169 lines
37 KiB
CSV
169 lines
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",0,0,0,157887,157887,33554432,256,0,0,4,32,4160,0x0,0x7fc364c04280,16385586841853,16385586870073,16385587107675,16385587214525
|
|
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,157887,157887,32768,256,0,0,12,24,13888,0x0,0x7fc364c23f80,16385591930561,16385591946586,16385591956026,16385591977510
|
|
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,157887,157887,4194304,256,0,0,12,24,14336,0x7fc367c0c380,0x7fc364c23fc0,16385591979080,16385592030587,16385592123387,16385592125537
|
|
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,157887,157887,4194304,256,0,0,16,24,15040,0x7fc367c0c200,0x7fc364c24000,16385592147106,16385592157307,16385592336509,16385592338622
|
|
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,157887,157887,4194304,256,0,0,16,24,15488,0x7fc367c0c080,0x7fc364c24040,16385592353042,16385592361309,16385592541310,16385592543508
|
|
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,157887,157887,4194304,256,0,0,12,24,15936,0x7fc36546bf00,0x7fc364c24080,16385592557587,16385592565790,16385592658591,16385592660635
|
|
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,157887,157887,4194304,256,0,0,12,24,16384,0x7fc36546bd80,0x7fc364c240c0,16385592675825,16385592683871,16385592775392,16385592777512
|
|
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,157887,157887,4194304,256,0,0,12,24,17088,0x7fc36546bc00,0x7fc364c24100,16385592806682,16385592817632,16385592909632,16385592911580
|
|
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,157887,157887,4194304,256,0,0,16,24,17792,0x7fc36546ba80,0x7fc364c24140,16385592930549,16385592947873,16385593127874,16385593129985
|
|
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,157887,157887,4194304,256,0,0,16,24,18496,0x7fc36546b900,0x7fc364c24180,16385593145314,16385593154434,16385593333955,16385593336150
|
|
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,157887,157887,4194304,256,0,0,16,24,19200,0x7fc36546b780,0x7fc364c241c0,16385593352920,16385593367556,16385593460676,16385593462687
|
|
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,157887,157887,4194304,256,0,0,16,24,19904,0x7fc36546b600,0x7fc364c24200,16385593483147,16385593500036,16385593592197,16385593594365
|
|
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,157887,157887,4194304,256,0,0,12,24,20608,0x7fc367c0c480,0x7fc364c24240,16385593613744,16385593629637,16385593721958,16385593723882
|
|
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,157887,157887,4194304,256,0,0,16,24,21312,0x7fc367c0c300,0x7fc364c24280,16385593748031,16385593758278,16385593938279,16385593940257
|
|
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,157887,157887,4194304,256,0,0,16,24,22016,0x7fc367c0c180,0x7fc364c242c0,16385593964406,16385593973800,16385594154441,16385594156592
|
|
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,157887,157887,4194304,256,0,0,16,24,22720,0x7fc367c0c000,0x7fc364c24300,16385594171002,16385594180521,16385594272842,16385594274780
|
|
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,157887,157887,4194304,256,0,0,12,24,23424,0x7fc36546be80,0x7fc364c24340,16385594293339,16385594303082,16385594394762,16385594396797
|
|
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,157887,157887,4194304,256,0,0,12,24,24128,0x7fc36546bd00,0x7fc364c24380,16385594418036,16385594428363,16385594519883,16385594521954
|
|
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,157887,157887,4194304,256,0,0,16,24,24832,0x7fc36546bb80,0x7fc364c243c0,16385594538244,16385594546763,16385594726925,16385594728909
|
|
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,157887,157887,4194304,256,0,0,16,24,25536,0x7fc36546ba00,0x7fc364c24400,16385594746269,16385594754605,16385594934446,16385594936355
|
|
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,157887,157887,4194304,256,0,0,12,24,26240,0x7fc36546b880,0x7fc364c24440,16385594950715,16385594959566,16385595052367,16385595054362
|
|
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,157887,157887,4194304,256,0,0,12,24,26944,0x7fc36546b700,0x7fc364c24480,16385595072642,16385595095567,16385595187728,16385595189769
|
|
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,157887,157887,4194304,256,0,0,12,24,27648,0x7fc367c0c580,0x7fc364c244c0,16385595211049,16385595221808,16385595313489,16385595315386
|
|
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,157887,157887,4194304,256,0,0,16,24,28608,0x7fc367c0c400,0x7fc364c24500,16385595333146,16385595342289,16385595521650,16385595523632
|
|
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,157887,157887,4194304,256,0,0,16,24,29312,0x7fc367c0c280,0x7fc364c24540,16385595537832,16385595547250,16385595727731,16385595729667
|
|
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,157887,157887,4194304,256,0,0,12,24,30016,0x7fc367c0c100,0x7fc364c24580,16385595746567,16385595754771,16385595847092,16385595849065
|
|
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,157887,157887,4194304,256,0,0,8,24,30976,0x7fc36546bf80,0x7fc364c245c0,16385595865934,16385595874292,16385595966293,16385595968352
|
|
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,157887,157887,4194304,256,0,0,12,24,31680,0x7fc36546be00,0x7fc364c24600,16385595989451,16385596000533,16385596092214,16385596094109
|
|
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,157887,157887,4194304,256,0,0,16,24,32640,0x7fc36546bc80,0x7fc364c24640,16385596111539,16385596121174,16385596300855,16385596302995
|
|
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,157887,157887,4194304,256,0,0,12,24,33600,0x7fc36546bb00,0x7fc364c24680,16385596317064,16385596325655,16385596504856,16385596506900
|
|
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,157887,157887,4194304,256,0,0,12,24,34560,0x7fc36546b980,0x7fc364c246c0,16385596523540,16385596531257,16385596623577,16385596625557
|
|
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,157887,157887,4194304,256,0,0,8,24,35520,0x7fc36546b800,0x7fc364c24700,16385596643137,16385596653017,16385596745818,16385596747795
|
|
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,157887,157887,4194304,256,0,0,12,24,36224,0x7fc36546b680,0x7fc364c24740,16385596769264,16385596778618,16385596870459,16385596872452
|
|
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,157887,157887,4194304,256,0,0,12,24,37184,0x7fc367c0c500,0x7fc364c24780,16385596895051,16385596905659,16385597084860,16385597086827
|
|
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,157887,157887,4194304,256,0,0,12,24,38144,0x7fc367c0c380,0x7fc364c247c0,16385597103757,16385597113501,16385597293182,16385597295293
|
|
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,157887,157887,4194304,256,0,0,12,24,39104,0x7fc367c0c200,0x7fc364c24800,16385597308762,16385597318302,16385597410943,16385597412920
|
|
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,157887,157887,4194304,256,0,0,8,24,40320,0x7fc367c0c080,0x7fc364c24840,16385597427720,16385597436543,16385597528863,16385597530857
|
|
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,157887,157887,4194304,256,0,0,12,24,41280,0x7fc36546bf00,0x7fc364c24880,16385597551197,16385597562144,16385597654784,16385597656685
|
|
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,157887,157887,4194304,256,0,0,12,24,42240,0x7fc36546bd80,0x7fc364c248c0,16385597671934,16385597680064,16385597859586,16385597861590
|
|
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,157887,157887,4194304,256,0,0,12,24,43200,0x7fc36546bc00,0x7fc364c24900,16385597881240,16385597889826,16385598069187,16385598071185
|
|
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,157887,157887,4194304,256,0,0,8,24,44160,0x7fc36546ba80,0x7fc364c24940,16385598090675,16385598117347,16385598209988,16385598212212
|
|
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,157887,157887,4194304,256,0,0,12,24,45376,0x7fc36546b900,0x7fc364c24980,16385598227542,16385598237188,16385598330469,16385598332500
|
|
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,157887,157887,4194304,256,0,0,12,24,46336,0x7fc36546b780,0x7fc364c249c0,16385598353119,16385598364069,16385598456069,16385598457987
|
|
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,157887,157887,4194304,256,0,0,12,24,47552,0x7fc36546b600,0x7fc364c24a00,16385598476976,16385598488230,16385598669031,16385598670512
|
|
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,157887,157887,4194304,256,0,0,12,24,48512,0x7fc367c0c480,0x7fc364c24a40,16385598684182,16385598692391,16385598871912,16385598873338
|
|
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,157887,157887,4194304,256,0,0,8,24,49472,0x7fc367c0c300,0x7fc364c24a80,16385598887357,16385598895432,16385598988233,16385598989645
|
|
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,157887,157887,4194304,256,0,0,12,24,50688,0x7fc367c0c180,0x7fc364c24ac0,16385599003375,16385599011753,16385599103754,16385599105143
|
|
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,157887,157887,4194304,256,0,0,12,24,51648,0x7fc367c0c000,0x7fc364c24b00,16385599124642,16385599135754,16385599227595,16385599229020
|
|
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,157887,157887,4194304,256,0,0,12,24,52864,0x7fc36546be80,0x7fc364c24b40,16385599245599,16385599253515,16385599431596,16385599433075
|
|
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,157887,157887,4194304,256,0,0,12,24,54080,0x7fc36546bd00,0x7fc364c24b80,16385599446785,16385599456876,16385599634797,16385599636331
|
|
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,157887,157887,4194304,256,0,0,8,24,55296,0x7fc36546bb80,0x7fc364c24bc0,16385599649911,16385599657997,16385599750158,16385599751668
|
|
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,157887,157887,4194304,256,0,0,12,24,56768,0x7fc36546ba00,0x7fc364c24c00,16385599765958,16385599773998,16385599867279,16385599868706
|
|
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,157887,157887,4194304,256,0,0,12,24,57728,0x7fc36546b880,0x7fc364c24c40,16385599888255,16385599899439,16385599991280,16385599992643
|
|
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,157887,157887,4194304,256,0,0,12,24,58944,0x7fc36546b700,0x7fc364c24c80,16385600006773,16385600014640,16385600194161,16385600195589
|
|
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,157887,157887,4194304,256,0,0,12,24,60160,0x7fc367c0c580,0x7fc364c24cc0,16385600209298,16385600217361,16385600398482,16385600399994
|
|
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,157887,157887,4194304,256,0,0,8,24,61376,0x7fc367c0c400,0x7fc364c24d00,16385600414124,16385600422163,16385600515603,16385600517082
|
|
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,157887,157887,4194304,256,0,0,12,24,62848,0x7fc367c0c280,0x7fc364c24d40,16385600533441,16385600541523,16385600639284,16385600640869
|
|
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,157887,157887,4194304,256,0,0,12,24,63808,0x7fc367c0c100,0x7fc364c24d80,16385600660068,16385600671444,16385600764085,16385600765646
|
|
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,157887,157887,4194304,256,0,0,12,24,65024,0x7fc36546bf80,0x7fc364c24dc0,16385600782166,16385600791285,16385600970166,16385600971592
|
|
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,157887,157887,4194304,256,0,0,12,24,66240,0x7fc36546be00,0x7fc364c24e00,16385600986131,16385600994326,16385601172888,16385601174337
|
|
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,157887,157887,4194304,256,0,0,8,24,67456,0x7fc36546bc80,0x7fc364c24e40,16385601189477,16385601197688,16385601290328,16385601291804
|
|
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,157887,157887,4194304,256,0,0,12,24,68928,0x7fc36546bb00,0x7fc364c24e80,16385601305554,16385601313689,16385601415609,16385601417152
|
|
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,157887,157887,4194304,256,0,0,12,24,70144,0x7fc36546b980,0x7fc364c24ec0,16385601437861,16385601448249,16385601540410,16385601541879
|
|
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,157887,157887,4194304,256,0,0,12,24,71616,0x7fc36546b800,0x7fc364c24f00,16385601556929,16385601564570,16385601744251,16385601745684
|
|
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,157887,157887,4194304,256,0,0,12,24,72832,0x7fc36546b680,0x7fc364c24f40,16385601759964,16385601768252,16385601946653,16385601948190
|
|
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,157887,157887,4194304,256,0,0,8,24,74048,0x7fc367c0c500,0x7fc364c24f80,16385601961890,16385601970013,16385602061854,16385602063327
|
|
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,157887,157887,4194304,256,0,0,12,24,75776,0x7fc367c0c380,0x7fc364c24fc0,16385602089307,16385602101854,16385602207454,16385602209094
|
|
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,157887,157887,4194304,256,0,0,12,24,76992,0x7fc367c0c200,0x7fc364c25000,16385602227874,16385602239935,16385602332735,16385602334172
|
|
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,157887,157887,4194304,256,0,0,12,24,78464,0x7fc367c0c080,0x7fc364c25040,16385602348431,16385602356575,16385602537057,16385602538577
|
|
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,157887,157887,4194304,256,0,0,12,24,79936,0x7fc36546bf00,0x7fc364c25080,16385602552067,16385602560257,16385602740738,16385602742103
|
|
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,157887,157887,4194304,256,0,0,8,24,81408,0x7fc36546bd80,0x7fc364c250c0,16385602756002,16385602765218,16385602858979,16385602860370
|
|
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,157887,157887,4194304,256,0,0,12,24,83136,0x7fc36546bc00,0x7fc364c25100,16385602873580,16385602881539,16385602993380,16385602994807
|
|
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,157887,157887,4194304,256,0,0,12,24,84352,0x7fc36546ba80,0x7fc364c25140,16385603030876,16385603040740,16385603133381,16385603134744
|
|
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,157887,157887,4194304,256,0,0,12,24,85824,0x7fc36546b900,0x7fc364c25180,16385603149944,16385603158021,16385603336422,16385603338059
|
|
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,157887,157887,4194304,256,0,0,12,24,87296,0x7fc36546b780,0x7fc364c251c0,16385603352409,16385603360262,16385603538823,16385603540185
|
|
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,157887,157887,4194304,256,0,0,12,24,88768,0x7fc36546b600,0x7fc364c25200,16385603554235,16385603562024,16385603656104,16385603657532
|
|
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,157887,157887,4194304,256,0,0,12,24,90752,0x7fc367c0c480,0x7fc364c25240,16385603671282,16385603679464,16385603798345,16385603799869
|
|
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,157887,157887,4194304,256,0,0,12,24,91968,0x7fc367c0c300,0x7fc364c25280,16385603819139,16385603830505,16385603922986,16385603924367
|
|
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,157887,157887,4194304,256,0,0,12,24,93440,0x7fc367c0c180,0x7fc364c252c0,16385603938326,16385603946506,16385604125387,16385604126852
|
|
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,157887,157887,4194304,256,0,0,12,24,94912,0x7fc367c0c000,0x7fc364c25300,16385604140432,16385604148587,16385604327789,16385604329258
|
|
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,157887,157887,4194304,256,0,0,12,24,96384,0x7fc36546be80,0x7fc364c25340,16385604343167,16385604350989,16385604445389,16385604446775
|
|
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,157887,157887,4194304,256,0,0,12,24,98368,0x7fc36546bd00,0x7fc364c25380,16385604460775,16385604468590,16385604592270,16385604593752
|
|
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,157887,157887,4194304,256,0,0,12,24,99584,0x7fc36546bb80,0x7fc364c253c0,16385604612821,16385604621071,16385604713391,16385604714909
|
|
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,157887,157887,4194304,256,0,0,12,24,101312,0x7fc36546ba00,0x7fc364c25400,16385604729249,16385604737391,16385604915473,16385604916915
|
|
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,157887,157887,4194304,256,0,0,12,24,102784,0x7fc36546b880,0x7fc364c25440,16385604930994,16385604939313,16385605120114,16385605121480
|
|
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,157887,157887,4194304,256,0,0,12,24,104256,0x7fc36546b700,0x7fc364c25480,16385605135470,16385605143474,16385605236915,16385605238448
|
|
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,157887,157887,4194304,256,0,0,12,24,106240,0x7fc367c0c580,0x7fc364c254c0,16385605253637,16385605261555,16385605390836,16385605392224
|
|
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,157887,157887,4194304,256,0,0,12,24,107712,0x7fc367c0c400,0x7fc364c25500,16385605411604,16385605422996,16385605515317,16385605516711
|
|
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,157887,157887,4194304,256,0,0,16,24,109440,0x7fc367c0c280,0x7fc364c25540,16385605533601,16385605541237,16385605720438,16385605721887
|
|
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,157887,157887,4194304,256,0,0,16,24,111168,0x7fc367c0c100,0x7fc364c25580,16385605735527,16385605743638,16385605923159,16385605924613
|
|
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,157887,157887,4194304,256,0,0,8,24,112896,0x7fc36546bf80,0x7fc364c255c0,16385605940172,16385605947959,16385606042680,16385606044070
|
|
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,157887,157887,4194304,256,0,0,12,24,115136,0x7fc36546be00,0x7fc364c25600,16385606058570,16385606066680,16385606202521,16385606203976
|
|
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,157887,157887,4194304,256,0,0,12,24,116608,0x7fc36546bc80,0x7fc364c25640,16385606224966,16385606235641,16385606328922,16385606330344
|
|
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,157887,157887,4194304,256,0,0,16,24,118336,0x7fc36546bb00,0x7fc364c25680,16385606344243,16385606352442,16385606531963,16385606533509
|
|
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,157887,157887,4194304,256,0,0,16,24,120064,0x7fc36546b980,0x7fc364c256c0,16385606547109,16385606555163,16385606736445,16385606737945
|
|
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,157887,157887,4194304,256,0,0,12,24,121792,0x7fc36546b800,0x7fc364c25700,16385606752844,16385606760925,16385606855965,16385606857392
|
|
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,157887,157887,4194304,256,0,0,12,24,124032,0x7fc36546b680,0x7fc364c25740,16385606871832,16385606879486,16385607021247,16385607022718
|
|
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,157887,157887,4194304,256,0,0,12,24,125504,0x7fc367c0c500,0x7fc364c25780,16385607042568,16385607053407,16385607146687,16385607148026
|
|
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,157887,157887,4194304,256,0,0,12,24,127488,0x7fc367c0c380,0x7fc364c257c0,16385607162255,16385607170048,16385607348609,16385607350081
|
|
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,157887,157887,4194304,256,0,0,12,24,129216,0x7fc367c0c200,0x7fc364c25800,16385607363861,16385607371969,16385607551330,16385607552697
|
|
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,157887,157887,4194304,256,0,0,12,24,130944,0x7fc367c0c080,0x7fc364c25840,16385607566806,16385607575010,16385607673571,16385607675104
|
|
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,157887,157887,4194304,256,0,0,12,24,133440,0x7fc36546bf00,0x7fc364c25880,16385607688574,16385607696771,16385607849732,16385607851170
|
|
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,157887,157887,4194304,256,0,0,12,24,134912,0x7fc36546bd80,0x7fc364c258c0,16385607871090,16385607881892,16385607975013,16385607976457
|
|
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,157887,157887,4194304,256,0,0,12,24,136896,0x7fc36546bc00,0x7fc364c25900,16385607990847,16385607998533,16385608177254,16385608178763
|
|
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,157887,157887,4194304,256,0,0,12,24,138880,0x7fc36546ba80,0x7fc364c25940,16385608193583,16385608201734,16385608381096,16385608382588
|
|
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,157887,157887,4194304,256,0,0,12,24,140864,0x7fc36546b900,0x7fc364c25980,16385608395888,16385608404136,16385608507817,16385608509176
|
|
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,157887,157887,4194304,256,0,0,12,24,143616,0x7fc36546b780,0x7fc364c259c0,16385608523035,16385608531177,16385608699178,16385608700521
|
|
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,157887,157887,4194304,256,0,0,12,24,145344,0x7fc36546b600,0x7fc364c25a00,16385608720741,16385608731818,16385608826219,16385608827639
|
|
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,157887,157887,4194304,256,0,0,12,24,147584,0x7fc367c0c480,0x7fc364c25a40,16385608841278,16385608849579,16385609028620,16385609029954
|
|
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,157887,157887,4194304,256,0,0,12,24,149568,0x7fc367c0c300,0x7fc364c25a80,16385609043484,16385609051500,16385609231661,16385609233120
|
|
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,157887,157887,4194304,256,0,0,12,24,151552,0x7fc367c0c180,0x7fc364c25ac0,16385609246429,16385609254541,16385609363182,16385609364677
|
|
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,157887,157887,4194304,256,0,0,12,24,154304,0x7fc367c0c000,0x7fc364c25b00,16385609377997,16385609386062,16385609565104,16385609566412
|
|
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,157887,157887,4194304,256,0,0,12,24,156288,0x7fc36546be80,0x7fc364c25b40,16385609586122,16385609597264,16385609697264,16385609698589
|
|
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,157887,157887,4194304,256,0,0,12,24,158784,0x7fc36546bd00,0x7fc364c25b80,16385609713229,16385609721425,16385609903666,16385609905165
|
|
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,157887,157887,4194304,256,0,0,12,24,161024,0x7fc36546bb80,0x7fc364c25bc0,16385609919165,16385609927346,16385610109907,16385610111670
|
|
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,157887,157887,4194304,256,0,0,12,24,163264,0x7fc36546ba00,0x7fc364c25c00,16385610126410,16385610134387,16385610255508,16385610256967
|
|
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,157887,157887,4194304,256,0,0,12,24,166528,0x7fc36546b880,0x7fc364c25c40,16385610270477,16385610278708,16385610483350,16385610500432
|
|
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,157887,157887,4194304,256,0,0,12,24,168512,0x7fc36546b700,0x7fc364c25c80,16385610515451,16385610526390,16385610635191,16385610636669
|
|
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,157887,157887,4194304,256,0,0,12,24,171264,0x7fc367c0c580,0x7fc364c25cc0,16385610653388,16385610661751,16385610844472,16385610845974
|
|
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,157887,157887,4194304,256,0,0,12,24,173760,0x7fc367c0c400,0x7fc364c25d00,16385610859894,16385610867672,16385611050553,16385611052100
|
|
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,157887,157887,4194304,256,0,0,12,24,176256,0x7fc367c0c280,0x7fc364c25d40,16385611066229,16385611073914,16385611206555,16385611207966
|
|
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,157887,157887,4194304,256,0,0,12,24,179776,0x7fc367c0c100,0x7fc364c25d80,16385611221936,16385611230235,16385611460316,16385611476550
|
|
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,157887,157887,4194304,256,0,0,12,24,182272,0x7fc36546bf80,0x7fc364c25dc0,16385611491640,16385611502556,16385611627837,16385611629307
|
|
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,157887,157887,4194304,256,0,0,12,24,185536,0x7fc36546be00,0x7fc364c25e00,16385611644066,16385611651997,16385611843039,16385611844492
|
|
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,157887,157887,4194304,256,0,0,12,24,188544,0x7fc36546bc80,0x7fc364c25e40,16385611858322,16385611866719,16385612061120,16385612062917
|
|
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,157887,157887,4194304,256,0,0,12,24,191552,0x7fc36546bb00,0x7fc364c25e80,16385612078237,16385612086880,16385612245601,16385612247003
|
|
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,157887,157887,4194304,256,0,0,12,24,195840,0x7fc36546b980,0x7fc364c25ec0,16385612260673,16385612268642,16385612549923,16385612569296
|
|
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,157887,157887,4194304,256,0,0,12,24,198592,0x7fc36546b800,0x7fc364c25f00,16385612585606,16385612596004,16385612742405,16385612744072
|
|
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,157887,157887,4194304,256,0,0,12,24,202368,0x7fc36546b680,0x7fc364c25f40,16385612759362,16385612766885,16385612978406,16385612996626
|
|
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,157887,157887,4194304,256,0,0,12,24,205888,0x7fc367c0c500,0x7fc364c25f80,16385613005016,16385613015207,16385613225448,16385613245771
|
|
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,157887,157887,4194304,256,0,0,12,24,209408,0x7fc367c0c380,0x7fc364c25fc0,16385613253591,16385613263688,16385613447529,16385613449116
|
|
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,157887,157887,4194304,256,0,0,12,24,214464,0x7fc367c0c200,0x7fc364c26000,16385613464186,16385613472170,16385613804812,16385613816868
|
|
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,157887,157887,4194304,256,0,0,12,24,217728,0x7fc367c0c080,0x7fc364c26040,16385613833968,16385613844812,16385614009133,16385614010574
|
|
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,157887,157887,4194304,256,0,0,12,24,222016,0x7fc36546bf00,0x7fc364c26080,16385614025064,16385614033293,16385614261775,16385614278238
|
|
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,157887,157887,4194304,256,0,0,12,24,226048,0x7fc36546bd80,0x7fc364c260c0,16385614289198,16385614299535,16385614529137,16385614545692
|
|
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,157887,157887,4194304,256,0,0,12,24,230080,0x7fc36546bc00,0x7fc364c26100,16385614554362,16385614565297,16385614774738,16385614790367
|
|
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,157887,157887,4194304,256,0,0,12,24,235904,0x7fc36546ba80,0x7fc364c26140,16385614800937,16385614810899,16385615194261,16385615209068
|
|
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,157887,157887,4194304,256,0,0,12,24,239424,0x7fc36546b900,0x7fc364c26180,16385615225217,16385615236181,16385615420663,16385615422013
|
|
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,157887,157887,4194304,256,0,0,12,24,244224,0x7fc36546b780,0x7fc364c261c0,16385615436703,16385615444503,16385615697144,16385615711856
|
|
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,157887,157887,4194304,256,0,0,12,24,248768,0x7fc36546b600,0x7fc364c26200,16385615720246,16385615730745,16385615977146,16385615993860
|
|
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,157887,157887,4194304,256,0,0,12,24,253312,0x7fc367c0c480,0x7fc364c26240,16385616002020,16385616012347,16385616248028,16385616266244
|
|
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,157887,157887,4194304,256,0,0,8,24,255552,0x7fc367c0c300,0x7fc364c26280,16385616273554,16385616284348,16385616734911,16385616752894
|
|
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,157887,157887,4194304,256,0,0,12,24,259840,0x7fc367c0c180,0x7fc364c262c0,16385616768153,16385616779072,16385617001633,16385617019068
|
|
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,157887,157887,4194304,256,0,0,12,24,265664,0x7fc367c0c000,0x7fc364c26300,16385617027348,16385617037633,16385617336515,16385617354230
|
|
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,157887,157887,4194304,256,0,0,12,24,271232,0x7fc36546be80,0x7fc364c26340,16385617365380,16385617375396,16385617674758,16385617686173
|
|
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,157887,157887,4194304,256,0,0,8,24,273216,0x7fc36546bd00,0x7fc364c26380,16385617696813,16385617707078,16385618001960,16385618013716
|
|
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,157887,157887,4194304,256,0,0,8,24,275712,0x7fc36546bb80,0x7fc364c263c0,16385618021826,16385618032200,16385618586764,16385618606213
|
|
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,157887,157887,4194304,256,0,0,12,24,280768,0x7fc36546ba00,0x7fc364c26400,16385618622302,16385618633004,16385618895406,16385618913566
|
|
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,157887,157887,4194304,256,0,0,12,24,287616,0x7fc36546b880,0x7fc364c26440,16385618921866,16385618932206,16385619283728,16385619301567
|
|
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,157887,157887,4194304,256,0,0,12,24,294208,0x7fc36546b700,0x7fc364c26480,16385619309547,16385619320209,16385619670611,16385619688329
|
|
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,157887,157887,4194304,256,0,0,8,24,296960,0x7fc367c0c580,0x7fc364c264c0,16385619696539,16385619707091,16385620052053,16385620069881
|
|
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,157887,157887,4194304,256,0,0,8,24,299968,0x7fc367c0c400,0x7fc364c26500,16385620078500,16385620088374,16385620746458,16385620764275
|
|
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,157887,157887,4194304,256,0,0,8,24,302720,0x7fc367c0c280,0x7fc364c26540,16385620781715,16385620791418,16385621236061,16385621253575
|
|
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,157887,157887,4194304,256,0,0,12,24,305472,0x7fc367c0c100,0x7fc364c26580,16385621262074,16385621272542,16385621733985,16385621745864
|
|
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,157887,157887,4194304,256,0,0,12,24,308224,0x7fc36546bf80,0x7fc364c265c0,16385621756993,16385621767585,16385622226148,16385622249603
|
|
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,157887,157887,4194304,256,0,0,8,24,310976,0x7fc36546be00,0x7fc364c26600,16385622257692,16385622268068,16385622716391,16385622735392
|
|
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,157887,157887,4194304,256,0,0,8,24,313216,0x7fc36546bc80,0x7fc364c26640,16385622746842,16385622757512,16385623623277,16385623643382
|
|
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,157887,157887,4194304,256,0,0,8,24,315968,0x7fc36546bb00,0x7fc364c26680,16385623660311,16385623670958,16385624522163,16385624540112
|
|
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,157887,157887,4194304,256,0,0,12,24,318720,0x7fc36546b980,0x7fc364c266c0,16385624547672,16385624558484,16385625440729,16385625458631
|
|
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,157887,157887,4194304,256,0,0,12,24,321472,0x7fc36546b800,0x7fc364c26700,16385625469061,16385625479770,16385626356256,16385626376031
|
|
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,157887,157887,4194304,256,0,0,8,24,324224,0x7fc36546b680,0x7fc364c26740,16385626387221,16385626403776,16385627260902,16385627279921
|
|
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,157887,157887,4194304,256,0,0,8,24,326464,0x7fc367c0c500,0x7fc364c26780,16385627288081,16385627298342,16385628993713,16385629056352
|
|
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,157887,157887,4194304,256,0,0,8,24,329216,0x7fc367c0c380,0x7fc364c267c0,16385629072742,16385629083474,16385630746205,16385630809424
|
|
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,157887,157887,4194304,256,0,0,12,24,331968,0x7fc367c0c200,0x7fc364c26800,16385630818413,16385630828125,16385632550377,16385632614354
|
|
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,157887,157887,4194304,256,0,0,12,24,334720,0x7fc367c0c080,0x7fc364c26840,16385632623974,16385632634857,16385634347989,16385634414404
|
|
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,157887,157887,4194304,256,0,0,8,24,337472,0x7fc36546bf00,0x7fc364c26880,16385634423564,16385634433909,16385636105921,16385636168556
|
|
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,157887,157887,4194304,256,0,0,8,24,0,0x7fc36546bd80,0x7fc364c268c0,16385636176495,16385636187361,16385639542103,16385639613550
|