169 rindas
37 KiB
CSV
169 rindas
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",0,0,0,170998,170998,33554432,256,0,0,4,32,4160,0x0,0x7ff430404280,16706281344389,16706281370699,16706281613098,16706281723087
|
|
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,170998,170998,32768,256,0,0,12,24,13888,0x0,0x7ff430423f80,16706286431293,16706286446350,16706286459150,16706286476871
|
|
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,170998,170998,4194304,256,0,0,12,24,14336,0x7ff43341d380,0x7ff430423fc0,16706286480211,16706286530989,16706286622989,16706286625156
|
|
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,170998,170998,4194304,256,0,0,16,24,15040,0x7ff43341d200,0x7ff430424000,16706286647216,16706286656589,16706286836588,16706286838709
|
|
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,170998,170998,4194304,256,0,0,16,24,15488,0x7ff43341d080,0x7ff430424040,16706286854579,16706286862507,16706287042986,16706287045052
|
|
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,170998,170998,4194304,256,0,0,12,24,15936,0x7ff430cc7f00,0x7ff430424080,16706287059252,16706287067306,16706287161386,16706287163399
|
|
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,170998,170998,4194304,256,0,0,12,24,16384,0x7ff430cc7d80,0x7ff4304240c0,16706287179528,16706287187626,16706287279625,16706287281425
|
|
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,170998,170998,4194304,256,0,0,12,24,17088,0x7ff430cc7c00,0x7ff430424100,16706287308344,16706287318985,16706287410664,16706287412560
|
|
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,170998,170998,4194304,256,0,0,16,24,17792,0x7ff430cc7a80,0x7ff430424140,16706287436690,16706287446824,16706287625383,16706287627273
|
|
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,170998,170998,4194304,256,0,0,16,24,18496,0x7ff430cc7900,0x7ff430424180,16706287644983,16706287653543,16706287834982,16706287837006
|
|
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,170998,170998,4194304,256,0,0,16,24,19200,0x7ff430cc7780,0x7ff4304241c0,16706287855066,16706287879302,16706287972261,16706287974382
|
|
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,170998,170998,4194304,256,0,0,16,24,19904,0x7ff430cc7600,0x7ff430424200,16706287990771,16706287998981,16706288092420,16706288094438
|
|
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,170998,170998,4194304,256,0,0,12,24,20608,0x7ff43341d480,0x7ff430424240,16706288117107,16706288141860,16706288234820,16706288236903
|
|
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,170998,170998,4194304,256,0,0,16,24,21312,0x7ff43341d300,0x7ff430424280,16706288256943,16706288266980,16706288446498,16706288448496
|
|
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,170998,170998,4194304,256,0,0,16,24,22016,0x7ff43341d180,0x7ff4304242c0,16706288471746,16706288481538,16706288660897,16706288662819
|
|
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,170998,170998,4194304,256,0,0,16,24,22720,0x7ff43341d000,0x7ff430424300,16706288680649,16706288690017,16706288783137,16706288785075
|
|
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,170998,170998,4194304,256,0,0,12,24,23424,0x7ff430cc7e80,0x7ff430424340,16706288802515,16706288812256,16706288905536,16706288907501
|
|
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,170998,170998,4194304,256,0,0,12,24,24128,0x7ff430cc7d00,0x7ff430424380,16706288929271,16706288939616,16706289032575,16706289034517
|
|
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,170998,170998,4194304,256,0,0,16,24,24832,0x7ff430cc7b80,0x7ff4304243c0,16706289053456,16706289061855,16706289241694,16706289243630
|
|
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,170998,170998,4194304,256,0,0,16,24,25536,0x7ff430cc7a00,0x7ff430424400,16706289259920,16706289269374,16706289451133,16706289453023
|
|
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,170998,170998,4194304,256,0,0,12,24,26240,0x7ff430cc7880,0x7ff430424440,16706289467633,16706289476413,16706289569692,16706289571479
|
|
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,170998,170998,4194304,256,0,0,12,24,26944,0x7ff430cc7700,0x7ff430424480,16706289595289,16706289605212,16706289698491,16706289700335
|
|
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,170998,170998,4194304,256,0,0,12,24,27648,0x7ff43341d580,0x7ff4304244c0,16706289721395,16706289732091,16706289823931,16706289825781
|
|
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,170998,170998,4194304,256,0,0,16,24,28608,0x7ff43341d400,0x7ff430424500,16706289846130,16706289872890,16706290051769,16706290053724
|
|
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,170998,170998,4194304,256,0,0,16,24,29312,0x7ff43341d280,0x7ff430424540,16706290067683,16706290076569,16706290254968,16706290256947
|
|
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,170998,170998,4194304,256,0,0,12,24,30016,0x7ff43341d100,0x7ff430424580,16706290273106,16706290282008,16706290373848,16706290375783
|
|
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,170998,170998,4194304,256,0,0,8,24,30976,0x7ff430cc7f80,0x7ff4304245c0,16706290400362,16706290409687,16706290501847,16706290503809
|
|
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,170998,170998,4194304,256,0,0,12,24,31680,0x7ff430cc7e00,0x7ff430424600,16706290525148,16706290535607,16706290628246,16706290630265
|
|
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,170998,170998,4194304,256,0,0,16,24,32640,0x7ff430cc7c80,0x7ff430424640,16706290649694,16706290660886,16706290841685,16706290843528
|
|
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,170998,170998,4194304,256,0,0,12,24,33600,0x7ff430cc7b00,0x7ff430424680,16706290857647,16706290866805,16706291046004,16706291047321
|
|
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,170998,170998,4194304,256,0,0,12,24,34560,0x7ff430cc7980,0x7ff4304246c0,16706291061371,16706291069204,16706291162003,16706291163417
|
|
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,170998,170998,4194304,256,0,0,8,24,35520,0x7ff430cc7800,0x7ff430424700,16706291178017,16706291185843,16706291279442,16706291280783
|
|
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,170998,170998,4194304,256,0,0,12,24,36224,0x7ff430cc7680,0x7ff430424740,16706291301243,16706291311442,16706291404242,16706291405659
|
|
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,170998,170998,4194304,256,0,0,12,24,37184,0x7ff43341d500,0x7ff430424780,16706291420589,16706291428722,16706291608401,16706291609852
|
|
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,170998,170998,4194304,256,0,0,12,24,38144,0x7ff43341d380,0x7ff4304247c0,16706291623942,16706291632720,16706291811439,16706291812846
|
|
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,170998,170998,4194304,256,0,0,12,24,39104,0x7ff43341d200,0x7ff430424800,16706291826925,16706291834799,16706291928239,16706291929782
|
|
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,170998,170998,4194304,256,0,0,8,24,40320,0x7ff43341d080,0x7ff430424840,16706291943822,16706291952079,16706292045998,16706292047478
|
|
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,170998,170998,4194304,256,0,0,12,24,41280,0x7ff430cc7f00,0x7ff430424880,16706292067047,16706292077998,16706292171437,16706292172924
|
|
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,170998,170998,4194304,256,0,0,12,24,42240,0x7ff430cc7d80,0x7ff4304248c0,16706292187814,16706292195597,16706292374796,16706292376437
|
|
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,170998,170998,4194304,256,0,0,12,24,43200,0x7ff430cc7c00,0x7ff430424900,16706292391147,16706292399756,16706292581355,16706292582661
|
|
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,170998,170998,4194304,256,0,0,8,24,44160,0x7ff430cc7a80,0x7ff430424940,16706292596810,16706292605675,16706292699434,16706292700707
|
|
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,170998,170998,4194304,256,0,0,12,24,45376,0x7ff430cc7900,0x7ff430424980,16706292715226,16706292723754,16706292817994,16706292819333
|
|
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,170998,170998,4194304,256,0,0,12,24,46336,0x7ff430cc7780,0x7ff4304249c0,16706292838302,16706292846154,16706292939273,16706292940679
|
|
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,170998,170998,4194304,256,0,0,12,24,47552,0x7ff430cc7600,0x7ff430424a00,16706292956758,16706292965513,16706293144712,16706293146152
|
|
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,170998,170998,4194304,256,0,0,12,24,48512,0x7ff43341d480,0x7ff430424a40,16706293159842,16706293167592,16706293346951,16706293348325
|
|
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,170998,170998,4194304,256,0,0,8,24,49472,0x7ff43341d300,0x7ff430424a80,16706293361915,16706293370471,16706293463590,16706293464892
|
|
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,170998,170998,4194304,256,0,0,12,24,50688,0x7ff43341d180,0x7ff430424ac0,16706293479681,16706293488550,16706293581669,16706293583038
|
|
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,170998,170998,4194304,256,0,0,12,24,51648,0x7ff43341d000,0x7ff430424b00,16706293604837,16706293615269,16706293707269,16706293708834
|
|
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,170998,170998,4194304,256,0,0,12,24,52864,0x7ff430cc7e80,0x7ff430424b40,16706293725643,16706293733029,16706293912388,16706293913747
|
|
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,170998,170998,4194304,256,0,0,12,24,54080,0x7ff430cc7d00,0x7ff430424b80,16706293928756,16706293936547,16706294117506,16706294119240
|
|
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,170998,170998,4194304,256,0,0,8,24,55296,0x7ff430cc7b80,0x7ff430424bc0,16706294133170,16706294140866,16706294235426,16706294236696
|
|
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,170998,170998,4194304,256,0,0,12,24,56768,0x7ff430cc7a00,0x7ff430424c00,16706294251416,16706294259106,16706294354625,16706294356032
|
|
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,170998,170998,4194304,256,0,0,12,24,57728,0x7ff430cc7880,0x7ff430424c40,16706294376812,16706294387585,16706294481504,16706294482938
|
|
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,170998,170998,4194304,256,0,0,12,24,58944,0x7ff430cc7700,0x7ff430424c80,16706294499218,16706294507584,16706294688223,16706294689561
|
|
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,170998,170998,4194304,256,0,0,12,24,60160,0x7ff43341d580,0x7ff430424cc0,16706294704101,16706294712383,16706294894142,16706294895405
|
|
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,170998,170998,4194304,256,0,0,8,24,61376,0x7ff43341d400,0x7ff430424d00,16706294909834,16706294917662,16706295013021,16706295014451
|
|
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,170998,170998,4194304,256,0,0,12,24,62848,0x7ff43341d280,0x7ff430424d40,16706295029290,16706295037181,16706295137021,16706295138607
|
|
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,170998,170998,4194304,256,0,0,12,24,63808,0x7ff43341d100,0x7ff430424d80,16706295157826,16706295169821,16706295263260,16706295264672
|
|
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,170998,170998,4194304,256,0,0,12,24,65024,0x7ff430cc7f80,0x7ff430424dc0,16706295281132,16706295289660,16706295469659,16706295471216
|
|
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,170998,170998,4194304,256,0,0,12,24,66240,0x7ff430cc7e00,0x7ff430424e00,16706295484965,16706295493179,16706295673498,16706295674969
|
|
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,170998,170998,4194304,256,0,0,8,24,67456,0x7ff430cc7c80,0x7ff430424e40,16706295689318,16706295697338,16706295791897,16706295793365
|
|
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,170998,170998,4194304,256,0,0,12,24,68928,0x7ff430cc7b00,0x7ff430424e80,16706295807235,16706295815417,16706295921016,16706295922441
|
|
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,170998,170998,4194304,256,0,0,12,24,70144,0x7ff430cc7980,0x7ff430424ec0,16706295943560,16706295953976,16706296046776,16706296048107
|
|
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,170998,170998,4194304,256,0,0,12,24,71616,0x7ff430cc7800,0x7ff430424f00,16706296064306,16706296071895,16706296251894,16706296253340
|
|
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,170998,170998,4194304,256,0,0,12,24,72832,0x7ff430cc7680,0x7ff430424f40,16706296269719,16706296280214,16706296459893,16706296461203
|
|
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,170998,170998,4194304,256,0,0,8,24,74048,0x7ff43341d500,0x7ff430424f80,16706296476673,16706296484213,16706296577493,16706296578839
|
|
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,170998,170998,4194304,256,0,0,12,24,75776,0x7ff43341d380,0x7ff430424fc0,16706296594579,16706296602292,16706296708372,16706296709695
|
|
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,170998,170998,4194304,256,0,0,12,24,76992,0x7ff43341d200,0x7ff430425000,16706296730984,16706296741652,16706296835251,16706296836661
|
|
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,170998,170998,4194304,256,0,0,12,24,78464,0x7ff43341d080,0x7ff430425040,16706296852800,16706296860851,16706297041010,16706297042454
|
|
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,170998,170998,4194304,256,0,0,12,24,79936,0x7ff430cc7f00,0x7ff430425080,16706297059643,16706297067570,16706297247889,16706297249287
|
|
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,170998,170998,4194304,256,0,0,8,24,81408,0x7ff430cc7d80,0x7ff4304250c0,16706297265017,16706297272849,16706297367408,16706297368833
|
|
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,170998,170998,4194304,256,0,0,12,24,83136,0x7ff430cc7c00,0x7ff430425100,16706297382933,16706297391248,16706297506767,16706297508109
|
|
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,170998,170998,4194304,256,0,0,12,24,84352,0x7ff430cc7a80,0x7ff430425140,16706297541508,16706297551567,16706297645327,16706297646774
|
|
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,170998,170998,4194304,256,0,0,12,24,85824,0x7ff430cc7900,0x7ff430425180,16706297661524,16706297669486,16706297849485,16706297850807
|
|
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,170998,170998,4194304,256,0,0,12,24,87296,0x7ff430cc7780,0x7ff4304251c0,16706297864837,16706297872685,16706298053804,16706298055481
|
|
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,170998,170998,4194304,256,0,0,12,24,88768,0x7ff430cc7600,0x7ff430425200,16706298069420,16706298077644,16706298172684,16706298174257
|
|
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,170998,170998,4194304,256,0,0,12,24,90752,0x7ff43341d480,0x7ff430425240,16706298188156,16706298196683,16706298316523,16706298318022
|
|
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,170998,170998,4194304,256,0,0,12,24,91968,0x7ff43341d300,0x7ff430425280,16706298337051,16706298348843,16706298442922,16706298444358
|
|
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,170998,170998,4194304,256,0,0,12,24,93440,0x7ff43341d180,0x7ff4304252c0,16706298459777,16706298467722,16706298646281,16706298647971
|
|
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,170998,170998,4194304,256,0,0,12,24,94912,0x7ff43341d000,0x7ff430425300,16706298663101,16706298670601,16706298851080,16706298852585
|
|
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,170998,170998,4194304,256,0,0,12,24,96384,0x7ff430cc7e80,0x7ff430425340,16706298868604,16706298876680,16706298972039,16706298973641
|
|
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,170998,170998,4194304,256,0,0,12,24,98368,0x7ff430cc7d00,0x7ff430425380,16706298988540,16706298996839,16706299123398,16706299125026
|
|
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,170998,170998,4194304,256,0,0,12,24,99584,0x7ff430cc7b80,0x7ff4304253c0,16706299144575,16706299155238,16706299249637,16706299251181
|
|
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,170998,170998,4194304,256,0,0,12,24,101312,0x7ff430cc7a00,0x7ff430425400,16706299265701,16706299274117,16706299453636,16706299454935
|
|
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,170998,170998,4194304,256,0,0,12,24,102784,0x7ff430cc7880,0x7ff430425440,16706299469514,16706299477316,16706299658275,16706299659728
|
|
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,170998,170998,4194304,256,0,0,12,24,104256,0x7ff430cc7700,0x7ff430425480,16706299674038,16706299681795,16706299776034,16706299777544
|
|
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,170998,170998,4194304,256,0,0,12,24,106240,0x7ff43341d580,0x7ff4304254c0,16706299790844,16706299798914,16706299929474,16706299930949
|
|
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,170998,170998,4194304,256,0,0,12,24,107712,0x7ff43341d400,0x7ff430425500,16706299952378,16706299962433,16706300055553,16706300057065
|
|
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,170998,170998,4194304,256,0,0,16,24,109440,0x7ff43341d280,0x7ff430425540,16706300072224,16706300080193,16706300259712,16706300261208
|
|
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,170998,170998,4194304,256,0,0,16,24,111168,0x7ff43341d100,0x7ff430425580,16706300276558,16706300284832,16706300464511,16706300465862
|
|
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,170998,170998,4194304,256,0,0,8,24,112896,0x7ff430cc7f80,0x7ff4304255c0,16706300480181,16706300488670,16706300583390,16706300584858
|
|
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,170998,170998,4194304,256,0,0,12,24,115136,0x7ff430cc7e00,0x7ff430425600,16706300598697,16706300606590,16706300744509,16706300745922
|
|
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,170998,170998,4194304,256,0,0,12,24,116608,0x7ff430cc7c80,0x7ff430425640,16706300765682,16706300776829,16706300871868,16706300873148
|
|
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,170998,170998,4194304,256,0,0,16,24,118336,0x7ff430cc7b00,0x7ff430425680,16706300887288,16706300895228,16706301074267,16706301075601
|
|
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,170998,170998,4194304,256,0,0,16,24,120064,0x7ff430cc7980,0x7ff4304256c0,16706301089221,16706301098107,16706301276986,16706301278365
|
|
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,170998,170998,4194304,256,0,0,12,24,121792,0x7ff430cc7800,0x7ff430425700,16706301295174,16706301303226,16706301399865,16706301401191
|
|
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,170998,170998,4194304,256,0,0,12,24,124032,0x7ff430cc7680,0x7ff430425740,16706301415910,16706301424185,16706301569784,16706301571085
|
|
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,170998,170998,4194304,256,0,0,12,24,125504,0x7ff43341d500,0x7ff430425780,16706301590975,16706301601784,16706301696344,16706301697651
|
|
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,170998,170998,4194304,256,0,0,12,24,127488,0x7ff43341d380,0x7ff4304257c0,16706301714111,16706301721943,16706301902102,16706301903464
|
|
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,170998,170998,4194304,256,0,0,12,24,129216,0x7ff43341d200,0x7ff430425800,16706301918954,16706301926902,16706302105781,16706302107168
|
|
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,170998,170998,4194304,256,0,0,12,24,130944,0x7ff43341d080,0x7ff430425840,16706302121697,16706302130101,16706302230101,16706302231464
|
|
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,170998,170998,4194304,256,0,0,12,24,133440,0x7ff430cc7f00,0x7ff430425880,16706302246763,16706302254580,16706302409620,16706302410918
|
|
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,170998,170998,4194304,256,0,0,12,24,134912,0x7ff430cc7d80,0x7ff4304258c0,16706302431567,16706302442099,16706302536979,16706302538424
|
|
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,170998,170998,4194304,256,0,0,12,24,136896,0x7ff430cc7c00,0x7ff430425900,16706302552503,16706302560339,16706302739698,16706302741157
|
|
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,170998,170998,4194304,256,0,0,12,24,138880,0x7ff430cc7a80,0x7ff430425940,16706302755816,16706302763538,16706302946417,16706302947950
|
|
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,170998,170998,4194304,256,0,0,12,24,140864,0x7ff430cc7900,0x7ff430425980,16706302961220,16706302969296,16706303076016,16706303077596
|
|
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,170998,170998,4194304,256,0,0,12,24,143616,0x7ff430cc7780,0x7ff4304259c0,16706303091015,16706303099056,16706303269615,16706303271140
|
|
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,170998,170998,4194304,256,0,0,12,24,145344,0x7ff430cc7600,0x7ff430425a00,16706303290869,16706303301935,16706303397294,16706303398925
|
|
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,170998,170998,4194304,256,0,0,12,24,147584,0x7ff43341d480,0x7ff430425a40,16706303413515,16706303421294,16706303601453,16706303603039
|
|
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,170998,170998,4194304,256,0,0,12,24,149568,0x7ff43341d300,0x7ff430425a80,16706303616248,16706303623693,16706303803212,16706303804522
|
|
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,170998,170998,4194304,256,0,0,12,24,151552,0x7ff43341d180,0x7ff430425ac0,16706303818212,16706303826092,16706303936491,16706303937768
|
|
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,170998,170998,4194304,256,0,0,12,24,154304,0x7ff43341d000,0x7ff430425b00,16706303951917,16706303959531,16706304140170,16706304141721
|
|
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,170998,170998,4194304,256,0,0,12,24,156288,0x7ff430cc7e80,0x7ff430425b40,16706304162040,16706304172330,16706304273609,16706304274847
|
|
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,170998,170998,4194304,256,0,0,12,24,158784,0x7ff430cc7d00,0x7ff430425b80,16706304289226,16706304297929,16706304483688,16706304485090
|
|
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,170998,170998,4194304,256,0,0,12,24,161024,0x7ff430cc7b80,0x7ff430425bc0,16706304498829,16706304506888,16706304691047,16706304692493
|
|
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,170998,170998,4194304,256,0,0,12,24,163264,0x7ff430cc7a00,0x7ff430425c00,16706304706363,16706304714247,16706304836326,16706304837618
|
|
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,170998,170998,4194304,256,0,0,12,24,166528,0x7ff430cc7880,0x7ff430425c40,16706304852268,16706304860486,16706305066725,16706305087700
|
|
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,170998,170998,4194304,256,0,0,12,24,168512,0x7ff430cc7700,0x7ff430425c80,16706305102010,16706305112804,16706305224484,16706305225926
|
|
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,170998,170998,4194304,256,0,0,12,24,171264,0x7ff43341d580,0x7ff430425cc0,16706305242865,16706305251684,16706305436002,16706305437289
|
|
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,170998,170998,4194304,256,0,0,12,24,173760,0x7ff43341d400,0x7ff430425d00,16706305451378,16706305459522,16706305646401,16706305647692
|
|
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,170998,170998,4194304,256,0,0,12,24,176256,0x7ff43341d280,0x7ff430425d40,16706305661651,16706305671361,16706305805760,16706305807027
|
|
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,170998,170998,4194304,256,0,0,12,24,179776,0x7ff43341d100,0x7ff430425d80,16706305822606,16706305831040,16706306062879,16706306082588
|
|
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,170998,170998,4194304,256,0,0,12,24,182272,0x7ff430cc7f80,0x7ff430425dc0,16706306100197,16706306110879,16706306237118,16706306238723
|
|
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,170998,170998,4194304,256,0,0,12,24,185536,0x7ff430cc7e00,0x7ff430425e00,16706306253122,16706306260958,16706306451517,16706306453055
|
|
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,170998,170998,4194304,256,0,0,12,24,188544,0x7ff430cc7c80,0x7ff430425e40,16706306467405,16706306475357,16706306669596,16706306671158
|
|
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,170998,170998,4194304,256,0,0,12,24,191552,0x7ff430cc7b00,0x7ff430425e80,16706306684838,16706306692635,16706306852474,16706306854012
|
|
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,170998,170998,4194304,256,0,0,12,24,195840,0x7ff430cc7980,0x7ff430425ec0,16706306867842,16706306875674,16706307158553,16706307201851
|
|
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,170998,170998,4194304,256,0,0,12,24,198592,0x7ff430cc7800,0x7ff430425f00,16706307216370,16706307227032,16706307377112,16706307378545
|
|
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,170998,170998,4194304,256,0,0,12,24,202368,0x7ff430cc7680,0x7ff430425f40,16706307394335,16706307402071,16706307608310,16706307651826
|
|
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,170998,170998,4194304,256,0,0,12,24,205888,0x7ff43341d500,0x7ff430425f80,16706307662056,16706307672150,16706307879349,16706307919257
|
|
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,170998,170998,4194304,256,0,0,12,24,209408,0x7ff43341d380,0x7ff430425fc0,16706307928107,16706307937908,16706308123187,16706308124601
|
|
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,170998,170998,4194304,256,0,0,12,24,214464,0x7ff43341d200,0x7ff430426000,16706308140830,16706308148467,16706308482865,16706308522837
|
|
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,170998,170998,4194304,256,0,0,12,24,217728,0x7ff43341d080,0x7ff430426040,16706308539187,16706308549905,16706308717744,16706308719141
|
|
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,170998,170998,4194304,256,0,0,12,24,222016,0x7ff430cc7f00,0x7ff430426080,16706308734611,16706308742544,16706308971343,16706309011291
|
|
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,170998,170998,4194304,256,0,0,12,24,226048,0x7ff430cc7d80,0x7ff4304260c0,16706309019221,16706309029422,16706309258701,16706309274863
|
|
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,170998,170998,4194304,256,0,0,12,24,230080,0x7ff430cc7c00,0x7ff430426100,16706309284362,16706309294381,16706309505419,16706309521445
|
|
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,170998,170998,4194304,256,0,0,12,24,235904,0x7ff430cc7a80,0x7ff430426140,16706309531034,16706309540139,16706309925577,16706309941321
|
|
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,170998,170998,4194304,256,0,0,12,24,239424,0x7ff430cc7900,0x7ff430426180,16706309957230,16706309967497,16706310153736,16706310155054
|
|
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,170998,170998,4194304,256,0,0,12,24,244224,0x7ff430cc7780,0x7ff4304261c0,16706310171603,16706310179176,16706310428294,16706310471053
|
|
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,170998,170998,4194304,256,0,0,12,24,248768,0x7ff430cc7600,0x7ff430426200,16706310479493,16706310489574,16706310737573,16706310780853
|
|
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,170998,170998,4194304,256,0,0,12,24,253312,0x7ff43341d480,0x7ff430426240,16706310788993,16706310799492,16706311035971,16706311079074
|
|
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,170998,170998,4194304,256,0,0,8,24,255552,0x7ff43341d300,0x7ff430426280,16706311086803,16706311097251,16706311550208,16706311593287
|
|
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,170998,170998,4194304,256,0,0,12,24,259840,0x7ff43341d180,0x7ff4304262c0,16706311608306,16706311619168,16706311844926,16706311887947
|
|
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,170998,170998,4194304,256,0,0,12,24,265664,0x7ff43341d000,0x7ff430426300,16706311896657,16706311906686,16706312205404,16706312245105
|
|
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,170998,170998,4194304,256,0,0,12,24,271232,0x7ff430cc7e80,0x7ff430426340,16706312254365,16706312263964,16706312561722,16706312584544
|
|
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,170998,170998,4194304,256,0,0,8,24,273216,0x7ff430cc7d00,0x7ff430426380,16706312592134,16706312602522,16706312898840,16706312920803
|
|
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,170998,170998,4194304,256,0,0,8,24,275712,0x7ff430cc7b80,0x7ff4304263c0,16706312928713,16706312938840,16706313494677,16706313510184
|
|
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,170998,170998,4194304,256,0,0,12,24,280768,0x7ff430cc7a00,0x7ff430426400,16706313525753,16706313536437,16706313800115,16706313818593
|
|
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,170998,170998,4194304,256,0,0,12,24,287616,0x7ff430cc7880,0x7ff430426440,16706313827713,16706313838035,16706314188913,16706314235210
|
|
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,170998,170998,4194304,256,0,0,12,24,294208,0x7ff430cc7700,0x7ff430426480,16706314243200,16706314258513,16706314609231,16706314654626
|
|
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,170998,170998,4194304,256,0,0,8,24,296960,0x7ff43341d580,0x7ff4304264c0,16706314663796,16706314673710,16706315021068,16706315064113
|
|
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,170998,170998,4194304,256,0,0,8,24,299968,0x7ff43341d400,0x7ff430426500,16706315072982,16706315082828,16706315744584,16706315787649
|
|
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,170998,170998,4194304,256,0,0,8,24,302720,0x7ff43341d280,0x7ff430426540,16706315803878,16706315814024,16706316261861,16706316304762
|
|
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,170998,170998,4194304,256,0,0,12,24,305472,0x7ff43341d100,0x7ff430426580,16706316312962,16706316322981,16706316787298,16706316830045
|
|
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,170998,170998,4194304,256,0,0,12,24,308224,0x7ff430cc7f80,0x7ff4304265c0,16706316839274,16706316849218,16706317310015,16706317354197
|
|
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,170998,170998,4194304,256,0,0,8,24,310976,0x7ff430cc7e00,0x7ff430426600,16706317363367,16706317373375,16706317825052,16706317842391
|
|
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,170998,170998,4194304,256,0,0,8,24,313216,0x7ff430cc7c80,0x7ff430426640,16706317851371,16706317861372,16706318730167,16706318780160
|
|
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,170998,170998,4194304,256,0,0,8,24,315968,0x7ff430cc7b00,0x7ff430426680,16706318796280,16706318807127,16706319659922,16706319708390
|
|
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,170998,170998,4194304,256,0,0,12,24,318720,0x7ff430cc7980,0x7ff4304266c0,16706319717370,16706319727282,16706320612397,16706320657499
|
|
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,170998,170998,4194304,256,0,0,12,24,321472,0x7ff430cc7800,0x7ff430426700,16706320669018,16706320685036,16706321564391,16706321609548
|
|
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,170998,170998,4194304,256,0,0,8,24,324224,0x7ff430cc7680,0x7ff430426740,16706321618917,16706321634951,16706322493666,16706322544467
|
|
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,170998,170998,4194304,256,0,0,8,24,326464,0x7ff43341d500,0x7ff430426780,16706322553687,16706322565026,16706324263096,16706324337288
|
|
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,170998,170998,4194304,256,0,0,8,24,329216,0x7ff43341d380,0x7ff4304267c0,16706324353068,16706324363736,16706326027406,16706326111670
|
|
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,170998,170998,4194304,256,0,0,12,24,331968,0x7ff43341d200,0x7ff430426800,16706326120790,16706326130926,16706327855396,16706327922961
|
|
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,170998,170998,4194304,256,0,0,12,24,334720,0x7ff43341d080,0x7ff430426840,16706327931830,16706327942595,16706329658106,16706329725062
|
|
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,170998,170998,4194304,256,0,0,8,24,337472,0x7ff430cc7f00,0x7ff430426880,16706329736971,16706329752345,16706331425456,16706331497983
|
|
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,170998,170998,4194304,256,0,0,8,24,0,0x7ff430cc7d80,0x7ff4304268c0,16706331506723,16706331518735,16706334875996,16706334955330
|