 0 0 12 24 154304 0x7f295a882000 0x7f294c025b00 299341 299341 22984 2394736 65536 200769001 2287059 0 804830740 17231622210747 17231622167883 17231622550923 17231622552358
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 335 200422 200422 4194304 256 0 0 12 24 156288 0x7f2958223e80 0x7f294c025b40 171560 171560 16562 1372488 65536 103736801 1268941 0 416699940 17231622600427 17231622550923 17231622851243 17231622852750
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 200422 200422 4194304 256 0 0 12 24 158784 0x7f2958223d00 0x7f294c025b80 296654 296654 19621 2373240 65536 185843027 2263227 0 745118084 17231622893479 17231622851243 17231623231243 17231623232619
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 341 200422 200422 4194304 256 0 0 12 24 161024 0x7f2958223b80 0x7f294c025bc0 296141 296141 20019 2369136 65536 200900158 2261354 0 805356028 17231623273688 17231623231243 17231623611404 17231623612949
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 344 200422 200422 4194304 256 0 0 12 24 163264 0x7f2958223a00 0x7f294c025c00 205397 205397 18078 1643184 65536 128144857 1530767 0 514324964 17231623652688 17231623611404 17231623932044 17231623933490
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 347 200422 200422 4194304 256 0 0 12 24 166528 0x7f2958223880 0x7f294c025c40 339666 339666 25004 2717336 65536 240492471 2608449 0 963724140 17231623973549 17231623932044 17231624337324 17231624380198
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 350 200422 200422 4194304 256 0 0 12 24 168512 0x7f2958223700 0x7f294c025c80 183456 183456 16786 1467656 65536 104208680 1361092 0 418582216 17231624398528 17231624337324 17231624672684 17231624674130
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 200422 200422 4194304 256 0 0 12 24 171264 0x7f295a882580 0x7f294c025cc0 295239 295239 18697 2361920 65536 164466383 2237031 0 659627484 17231624715079 17231624672684 17231625054444 17231625055970
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 356 200422 200422 4194304 256 0 0 12 24 173760 0x7f295a882400 0x7f294c025d00 295772 295772 20762 2366184 65536 196869949 2258497 0 789226500 17231625097169 17231625054444 17231625435404 17231625436859
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 359 200422 200422 4194304 256 0 0 12 24 176256 0x7f295a882280 0x7f294c025d40 225282 225282 19480 1802264 65536 145542428 1695158 0 583922244 17231625477358 17231625435404 17231625770124 17231625771560
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 362 200422 200422 4194304 256 0 0 12 24 179776 0x7f295a882100 0x7f294c025d80 379656 379656 26922 3037256 65536 280209836 2929653 0 1122589780 17231625812829 17231625770124 17231626199884 17231626223518
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 365 200422 200422 4194304 256 0 0 12 24 182272 0x7f2958223f80 0x7f294c025dc0 210469 210469 18571 1683760 65536 133685792 1577480 0 536494544 17231626250577 17231626199884 17231626538924 17231626540340
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 200422 200422 4194304 256 0 0 12 24 185536 0x7f2958223e00 0x7f294c025e00 303172 303172 22112 2425384 65536 191823665 2305203 0 769052816 17231626580688 17231626538924 17231626933164 17231626935539
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 371 200422 200422 4194304 256 0 0 12 24 188544 0x7f2958223c80 0x7f294c025e40 307442 307442 22485 2459544 65536 176953968 2332701 0 709577508 17231626974578 17231626933164 17231627331405 17231627333718
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 374 200422 200422 4194304 256 0 0 12 24 191552 0x7f2958223b00 0x7f294c025e80 266294 266294 21926 2130360 65536 180065375 2018223 0 722023816 17231627372797 17231627331405 17231627692845 17231627694478
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 377 200422 200422 4194304 256 0 0 12 24 195840 0x7f2958223980 0x7f294c025ec0 460636 460636 31321 3685096 65536 346846106 3577428 0 1389144048 17231627734717 17231627692845 17231628177805 17231628195495
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 380 200422 200422 4194304 256 0 0 12 24 198592 0x7f2958223800 0x7f294c025f00 244610 244610 20263 1956888 65536 151009413 1844672 0 605798556 17231628227354 17231628177805 17231628526125 17231628527686
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 200422 200422 4194304 256 0 0 12 24 202368 0x7f2958223680 0x7f294c025f40 334198 334198 22628 2673592 65536 213497531 2558930 0 855765908 17231628568385 17231628526125 17231628932845 17231628947655
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 386 200422 200422 4194304 256 0 0 12 24 205888 0x7f295a882500 0x7f294c025f80 330180 330180 22761 2641448 65536 210071669 2521111 0 842056988 17231628975584 17231628932845 17231629346765 17231629361293
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 389 200422 200422 4194304 256 0 0 12 24 209408 0x7f295a882380 0x7f294c025fc0 305389 305389 23176 2443120 65536 218513807 2340306 0 875811112 17231629387873 17231629346765 17231629737965 17231629739543
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 392 200422 200422 4194304 256 0 0 12 24 214464 0x7f295a882200 0x7f294c026000 541966 541966 35270 4335736 65536 412537177 4224256 0 1651912024 17231629779832 17231629737965 17231630273325 17231630287808
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 395 200422 200422 4194304 256 0 0 12 24 217728 0x7f295a882080 0x7f294c026040 273069 273069 21327 2184560 65536 171320182 2075622 0 687039236 17231630323797 17231630273325 17231630643565 17231630645059
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 200422 200422 4194304 256 0 0 12 24 222016 0x7f2958223f00 0x7f294c026080 363323 363323 28653 2906592 65536 247955699 2796665 0 993603528 17231630686228 17231630643565 17231631071566 17231631113446
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 401 200422 200422 4194304 256 0 0 12 24 226048 0x7f2958223d80 0x7f294c0260c0 365450 365450 27686 2923608 65536 256753072 2817239 0 1028783604 17231631122856 17231631071566 17231631521646 17231631563344
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 404 200422 200422 4194304 256 0 0 12 24 230080 0x7f2958223c00 0x7f294c026100 347119 347119 25241 2776960 65536 248017257 2666784 0 993835092 17231631573494 17231631521646 17231631953006 17231631994052
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 407 200422 200422 4194304 256 0 0 12 24 235904 0x7f2958223a80 0x7f294c026140 624722 624722 40660 4997784 65536 473810578 4875511 0 1897002308 17231632004202 17231631953006 17231632559246 17231632600426
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 410 200422 200422 4194304 256 0 0 12 24 239424 0x7f2958223900 0x7f294c026180 302147 302147 22621 2417184 65536 211567813 2315765 0 848034748 17231632618725 17231632559246 17231632971726 17231632973296
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 200422 200422 4194304 256 0 0 12 24 244224 0x7f2958223780 0x7f294c0261c0 397576 397576 27872 3180616 65536 273852920 3068198 0 1097194364 17231633014045 17231632971726 17231633419246 17231633460683
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 416 200422 200422 4194304 256 0 0 12 24 248768 0x7f2958223600 0x7f294c026200 389877 389877 27191 3119024 65536 294496227 3021203 0 1179756088 17231633470072 17231633419246 17231633884686 17231633902211
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 419 200422 200422 4194304 256 0 0 12 24 253312 0x7f295a882480 0x7f294c026240 387204 387204 27520 3097640 65536 290449581 2990639 0 1163591664 17231633926980 17231633884686 17231634322926 17231634369898
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 422 200422 200422 4194304 256 0 0 8 24 255552 0x7f295a882300 0x7f294c026280 716980 716980 43862 5735848 65536 550929702 5630413 0 2205458468 17231634380888 17231634322926 17231635004047 17231635047210
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 425 200422 200422 4194304 256 0 0 12 24 259840 0x7f295a882180 0x7f294c0262c0 364380 364380 26166 2915048 65536 257305393 2804173 0 1030985812 17231635066309 17231635004047 17231635448687 17231635491298
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 200422 200422 4194304 256 0 0 12 24 265664 0x7f295a882000 0x7f294c026300 469213 469213 31164 3753712 65536 353538872 3646434 0 1415942712 17231635501767 17231635448687 17231635971727 17231636012804
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 431 200422 200422 4194304 256 0 0 12 24 271232 0x7f2958223e80 0x7f294c026340 472782 472782 32208 3782264 65536 350692765 3674988 0 1404554008 17231636023083 17231635971727 17231636494287 17231636535000
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 434 200422 200422 4194304 256 0 0 8 24 273216 0x7f2958223d00 0x7f294c026380 483410 483410 33165 3867288 65536 356741343 3755658 0 1428705704 17231636545169 17231636494287 17231637010127 17231637050746
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 437 200422 200422 4194304 256 0 0 8 24 275712 0x7f2958223b80 0x7f294c0263c0 879208 879208 52783 7033672 65536 683750772 6923919 0 2736744260 17231637061125 17231637010127 17231637786927 17231637828775
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 440 200422 200422 4194304 256 0 0 12 24 280768 0x7f2958223a00 0x7f294c026400 425745 425745 29144 3405968 65536 319495457 3301280 0 1279750752 17231637847614 17231637786927 17231638272848 17231638317091
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 200422 200422 4194304 256 0 0 12 24 287616 0x7f2958223880 0x7f294c026440 548289 548289 35218 4386320 65536 414758485 4286026 0 1660820752 17231638328781 17231638272848 17231638847888 17231638891636
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 446 200422 200422 4194304 256 0 0 12 24 294208 0x7f2958223700 0x7f294c026480 550983 550983 35718 4407872 65536 406158858 4298525 0 1626419400 17231638901696 17231638847888 17231639418448 17231639459870
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 449 200422 200422 4194304 256 0 0 8 24 296960 0x7f295a882580 0x7f294c0264c0 562022 562022 36282 4496184 65536 424763207 4387586 0 1700795720 17231639469750 17231639418448 17231639984528 17231640025425
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 452 200422 200422 4194304 256 0 0 8 24 299968 0x7f295a882400 0x7f294c026500 1042215 1042215 61270 8337728 65536 817003442 8220806 0 3269755936 17231640035765 17231639984528 17231640867408 17231640911091
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 455 200422 200422 4194304 256 0 0 8 24 302720 0x7f295a882280 0x7f294c026540 722641 722641 44551 5781136 65536 545394791 5656491 0 2183322012 17231640929850 17231640867408 17231641536528 17231641577063
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 200422 200422 4194304 256 0 0 12 24 305472 0x7f295a882100 0x7f294c026580 723095 723095 44448 5784768 65536 552455064 5673853 0 2211561192 17231641587173 17231641536528 17231642221969 17231642266534
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 461 200422 200422 4194304 256 0 0 12 24 308224 0x7f2958223f80 0x7f294c0265c0 721259 721259 43987 5770080 65536 548760037 5661350 0 2196780064 17231642277424 17231642221816 17231642907256 17231642958655
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 464 200422 200422 4194304 256 0 0 8 24 310976 0x7f2958223e00 0x7f294c026600 726630 726630 44644 5813048 65536 555561140 5697271 0 2223985996 17231642969215 17231642907256 17231643588214 17231643631587
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 467 200422 200422 4194304 256 0 0 8 24 313216 0x7f2958223c80 0x7f294c026640 1367304 1367304 77501 10938440 65536 1067749919 10822414 0 4272741176 17231643642027 17231643588214 17231644680054 17231644723038
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 470 200422 200422 4194304 256 0 0 8 24 315968 0x7f2958223b00 0x7f294c026680 1371228 1371228 77375 10969832 65536 1082524152 10849956 0 4331838720 17231644744147 17231644680054 17231645780534 17231645844557
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 200422 200422 4194304 256 0 0 12 24 318720 0x7f2958223980 0x7f294c0266c0 1372315 1372315 77166 10978528 65536 1074250970 10862144 0 4298744480 17231645855407 17231645780534 17231646920534 17231646986267
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 476 200422 200422 4194304 256 0 0 12 24 321472 0x7f2958223800 0x7f294c026700 1371465 1371465 77029 10971728 65536 1079868798 10849505 0 4321216184 17231646996746 17231646920534 17231648061174 17231648127126
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 479 200422 200422 4194304 256 0 0 8 24 324224 0x7f2958223680 0x7f294c026740 1377412 1377412 77862 11019304 65536 1067129407 10891598 0 4270259980 17231648136856 17231648061174 17231649191414 17231649257825
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 482 200422 200422 4194304 256 0 0 8 24 326464 0x7f295a882500 0x7f294c026780 2664265 2664265 142063 21314128 65536 2119458099 21183122 0 8479574076 17231649267665 17231649191414 17231651150614 17231651226242
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 485 200422 200422 4194304 256 0 0 8 24 329216 0x7f295a882380 0x7f294c0267c0 2669748 2669748 143521 21357992 65536 2133181962 21231914 0 8534468992 17231651245222 17231651150614 17231653089654 17231653156420
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 200422 200422 4194304 256 0 0 12 24 331968 0x7f295a882200 0x7f294c026800 2671224 2671224 142967 21369800 65536 2131474553 21239023 0 8527638892 17231653167080 17231653089654 17231655078614 17231655150156
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 491 200422 200422 4194304 256 0 0 12 24 334720 0x7f295a882080 0x7f294c026840 2668850 2668850 142948 21350808 65536 2125485042 21234779 0 8503680176 17231655160816 17231655078614 17231657070614 17231657135542
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 494 200422 200422 4194304 256 0 0 8 24 337472 0x7f2958223f00 0x7f294c026880 2674558 2674558 142583 21396472 65536 2127696938 21262653 0 8512530040 17231657146272 17231657070614 17231659003254 17231659074779
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 497 200422 200422 4194304 256 0 0 8 24 0 0x7f2958223d80 0x7f294c0268c0 5256982 5256982 274055 42055864 65536 4232667833 41931017 0 16932412712 17231659085669 17231659003254 17231662631094 17231662703371
@@ -1,5 +0,0 @@
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -1,5 +0,0 @@
pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -1,5 +0,0 @@
pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -1,5 +0,0 @@
pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -1,5 +0,0 @@
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:
@@ -1,21 +0,0 @@
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:
@@ -1,168 +0,0 @@
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
@@ -1,11 +0,0 @@
Kernel_Name,Count,Sum(ns),Mean(ns),Median(ns),Pct
"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",1,3358076.0,3358076.0,3358076.0,7.841553576961169
"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",1,1725119.0,1725119.0,1725119.0,4.028382045294292
"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",1,1715679.0,1715679.0,1715679.0,4.006338391199949
"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",1,1699359.0,1699359.0,1699359.0,3.968229023104645
"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",1,1673598.0,1673598.0,1673598.0,3.9080736657821498
"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",1,1664639.0,1664639.0,1664639.0,3.887153210588165
"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",1,885599.0,885599.0,885599.0,2.0679913159211507
"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",1,879999.0,879999.0,879999.0,2.0549145719668798
"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",1,868639.0,868639.0,868639.0,2.0283874628025016
"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",1,859200.0,859200.0,859200.0,2.006346143841008
1 Kernel_Name Count Sum(ns) Mean(ns) Median(ns) Pct
2 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 1 3358076.0 3358076.0 3358076.0 7.841553576961169
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 1725119.0 1725119.0 1725119.0 4.028382045294292
4 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 1 1715679.0 1715679.0 1715679.0 4.006338391199949
5 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 1 1699359.0 1699359.0 1699359.0 3.968229023104645
6 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 1 1673598.0 1673598.0 1673598.0 3.9080736657821498
7 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 1 1664639.0 1664639.0 1664639.0 3.887153210588165
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 885599.0 885599.0 885599.0 2.0679913159211507
9 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 1 879999.0 879999.0 879999.0 2.0549145719668798
10 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 1 868639.0 868639.0 868639.0 2.0283874628025016
11 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 1 859200.0 859200.0 859200.0 2.006346143841008
@@ -1,9 +0,0 @@
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
@@ -1,16 +0,0 @@
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
@@ -1,9 +0,0 @@
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
@@ -1,6 +0,0 @@
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
@@ -1,26 +0,0 @@
Info
Axes1
06fa5f860366
AMD EPYC 7282 16-Core Processor
Ubuntu 20.04.5 LTS
5.11.0-27-generic
5.1.3-66
Wed Sep 28 20:40:30 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 Axes1
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 20:40:30 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
@@ -1,7 +0,0 @@
Metric,Value
valu_flops_pop,32.87183291408655
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 32.87183291408655
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
@@ -1,8 +0,0 @@
Metric,Avg,Min,Max,Unit
IPC (Avg),0.7033596650333737,0.026053251051628624,1.1590617422886735,Instr/cycle
IPC (Issue),1.0,1.0,1.0,Instr/cycle
SALU Util,2.6255671288327265,0.029816048954225374,27.40267389198107,Pct
VALU Util,58.34159376029337,0.760309248332747,98.95101496003933,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) 0.7033596650333737 0.026053251051628624 1.1590617422886735 Instr/cycle
3 IPC (Issue) 1.0 1.0 1.0 Instr/cycle
4 SALU Util 2.6255671288327265 0.029816048954225374 27.40267389198107 Pct
5 VALU Util 58.34159376029337 0.760309248332747 98.95101496003933 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
@@ -1,7 +0,0 @@
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
@@ -1,5 +0,0 @@
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
@@ -1,12 +0,0 @@
Metric,Avg,Min,Max,Unit
Wave Cycles,18370.77323406471,1864.6040878295898,258441.6922607422,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 18370.77323406471 1864.6040878295898 258441.6922607422 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
@@ -1,3 +0,0 @@
Metric,Value
Bandwidth,27.451141851478866
Cache Hit,99.55893035457983
1 Metric Value
2 Bandwidth 27.451141851478866
3 Cache Hit 99.55893035457983
@@ -1,6 +0,0 @@
Metric,Mean,Min,Max,Unit
Req,127.76646706586827,9.0,1835.0,Req per wave
Hits,127.53083819543531,8.992919921875,1834.916763305664,Hits per wave
Misses - Non Duplicated,0.0017547607421875,0.0,0.109375,Misses per wave
Misses - Duplicated,0.2338741096907747,0.006866455078125,3.861328125,Misses per wave
Cache Hit,99.55893035457983,75.18310546875,99.99546394036317,Pct
1 Metric Mean Min Max Unit
2 Req 127.76646706586827 9.0 1835.0 Req per wave
3 Hits 127.53083819543531 8.992919921875 1834.916763305664 Hits per wave
4 Misses - Non Duplicated 0.0017547607421875 0.0 0.109375 Misses per wave
5 Misses - Duplicated 0.2338741096907747 0.006866455078125 3.861328125 Misses per wave
6 Cache Hit 99.55893035457983 75.18310546875 99.99546394036317 Pct
@@ -1,3 +0,0 @@
Metric,Value
Bandwidth,0.9353005283918872
Cache Hit,97.79806226823348
1 Metric Value
2 Bandwidth 0.9353005283918872
3 Cache Hit 97.79806226823348
@@ -1,13 +0,0 @@
Metric,Mean,Min,Max,Unit
Req,1.8023952095808384,1.0,7.0,Req per wave
Hits,1.7701588362276912,0.0,6.987253189086914,Req per wave
Misses - Non Duplicated,0.001501757227732036,0.00042724609375,0.109375,Req per wave
Misses- Duplicated,0.030734616125415185,0.012319564819335938,0.890625,Req per wave
Cache Hit,97.79806226823348,0.0,99.81790270124164,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 1.7701588362276912 0.0 6.987253189086914 Req per wave
4 Misses - Non Duplicated 0.001501757227732036 0.00042724609375 0.109375 Req per wave
5 Misses- Duplicated 0.030734616125415185 0.012319564819335938 0.890625 Req per wave
6 Cache Hit 97.79806226823348 0.0 99.81790270124164 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
@@ -1,5 +0,0 @@
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
@@ -1,17 +0,0 @@
Metric,Avg,Min,Max,Unit
TA Busy,60.283533313676124,1.0250722689780316,91.50485097534684,Pct
TC2TA Addr Stall,39.17016420138271,0.009756550575422095,70.65047602359675,Pct
TC2TA Data Stall,0.31377083561967395,0.0,52.399729548485546,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 60.283533313676124 1.0250722689780316 91.50485097534684 Pct
3 TC2TA Addr Stall 39.17016420138271 0.009756550575422095 70.65047602359675 Pct
4 TC2TA Data Stall 0.31377083561967395 0.0 52.399729548485546 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
@@ -1,8 +0,0 @@
Metric,Avg,Min,Max,Unit
TD Busy,79.2434596384546,4.217922706551843,95.33468150914454,Pct
TC2TD Stall,63.8040992982216,3.671596020489216,93.93900295917722,Pct
SPI2TD Stall,0.007826672742596946,0.0,0.01880596741520191,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 79.2434596384546 4.217922706551843 95.33468150914454 Pct
3 TC2TD Stall 63.8040992982216 3.671596020489216 93.93900295917722 Pct
4 SPI2TD Stall 0.007826672742596946 0.0 0.01880596741520191 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
@@ -1,5 +0,0 @@
Metric,Value
Buffer Coalescing,69.91017964071857
Cache Util,83.88664040663554
Cache BW,3.7844437668807758
Cache Hit,20.35928143712575
1 Metric Value
2 Buffer Coalescing 69.91017964071857
3 Cache Util 83.88664040663554
4 Cache BW 3.7844437668807758
5 Cache Hit 20.35928143712575
@@ -1,6 +0,0 @@
Metric,Mean,Min,Max,unit
Stalled on L2 Data,66.03809763204391,4.6735976987169074,90.6149422264747,Pct
Stalled on L2 Req,2.113855322857978,0.0,10.626986282936222,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 66.03809763204391 4.6735976987169074 90.6149422264747 Pct
3 Stalled on L2 Req 2.113855322857978 0.0 10.626986282936222 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
@@ -1,15 +0,0 @@
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,0.0027949167582803146,0.0001983642578125,0.203125,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,1266.0323366861858,438.5471248626709,1931.6400604248047,Cycles
L1-L2 Read Latency,777.4817830855587,374.88433170318604,1131.0075149536133,Cycles
L1-L2 Write Latency,353.30434226989746,353.30434226989746,353.30434226989746,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 0.0027949167582803146 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 1266.0323366861858 438.5471248626709 1931.6400604248047 Cycles
14 L1-L2 Read Latency 777.4817830855587 374.88433170318604 1131.0075149536133 Cycles
15 L1-L2 Write Latency 353.30434226989746 353.30434226989746 353.30434226989746 Cycles
@@ -1,13 +0,0 @@
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
@@ -1,6 +0,0 @@
Metric,Mean,Min,Max,Units
Req,69.8443113772455,16.0,128.0, per wave
Hit Ratio,97.73338069458921,93.017578125,98.52089881896973,Pct
Hits,68.49202056702026,15.721206665039062,126.01361083984375, per wave
Misses (Translation),0.13861769259332896,0.0253448486328125,0.203125, 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 97.73338069458921 93.017578125 98.52089881896973 Pct
4 Hits 68.49202056702026 15.721206665039062 126.01361083984375 per wave
5 Misses (Translation) 0.13861769259332896 0.0253448486328125 0.203125 per wave
6 Misses (Permission) 0.0 0.0 0.0 per wave
@@ -1,5 +0,0 @@
Metric,Value,Unit
L2 Util,90.77236524088651,Pct
Cache Hit,3.8417762194455456,Pct
L2-EA Rd BW,1157.8723191926538,Gb/s
L2-EA Wr BW,6.588450813230302,Gb/s
1 Metric Value Unit
2 L2 Util 90.77236524088651 Pct
3 Cache Hit 3.8417762194455456 Pct
4 L2-EA Rd BW 1157.8723191926538 Gb/s
5 L2-EA Wr BW 6.588450813230302 Gb/s
@@ -1,16 +0,0 @@
Metric,Avg,Min,Max,Unit
Read BW,2839.271734363305,0.037841796875,4096.3359375,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),0.007529024592416729,0.00115203857421875,0.23828125,Req per wave
Read (64B),44.36362084942664,0.000591278076171875,64.0052490234375,Req per wave
HBM Read,44.362105455227244,0.00026702880859375,64.00428771972656,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,538.4776558266657,254.08619921417096,3186.6193548387096,Cycles
Write Latency,411.84558250790553,411.84558250790553,411.84558250790553,Cycles
Atomic Latency,,,,Cycles
Read Stall,5.743587754352941,0.0,14.029306191308068,Pct
Write Stall,0.09697794264893661,0.0,16.195316422372414,Pct
1 Metric Avg Min Max Unit
2 Read BW 2839.271734363305 0.037841796875 4096.3359375 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) 0.007529024592416729 0.00115203857421875 0.23828125 Req per wave
6 Read (64B) 44.36362084942664 0.000591278076171875 64.0052490234375 Req per wave
7 HBM Read 44.362105455227244 0.00026702880859375 64.00428771972656 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 538.4776558266657 254.08619921417096 3186.6193548387096 Cycles
13 Write Latency 411.84558250790553 411.84558250790553 411.84558250790553 Cycles
14 Atomic Latency Cycles
15 Read Stall 5.743587754352941 0.0 14.029306191308068 Pct
16 Write Stall 0.09697794264893661 0.0 16.195316422372414 Pct
@@ -1,19 +0,0 @@
Metric,Avg,Min,Max,Unit
Req,23.461844975362993,8.001432418823242,36.32011413574219,Req per wave
Streaming Req,0.0,0.0,0.0,Req per wave
Read Req,23.43325428762836,0.001430511474609375,36.38771057128906,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,1.2542543011511158,0.00592041015625,4.315765380859375,Hits per wave
Misses,22.20759067421188,4.000589370727539,32.00495910644531,Misses per wave
Cache Hit,3.8417762194455456,0.03698235426998453,50.00158519971728,Pct
Writeback,0.024407792234135244,0.0004730224609375,3.9375057220458984, per wave
NC Req,6.395899607035928e-07,0.0,0.0001068115234375,Req per wave
UC Req,0.0036956421629397453,0.000579833984375,0.115234375,Req per wave
CC Req,0.0,0.0,0.0,Req per wave
RW Req,23.467964949008234,8.000747680664062,36.394683837890625,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),21.167202601175823,0.0,31.0008544921875, per wave
Evict (TC Req),0.0,0.0,0.0, per wave
1 Metric Avg Min Max Unit
2 Req 23.461844975362993 8.001432418823242 36.32011413574219 Req per wave
3 Streaming Req 0.0 0.0 0.0 Req per wave
4 Read Req 23.43325428762836 0.001430511474609375 36.38771057128906 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 1.2542543011511158 0.00592041015625 4.315765380859375 Hits per wave
9 Misses 22.20759067421188 4.000589370727539 32.00495910644531 Misses per wave
10 Cache Hit 3.8417762194455456 0.03698235426998453 50.00158519971728 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 0.0036956421629397453 0.000579833984375 0.115234375 Req per wave
14 CC Req 0.0 0.0 0.0 Req per wave
15 RW Req 23.467964949008234 8.000747680664062 36.394683837890625 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) 21.167202601175823 0.0 31.0008544921875 per wave
19 Evict (TC Req) 0.0 0.0 0.0 per wave
@@ -1,8 +0,0 @@
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,5.700341139011041,0.0,13.659622192382812,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,0.017474203052634963,0.0,2.918191909790039,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 5.700341139011041 0.0 13.659622192382812 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 0.017474203052634963 0.0 2.918191909790039 Req per wave
8 Write - Credit Starvation 0.0 0.0 0.0 Req per wave
@@ -1,17 +0,0 @@
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
0,3.852441749242522,0.734164940382906,0.7326679343948821,0.0014970059880239522,0.0,1.386548436330464,0.0014736152694610778,0.0,496.7666682597019,394.6491970486111,,0.0,0.0,0.13978640619152322,0.0,0.0,0.0005086453374988305,0.0
1,3.8519449697218873,0.7339705050348522,0.7324734990468282,0.0014970059880239522,0.0,1.3862424382192646,0.0014736152694610778,0.0,506.1977987458184,398.21392919146825,,0.0,0.0,0.14687150966621446,0.0,0.0,0.0005267480176366018,0.0
2,3.835472511408126,0.7335637258198446,0.7320667198318207,0.0014970059880239522,0.0,1.386241992790542,0.0014736152694610778,0.0,518.9346897983831,395.2583240327381,,0.0,0.0,0.2105740301623316,0.0,0.0,0.0005252746764771238,0.0
3,3.862377083505944,0.7338388408729416,0.7323418348849177,0.0014970059880239522,0.0,1.3862689469388858,0.0014736152694610778,0.0,808.8299663613633,406.77442956349205,,0.0,0.0,0.16030929474059694,0.0,0.0,0.0005433316716177021,0.0
4,3.8649337048827093,0.7338255922237557,0.7323285862357317,0.0014970059880239522,0.0,1.3862425524317576,0.0014736152694610778,0.0,520.0584365763441,400.46654110863096,,0.0,0.0,0.21867059947487838,0.0,0.0,0.0005128255147420004,0.0
5,4.262949398136805,0.7368027007508421,0.7353056947628182,0.0014970059880239522,0.0,1.386288854176413,0.0014736152694610778,0.0,533.3776670875,402.01195126488096,,0.0,0.0,0.2428210595410741,0.0,0.0,0.0005302200774232785,0.0
6,3.8777123993803007,0.734131316224972,0.732634310236948,0.0014970059880239522,0.0,1.3862421641092815,0.0014736152694610778,0.0,538.519683334009,397.8499503968254,,0.0,0.0,0.23522556327774138,0.0,0.0,0.0005170285344837668,0.0
7,3.8672309174392585,0.7340713089811588,0.7325743029931349,0.0014970059880239522,0.0,1.386242072739287,0.0014736152694610778,0.0,559.384656760157,412.8696754092262,,0.0,0.0,0.2680802944891467,0.0,0.0,0.0005480258050792945,0.0
8,3.8765146437048204,0.7340552050196482,0.7325581990316242,0.0014970059880239522,0.0,1.386242255479276,0.0014736152694610778,0.0,505.7198768181544,397.43865482390873,,0.0,0.0,0.15542894923044537,0.0,0.0,0.0005191186231053518,0.0
9,3.8566068877121387,0.7341692347726422,0.7326722287846182,0.0014970059880239522,0.0,1.3865245887619293,0.0014736152694610778,0.0,492.05402348992106,399.84019252232144,,0.0,0.0,0.12198579525519274,0.0,0.0,0.0005402479343071669,0.0
10,3.8525423840206505,0.7339674898250375,0.7324704838370135,0.0014970059880239522,0.0,1.3862422669005252,0.0014736152694610778,0.0,482.909822945595,394.1922588045635,,0.0,0.0,0.12960705785694238,0.0,0.0,0.0005139904821704248,0.0
11,3.8318500442226933,0.7335750556991486,0.7320780497111247,0.0014970059880239522,0.0,1.3862418899992983,0.0014736152694610778,0.0,510.2971231856125,407.6408962673611,,0.0,0.0,0.13869846366836638,0.0,0.0,0.0005494420399922811,0.0
12,3.8561189819715853,0.7337997687790923,0.7323027627910682,0.0014970059880239522,0.0,1.3862421641092815,0.0014736152694610778,0.0,508.3051273734965,406.94891648065476,,0.0,0.0,0.14768589042617888,0.0,0.0,0.0005385233256631268,0.0
13,3.8593964565525654,0.7338323536033402,0.7323353476153163,0.0014970059880239522,0.0,1.386242255479276,0.0014736152694610778,0.0,531.0838790657946,406.99742683531747,,0.0,0.0,0.2009066279062968,0.0,0.0,0.0005557694121035273,0.0
14,4.262260440146878,0.7367735537226329,0.7352765477346089,0.0014970059880239522,0.0,1.386288854176413,0.0014736152694610778,0.0,507.90263893210425,400.44325861855157,,0.0,0.0,0.1754768051787051,0.0,0.0,0.0005250462514911583,0.0
15,3.88401829525895,0.734164940382906,0.7326679343948821,0.0014970059880239522,0.0,1.3862695065801016,0.0014736152694610778,0.0,532.687622115115,416.71512276785717,,0.0,0.0,0.16075253058336453,0.0,0.0,0.0005653746827633795,0.0
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 3.852441749242522 0.734164940382906 0.7326679343948821 0.0014970059880239522 0.0 1.386548436330464 0.0014736152694610778 0.0 496.7666682597019 394.6491970486111 0.0 0.0 0.13978640619152322 0.0 0.0 0.0005086453374988305 0.0
3 1 3.8519449697218873 0.7339705050348522 0.7324734990468282 0.0014970059880239522 0.0 1.3862424382192646 0.0014736152694610778 0.0 506.1977987458184 398.21392919146825 0.0 0.0 0.14687150966621446 0.0 0.0 0.0005267480176366018 0.0
4 2 3.835472511408126 0.7335637258198446 0.7320667198318207 0.0014970059880239522 0.0 1.386241992790542 0.0014736152694610778 0.0 518.9346897983831 395.2583240327381 0.0 0.0 0.2105740301623316 0.0 0.0 0.0005252746764771238 0.0
5 3 3.862377083505944 0.7338388408729416 0.7323418348849177 0.0014970059880239522 0.0 1.3862689469388858 0.0014736152694610778 0.0 808.8299663613633 406.77442956349205 0.0 0.0 0.16030929474059694 0.0 0.0 0.0005433316716177021 0.0
6 4 3.8649337048827093 0.7338255922237557 0.7323285862357317 0.0014970059880239522 0.0 1.3862425524317576 0.0014736152694610778 0.0 520.0584365763441 400.46654110863096 0.0 0.0 0.21867059947487838 0.0 0.0 0.0005128255147420004 0.0
7 5 4.262949398136805 0.7368027007508421 0.7353056947628182 0.0014970059880239522 0.0 1.386288854176413 0.0014736152694610778 0.0 533.3776670875 402.01195126488096 0.0 0.0 0.2428210595410741 0.0 0.0 0.0005302200774232785 0.0
8 6 3.8777123993803007 0.734131316224972 0.732634310236948 0.0014970059880239522 0.0 1.3862421641092815 0.0014736152694610778 0.0 538.519683334009 397.8499503968254 0.0 0.0 0.23522556327774138 0.0 0.0 0.0005170285344837668 0.0
9 7 3.8672309174392585 0.7340713089811588 0.7325743029931349 0.0014970059880239522 0.0 1.386242072739287 0.0014736152694610778 0.0 559.384656760157 412.8696754092262 0.0 0.0 0.2680802944891467 0.0 0.0 0.0005480258050792945 0.0
10 8 3.8765146437048204 0.7340552050196482 0.7325581990316242 0.0014970059880239522 0.0 1.386242255479276 0.0014736152694610778 0.0 505.7198768181544 397.43865482390873 0.0 0.0 0.15542894923044537 0.0 0.0 0.0005191186231053518 0.0
11 9 3.8566068877121387 0.7341692347726422 0.7326722287846182 0.0014970059880239522 0.0 1.3865245887619293 0.0014736152694610778 0.0 492.05402348992106 399.84019252232144 0.0 0.0 0.12198579525519274 0.0 0.0 0.0005402479343071669 0.0
12 10 3.8525423840206505 0.7339674898250375 0.7324704838370135 0.0014970059880239522 0.0 1.3862422669005252 0.0014736152694610778 0.0 482.909822945595 394.1922588045635 0.0 0.0 0.12960705785694238 0.0 0.0 0.0005139904821704248 0.0
13 11 3.8318500442226933 0.7335750556991486 0.7320780497111247 0.0014970059880239522 0.0 1.3862418899992983 0.0014736152694610778 0.0 510.2971231856125 407.6408962673611 0.0 0.0 0.13869846366836638 0.0 0.0 0.0005494420399922811 0.0
14 12 3.8561189819715853 0.7337997687790923 0.7323027627910682 0.0014970059880239522 0.0 1.3862421641092815 0.0014736152694610778 0.0 508.3051273734965 406.94891648065476 0.0 0.0 0.14768589042617888 0.0 0.0 0.0005385233256631268 0.0
15 13 3.8593964565525654 0.7338323536033402 0.7323353476153163 0.0014970059880239522 0.0 1.386242255479276 0.0014736152694610778 0.0 531.0838790657946 406.99742683531747 0.0 0.0 0.2009066279062968 0.0 0.0 0.0005557694121035273 0.0
16 14 4.262260440146878 0.7367735537226329 0.7352765477346089 0.0014970059880239522 0.0 1.386288854176413 0.0014736152694610778 0.0 507.90263893210425 400.44325861855157 0.0 0.0 0.1754768051787051 0.0 0.0 0.0005250462514911583 0.0
17 15 3.88401829525895 0.734164940382906 0.7326679343948821 0.0014970059880239522 0.0 1.3862695065801016 0.0014736152694610778 0.0 532.687622115115 416.71512276785717 0.0 0.0 0.16075253058336453 0.0 0.0 0.0005653746827633795 0.0
@@ -1,17 +0,0 @@
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
16,3.878801372698822,0.7341557120134731,0.7326587060254491,0.0014970059880239522,0.0,1.3862423468492702,0.0014736152694610778,0.0,536.3530681993926,396.50965711805554,,0.0,0.0,0.1937780323142777,0.0,0.0,0.0005166630545062219,0.0
17,3.8873569540964716,0.7342412457494678,0.7327442397614439,0.0014970059880239522,0.0,1.3862691296788747,0.0014736152694610778,0.0,529.4299946890735,396.7351578000992,,0.0,0.0,0.1735899234246351,0.0,0.0,0.000526508171401338,0.0
18,3.873634392983917,0.7349497629496866,0.7334527569616626,0.0014970059880239522,0.0,1.388517219863252,0.0014736152694610778,0.0,516.643063779441,393.791496155754,,0.0,0.0,0.1251149434529379,0.0,0.0,0.0005135336321984937,0.0
19,3.8455667854296616,0.7337817346264502,0.7322847286384263,0.0014970059880239522,0.0,1.3862572401583553,0.0014736152694610778,0.0,536.339878186267,407.14646887400795,,0.0,0.0,0.19883289451370695,0.0,0.0,0.0005505955861714072,0.0
20,3.861336852381705,0.7338237648238679,0.732326758835844,0.0014970059880239522,0.0,1.386242529589259,0.0014736152694610778,0.0,523.0522755165881,400.6077086433532,,0.0,0.0,0.20730408080323728,0.0,0.0,0.0005164803145174495,0.0
21,3.8444481743388508,0.7336296949557916,0.7321326889677676,0.0014970059880239522,0.0,1.3862426209592533,0.0014736152694610778,0.0,515.3855493332729,404.0201357886905,,0.0,0.0,0.1730606170471557,0.0,0.0,0.0005407276267776946,0.0
22,3.885150672716443,0.7341090219463416,0.7326120159583177,0.0014970059880239522,0.0,1.38624202705429,0.0014736152694610778,0.0,529.4526886556293,396.8317057291667,,0.0,0.0,0.21150326300523953,0.0,0.0,0.0005153496108369199,0.0
23,4.048186838985765,0.7346522165629679,0.7331552105749438,0.0014970059880239522,0.0,1.3862543163185348,0.0014736152694610778,0.0,557.4698211258561,412.63494388640873,,0.0,0.0,0.26494465902180014,0.0,0.0,0.0005551184008935255,0.0
24,3.87719341301055,0.734042139110451,0.732545133122427,0.0014970059880239522,0.0,1.3862428036992422,0.0014736152694610778,0.0,492.59422678066363,398.0775204613095,,0.0,0.0,0.17701830835399512,0.0,0.0,0.0005313050961066149,0.0
25,3.8739166456583103,0.7356332561926927,0.7341362502046688,0.0014970059880239522,0.0,1.3862428036992422,0.0014736152694610778,0.0,509.5064444910525,399.06075613839283,,0.0,0.0,0.12600945569797903,0.0,0.0,0.0005342974634227638,0.0
26,3.883334544348763,0.7342182090896332,0.7327212031016093,0.0014970059880239522,0.0,1.3862419813692928,0.0014736152694610778,0.0,498.90716149783583,393.4052501860119,,0.0,0.0,0.15660003844849363,0.0,0.0,0.0005239612328078218,0.0
27,3.86894251620647,0.7348508549307635,0.7333538489427395,0.0014970059880239522,0.0,1.3870011746526478,0.0014736152694610778,0.0,512.4641347100008,409.0060221354167,,0.0,0.0,0.15951766510923465,0.0,0.0,0.0005572084895151104,0.0
28,3.8476767337748585,0.733837744433009,0.732340738444985,0.0014970059880239522,0.0,1.386242072739287,0.0014736152694610778,0.0,501.0789921950466,402.994876922123,,0.0,0.0,0.16795778560067365,0.0,0.0,0.0005286096812722212,0.0
29,3.858031908257436,0.7338014705452377,0.7323044645572137,0.0014970059880239522,0.0,1.3862424382192646,0.0014736152694610778,0.0,523.7122534101895,404.3495163690476,,0.0,0.0,0.18928089256058195,0.0,0.0,0.0005423380229287518,0.0
30,3.8387502789701737,0.7335887611983065,0.7320917552102826,0.0014970059880239522,0.0,1.3862419813692928,0.0014736152694610778,0.0,506.900013858403,401.35257006448415,,0.0,0.0,0.1798972855071108,0.0,0.0,0.0005325956972773204,0.0
31,3.8887486996148826,0.7341617424331025,0.7326647364450786,0.0014970059880239522,0.0,1.3862425410105084,0.0014736152694610778,0.0,545.1201500343603,413.50323195684524,,0.0,0.0,0.19778634259800712,0.0,0.0,0.0005590130469042384,0.0
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 3.878801372698822 0.7341557120134731 0.7326587060254491 0.0014970059880239522 0.0 1.3862423468492702 0.0014736152694610778 0.0 536.3530681993926 396.50965711805554 0.0 0.0 0.1937780323142777 0.0 0.0 0.0005166630545062219 0.0
3 17 3.8873569540964716 0.7342412457494678 0.7327442397614439 0.0014970059880239522 0.0 1.3862691296788747 0.0014736152694610778 0.0 529.4299946890735 396.7351578000992 0.0 0.0 0.1735899234246351 0.0 0.0 0.000526508171401338 0.0
4 18 3.873634392983917 0.7349497629496866 0.7334527569616626 0.0014970059880239522 0.0 1.388517219863252 0.0014736152694610778 0.0 516.643063779441 393.791496155754 0.0 0.0 0.1251149434529379 0.0 0.0 0.0005135336321984937 0.0
5 19 3.8455667854296616 0.7337817346264502 0.7322847286384263 0.0014970059880239522 0.0 1.3862572401583553 0.0014736152694610778 0.0 536.339878186267 407.14646887400795 0.0 0.0 0.19883289451370695 0.0 0.0 0.0005505955861714072 0.0
6 20 3.861336852381705 0.7338237648238679 0.732326758835844 0.0014970059880239522 0.0 1.386242529589259 0.0014736152694610778 0.0 523.0522755165881 400.6077086433532 0.0 0.0 0.20730408080323728 0.0 0.0 0.0005164803145174495 0.0
7 21 3.8444481743388508 0.7336296949557916 0.7321326889677676 0.0014970059880239522 0.0 1.3862426209592533 0.0014736152694610778 0.0 515.3855493332729 404.0201357886905 0.0 0.0 0.1730606170471557 0.0 0.0 0.0005407276267776946 0.0
8 22 3.885150672716443 0.7341090219463416 0.7326120159583177 0.0014970059880239522 0.0 1.38624202705429 0.0014736152694610778 0.0 529.4526886556293 396.8317057291667 0.0 0.0 0.21150326300523953 0.0 0.0 0.0005153496108369199 0.0
9 23 4.048186838985765 0.7346522165629679 0.7331552105749438 0.0014970059880239522 0.0 1.3862543163185348 0.0014736152694610778 0.0 557.4698211258561 412.63494388640873 0.0 0.0 0.26494465902180014 0.0 0.0 0.0005551184008935255 0.0
10 24 3.87719341301055 0.734042139110451 0.732545133122427 0.0014970059880239522 0.0 1.3862428036992422 0.0014736152694610778 0.0 492.59422678066363 398.0775204613095 0.0 0.0 0.17701830835399512 0.0 0.0 0.0005313050961066149 0.0
11 25 3.8739166456583103 0.7356332561926927 0.7341362502046688 0.0014970059880239522 0.0 1.3862428036992422 0.0014736152694610778 0.0 509.5064444910525 399.06075613839283 0.0 0.0 0.12600945569797903 0.0 0.0 0.0005342974634227638 0.0
12 26 3.883334544348763 0.7342182090896332 0.7327212031016093 0.0014970059880239522 0.0 1.3862419813692928 0.0014736152694610778 0.0 498.90716149783583 393.4052501860119 0.0 0.0 0.15660003844849363 0.0 0.0 0.0005239612328078218 0.0
13 27 3.86894251620647 0.7348508549307635 0.7333538489427395 0.0014970059880239522 0.0 1.3870011746526478 0.0014736152694610778 0.0 512.4641347100008 409.0060221354167 0.0 0.0 0.15951766510923465 0.0 0.0 0.0005572084895151104 0.0
14 28 3.8476767337748585 0.733837744433009 0.732340738444985 0.0014970059880239522 0.0 1.386242072739287 0.0014736152694610778 0.0 501.0789921950466 402.994876922123 0.0 0.0 0.16795778560067365 0.0 0.0 0.0005286096812722212 0.0
15 29 3.858031908257436 0.7338014705452377 0.7323044645572137 0.0014970059880239522 0.0 1.3862424382192646 0.0014736152694610778 0.0 523.7122534101895 404.3495163690476 0.0 0.0 0.18928089256058195 0.0 0.0 0.0005423380229287518 0.0
16 30 3.8387502789701737 0.7335887611983065 0.7320917552102826 0.0014970059880239522 0.0 1.3862419813692928 0.0014736152694610778 0.0 506.900013858403 401.35257006448415 0.0 0.0 0.1798972855071108 0.0 0.0 0.0005325956972773204 0.0
17 31 3.8887486996148826 0.7341617424331025 0.7326647364450786 0.0014970059880239522 0.0 1.3862425410105084 0.0014736152694610778 0.0 545.1201500343603 413.50323195684524 0.0 0.0 0.19778634259800712 0.0 0.0 0.0005590130469042384 0.0
@@ -1,55 +0,0 @@
Metric,Value,Alias
Wave Life,18371.0,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,1266.0,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,777.0,l2_rd_lat_
L2 Wr Lat,353.0,l2_wr_lat_
Fabric Rd Lat,538.0,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,26.0,wave_occ_
1 Metric Value Alias
2 Wave Life 18371.0 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 1266.0 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 777.0 l2_rd_lat_
40 L2 Wr Lat 353.0 l2_wr_lat_
41 Fabric Rd Lat 538.0 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 26.0 wave_occ_
@@ -1,168 +0,0 @@
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
@@ -1,30 +0,0 @@
Metric,Value,Unit,Peak,PoP
VALU FLOPs,7439.027275789444,Gflop,22630.4,32.87183291408655
VALU IOPs,2298.074202847959,Giop,22630.4,10.154810356193257
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,2.6255671288327265,Pct,100,2.6255671288327265
VALU Util,58.34159376029337,Pct,100,58.34159376029337
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,99.9925706103068,Pct,100,99.9925706103068
Instr Cache BW,1672.543170726904,Gb/s,6092.8,27.45114185147886
Scalar L1D Cache Hit Rate,99.34855886083365,Pct,100,99.34855886083365
Scalar L1D Cache BW,56.9859905938609,Gb/s,6092.8,0.935300528391887
Vector L1D Cache Hit Rate,20.35928143712575,Pct,100,20.35928143712575
Vector L1D Cache BW,1690.8692036459622,Gb/s,11315.199999999999,14.94334349941638
L2 Cache Hit Rate,3.8417762194455456,Pct,100,3.8417762194455456
L2-Fabric Read BW,1157.8723191926538,Gb/s,1638.4,70.6709179194735
L2-Fabric Write BW,6.588450813230302,Gb/s,1638.4,0.40212712483095103
L2-Fabric Read Latency,538.4776558266657,Cycles,,
L2-Fabric Write Latency,411.84558250790553,Cycles,,
Wave Occupancy,2673.4087507168674,Wavefronts,3328,80.33079178836743
Instr Fetch BW,398.2116780910466,Gb/s,3046.4,13.071549307085302
Instr Fetch Latency,17.24045424912299,Cycles,,
1 Metric Value Unit Peak PoP
2 VALU FLOPs 7439.027275789444 Gflop 22630.4 32.87183291408655
3 VALU IOPs 2298.074202847959 Giop 22630.4 10.154810356193257
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 2.6255671288327265 Pct 100 2.6255671288327265
11 VALU Util 58.34159376029337 Pct 100 58.34159376029337
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 99.9925706103068 Pct 100 99.9925706103068
18 Instr Cache BW 1672.543170726904 Gb/s 6092.8 27.45114185147886
19 Scalar L1D Cache Hit Rate 99.34855886083365 Pct 100 99.34855886083365
20 Scalar L1D Cache BW 56.9859905938609 Gb/s 6092.8 0.935300528391887
21 Vector L1D Cache Hit Rate 20.35928143712575 Pct 100 20.35928143712575
22 Vector L1D Cache BW 1690.8692036459622 Gb/s 11315.199999999999 14.94334349941638
23 L2 Cache Hit Rate 3.8417762194455456 Pct 100 3.8417762194455456
24 L2-Fabric Read BW 1157.8723191926538 Gb/s 1638.4 70.6709179194735
25 L2-Fabric Write BW 6.588450813230302 Gb/s 1638.4 0.40212712483095103
26 L2-Fabric Read Latency 538.4776558266657 Cycles
27 L2-Fabric Write Latency 411.84558250790553 Cycles
28 Wave Occupancy 2673.4087507168674 Wavefronts 3328 80.33079178836743
29 Instr Fetch BW 398.2116780910466 Gb/s 3046.4 13.071549307085302
30 Instr Fetch Latency 17.24045424912299 Cycles
@@ -1,9 +0,0 @@
Metric,Avg,Min,Max,Unit
GPU Busy Cycles,416718.7604790419,33023,5256429,Cycles/kernel
CPF Busy,416718.7604790419,33023,5256429,Cycles/kernel
CPF Util,100.0,100.0,100.0,Pct
CPF Stall,0.0,0.0,0.0,Cycles/kernel
L2Cache Intf Busy,2263.1676646706587,2205,2334,Cycles/kernel
L2Cache Intf Util,0.9378580669604158,0.04277195757113096,6.76673526207481,Pct
L2Cache Intf Stall,0.0,0.0,0.0,Pct
UTCL1 Stall,4.0119760479041915,0,670,Cycles/kernel
1 Metric Avg Min Max Unit
2 GPU Busy Cycles 416718.7604790419 33023 5256429 Cycles/kernel
3 CPF Busy 416718.7604790419 33023 5256429 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 2263.1676646706587 2205 2334 Cycles/kernel
7 L2Cache Intf Util 0.9378580669604158 0.04277195757113096 6.76673526207481 Pct
8 L2Cache Intf Stall 0.0 0.0 0.0 Pct
9 UTCL1 Stall 4.0119760479041915 0 670 Cycles/kernel
@@ -1,13 +0,0 @@
Metric,Avg,Min,Max,Unit
GPU Busy Cycles,416718.7604790419,33023,5256429,Cycles
CPC Busy Cycles,416718.7604790419,33023,5256429,Cycles
CPC Util,100.0,100.0,100.0,Pct
CPC Stall Cycles,11956.508982035928,8675,44733,Cycles
CPC Stall Rate,4.4883872366162745,0.851015014185486,34.40026648093753,Pct
CPC Packet Decoding,28834.077844311378,8911,275176,Cycles
SPI Intf Busy Cycles,385383.8862275449,498,4980536,Cycles
SPI Intf Util,90.43288163133764,1.5080398510129305,97.73848535205289,Pct
L2Cache Intf Util,0.12525111899032346,0.005745562884424769,0.91947023900137,Pct
UTCL1 Stall Cycles,2615.011976047904,931,3368,Cycles
UTCL2 Intf Busy Cycles,2918.011976047904,1203,5730,Cycles
UTCL2 Intf Util,1.1854341703985185,0.05303687994711156,3.937007874015748,Pct
1 Metric Avg Min Max Unit
2 GPU Busy Cycles 416718.7604790419 33023 5256429 Cycles
3 CPC Busy Cycles 416718.7604790419 33023 5256429 Cycles
4 CPC Util 100.0 100.0 100.0 Pct
5 CPC Stall Cycles 11956.508982035928 8675 44733 Cycles
6 CPC Stall Rate 4.4883872366162745 0.851015014185486 34.40026648093753 Pct
7 CPC Packet Decoding 28834.077844311378 8911 275176 Cycles
8 SPI Intf Busy Cycles 385383.8862275449 498 4980536 Cycles
9 SPI Intf Util 90.43288163133764 1.5080398510129305 97.73848535205289 Pct
10 L2Cache Intf Util 0.12525111899032346 0.005745562884424769 0.91947023900137 Pct
11 UTCL1 Stall Cycles 2615.011976047904 931 3368 Cycles
12 UTCL2 Intf Busy Cycles 2918.011976047904 1203 5730 Cycles
13 UTCL2 Intf Util 1.1854341703985185 0.05303687994711156 3.937007874015748 Pct

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