Files
rocm-systems/tests/workloads/Axes3/mi200/timestamps.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

169 rivejä
37 KiB
CSV

Index,KernelName,gpu-id,queue-id,queue-index,pid,tid,grd,wgr,lds,scr,vgpr,sgpr,fbar,sig,obj,DispatchNs,BeginNs,EndNs,CompleteNs
0,"__amd_rocclr_fillBufferAligned.kd",0,0,0,213680,213680,33554432,256,0,0,4,32,4160,0x0,0x7f74dee04280,17434480786238,17434480811769,17434481051609,17434481140839
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,213680,213680,32768,256,0,0,12,24,13888,0x0,0x7f74dee23f80,17434485759828,17434485775291,17434485788571,17434485806437
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,213680,213680,4194304,256,0,0,12,24,14336,0x7f74e1b36380,0x7f74dee23fc0,17434485810857,17434485856091,17434485948571,17434485950813
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,213680,213680,4194304,256,0,0,16,24,15040,0x7f74e1b36200,0x7f74dee24000,17434485973813,17434485984091,17434486162331,17434486164718
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,213680,213680,4194304,256,0,0,16,24,15488,0x7f74e1b36080,0x7f74dee24040,17434486179418,17434486188091,17434486366332,17434486368473
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,213680,213680,4194304,256,0,0,12,24,15936,0x7f74df71bf00,0x7f74dee24080,17434486382572,17434486390812,17434486484732,17434486486720
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,213680,213680,4194304,256,0,0,12,24,16384,0x7f74df71bd80,0x7f74dee240c0,17434486503859,17434486511772,17434486603612,17434486605596
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,213680,213680,4194304,256,0,0,12,24,17088,0x7f74df71bc00,0x7f74dee24100,17434486632886,17434486643292,17434486736252,17434486738173
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,213680,213680,4194304,256,0,0,16,24,17792,0x7f74df71ba80,0x7f74dee24140,17434486761662,17434486771132,17434486950332,17434486952347
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,213680,213680,4194304,256,0,0,16,24,18496,0x7f74df71b900,0x7f74dee24180,17434486978747,17434486989052,17434487168732,17434487170832
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,213680,213680,4194304,256,0,0,16,24,19200,0x7f74df71b780,0x7f74dee241c0,17434487192801,17434487203292,17434487296572,17434487298588
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,213680,213680,4194304,256,0,0,16,24,19904,0x7f74df71b600,0x7f74dee24200,17434487316298,17434487325372,17434487418652,17434487420605
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,213680,213680,4194304,256,0,0,12,24,20608,0x7f74e1b36480,0x7f74dee24240,17434487440605,17434487453532,17434487547452,17434487549432
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,213680,213680,4194304,256,0,0,16,24,21312,0x7f74e1b36300,0x7f74dee24280,17434487566971,17434487577212,17434487756412,17434487758476
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,213680,213680,4194304,256,0,0,16,24,22016,0x7f74e1b36180,0x7f74dee242c0,17434487774026,17434487789532,17434487969213,17434487971251
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,213680,213680,4194304,256,0,0,16,24,22720,0x7f74e1b36000,0x7f74dee24300,17434487990560,17434487999933,17434488093373,17434488095818
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,213680,213680,4194304,256,0,0,12,24,23424,0x7f74df71be80,0x7f74dee24340,17434488115927,17434488131613,17434488225373,17434488227384
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,213680,213680,4194304,256,0,0,12,24,24128,0x7f74df71bd00,0x7f74dee24380,17434488249484,17434488259773,17434488352253,17434488354231
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,213680,213680,4194304,256,0,0,16,24,24832,0x7f74df71bb80,0x7f74dee243c0,17434488368341,17434488378173,17434488556573,17434488558486
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,213680,213680,4194304,256,0,0,16,24,25536,0x7f74df71ba00,0x7f74dee24400,17434488578455,17434488588893,17434488767933,17434488769770
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,213680,213680,4194304,256,0,0,12,24,26240,0x7f74df71b880,0x7f74dee24440,17434488787470,17434488796733,17434488890173,17434488892147
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,213680,213680,4194304,256,0,0,12,24,26944,0x7f74df71b700,0x7f74dee24480,17434488912306,17434488922013,17434489014493,17434489016464
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,213680,213680,4194304,256,0,0,12,24,27648,0x7f74e1b36580,0x7f74dee244c0,17434489038573,17434489048893,17434489141693,17434489143590
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,213680,213680,4194304,256,0,0,16,24,28608,0x7f74e1b36400,0x7f74dee24500,17434489160660,17434489188093,17434489367453,17434489369505
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,213680,213680,4194304,256,0,0,16,24,29312,0x7f74e1b36280,0x7f74dee24540,17434489384264,17434489394653,17434489575613,17434489577579
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,213680,213680,4194304,256,0,0,12,24,30016,0x7f74e1b36100,0x7f74dee24580,17434489596589,17434489606973,17434489699134,17434489701216
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,213680,213680,4194304,256,0,0,8,24,30976,0x7f74df71bf80,0x7f74dee245c0,17434489716086,17434489725054,17434489816574,17434489818533
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,213680,213680,4194304,256,0,0,12,24,31680,0x7f74df71be00,0x7f74dee24600,17434489840402,17434489851134,17434489943774,17434489945670
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,213680,213680,4194304,256,0,0,16,24,32640,0x7f74df71bc80,0x7f74dee24640,17434489961889,17434489971774,17434490152574,17434490154684
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,213680,213680,4194304,256,0,0,12,24,33600,0x7f74df71bb00,0x7f74dee24680,17434490168834,17434490178494,17434490358814,17434490360789
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,213680,213680,4194304,256,0,0,12,24,34560,0x7f74df71b980,0x7f74dee246c0,17434490377078,17434490385854,17434490479294,17434490480856
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,213680,213680,4194304,256,0,0,8,24,35520,0x7f74df71b800,0x7f74dee24700,17434490495045,17434490503934,17434490598174,17434490599603
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,213680,213680,4194304,256,0,0,12,24,36224,0x7f74df71b680,0x7f74dee24740,17434490620152,17434490630174,17434490722974,17434490724489
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,213680,213680,4194304,256,0,0,12,24,37184,0x7f74e1b36500,0x7f74dee24780,17434490738899,17434490747294,17434490928254,17434490929824
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,213680,213680,4194304,256,0,0,12,24,38144,0x7f74e1b36380,0x7f74dee247c0,17434490943464,17434490952254,17434491132894,17434491134559
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,213680,213680,4194304,256,0,0,12,24,39104,0x7f74e1b36200,0x7f74dee24800,17434491150058,17434491158654,17434491252574,17434491254146
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,213680,213680,4194304,256,0,0,8,24,40320,0x7f74e1b36080,0x7f74dee24840,17434491268435,17434491276734,17434491370655,17434491372172
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,213680,213680,4194304,256,0,0,12,24,41280,0x7f74df71bf00,0x7f74dee24880,17434491391382,17434491403775,17434491497855,17434491499399
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,213680,213680,4194304,256,0,0,12,24,42240,0x7f74df71bd80,0x7f74dee248c0,17434491513859,17434491521855,17434491701535,17434491703074
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,213680,213680,4194304,256,0,0,12,24,43200,0x7f74df71bc00,0x7f74dee24900,17434491716154,17434491724255,17434491904415,17434491905939
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,213680,213680,4194304,256,0,0,8,24,44160,0x7f74df71ba80,0x7f74dee24940,17434491921058,17434491930175,17434492024415,17434492026075
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,213680,213680,4194304,256,0,0,12,24,45376,0x7f74df71b900,0x7f74dee24980,17434492041345,17434492049535,17434492144415,17434492146052
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,213680,213680,4194304,256,0,0,12,24,46336,0x7f74df71b780,0x7f74dee249c0,17434492165542,17434492176415,17434492269055,17434492270549
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,213680,213680,4194304,256,0,0,12,24,47552,0x7f74df71b600,0x7f74dee24a00,17434492285719,17434492294655,17434492472895,17434492474444
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,213680,213680,4194304,256,0,0,12,24,48512,0x7f74e1b36480,0x7f74dee24a40,17434492488373,17434492496895,17434492676415,17434492677979
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,213680,213680,4194304,256,0,0,8,24,49472,0x7f74e1b36300,0x7f74dee24a80,17434492691308,17434492699615,17434492793375,17434492794875
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,213680,213680,4194304,256,0,0,12,24,50688,0x7f74e1b36180,0x7f74dee24ac0,17434492811905,17434492820575,17434492913695,17434492915232
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,213680,213680,4194304,256,0,0,12,24,51648,0x7f74e1b36000,0x7f74dee24b00,17434492936972,17434492947455,17434493039136,17434493040669
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,213680,213680,4194304,256,0,0,12,24,52864,0x7f74df71be80,0x7f74dee24b40,17434493056969,17434493064896,17434493245056,17434493246514
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,213680,213680,4194304,256,0,0,12,24,54080,0x7f74df71bd00,0x7f74dee24b80,17434493260693,17434493269216,17434493449856,17434493451388
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,213680,213680,4194304,256,0,0,8,24,55296,0x7f74df71bb80,0x7f74dee24bc0,17434493464648,17434493473376,17434493567776,17434493569275
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,213680,213680,4194304,256,0,0,12,24,56768,0x7f74df71ba00,0x7f74dee24c00,17434493583025,17434493591456,17434493686496,17434493688042
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,213680,213680,4194304,256,0,0,12,24,57728,0x7f74df71b880,0x7f74dee24c40,17434493708452,17434493719296,17434493812096,17434493813599
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,213680,213680,4194304,256,0,0,12,24,58944,0x7f74df71b700,0x7f74dee24c80,17434493829029,17434493837216,17434494016736,17434494018174
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,213680,213680,4194304,256,0,0,12,24,60160,0x7f74e1b36580,0x7f74dee24cc0,17434494031583,17434494040416,17434494221376,17434494223028
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,213680,213680,4194304,256,0,0,8,24,61376,0x7f74e1b36400,0x7f74dee24d00,17434494236898,17434494245056,17434494339296,17434494340805
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,213680,213680,4194304,256,0,0,12,24,62848,0x7f74e1b36280,0x7f74dee24d40,17434494355655,17434494363776,17434494463616,17434494465202
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,213680,213680,4194304,256,0,0,12,24,63808,0x7f74e1b36100,0x7f74dee24d80,17434494485461,17434494495936,17434494590496,17434494592049
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,213680,213680,4194304,256,0,0,12,24,65024,0x7f74df71bf80,0x7f74dee24dc0,17434494611378,17434494622496,17434494802817,17434494804453
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,213680,213680,4194304,256,0,0,12,24,66240,0x7f74df71be00,0x7f74dee24e00,17434494818963,17434494827297,17434495008577,17434495010168
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,213680,213680,4194304,256,0,0,8,24,67456,0x7f74df71bc80,0x7f74dee24e40,17434495024197,17434495032417,17434495126817,17434495128395
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,213680,213680,4194304,256,0,0,12,24,68928,0x7f74df71bb00,0x7f74dee24e80,17434495142244,17434495150497,17434495253537,17434495255171
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,213680,213680,4194304,256,0,0,12,24,70144,0x7f74df71b980,0x7f74dee24ec0,17434495274881,17434495285537,17434495378017,17434495379698
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,213680,213680,4194304,256,0,0,12,24,71616,0x7f74df71b800,0x7f74dee24f00,17434495394328,17434495402657,17434495582817,17434495584483
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,213680,213680,4194304,256,0,0,12,24,72832,0x7f74df71b680,0x7f74dee24f40,17434495599283,17434495608097,17434495788097,17434495789718
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,213680,213680,4194304,256,0,0,8,24,74048,0x7f74e1b36500,0x7f74dee24f80,17434495803907,17434495812257,17434495905377,17434495907055
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,213680,213680,4194304,256,0,0,12,24,75776,0x7f74e1b36380,0x7f74dee24fc0,17434495920804,17434495929217,17434496035457,17434496037111
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,213680,213680,4194304,256,0,0,12,24,76992,0x7f74e1b36200,0x7f74dee25000,17434496056981,17434496067937,17434496161857,17434496163358
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,213680,213680,4194304,256,0,0,12,24,78464,0x7f74e1b36080,0x7f74dee25040,17434496177467,17434496185857,17434496365217,17434496366763
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,213680,213680,4194304,256,0,0,12,24,79936,0x7f74df71bf00,0x7f74dee25080,17434496383352,17434496391297,17434496570978,17434496572427
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,213680,213680,4194304,256,0,0,8,24,81408,0x7f74df71bd80,0x7f74dee250c0,17434496588757,17434496596898,17434496691778,17434496693264
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,213680,213680,4194304,256,0,0,12,24,83136,0x7f74df71bc00,0x7f74dee25100,17434496707584,17434496716098,17434496831138,17434496832650
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,213680,213680,4194304,256,0,0,12,24,84352,0x7f74df71ba80,0x7f74dee25140,17434496867950,17434496877538,17434496970818,17434496972247
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,213680,213680,4194304,256,0,0,12,24,85824,0x7f74df71b900,0x7f74dee25180,17434496988326,17434496996578,17434497176898,17434497178481
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,213680,213680,4194304,256,0,0,12,24,87296,0x7f74df71b780,0x7f74dee251c0,17434497193401,17434497201378,17434497382178,17434497383666
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,213680,213680,4194304,256,0,0,12,24,88768,0x7f74df71b600,0x7f74dee25200,17434497398196,17434497406818,17434497502018,17434497503453
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,213680,213680,4194304,256,0,0,12,24,90752,0x7f74e1b36480,0x7f74dee25240,17434497516853,17434497526978,17434497648738,17434497650109
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,213680,213680,4194304,256,0,0,12,24,91968,0x7f74e1b36300,0x7f74dee25280,17434497669779,17434497680898,17434497775778,17434497777216
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,213680,213680,4194304,256,0,0,12,24,93440,0x7f74e1b36180,0x7f74dee252c0,17434497792085,17434497800418,17434497979618,17434497981171
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,213680,213680,4194304,256,0,0,12,24,94912,0x7f74e1b36000,0x7f74dee25300,17434497995130,17434498003938,17434498184099,17434498185855
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,213680,213680,4194304,256,0,0,12,24,96384,0x7f74df71be80,0x7f74dee25340,17434498202535,17434498211299,17434498306339,17434498307872
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,213680,213680,4194304,256,0,0,12,24,98368,0x7f74df71bd00,0x7f74dee25380,17434498324922,17434498349379,17434498475619,17434498477138
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,213680,213680,4194304,256,0,0,12,24,99584,0x7f74df71bb80,0x7f74dee253c0,17434498498067,17434498508579,17434498602179,17434498603704
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,213680,213680,4194304,256,0,0,12,24,101312,0x7f74df71ba00,0x7f74dee25400,17434498619984,17434498628419,17434498807619,17434498809159
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,213680,213680,4194304,256,0,0,12,24,102784,0x7f74df71b880,0x7f74dee25440,17434498824169,17434498832579,17434499014979,17434499016674
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,213680,213680,4194304,256,0,0,12,24,104256,0x7f74df71b700,0x7f74dee25480,17434499031913,17434499040419,17434499134019,17434499135571
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,213680,213680,4194304,256,0,0,12,24,106240,0x7f74e1b36580,0x7f74dee254c0,17434499148560,17434499156899,17434499287299,17434499288847
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,213680,213680,4194304,256,0,0,12,24,107712,0x7f74e1b36400,0x7f74dee25500,17434499309086,17434499319459,17434499412579,17434499414033
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,213680,213680,4194304,256,0,0,16,24,109440,0x7f74e1b36280,0x7f74dee25540,17434499429233,17434499438019,17434499616419,17434499617988
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,213680,213680,4194304,256,0,0,16,24,111168,0x7f74e1b36100,0x7f74dee25580,17434499632598,17434499640419,17434499819940,17434499821573
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,213680,213680,4194304,256,0,0,8,24,112896,0x7f74df71bf80,0x7f74dee255c0,17434499835862,17434499843780,17434499939780,17434499941380
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,213680,213680,4194304,256,0,0,12,24,115136,0x7f74df71be00,0x7f74dee25600,17434499954959,17434499963140,17434500101540,17434500103145
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,213680,213680,4194304,256,0,0,12,24,116608,0x7f74df71bc80,0x7f74dee25640,17434500123505,17434500133860,17434500228580,17434500230042
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,213680,213680,4194304,256,0,0,16,24,118336,0x7f74df71bb00,0x7f74dee25680,17434500245612,17434500254020,17434500434500,17434500435917
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,213680,213680,4194304,256,0,0,16,24,120064,0x7f74df71b980,0x7f74dee256c0,17434500449766,17434500459300,17434500638820,17434500640291
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,213680,213680,4194304,256,0,0,12,24,121792,0x7f74df71b800,0x7f74dee25700,17434500653621,17434500662500,17434500759140,17434500760548
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,213680,213680,4194304,256,0,0,12,24,124032,0x7f74df71b680,0x7f74dee25740,17434500777578,17434500786180,17434500931460,17434500932904
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,213680,213680,4194304,256,0,0,12,24,125504,0x7f74e1b36500,0x7f74dee25780,17434500952133,17434500963140,17434501058020,17434501059590
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,213680,213680,4194304,256,0,0,12,24,127488,0x7f74e1b36380,0x7f74dee257c0,17434501076010,17434501083940,17434501265540,17434501266995
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,213680,213680,4194304,256,0,0,12,24,129216,0x7f74e1b36200,0x7f74dee25800,17434501283525,17434501291460,17434501474180,17434501475660
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,213680,213680,4194304,256,0,0,12,24,130944,0x7f74e1b36080,0x7f74dee25840,17434501489629,17434501499301,17434501599301,17434501600816
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,213680,213680,4194304,256,0,0,12,24,133440,0x7f74df71bf00,0x7f74dee25880,17434501615456,17434501624101,17434501779461,17434501780872
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,213680,213680,4194304,256,0,0,12,24,134912,0x7f74df71bd80,0x7f74dee258c0,17434501802031,17434501812421,17434501908101,17434501909478
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,213680,213680,4194304,256,0,0,12,24,136896,0x7f74df71bc00,0x7f74dee25900,17434501924578,17434501933061,17434502112741,17434502114603
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,213680,213680,4194304,256,0,0,12,24,138880,0x7f74df71ba80,0x7f74dee25940,17434502130573,17434502138821,17434502319301,17434502320768
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,213680,213680,4194304,256,0,0,12,24,140864,0x7f74df71b900,0x7f74dee25980,17434502334047,17434502342181,17434502450821,17434502452454
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,213680,213680,4194304,256,0,0,12,24,143616,0x7f74df71b780,0x7f74dee259c0,17434502466674,17434502474981,17434502645861,17434502647489
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,213680,213680,4194304,256,0,0,12,24,145344,0x7f74df71b600,0x7f74dee25a00,17434502667829,17434502678181,17434502775141,17434502776746
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,213680,213680,4194304,256,0,0,12,24,147584,0x7f74e1b36480,0x7f74dee25a40,17434502791555,17434502799621,17434502981221,17434502982680
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,213680,213680,4194304,256,0,0,12,24,149568,0x7f74e1b36300,0x7f74dee25a80,17434502996270,17434503005061,17434503187942,17434503189445
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,213680,213680,4194304,256,0,0,12,24,151552,0x7f74e1b36180,0x7f74dee25ac0,17434503203135,17434503211622,17434503321702,17434503323232
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,213680,213680,4194304,256,0,0,12,24,154304,0x7f74e1b36000,0x7f74dee25b00,17434503337181,17434503345062,17434503525702,17434503527336
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,213680,213680,4194304,256,0,0,12,24,156288,0x7f74df71be80,0x7f74dee25b40,17434503548166,17434503558022,17434503659782,17434503661463
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,213680,213680,4194304,256,0,0,12,24,158784,0x7f74df71bd00,0x7f74dee25b80,17434503678412,17434503686182,17434503871302,17434503872737
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,213680,213680,4194304,256,0,0,12,24,161024,0x7f74df71bb80,0x7f74dee25bc0,17434503886627,17434503894662,17434504080902,17434504082572
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,213680,213680,4194304,256,0,0,12,24,163264,0x7f74df71ba00,0x7f74dee25c00,17434504096501,17434504105542,17434504227942,17434504229418
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,213680,213680,4194304,256,0,0,12,24,166528,0x7f74df71b880,0x7f74dee25c40,17434504243628,17434504252582,17434504459142,17434504480851
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,213680,213680,4194304,256,0,0,12,24,168512,0x7f74df71b700,0x7f74dee25c80,17434504496181,17434504506822,17434504617222,17434504618608
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,213680,213680,4194304,256,0,0,12,24,171264,0x7f74e1b36580,0x7f74dee25cc0,17434504635797,17434504643942,17434504826662,17434504828122
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,213680,213680,4194304,256,0,0,12,24,173760,0x7f74e1b36400,0x7f74dee25d00,17434504844722,17434504852582,17434505036743,17434505038237
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,213680,213680,4194304,256,0,0,12,24,176256,0x7f74e1b36280,0x7f74dee25d40,17434505052577,17434505061223,17434505195623,17434505197153
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,213680,213680,4194304,256,0,0,12,24,179776,0x7f74e1b36100,0x7f74dee25d80,17434505213502,17434505221543,17434505453703,17434505472846
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,213680,213680,4194304,256,0,0,12,24,182272,0x7f74df71bf80,0x7f74dee25dc0,17434505488035,17434505498983,17434505625543,17434505627042
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,213680,213680,4194304,256,0,0,12,24,185536,0x7f74df71be00,0x7f74dee25e00,17434505642291,17434505650823,17434505841703,17434505843146
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,213680,213680,4194304,256,0,0,12,24,188544,0x7f74df71bc80,0x7f74dee25e40,17434505857396,17434505866343,17434506058663,17434506060190
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,213680,213680,4194304,256,0,0,12,24,191552,0x7f74df71bb00,0x7f74dee25e80,17434506074990,17434506089063,17434506249063,17434506250835
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,213680,213680,4194304,256,0,0,12,24,195840,0x7f74df71b980,0x7f74dee25ec0,17434506266025,17434506274183,17434506557383,17434506603476
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,213680,213680,4194304,256,0,0,12,24,198592,0x7f74df71b800,0x7f74dee25f00,17434506619106,17434506629704,17434506778504,17434506779972
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,213680,213680,4194304,256,0,0,12,24,202368,0x7f74df71b680,0x7f74dee25f40,17434506796451,17434506804584,17434507012744,17434507056175
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,213680,213680,4194304,256,0,0,12,24,205888,0x7f74e1b36500,0x7f74dee25f80,17434507066574,17434507077224,17434507284904,17434507328147
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,213680,213680,4194304,256,0,0,12,24,209408,0x7f74e1b36380,0x7f74dee25fc0,17434507337297,17434507347784,17434507533704,17434507535152
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,213680,213680,4194304,256,0,0,12,24,214464,0x7f74e1b36200,0x7f74dee26000,17434507549742,17434507558024,17434507892264,17434507932572
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,213680,213680,4194304,256,0,0,12,24,217728,0x7f74e1b36080,0x7f74dee26040,17434507948251,17434507958824,17434508126344,17434508127827
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,213680,213680,4194304,256,0,0,12,24,222016,0x7f74df71bf00,0x7f74dee26080,17434508143536,17434508151624,17434508381705,17434508397720
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,213680,213680,4194304,256,0,0,12,24,226048,0x7f74df71bd80,0x7f74dee260c0,17434508405489,17434508415945,17434508645385,17434508661183
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,213680,213680,4194304,256,0,0,12,24,230080,0x7f74df71bc00,0x7f74dee26100,17434508670743,17434508681065,17434508892105,17434508908146
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,213680,213680,4194304,256,0,0,12,24,235904,0x7f74df71ba80,0x7f74dee26140,17434508917916,17434508927145,17434509312585,17434509328035
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,213680,213680,4194304,256,0,0,12,24,239424,0x7f74df71b900,0x7f74dee26180,17434509343755,17434509354505,17434509542345,17434509543810
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,213680,213680,4194304,256,0,0,12,24,244224,0x7f74df71b780,0x7f74dee261c0,17434509561409,17434509569065,17434509819785,17434509835822
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,213680,213680,4194304,256,0,0,12,24,248768,0x7f74df71b600,0x7f74dee26200,17434509844322,17434509854345,17434510101706,17434510126735
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,213680,213680,4194304,256,0,0,12,24,253312,0x7f74e1b36480,0x7f74dee26240,17434510136474,17434510146666,17434510383306,17434510398858
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,213680,213680,4194304,256,0,0,8,24,255552,0x7f74e1b36300,0x7f74dee26280,17434510407727,17434510418186,17434510871466,17434510886985
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,213680,213680,4194304,256,0,0,12,24,259840,0x7f74e1b36180,0x7f74dee262c0,17434510903224,17434510914186,17434511138666,17434511157028
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,213680,213680,4194304,256,0,0,12,24,265664,0x7f74e1b36000,0x7f74dee26300,17434511167408,17434511177866,17434511476106,17434511519248
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,213680,213680,4194304,256,0,0,12,24,271232,0x7f74df71be80,0x7f74dee26340,17434511531948,17434511542026,17434511840267,17434511859790
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,213680,213680,4194304,256,0,0,8,24,273216,0x7f74df71bd00,0x7f74dee26380,17434511870109,17434511880107,17434512176427,17434512192821
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,213680,213680,4194304,256,0,0,8,24,275712,0x7f74df71bb80,0x7f74dee263c0,17434512202271,17434512212267,17434512768747,17434512786985
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,213680,213680,4194304,256,0,0,12,24,280768,0x7f74df71ba00,0x7f74dee26400,17434512802585,17434512812907,17434513076747,17434513094847
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,213680,213680,4194304,256,0,0,12,24,287616,0x7f74df71b880,0x7f74dee26440,17434513105677,17434513116107,17434513466668,17434513484667
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,213680,213680,4194304,256,0,0,12,24,294208,0x7f74df71b700,0x7f74dee26480,17434513493077,17434513503628,17434513854028,17434513872457
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,213680,213680,4194304,256,0,0,8,24,296960,0x7f74e1b36580,0x7f74dee264c0,17434513882877,17434513892908,17434514240108,17434514291306
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,213680,213680,4194304,256,0,0,8,24,299968,0x7f74e1b36400,0x7f74dee26500,17434514301136,17434514310828,17434514971628,17434515011788
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,213680,213680,4194304,256,0,0,8,24,302720,0x7f74e1b36280,0x7f74dee26540,17434515029027,17434515038828,17434515484909,17434515528584
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,213680,213680,4194304,256,0,0,12,24,305472,0x7f74e1b36100,0x7f74dee26580,17434515539514,17434515549709,17434516013709,17434516056840
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,213680,213680,4194304,256,0,0,12,24,308224,0x7f74df71bf80,0x7f74dee265c0,17434516067630,17434516078029,17434516539309,17434516583147
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,213680,213680,4194304,256,0,0,8,24,310976,0x7f74df71be00,0x7f74dee26600,17434516593596,17434516603949,17434517055310,17434517075094
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,213680,213680,4194304,256,0,0,8,24,313216,0x7f74df71bc80,0x7f74dee26640,17434517084264,17434517094510,17434517964110,17434517985620
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,213680,213680,4194304,256,0,0,8,24,315968,0x7f74df71bb00,0x7f74dee26680,17434518003570,17434518014190,17434518867631,17434518912646
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,213680,213680,4194304,256,0,0,12,24,318720,0x7f74df71b980,0x7f74dee266c0,17434518921756,17434518931631,17434519816271,17434519860302
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,213680,213680,4194304,256,0,0,12,24,321472,0x7f74df71b800,0x7f74dee26700,17434519870561,17434519880911,17434520760752,17434520804337
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,213680,213680,4194304,256,0,0,8,24,324224,0x7f74df71b680,0x7f74dee26740,17434520817797,17434520833392,17434521692432,17434521736373
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,213680,213680,4194304,256,0,0,8,24,326464,0x7f74e1b36500,0x7f74dee26780,17434521745033,17434521754992,17434523453073,17434523523377
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,213680,213680,4194304,256,0,0,8,24,329216,0x7f74e1b36380,0x7f74dee267c0,17434523541166,17434523552274,17434525216595,17434525284931
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,213680,213680,4194304,256,0,0,12,24,331968,0x7f74e1b36200,0x7f74dee26800,17434525294491,17434525304595,17434527028756,17434527098794
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,213680,213680,4194304,256,0,0,12,24,334720,0x7f74e1b36080,0x7f74dee26840,17434527110434,17434527128596,17434528844117,17434528912267
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,213680,213680,4194304,256,0,0,8,24,337472,0x7f74df71bf00,0x7f74dee26880,17434528921636,17434528931157,17434530603958,17434530672351
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,213680,213680,4194304,256,0,0,8,24,0,0x7f74df71bd80,0x7f74dee268c0,17434530681571,17434530692758,17434534049880,17434534136011