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",0,0,0,183519,183519,33554432,256,0,0,4,32,4160,0x0,0x7f4af2404280,16925492322133,16925492349123,16925492592483,16925492682502
|
|
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,183519,183519,32768,256,0,0,12,24,13888,0x0,0x7f4af2423f80,16925497366713,16925497381908,16925497395028,16925497413372
|
|
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,183519,183519,4194304,256,0,0,12,24,14336,0x7f4af5424380,0x7f4af2423fc0,16925497417351,16925497462068,16925497554548,16925497556747
|
|
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,183519,183519,4194304,256,0,0,16,24,15040,0x7f4af5424200,0x7f4af2424000,16925497578237,16925497588308,16925497767667,16925497769831
|
|
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,183519,183519,4194304,256,0,0,16,24,15488,0x7f4af5424080,0x7f4af2424040,16925497785421,16925497794067,16925497974227,16925497976375
|
|
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,183519,183519,4194304,256,0,0,12,24,15936,0x7f4af2ccdf00,0x7f4af2424080,16925497992194,16925498000307,16925498093746,16925498095751
|
|
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,183519,183519,4194304,256,0,0,12,24,16384,0x7f4af2ccdd80,0x7f4af24240c0,16925498112591,16925498120466,16925498212626,16925498214858
|
|
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,183519,183519,4194304,256,0,0,12,24,17088,0x7f4af2ccdc00,0x7f4af2424100,16925498242587,16925498253426,16925498345746,16925498347734
|
|
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,183519,183519,4194304,256,0,0,16,24,17792,0x7f4af2ccda80,0x7f4af2424140,16925498368613,16925498386226,16925498565105,16925498567227
|
|
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,183519,183519,4194304,256,0,0,16,24,18496,0x7f4af2ccd900,0x7f4af2424180,16925498587597,16925498598545,16925498778225,16925498780351
|
|
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,183519,183519,4194304,256,0,0,16,24,19200,0x7f4af2ccd780,0x7f4af24241c0,16925498797201,16925498805744,16925498898864,16925498900967
|
|
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,183519,183519,4194304,256,0,0,16,24,19904,0x7f4af2ccd600,0x7f4af2424200,16925498920167,16925498931184,16925499024304,16925499026274
|
|
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,183519,183519,4194304,256,0,0,12,24,20608,0x7f4af5424480,0x7f4af2424240,16925499049973,16925499073744,16925499167023,16925499169119
|
|
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,183519,183519,4194304,256,0,0,16,24,21312,0x7f4af5424300,0x7f4af2424280,16925499189409,16925499199503,16925499378543,16925499380643
|
|
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,183519,183519,4194304,256,0,0,16,24,22016,0x7f4af5424180,0x7f4af24242c0,16925499394163,16925499403663,16925499583342,16925499585357
|
|
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,183519,183519,4194304,256,0,0,16,24,22720,0x7f4af5424000,0x7f4af2424300,16925499602497,16925499611662,16925499704622,16925499706834
|
|
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,183519,183519,4194304,256,0,0,12,24,23424,0x7f4af2ccde80,0x7f4af2424340,16925499721743,16925499731822,16925499825102,16925499827100
|
|
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,183519,183519,4194304,256,0,0,12,24,24128,0x7f4af2ccdd00,0x7f4af2424380,16925499848749,16925499859182,16925499952461,16925499954396
|
|
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,183519,183519,4194304,256,0,0,16,24,24832,0x7f4af2ccdb80,0x7f4af24243c0,16925499974526,16925499997901,16925500177901,16925500179959
|
|
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,183519,183519,4194304,256,0,0,16,24,25536,0x7f4af2ccda00,0x7f4af2424400,16925500201109,16925500210381,16925500391820,16925500393873
|
|
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,183519,183519,4194304,256,0,0,12,24,26240,0x7f4af2ccd880,0x7f4af2424440,16925500409973,16925500418860,16925500512140,16925500514150
|
|
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,183519,183519,4194304,256,0,0,12,24,26944,0x7f4af2ccd700,0x7f4af2424480,16925500533209,16925500543980,16925500637739,16925500639926
|
|
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,183519,183519,4194304,256,0,0,12,24,27648,0x7f4af5424580,0x7f4af24244c0,16925500660615,16925500671339,16925500763499,16925500765522
|
|
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,183519,183519,4194304,256,0,0,16,24,28608,0x7f4af5424400,0x7f4af2424500,16925500784382,16925500793259,16925500972458,16925500974536
|
|
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,183519,183519,4194304,256,0,0,16,24,29312,0x7f4af5424280,0x7f4af2424540,16925500989035,16925500998538,16925501177738,16925501179790
|
|
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,183519,183519,4194304,256,0,0,12,24,30016,0x7f4af5424100,0x7f4af2424580,16925501200839,16925501210698,16925501302698,16925501304716
|
|
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,183519,183519,4194304,256,0,0,8,24,30976,0x7f4af2ccdf80,0x7f4af24245c0,16925501322736,16925501350537,16925501442857,16925501444932
|
|
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,183519,183519,4194304,256,0,0,12,24,31680,0x7f4af2ccde00,0x7f4af2424600,16925501467321,16925501477897,16925501571017,16925501573018
|
|
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,183519,183519,4194304,256,0,0,16,24,32640,0x7f4af2ccdc80,0x7f4af2424640,16925501590618,16925501602537,16925501782216,16925501784352
|
|
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,183519,183519,4194304,256,0,0,12,24,33600,0x7f4af2ccdb00,0x7f4af2424680,16925501804301,16925501822056,16925502002696,16925502004855
|
|
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,183519,183519,4194304,256,0,0,12,24,34560,0x7f4af2ccd980,0x7f4af24246c0,16925502023365,16925502032136,16925502126055,16925502128052
|
|
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,183519,183519,4194304,256,0,0,8,24,35520,0x7f4af2ccd800,0x7f4af2424700,16925502142471,16925502151815,16925502246055,16925502248078
|
|
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,183519,183519,4194304,256,0,0,12,24,36224,0x7f4af2ccd680,0x7f4af2424740,16925502270277,16925502279495,16925502372775,16925502374494
|
|
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,183519,183519,4194304,256,0,0,12,24,37184,0x7f4af5424500,0x7f4af2424780,16925502390174,16925502399015,16925502578854,16925502580548
|
|
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,183519,183519,4194304,256,0,0,12,24,38144,0x7f4af5424380,0x7f4af24247c0,16925502594748,16925502603654,16925502785413,16925502787122
|
|
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,183519,183519,4194304,256,0,0,12,24,39104,0x7f4af5424200,0x7f4af2424800,16925502801872,16925502809893,16925502903013,16925502904669
|
|
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,183519,183519,4194304,256,0,0,8,24,40320,0x7f4af5424080,0x7f4af2424840,16925502917788,16925502925893,16925503019653,16925503021155
|
|
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,183519,183519,4194304,256,0,0,12,24,41280,0x7f4af2ccdf00,0x7f4af2424880,16925503042065,16925503052293,16925503145412,16925503147091
|
|
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,183519,183519,4194304,256,0,0,12,24,42240,0x7f4af2ccdd80,0x7f4af24248c0,16925503163331,16925503171012,16925503351172,16925503352765
|
|
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,183519,183519,4194304,256,0,0,12,24,43200,0x7f4af2ccdc00,0x7f4af2424900,16925503369785,16925503377572,16925503556771,16925503558329
|
|
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,183519,183519,4194304,256,0,0,8,24,44160,0x7f4af2ccda80,0x7f4af2424940,16925503576209,16925503585251,16925503678371,16925503679986
|
|
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,183519,183519,4194304,256,0,0,12,24,45376,0x7f4af2ccd900,0x7f4af2424980,16925503695235,16925503703811,16925503798211,16925503799812
|
|
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,183519,183519,4194304,256,0,0,12,24,46336,0x7f4af2ccd780,0x7f4af24249c0,16925503818711,16925503826691,16925503919330,16925503920828
|
|
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,183519,183519,4194304,256,0,0,12,24,47552,0x7f4af2ccd600,0x7f4af2424a00,16925503936348,16925503944610,16925504122690,16925504124122
|
|
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,183519,183519,4194304,256,0,0,12,24,48512,0x7f4af5424480,0x7f4af2424a40,16925504138702,16925504147330,16925504326689,16925504328186
|
|
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,183519,183519,4194304,256,0,0,8,24,49472,0x7f4af5424300,0x7f4af2424a80,16925504343206,16925504351329,16925504444609,16925504446083
|
|
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,183519,183519,4194304,256,0,0,12,24,50688,0x7f4af5424180,0x7f4af2424ac0,16925504461282,16925504470369,16925504563648,16925504565089
|
|
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,183519,183519,4194304,256,0,0,12,24,51648,0x7f4af5424000,0x7f4af2424b00,16925504585279,16925504595648,16925504687648,16925504689166
|
|
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,183519,183519,4194304,256,0,0,12,24,52864,0x7f4af2ccde80,0x7f4af2424b40,16925504704875,16925504712928,16925504891808,16925504893320
|
|
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,183519,183519,4194304,256,0,0,12,24,54080,0x7f4af2ccdd00,0x7f4af2424b80,16925504907439,16925504916128,16925505096447,16925505097883
|
|
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,183519,183519,4194304,256,0,0,8,24,55296,0x7f4af2ccdb80,0x7f4af2424bc0,16925505112033,16925505121087,16925505215007,16925505216490
|
|
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,183519,183519,4194304,256,0,0,12,24,56768,0x7f4af2ccda00,0x7f4af2424c00,16925505230630,16925505241087,16925505336286,16925505337736
|
|
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,183519,183519,4194304,256,0,0,12,24,57728,0x7f4af2ccd880,0x7f4af2424c40,16925505359726,16925505370526,16925505463486,16925505465053
|
|
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,183519,183519,4194304,256,0,0,12,24,58944,0x7f4af2ccd700,0x7f4af2424c80,16925505480832,16925505488926,16925505669405,16925505670796
|
|
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,183519,183519,4194304,256,0,0,12,24,60160,0x7f4af5424580,0x7f4af2424cc0,16925505685556,16925505693725,16925505873085,16925505874610
|
|
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,183519,183519,4194304,256,0,0,8,24,61376,0x7f4af5424400,0x7f4af2424d00,16925505890960,16925505899485,16925505994365,16925505995927
|
|
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,183519,183519,4194304,256,0,0,12,24,62848,0x7f4af5424280,0x7f4af2424d40,16925506013206,16925506021724,16925506120124,16925506121763
|
|
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,183519,183519,4194304,256,0,0,12,24,63808,0x7f4af5424100,0x7f4af2424d80,16925506142622,16925506152924,16925506247004,16925506248549
|
|
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,183519,183519,4194304,256,0,0,12,24,65024,0x7f4af2ccdf80,0x7f4af2424dc0,16925506268529,16925506279004,16925506458203,16925506459753
|
|
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,183519,183519,4194304,256,0,0,12,24,66240,0x7f4af2ccde00,0x7f4af2424e00,16925506475113,16925506483163,16925506663803,16925506665297
|
|
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,183519,183519,4194304,256,0,0,8,24,67456,0x7f4af2ccdc80,0x7f4af2424e40,16925506679837,16925506687643,16925506782202,16925506783683
|
|
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,183519,183519,4194304,256,0,0,12,24,68928,0x7f4af2ccdb00,0x7f4af2424e80,16925506798213,16925506806682,16925506910682,16925506912220
|
|
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,183519,183519,4194304,256,0,0,12,24,70144,0x7f4af2ccd980,0x7f4af2424ec0,16925506933669,16925506943962,16925507036442,16925507037916
|
|
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,183519,183519,4194304,256,0,0,12,24,71616,0x7f4af2ccd800,0x7f4af2424f00,16925507052415,16925507060762,16925507240441,16925507241950
|
|
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,183519,183519,4194304,256,0,0,12,24,72832,0x7f4af2ccd680,0x7f4af2424f40,16925507258369,16925507267001,16925507448280,16925507449784
|
|
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,183519,183519,4194304,256,0,0,8,24,74048,0x7f4af5424500,0x7f4af2424f80,16925507465873,16925507474520,16925507567960,16925507569410
|
|
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,183519,183519,4194304,256,0,0,12,24,75776,0x7f4af5424380,0x7f4af2424fc0,16925507585650,16925507593720,16925507700440,16925507701906
|
|
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,183519,183519,4194304,256,0,0,12,24,76992,0x7f4af5424200,0x7f4af2425000,16925507721936,16925507732760,16925507826839,16925507828362
|
|
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,183519,183519,4194304,256,0,0,12,24,78464,0x7f4af5424080,0x7f4af2425040,16925507844182,16925507852599,16925508032119,16925508033626
|
|
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,183519,183519,4194304,256,0,0,12,24,79936,0x7f4af2ccdf00,0x7f4af2425080,16925508048326,16925508056439,16925508236598,16925508238140
|
|
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,183519,183519,4194304,256,0,0,8,24,81408,0x7f4af2ccdd80,0x7f4af24250c0,16925508252630,16925508261238,16925508356278,16925508357757
|
|
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,183519,183519,4194304,256,0,0,12,24,83136,0x7f4af2ccdc00,0x7f4af2425100,16925508372806,16925508380918,16925508495958,16925508497523
|
|
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,183519,183519,4194304,256,0,0,12,24,84352,0x7f4af2ccda80,0x7f4af2425140,16925508534421,16925508543797,16925508637877,16925508639348
|
|
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,183519,183519,4194304,256,0,0,12,24,85824,0x7f4af2ccd900,0x7f4af2425180,16925508655478,16925508663477,16925508843637,16925508845422
|
|
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,183519,183519,4194304,256,0,0,12,24,87296,0x7f4af2ccd780,0x7f4af24251c0,16925508860012,16925508868117,16925509047796,16925509049346
|
|
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,183519,183519,4194304,256,0,0,12,24,88768,0x7f4af2ccd600,0x7f4af2425200,16925509065506,16925509074036,16925509169076,16925509170473
|
|
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,183519,183519,4194304,256,0,0,12,24,90752,0x7f4af5424480,0x7f4af2425240,16925509184542,16925509193396,16925509313075,16925509314618
|
|
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,183519,183519,4194304,256,0,0,12,24,91968,0x7f4af5424300,0x7f4af2425280,16925509336758,16925509347155,16925509440595,16925509442175
|
|
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,183519,183519,4194304,256,0,0,12,24,93440,0x7f4af5424180,0x7f4af24252c0,16925509457934,16925509465875,16925509645234,16925509646748
|
|
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,183519,183519,4194304,256,0,0,12,24,94912,0x7f4af5424000,0x7f4af2425300,16925509662738,16925509670674,16925509850034,16925509851512
|
|
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,183519,183519,4194304,256,0,0,12,24,96384,0x7f4af2ccde80,0x7f4af2425340,16925509868452,16925509876434,16925509971953,16925509973479
|
|
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,183519,183519,4194304,256,0,0,12,24,98368,0x7f4af2ccdd00,0x7f4af2425380,16925509989868,16925509998193,16925510124433,16925510126044
|
|
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,183519,183519,4194304,256,0,0,12,24,99584,0x7f4af2ccdb80,0x7f4af24253c0,16925510148334,16925510158673,16925510252753,16925510254300
|
|
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,183519,183519,4194304,256,0,0,12,24,101312,0x7f4af2ccda00,0x7f4af2425400,16925510269980,16925510278513,16925510458672,16925510460174
|
|
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,183519,183519,4194304,256,0,0,12,24,102784,0x7f4af2ccd880,0x7f4af2425440,16925510475724,16925510483792,16925510664432,16925510665908
|
|
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,183519,183519,4194304,256,0,0,12,24,104256,0x7f4af2ccd700,0x7f4af2425480,16925510682168,16925510690991,16925510785231,16925510786715
|
|
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,183519,183519,4194304,256,0,0,12,24,106240,0x7f4af5424580,0x7f4af24254c0,16925510801104,16925510809551,16925510939791,16925510941260
|
|
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,183519,183519,4194304,256,0,0,12,24,107712,0x7f4af5424400,0x7f4af2425500,16925510961879,16925510971791,16925511064750,16925511066256
|
|
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,183519,183519,4194304,256,0,0,16,24,109440,0x7f4af5424280,0x7f4af2425540,16925511082716,16925511091630,16925511270990,16925511272500
|
|
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,183519,183519,4194304,256,0,0,16,24,111168,0x7f4af5424100,0x7f4af2425580,16925511287090,16925511295310,16925511474829,16925511476294
|
|
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,183519,183519,4194304,256,0,0,8,24,112896,0x7f4af2ccdf80,0x7f4af24255c0,16925511491514,16925511499949,16925511595629,16925511597081
|
|
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,183519,183519,4194304,256,0,0,12,24,115136,0x7f4af2ccde00,0x7f4af2425600,16925511612690,16925511620909,16925511758509,16925511760006
|
|
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,183519,183519,4194304,256,0,0,12,24,116608,0x7f4af2ccdc80,0x7f4af2425640,16925511780425,16925511790988,16925511885708,16925511887262
|
|
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,183519,183519,4194304,256,0,0,16,24,118336,0x7f4af2ccdb00,0x7f4af2425680,16925511901822,16925511910028,16925512090348,16925512091876
|
|
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,183519,183519,4194304,256,0,0,16,24,120064,0x7f4af2ccd980,0x7f4af24256c0,16925512106345,16925512115468,16925512296267,16925512297840
|
|
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,183519,183519,4194304,256,0,0,12,24,121792,0x7f4af2ccd800,0x7f4af2425700,16925512312919,16925512320747,16925512416427,16925512417966
|
|
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,183519,183519,4194304,256,0,0,12,24,124032,0x7f4af2ccd680,0x7f4af2425740,16925512433176,16925512441387,16925512586026,16925512587541
|
|
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,183519,183519,4194304,256,0,0,12,24,125504,0x7f4af5424500,0x7f4af2425780,16925512607311,16925512617866,16925512713066,16925512714497
|
|
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,183519,183519,4194304,256,0,0,12,24,127488,0x7f4af5424380,0x7f4af24257c0,16925512729087,16925512737226,16925512916585,16925512918141
|
|
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,183519,183519,4194304,256,0,0,12,24,129216,0x7f4af5424200,0x7f4af2425800,16925512932111,16925512940265,16925513120745,16925513122205
|
|
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,183519,183519,4194304,256,0,0,12,24,130944,0x7f4af5424080,0x7f4af2425840,16925513136295,16925513148105,16925513248264,16925513249771
|
|
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,183519,183519,4194304,256,0,0,12,24,133440,0x7f4af2ccdf00,0x7f4af2425880,16925513264491,16925513272584,16925513427944,16925513429436
|
|
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,183519,183519,4194304,256,0,0,12,24,134912,0x7f4af2ccdd80,0x7f4af24258c0,16925513449836,16925513460264,16925513554664,16925513556162
|
|
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,183519,183519,4194304,256,0,0,12,24,136896,0x7f4af2ccdc00,0x7f4af2425900,16925513571912,16925513580103,16925513759303,16925513760896
|
|
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,183519,183519,4194304,256,0,0,12,24,138880,0x7f4af2ccda80,0x7f4af2425940,16925513778956,16925513786343,16925513968582,16925513970200
|
|
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,183519,183519,4194304,256,0,0,12,24,140864,0x7f4af2ccd900,0x7f4af2425980,16925513987190,16925513994982,16925514102182,16925514103766
|
|
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,183519,183519,4194304,256,0,0,12,24,143616,0x7f4af2ccd780,0x7f4af24259c0,16925514118276,16925514127142,16925514296581,16925514298110
|
|
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,183519,183519,4194304,256,0,0,12,24,145344,0x7f4af2ccd600,0x7f4af2425a00,16925514318670,16925514329221,16925514424581,16925514426097
|
|
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,183519,183519,4194304,256,0,0,12,24,147584,0x7f4af5424480,0x7f4af2425a40,16925514442966,16925514451781,16925514631621,16925514633160
|
|
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,183519,183519,4194304,256,0,0,12,24,149568,0x7f4af5424300,0x7f4af2425a80,16925514647860,16925514656100,16925514839620,16925514841224
|
|
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,183519,183519,4194304,256,0,0,12,24,151552,0x7f4af5424180,0x7f4af2425ac0,16925514856964,16925514865220,16925514975460,16925514976980
|
|
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,183519,183519,4194304,256,0,0,12,24,154304,0x7f4af5424000,0x7f4af2425b00,16925514991940,16925515000260,16925515181539,16925515183024
|
|
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,183519,183519,4194304,256,0,0,12,24,156288,0x7f4af2ccde80,0x7f4af2425b40,16925515204123,16925515213539,16925515314979,16925515316560
|
|
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,183519,183519,4194304,256,0,0,12,24,158784,0x7f4af2ccdd00,0x7f4af2425b80,16925515332460,16925515340579,16925515525538,16925515526954
|
|
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,183519,183519,4194304,256,0,0,12,24,161024,0x7f4af2ccdb80,0x7f4af2425bc0,16925515540534,16925515548578,16925515733217,16925515734808
|
|
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,183519,183519,4194304,256,0,0,12,24,163264,0x7f4af2ccda00,0x7f4af2425c00,16925515750377,16925515758497,16925515880737,16925515882253
|
|
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,183519,183519,4194304,256,0,0,12,24,166528,0x7f4af2ccd880,0x7f4af2425c40,16925515895883,16925515904257,16925516110816,16925516131316
|
|
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,183519,183519,4194304,256,0,0,12,24,168512,0x7f4af2ccd700,0x7f4af2425c80,16925516148915,16925516159616,16925516271776,16925516273352
|
|
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,183519,183519,4194304,256,0,0,12,24,171264,0x7f4af5424580,0x7f4af2425cc0,16925516290551,16925516299136,16925516483615,16925516485045
|
|
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,183519,183519,4194304,256,0,0,12,24,173760,0x7f4af5424400,0x7f4af2425d00,16925516499005,16925516507455,16925516692575,16925516694129
|
|
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,183519,183519,4194304,256,0,0,12,24,176256,0x7f4af5424280,0x7f4af2425d40,16925516710369,16925516719135,16925516853534,16925516855034
|
|
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,183519,183519,4194304,256,0,0,12,24,179776,0x7f4af5424100,0x7f4af2425d80,16925516869174,16925516877374,16925517109534,16925517129376
|
|
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,183519,183519,4194304,256,0,0,12,24,182272,0x7f4af2ccdf80,0x7f4af2425dc0,16925517145176,16925517155934,16925517282333,16925517283922
|
|
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,183519,183519,4194304,256,0,0,12,24,185536,0x7f4af2ccde00,0x7f4af2425e00,16925517300751,16925517309053,16925517503133,16925517504675
|
|
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,183519,183519,4194304,256,0,0,12,24,188544,0x7f4af2ccdc80,0x7f4af2425e40,16925517521265,16925517529852,16925517722332,16925517723899
|
|
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,183519,183519,4194304,256,0,0,12,24,191552,0x7f4af2ccdb00,0x7f4af2425e80,16925517739468,16925517746972,16925517906811,16925517908313
|
|
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,183519,183519,4194304,256,0,0,12,24,195840,0x7f4af2ccd980,0x7f4af2425ec0,16925517922783,16925517931451,16925518214651,16925518241233
|
|
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,183519,183519,4194304,256,0,0,12,24,198592,0x7f4af2ccd800,0x7f4af2425f00,16925518258603,16925518269210,16925518419290,16925518420748
|
|
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,183519,183519,4194304,256,0,0,12,24,202368,0x7f4af2ccd680,0x7f4af2425f40,16925518437687,16925518445850,16925518654489,16925518676940
|
|
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,183519,183519,4194304,256,0,0,12,24,205888,0x7f4af5424500,0x7f4af2425f80,16925518685380,16925518695289,16925518904089,16925518923613
|
|
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,183519,183519,4194304,256,0,0,12,24,209408,0x7f4af5424380,0x7f4af2425fc0,16925518934553,16925518945209,16925519130648,16925519132217
|
|
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,183519,183519,4194304,256,0,0,12,24,214464,0x7f4af5424200,0x7f4af2426000,16925519146856,16925519155928,16925519490007,16925519509115
|
|
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,183519,183519,4194304,256,0,0,12,24,217728,0x7f4af5424080,0x7f4af2426040,16925519526105,16925519536727,16925519704086,16925519705650
|
|
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,183519,183519,4194304,256,0,0,12,24,222016,0x7f4af2ccdf00,0x7f4af2426080,16925519723169,16925519731446,16925519958966,16925519978171
|
|
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,183519,183519,4194304,256,0,0,12,24,226048,0x7f4af2ccdd80,0x7f4af24260c0,16925519986141,16925519996886,16925520227125,16925520245723
|
|
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,183519,183519,4194304,256,0,0,12,24,230080,0x7f4af2ccdc00,0x7f4af2426100,16925520258353,16925520268885,16925520479924,16925520498646
|
|
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,183519,183519,4194304,256,0,0,12,24,235904,0x7f4af2ccda80,0x7f4af2426140,16925520511176,16925520520564,16925520906163,16925520927353
|
|
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,183519,183519,4194304,256,0,0,12,24,239424,0x7f4af2ccd900,0x7f4af2426180,16925520944843,16925520955603,16925521143122,16925521144607
|
|
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,183519,183519,4194304,256,0,0,12,24,244224,0x7f4af2ccd780,0x7f4af24261c0,16925521160006,16925521167762,16925521418322,16925521437228
|
|
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,183519,183519,4194304,256,0,0,12,24,248768,0x7f4af2ccd600,0x7f4af2426200,16925521445258,16925521455602,16925521702801,16925521718410
|
|
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,183519,183519,4194304,256,0,0,12,24,253312,0x7f4af5424480,0x7f4af2426240,16925521727029,16925521737201,16925521974000,16925521989671
|
|
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,183519,183519,4194304,256,0,0,8,24,255552,0x7f4af5424300,0x7f4af2426280,16925521998741,16925522008560,16925522461359,16925522481317
|
|
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,183519,183519,4194304,256,0,0,12,24,259840,0x7f4af5424180,0x7f4af24262c0,16925522500376,16925522510959,16925522736718,16925522756309
|
|
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,183519,183519,4194304,256,0,0,12,24,265664,0x7f4af5424000,0x7f4af2426300,16925522767508,16925522777998,16925523075917,16925523095419
|
|
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,183519,183519,4194304,256,0,0,12,24,271232,0x7f4af2ccde80,0x7f4af2426340,16925523107628,16925523117197,16925523416716,16925523438808
|
|
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,183519,183519,4194304,256,0,0,8,24,273216,0x7f4af2ccdd00,0x7f4af2426380,16925523452348,16925523462636,16925523758795,16925523780038
|
|
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,183519,183519,4194304,256,0,0,8,24,275712,0x7f4af2ccdb80,0x7f4af24263c0,16925523790398,16925523800875,16925524358954,16925524377911
|
|
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,183519,183519,4194304,256,0,0,12,24,280768,0x7f4af2ccda00,0x7f4af2426400,16925524395920,16925524405993,16925524669513,16925524690991
|
|
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,183519,183519,4194304,256,0,0,12,24,287616,0x7f4af2ccd880,0x7f4af2426440,16925524699591,16925524709673,16925525061192,16925525082900
|
|
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,183519,183519,4194304,256,0,0,12,24,294208,0x7f4af2ccd700,0x7f4af2426480,16925525091629,16925525101991,16925525452550,16925525473638
|
|
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,183519,183519,4194304,256,0,0,8,24,296960,0x7f4af5424580,0x7f4af24264c0,16925525489228,16925525499590,16925525846949,16925525862626
|
|
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,183519,183519,4194304,256,0,0,8,24,299968,0x7f4af5424400,0x7f4af2426500,16925525871586,16925525881509,16925526542627,16925526566056
|
|
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,183519,183519,4194304,256,0,0,8,24,302720,0x7f4af5424280,0x7f4af2426540,16925526584705,16925526594147,16925527041826,16925527064321
|
|
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,183519,183519,4194304,256,0,0,12,24,305472,0x7f4af5424100,0x7f4af2426580,16925527073660,16925527083106,16925527547425,16925527569546
|
|
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,183519,183519,4194304,256,0,0,12,24,308224,0x7f4af2ccdf80,0x7f4af24265c0,16925527578825,16925527589025,16925528049823,16925528071791
|
|
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,183519,183519,4194304,256,0,0,8,24,310976,0x7f4af2ccde00,0x7f4af2426600,16925528080791,16925528090623,16925528542142,16925528564106
|
|
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,183519,183519,4194304,256,0,0,8,24,313216,0x7f4af2ccdc80,0x7f4af2426640,16925528573316,16925528583262,16925529452379,16925529474599
|
|
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,183519,183519,4194304,256,0,0,8,24,315968,0x7f4af2ccdb00,0x7f4af2426680,16925529491089,16925529501979,16925530355417,16925530382032
|
|
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,183519,183519,4194304,256,0,0,12,24,318720,0x7f4af2ccd980,0x7f4af24266c0,16925530390642,16925530401017,16925531285974,16925531308355
|
|
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,183519,183519,4194304,256,0,0,12,24,321472,0x7f4af2ccd800,0x7f4af2426700,16925531320794,16925531330934,16925532210772,16925532232957
|
|
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,183519,183519,4194304,256,0,0,8,24,324224,0x7f4af2ccd680,0x7f4af2426740,16925532244667,16925532264532,16925533123089,16925533144820
|
|
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,183519,183519,4194304,256,0,0,8,24,326464,0x7f4af5424500,0x7f4af2426780,16925533154000,16925533163569,16925534861484,16925534910838
|
|
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,183519,183519,4194304,256,0,0,8,24,329216,0x7f4af5424380,0x7f4af24267c0,16925534928487,16925534939084,16925536604360,16925536673106
|
|
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,183519,183519,4194304,256,0,0,12,24,331968,0x7f4af5424200,0x7f4af2426800,16925536685215,16925536700359,16925538424834,16925538494731
|
|
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,183519,183519,4194304,256,0,0,12,24,334720,0x7f4af5424080,0x7f4af2426840,16925538503981,16925538514114,16925540229789,16925540299638
|
|
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,183519,183519,4194304,256,0,0,8,24,337472,0x7f4af2ccdf00,0x7f4af2426880,16925540312787,16925540378269,16925542052664,16925542126254
|
|
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,183519,183519,4194304,256,0,0,8,24,0,0x7f4af2ccdd80,0x7f4af24268c0,16925542162073,16925542177304,16925545536015,16925545611130
|