169 строки
37 KiB
CSV
169 строки
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",0,0,0,231318,231318,33554432,256,0,0,4,32,4160,0x0,0x7ff759c04280,17724136167316,17724136192787,17724136430867,17724136522737
|
|
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,231318,231318,32768,256,0,0,12,24,13888,0x0,0x7ff759c23f80,17724141183450,17724141198713,17724141212153,17724141230479
|
|
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,231318,231318,4194304,256,0,0,12,24,14336,0x7ff75cbbb380,0x7ff759c23fc0,17724141234519,17724141279193,17724141371673,17724141373895
|
|
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,231318,231318,4194304,256,0,0,16,24,15040,0x7ff75cbbb200,0x7ff759c24000,17724141393985,17724141403993,17724141582874,17724141585140
|
|
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,231318,231318,4194304,256,0,0,16,24,15488,0x7ff75cbbb080,0x7ff759c24040,17724141600090,17724141608634,17724141788154,17724141790255
|
|
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,231318,231318,4194304,256,0,0,12,24,15936,0x7ff75a58bf00,0x7ff759c24080,17724141804155,17724141812474,17724141906074,17724141908042
|
|
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,231318,231318,4194304,256,0,0,12,24,16384,0x7ff75a58bd80,0x7ff759c240c0,17724141923002,17724141931354,17724142023354,17724142025449
|
|
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,231318,231318,4194304,256,0,0,12,24,17088,0x7ff75a58bc00,0x7ff759c24100,17724142051688,17724142062714,17724142154394,17724142156686
|
|
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,231318,231318,4194304,256,0,0,16,24,17792,0x7ff75a58ba80,0x7ff759c24140,17724142174215,17724142183674,17724142363515,17724142365551
|
|
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,231318,231318,4194304,256,0,0,16,24,18496,0x7ff75a58b900,0x7ff759c24180,17724142384120,17724142409115,17724142588795,17724142591095
|
|
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,231318,231318,4194304,256,0,0,16,24,19200,0x7ff75a58b780,0x7ff759c241c0,17724142606494,17724142615035,17724142708795,17724142711072
|
|
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,231318,231318,4194304,256,0,0,16,24,19904,0x7ff75a58b600,0x7ff759c24200,17724142729691,17724142741435,17724142835195,17724142837249
|
|
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,231318,231318,4194304,256,0,0,12,24,20608,0x7ff75cbbb480,0x7ff759c24240,17724142861318,17724142884795,17724142978556,17724142980695
|
|
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,231318,231318,4194304,256,0,0,16,24,21312,0x7ff75cbbb300,0x7ff759c24280,17724143006234,17724143016956,17724143195356,17724143197400
|
|
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,231318,231318,4194304,256,0,0,16,24,22016,0x7ff75cbbb180,0x7ff759c242c0,17724143212209,17724143221436,17724143401436,17724143403494
|
|
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,231318,231318,4194304,256,0,0,16,24,22720,0x7ff75cbbb000,0x7ff759c24300,17724143417434,17724143426396,17724143519516,17724143521671
|
|
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,231318,231318,4194304,256,0,0,12,24,23424,0x7ff75a58be80,0x7ff759c24340,17724143542411,17724143551836,17724143644636,17724143646728
|
|
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,231318,231318,4194304,256,0,0,12,24,24128,0x7ff75a58bd00,0x7ff759c24380,17724143668188,17724143678557,17724143771677,17724143773745
|
|
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,231318,231318,4194304,256,0,0,16,24,24832,0x7ff75a58bb80,0x7ff759c243c0,17724143792885,17724143803517,17724143982397,17724143984630
|
|
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,231318,231318,4194304,256,0,0,16,24,25536,0x7ff75a58ba00,0x7ff759c24400,17724144008809,17724144018557,17724144199197,17724144201264
|
|
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,231318,231318,4194304,256,0,0,12,24,26240,0x7ff75a58b880,0x7ff759c24440,17724144220504,17724144251997,17724144345437,17724144347461
|
|
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,231318,231318,4194304,256,0,0,12,24,26944,0x7ff75a58b700,0x7ff759c24480,17724144361630,17724144371518,17724144465598,17724144467778
|
|
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,231318,231318,4194304,256,0,0,12,24,27648,0x7ff75cbbb580,0x7ff759c244c0,17724144487837,17724144498398,17724144590718,17724144592864
|
|
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,231318,231318,4194304,256,0,0,16,24,28608,0x7ff75cbbb400,0x7ff759c24500,17724144609294,17724144618078,17724144796798,17724144798939
|
|
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,231318,231318,4194304,256,0,0,16,24,29312,0x7ff75cbbb280,0x7ff759c24540,17724144813199,17724144822878,17724145001598,17724145003084
|
|
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,231318,231318,4194304,256,0,0,12,24,30016,0x7ff75cbbb100,0x7ff759c24580,17724145017884,17724145026238,17724145118719,17724145120271
|
|
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,231318,231318,4194304,256,0,0,8,24,30976,0x7ff75a58bf80,0x7ff759c245c0,17724145135511,17724145143679,17724145235679,17724145237248
|
|
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,231318,231318,4194304,256,0,0,12,24,31680,0x7ff75a58be00,0x7ff759c24600,17724145258088,17724145268799,17724145361919,17724145363585
|
|
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,231318,231318,4194304,256,0,0,16,24,32640,0x7ff75a58bc80,0x7ff759c24640,17724145378535,17724145386559,17724145566719,17724145568260
|
|
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,231318,231318,4194304,256,0,0,12,24,33600,0x7ff75a58bb00,0x7ff759c24680,17724145582600,17724145590719,17724145772159,17724145773655
|
|
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,231318,231318,4194304,256,0,0,12,24,34560,0x7ff75a58b980,0x7ff759c246c0,17724145787394,17724145795360,17724145888800,17724145890382
|
|
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,231318,231318,4194304,256,0,0,8,24,35520,0x7ff75a58b800,0x7ff759c24700,17724145904691,17724145912960,17724146006720,17724146008299
|
|
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,231318,231318,4194304,256,0,0,12,24,36224,0x7ff75a58b680,0x7ff759c24740,17724146028628,17724146038720,17724146131840,17724146133456
|
|
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,231318,231318,4194304,256,0,0,12,24,37184,0x7ff75cbbb500,0x7ff759c24780,17724146148165,17724146156320,17724146336320,17724146337861
|
|
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,231318,231318,4194304,256,0,0,12,24,38144,0x7ff75cbbb380,0x7ff759c247c0,17724146352570,17724146361280,17724146542401,17724146543965
|
|
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,231318,231318,4194304,256,0,0,12,24,39104,0x7ff75cbbb200,0x7ff759c24800,17724146558965,17724146567361,17724146661121,17724146662762
|
|
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,231318,231318,4194304,256,0,0,8,24,40320,0x7ff75cbbb080,0x7ff759c24840,17724146676442,17724146684641,17724146778561,17724146780049
|
|
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,231318,231318,4194304,256,0,0,12,24,41280,0x7ff75a58bf00,0x7ff759c24880,17724146799269,17724146811521,17724146904481,17724146905956
|
|
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,231318,231318,4194304,256,0,0,12,24,42240,0x7ff75a58bd80,0x7ff759c248c0,17724146921426,17724146929921,17724147108641,17724147110151
|
|
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,231318,231318,4194304,256,0,0,12,24,43200,0x7ff75a58bc00,0x7ff759c24900,17724147124671,17724147132481,17724147313282,17724147314716
|
|
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,231318,231318,4194304,256,0,0,8,24,44160,0x7ff75a58ba80,0x7ff759c24940,17724147330326,17724147338882,17724147432162,17724147433803
|
|
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,231318,231318,4194304,256,0,0,12,24,45376,0x7ff75a58b900,0x7ff759c24980,17724147447693,17724147455682,17724147550562,17724147552090
|
|
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,231318,231318,4194304,256,0,0,12,24,46336,0x7ff75a58b780,0x7ff759c249c0,17724147577200,17724147587842,17724147681922,17724147683427
|
|
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,231318,231318,4194304,256,0,0,12,24,47552,0x7ff75a58b600,0x7ff759c24a00,17724147698947,17724147706882,17724147886882,17724147888392
|
|
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,231318,231318,4194304,256,0,0,12,24,48512,0x7ff75cbbb480,0x7ff759c24a40,17724147903651,17724147911842,17724148094563,17724148096137
|
|
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,231318,231318,4194304,256,0,0,8,24,49472,0x7ff75cbbb300,0x7ff759c24a80,17724148110736,17724148118883,17724148211683,17724148213294
|
|
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,231318,231318,4194304,256,0,0,12,24,50688,0x7ff75cbbb180,0x7ff759c24ac0,17724148228163,17724148237123,17724148330243,17724148331841
|
|
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,231318,231318,4194304,256,0,0,12,24,51648,0x7ff75cbbb000,0x7ff759c24b00,17724148352450,17724148363203,17724148455203,17724148456778
|
|
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,231318,231318,4194304,256,0,0,12,24,52864,0x7ff75a58be80,0x7ff759c24b40,17724148473277,17724148481283,17724148661604,17724148663142
|
|
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,231318,231318,4194304,256,0,0,12,24,54080,0x7ff75a58bd00,0x7ff759c24b80,17724148676422,17724148684804,17724148865604,17724148867157
|
|
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,231318,231318,4194304,256,0,0,8,24,55296,0x7ff75a58bb80,0x7ff759c24bc0,17724148880697,17724148888484,17724148983204,17724148984824
|
|
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,231318,231318,4194304,256,0,0,12,24,56768,0x7ff75a58ba00,0x7ff759c24c00,17724148999484,17724149007364,17724149102564,17724149104041
|
|
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,231318,231318,4194304,256,0,0,12,24,57728,0x7ff75a58b880,0x7ff759c24c40,17724149124521,17724149135684,17724149229284,17724149230868
|
|
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,231318,231318,4194304,256,0,0,12,24,58944,0x7ff75a58b700,0x7ff759c24c80,17724149246438,17724149255364,17724149433605,17724149435113
|
|
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,231318,231318,4194304,256,0,0,12,24,60160,0x7ff75cbbb580,0x7ff759c24cc0,17724149448773,17724149457285,17724149637605,17724149639088
|
|
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,231318,231318,4194304,256,0,0,8,24,61376,0x7ff75cbbb400,0x7ff759c24d00,17724149653028,17724149661285,17724149755525,17724149757125
|
|
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,231318,231318,4194304,256,0,0,12,24,62848,0x7ff75cbbb280,0x7ff759c24d40,17724149771765,17724149780645,17724149880005,17724149881622
|
|
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,231318,231318,4194304,256,0,0,12,24,63808,0x7ff75cbbb100,0x7ff759c24d80,17724149902161,17724149912485,17724150005765,17724150007299
|
|
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,231318,231318,4194304,256,0,0,12,24,65024,0x7ff75a58bf80,0x7ff759c24dc0,17724150021708,17724150031045,17724150210566,17724150212424
|
|
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,231318,231318,4194304,256,0,0,12,24,66240,0x7ff75a58be00,0x7ff759c24e00,17724150227253,17724150235846,17724150415046,17724150416618
|
|
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,231318,231318,4194304,256,0,0,8,24,67456,0x7ff75a58bc80,0x7ff759c24e40,17724150431688,17724150440006,17724150534726,17724150536195
|
|
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,231318,231318,4194304,256,0,0,12,24,68928,0x7ff75a58bb00,0x7ff759c24e80,17724150550815,17724150559046,17724150663206,17724150664702
|
|
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,231318,231318,4194304,256,0,0,12,24,70144,0x7ff75a58b980,0x7ff759c24ec0,17724150684892,17724150695526,17724150788327,17724150789909
|
|
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,231318,231318,4194304,256,0,0,12,24,71616,0x7ff75a58b800,0x7ff759c24f00,17724150804729,17724150812647,17724150992647,17724150994224
|
|
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,231318,231318,4194304,256,0,0,12,24,72832,0x7ff75a58b680,0x7ff759c24f40,17724151010554,17724151019047,17724151198087,17724151199679
|
|
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,231318,231318,4194304,256,0,0,8,24,74048,0x7ff75cbbb500,0x7ff759c24f80,17724151213678,17724151222087,17724151315207,17724151316686
|
|
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,231318,231318,4194304,256,0,0,12,24,75776,0x7ff75cbbb380,0x7ff759c24fc0,17724151330865,17724151338727,17724151445287,17724151446813
|
|
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,231318,231318,4194304,256,0,0,12,24,76992,0x7ff75cbbb200,0x7ff759c25000,17724151466462,17724151477287,17724151571848,17724151573309
|
|
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,231318,231318,4194304,256,0,0,12,24,78464,0x7ff75cbbb080,0x7ff759c25040,17724151588539,17724151596968,17724151775688,17724151777144
|
|
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,231318,231318,4194304,256,0,0,12,24,79936,0x7ff75a58bf00,0x7ff759c25080,17724151791784,17724151800328,17724151979208,17724151980799
|
|
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,231318,231318,4194304,256,0,0,8,24,81408,0x7ff75a58bd80,0x7ff759c250c0,17724151995139,17724152004168,17724152098888,17724152100376
|
|
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,231318,231318,4194304,256,0,0,12,24,83136,0x7ff75a58bc00,0x7ff759c25100,17724152114866,17724152122888,17724152237609,17724152239203
|
|
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,231318,231318,4194304,256,0,0,12,24,84352,0x7ff75a58ba80,0x7ff759c25140,17724152273942,17724152283369,17724152378089,17724152379659
|
|
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,231318,231318,4194304,256,0,0,12,24,85824,0x7ff75a58b900,0x7ff759c25180,17724152395289,17724152403209,17724152583049,17724152584594
|
|
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,231318,231318,4194304,256,0,0,12,24,87296,0x7ff75a58b780,0x7ff759c251c0,17724152601663,17724152609289,17724152789769,17724152791339
|
|
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,231318,231318,4194304,256,0,0,12,24,88768,0x7ff75a58b600,0x7ff759c25200,17724152807558,17724152815689,17724152910729,17724152912296
|
|
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,231318,231318,4194304,256,0,0,12,24,90752,0x7ff75cbbb480,0x7ff759c25240,17724152927205,17724152935850,17724153056650,17724153058272
|
|
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,231318,231318,4194304,256,0,0,12,24,91968,0x7ff75cbbb300,0x7ff759c25280,17724153077531,17724153088810,17724153182250,17724153183789
|
|
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,231318,231318,4194304,256,0,0,12,24,93440,0x7ff75cbbb180,0x7ff759c252c0,17724153198328,17724153206410,17724153387370,17724153388954
|
|
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,231318,231318,4194304,256,0,0,12,24,94912,0x7ff75cbbb000,0x7ff759c25300,17724153403893,17724153412010,17724153594250,17724153595918
|
|
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,231318,231318,4194304,256,0,0,12,24,96384,0x7ff75a58be80,0x7ff759c25340,17724153611328,17724153619530,17724153715051,17724153716615
|
|
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,231318,231318,4194304,256,0,0,12,24,98368,0x7ff75a58bd00,0x7ff759c25380,17724153731325,17724153739531,17724153866411,17724153868022
|
|
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,231318,231318,4194304,256,0,0,12,24,99584,0x7ff75a58bb80,0x7ff759c253c0,17724153888901,17724153899371,17724153994891,17724153996488
|
|
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,231318,231318,4194304,256,0,0,12,24,101312,0x7ff75a58ba00,0x7ff759c25400,17724154011958,17724154019691,17724154198891,17724154200623
|
|
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,231318,231318,4194304,256,0,0,12,24,102784,0x7ff75a58b880,0x7ff759c25440,17724154215243,17724154223851,17724154403052,17724154404658
|
|
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,231318,231318,4194304,256,0,0,12,24,104256,0x7ff75a58b700,0x7ff759c25480,17724154420528,17724154428332,17724154522892,17724154524515
|
|
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,231318,231318,4194304,256,0,0,12,24,106240,0x7ff75cbbb580,0x7ff759c254c0,17724154539375,17724154547212,17724154678412,17724154679991
|
|
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,231318,231318,4194304,256,0,0,12,24,107712,0x7ff75cbbb400,0x7ff759c25500,17724154702421,17724154712972,17724154806572,17724154808108
|
|
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,231318,231318,4194304,256,0,0,16,24,109440,0x7ff75cbbb280,0x7ff759c25540,17724154823728,17724154831852,17724155010892,17724155012413
|
|
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,231318,231318,4194304,256,0,0,16,24,111168,0x7ff75cbbb100,0x7ff759c25580,17724155027493,17724155036012,17724155217613,17724155219198
|
|
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,231318,231318,4194304,256,0,0,8,24,112896,0x7ff75a58bf80,0x7ff759c255c0,17724155233277,17724155241453,17724155337293,17724155338975
|
|
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,231318,231318,4194304,256,0,0,12,24,115136,0x7ff75a58be00,0x7ff759c25600,17724155353554,17724155361773,17724155501133,17724155502721
|
|
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,231318,231318,4194304,256,0,0,12,24,116608,0x7ff75a58bc80,0x7ff759c25640,17724155524220,17724155535533,17724155630253,17724155631837
|
|
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,231318,231318,4194304,256,0,0,16,24,118336,0x7ff75a58bb00,0x7ff759c25680,17724155646907,17724155654893,17724155833774,17724155835322
|
|
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,231318,231318,4194304,256,0,0,16,24,120064,0x7ff75a58b980,0x7ff759c256c0,17724155849432,17724155858734,17724156040014,17724156041477
|
|
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,231318,231318,4194304,256,0,0,12,24,121792,0x7ff75a58b800,0x7ff759c25700,17724156055217,17724156063054,17724156159374,17724156160924
|
|
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,231318,231318,4194304,256,0,0,12,24,124032,0x7ff75a58b680,0x7ff759c25740,17724156177474,17724156186254,17724156331534,17724156333130
|
|
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,231318,231318,4194304,256,0,0,12,24,125504,0x7ff75cbbb500,0x7ff759c25780,17724156354399,17724156364654,17724156460974,17724156462547
|
|
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,231318,231318,4194304,256,0,0,12,24,127488,0x7ff75cbbb380,0x7ff759c257c0,17724156477036,17724156485455,17724156665935,17724156667472
|
|
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,231318,231318,4194304,256,0,0,12,24,129216,0x7ff75cbbb200,0x7ff759c25800,17724156681931,17724156690255,17724156869295,17724156870866
|
|
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,231318,231318,4194304,256,0,0,12,24,130944,0x7ff75cbbb080,0x7ff759c25840,17724156885106,17724156894575,17724156994575,17724156996223
|
|
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,231318,231318,4194304,256,0,0,12,24,133440,0x7ff75a58bf00,0x7ff759c25880,17724157011753,17724157019855,17724157175215,17724157176819
|
|
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,231318,231318,4194304,256,0,0,12,24,134912,0x7ff75a58bd80,0x7ff759c258c0,17724157197318,17724157207856,17724157302576,17724157304066
|
|
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,231318,231318,4194304,256,0,0,12,24,136896,0x7ff75a58bc00,0x7ff759c25900,17724157318925,17724157326736,17724157505616,17724157507151
|
|
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,231318,231318,4194304,256,0,0,12,24,138880,0x7ff75a58ba80,0x7ff759c25940,17724157522800,17724157531216,17724157711056,17724157712775
|
|
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,231318,231318,4194304,256,0,0,12,24,140864,0x7ff75a58b900,0x7ff759c25980,17724157727155,17724157735696,17724157842576,17724157844102
|
|
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,231318,231318,4194304,256,0,0,12,24,143616,0x7ff75a58b780,0x7ff759c259c0,17724157858392,17724157866896,17724158037937,17724158039507
|
|
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,231318,231318,4194304,256,0,0,12,24,145344,0x7ff75a58b600,0x7ff759c25a00,17724158060627,17724158070897,17724158166737,17724158168444
|
|
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,231318,231318,4194304,256,0,0,12,24,147584,0x7ff75cbbb480,0x7ff759c25a40,17724158183794,17724158192017,17724158371377,17724158372969
|
|
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,231318,231318,4194304,256,0,0,12,24,149568,0x7ff75cbbb300,0x7ff759c25a80,17724158386869,17724158394897,17724158576337,17724158577934
|
|
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,231318,231318,4194304,256,0,0,12,24,151552,0x7ff75cbbb180,0x7ff759c25ac0,17724158592173,17724158600177,17724158710418,17724158711940
|
|
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,231318,231318,4194304,256,0,0,12,24,154304,0x7ff75cbbb000,0x7ff759c25b00,17724158726560,17724158734738,17724158916018,17724158917595
|
|
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,231318,231318,4194304,256,0,0,12,24,156288,0x7ff75a58be80,0x7ff759c25b40,17724158939095,17724158948498,17724159050258,17724159051882
|
|
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,231318,231318,4194304,256,0,0,12,24,158784,0x7ff75a58bd00,0x7ff759c25b80,17724159067212,17724159075218,17724159257138,17724159258807
|
|
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,231318,231318,4194304,256,0,0,12,24,161024,0x7ff75a58bb80,0x7ff759c25bc0,17724159273406,17724159281618,17724159466259,17724159467791
|
|
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,231318,231318,4194304,256,0,0,12,24,163264,0x7ff75a58ba00,0x7ff759c25c00,17724159481821,17724159489779,17724159612339,17724159613918
|
|
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,231318,231318,4194304,256,0,0,12,24,166528,0x7ff75a58b880,0x7ff759c25c40,17724159628207,17724159638259,17724159845299,17724159867111
|
|
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,231318,231318,4194304,256,0,0,12,24,168512,0x7ff75a58b700,0x7ff759c25c80,17724159882351,17724159892819,17724160005779,17724160007408
|
|
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,231318,231318,4194304,256,0,0,12,24,171264,0x7ff75cbbb580,0x7ff759c25cc0,17724160023328,17724160031859,17724160216500,17724160217963
|
|
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,231318,231318,4194304,256,0,0,12,24,173760,0x7ff75cbbb400,0x7ff759c25d00,17724160232112,17724160241780,17724160428660,17724160430257
|
|
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,231318,231318,4194304,256,0,0,12,24,176256,0x7ff75cbbb280,0x7ff759c25d40,17724160445647,17724160454100,17724160588980,17724160590533
|
|
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,231318,231318,4194304,256,0,0,12,24,179776,0x7ff75cbbb100,0x7ff759c25d80,17724160604823,17724160612660,17724160844661,17724160864657
|
|
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,231318,231318,4194304,256,0,0,12,24,182272,0x7ff75a58bf80,0x7ff759c25dc0,17724160880146,17724160890741,17724161017781,17724161019303
|
|
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,231318,231318,4194304,256,0,0,12,24,185536,0x7ff75a58be00,0x7ff759c25e00,17724161034972,17724161042741,17724161234901,17724161236487
|
|
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,231318,231318,4194304,256,0,0,12,24,188544,0x7ff75a58bc80,0x7ff759c25e40,17724161251887,17724161260501,17724161451221,17724161452772
|
|
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,231318,231318,4194304,256,0,0,12,24,191552,0x7ff75a58bb00,0x7ff759c25e80,17724161468651,17724161476342,17724161636502,17724161638147
|
|
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,231318,231318,4194304,256,0,0,12,24,195840,0x7ff75a58b980,0x7ff759c25ec0,17724161652707,17724161660662,17724161944502,17724161964259
|
|
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,231318,231318,4194304,256,0,0,12,24,198592,0x7ff75a58b800,0x7ff759c25f00,17724161980929,17724161991542,17724162142102,17724162143675
|
|
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,231318,231318,4194304,256,0,0,12,24,202368,0x7ff75a58b680,0x7ff759c25f40,17724162160134,17724162168022,17724162375383,17724162398208
|
|
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,231318,231318,4194304,256,0,0,12,24,205888,0x7ff75cbbb500,0x7ff759c25f80,17724162407758,17724162417783,17724162626903,17724162649182
|
|
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,231318,231318,4194304,256,0,0,12,24,209408,0x7ff75cbbb380,0x7ff759c25fc0,17724162658282,17724162668663,17724162854743,17724162856357
|
|
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,231318,231318,4194304,256,0,0,12,24,214464,0x7ff75cbbb200,0x7ff759c26000,17724162872016,17724162880503,17724163215384,17724163234547
|
|
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,231318,231318,4194304,256,0,0,12,24,217728,0x7ff75cbbb080,0x7ff759c26040,17724163250327,17724163261144,17724163428984,17724163430532
|
|
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,231318,231318,4194304,256,0,0,12,24,222016,0x7ff75a58bf00,0x7ff759c26080,17724163445222,17724163453304,17724163681785,17724163701085
|
|
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,231318,231318,4194304,256,0,0,12,24,226048,0x7ff75a58bd80,0x7ff759c260c0,17724163711405,17724163721465,17724163950265,17724163969189
|
|
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,231318,231318,4194304,256,0,0,12,24,230080,0x7ff75a58bc00,0x7ff759c26100,17724163977898,17724163987705,17724164199225,17724164218192
|
|
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,231318,231318,4194304,256,0,0,12,24,235904,0x7ff75a58ba80,0x7ff759c26140,17724164229452,17724164238745,17724164624826,17724164643702
|
|
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,231318,231318,4194304,256,0,0,12,24,239424,0x7ff75a58b900,0x7ff759c26180,17724164660921,17724164671706,17724164859066,17724164860596
|
|
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,231318,231318,4194304,256,0,0,12,24,244224,0x7ff75a58b780,0x7ff759c261c0,17724164875886,17724164883706,17724165134107,17724165153699
|
|
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,231318,231318,4194304,256,0,0,12,24,248768,0x7ff75a58b600,0x7ff759c26200,17724165162409,17724165172827,17724165419867,17724165438482
|
|
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,231318,231318,4194304,256,0,0,12,24,253312,0x7ff75cbbb480,0x7ff759c26240,17724165448581,17724165458747,17724165695707,17724165711535
|
|
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,231318,231318,4194304,256,0,0,8,24,255552,0x7ff75cbbb300,0x7ff759c26280,17724165722144,17724165732027,17724166185148,17724166215182
|
|
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,231318,231318,4194304,256,0,0,12,24,259840,0x7ff75cbbb180,0x7ff759c262c0,17724166233232,17724166244028,17724166469949,17724166491765
|
|
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,231318,231318,4194304,256,0,0,12,24,265664,0x7ff75cbbb000,0x7ff759c26300,17724166500845,17724166510109,17724166807869,17724166829447
|
|
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,231318,231318,4194304,256,0,0,12,24,271232,0x7ff75a58be80,0x7ff759c26340,17724166839396,17724166848829,17724167147869,17724167169568
|
|
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,231318,231318,4194304,256,0,0,8,24,273216,0x7ff75a58bd00,0x7ff759c26380,17724167178438,17724167188510,17724167485470,17724167506970
|
|
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,231318,231318,4194304,256,0,0,8,24,275712,0x7ff75a58bb80,0x7ff759c263c0,17724167514990,17724167525310,17724168082911,17724168104505
|
|
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,231318,231318,4194304,256,0,0,12,24,280768,0x7ff75a58ba00,0x7ff759c26400,17724168120554,17724168131071,17724168394911,17724168417727
|
|
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,231318,231318,4194304,256,0,0,12,24,287616,0x7ff75a58b880,0x7ff759c26440,17724168428217,17724168438751,17724168789472,17724168811107
|
|
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,231318,231318,4194304,256,0,0,12,24,294208,0x7ff75a58b700,0x7ff759c26480,17724168819857,17724168831072,17724169180672,17724169202227
|
|
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,231318,231318,4194304,256,0,0,8,24,296960,0x7ff75cbbb580,0x7ff759c264c0,17724169212777,17724169222592,17724169569473,17724169588408
|
|
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,231318,231318,4194304,256,0,0,8,24,299968,0x7ff75cbbb400,0x7ff759c26500,17724169599457,17724169609153,17724170270754,17724170294260
|
|
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,231318,231318,4194304,256,0,0,8,24,302720,0x7ff75cbbb280,0x7ff759c26540,17724170313590,17724170322754,17724170770595,17724170792478
|
|
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,231318,231318,4194304,256,0,0,12,24,305472,0x7ff75cbbb100,0x7ff759c26580,17724170802457,17724170812675,17724171278275,17724171301985
|
|
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,231318,231318,4194304,256,0,0,12,24,308224,0x7ff75a58bf80,0x7ff759c265c0,17724171314225,17724171331395,17724171792996,17724171816212
|
|
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,231318,231318,4194304,256,0,0,8,24,310976,0x7ff75a58be00,0x7ff759c26600,17724171825032,17724171835236,17724172287077,17724172310790
|
|
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,231318,231318,4194304,256,0,0,8,24,313216,0x7ff75a58bc80,0x7ff759c26640,17724172326289,17724172335077,17724173204678,17724173227877
|
|
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,231318,231318,4194304,256,0,0,8,24,315968,0x7ff75a58bb00,0x7ff759c26680,17724173245296,17724173255878,17724174109639,17724174134014
|
|
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,231318,231318,4194304,256,0,0,12,24,318720,0x7ff75a58b980,0x7ff759c266c0,17724174143014,17724174153639,17724175038121,17724175062671
|
|
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,231318,231318,4194304,256,0,0,12,24,321472,0x7ff75a58b800,0x7ff759c26700,17724175072110,17724175081641,17724175961802,17724175986337
|
|
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,231318,231318,4194304,256,0,0,8,24,324224,0x7ff75a58b680,0x7ff759c26740,17724175996617,17724176015882,17724176876043,17724176900014
|
|
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,231318,231318,4194304,256,0,0,8,24,326464,0x7ff75cbbb500,0x7ff759c26780,17724176908194,17724176918443,17724178617966,17724178692319
|
|
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,231318,231318,4194304,256,0,0,8,24,329216,0x7ff75cbbb380,0x7ff759c267c0,17724178710539,17724178721646,17724180386128,17724180456225
|
|
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,231318,231318,4194304,256,0,0,12,24,331968,0x7ff75cbbb200,0x7ff759c26800,17724180465605,17724180475888,17724182202451,17724182272320
|
|
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,231318,231318,4194304,256,0,0,12,24,334720,0x7ff75cbbb080,0x7ff759c26840,17724182285899,17724182313971,17724184029333,17724184098844
|
|
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,231318,231318,4194304,256,0,0,8,24,337472,0x7ff75a58bf00,0x7ff759c26880,17724184110903,17724184126933,17724185801016,17724185868679
|
|
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,231318,231318,4194304,256,0,0,8,24,0,0x7ff75a58bd80,0x7ff759c268c0,17724185877859,17724185888216,17724189246140,17724189320083
|