169 lignes
39 KiB
CSV
169 lignes
39 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_fillBuffer.kd",0,0,0,937113,937118,33554432,256,0,0,8,32,6464,0x0,0x7f12eac04180,12076635381227990,12076635381273678,12076635381598795,12076635381689318
|
|
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,937113,937118,32768,256,0,0,24,24,12480,0x0,0x7f12eac35100,12076635396787522,12076635396887551,12076635396894271,12076635396915901
|
|
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,937113,937118,4194304,256,0,0,24,24,12928,0x7f141aca3900,0x7f12eac35140,12076635396946107,12076635396958910,12076635397089629,12076635397093471
|
|
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,937113,937118,4194304,256,0,0,36,24,13632,0x7f141aca3800,0x7f12eac35180,12076635397153844,12076635397172188,12076635397417626,12076635397502262
|
|
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,937113,937118,4194304,256,0,0,28,24,14080,0x7f141aca3700,0x7f12eac351c0,12076635397530284,12076635397541945,12076635397788343,12076635397870096
|
|
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,937113,937118,4194304,256,0,0,24,24,14528,0x7f141aca3600,0x7f12eac35200,12076635397898148,12076635397909782,12076635398035381,12076635398039221
|
|
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,937113,937118,4194304,256,0,0,24,24,14976,0x7f141aca3500,0x7f12eac35240,12076635398076520,12076635398088341,12076635398213780,12076635398217131
|
|
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,937113,937118,4194304,256,0,0,24,24,15424,0x7f141aca3400,0x7f12eac35280,12076635398270070,12076635398281939,12076635398406418,12076635398409309
|
|
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,937113,937118,4194304,256,0,0,28,24,16128,0x7f141aca3300,0x7f12eac352c0,12076635398437431,12076635398448658,12076635398696176,12076635398741717
|
|
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,937113,937118,4194304,256,0,0,28,24,16832,0x7f141aca3a00,0x7f12eac35300,12076635398764199,12076635398777615,12076635399025613,12076635399071551
|
|
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,937113,937118,4194304,256,0,0,24,24,17536,0x7f141aca3900,0x7f12eac35340,12076635399094343,12076635399107533,12076635399232652,12076635399235516
|
|
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,937113,937118,4194304,256,0,0,24,24,18240,0x7f141aca3800,0x7f12eac35380,12076635399263287,12076635399276171,12076635399401610,12076635399404741
|
|
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,937113,937118,4194304,256,0,0,24,24,18944,0x7f141aca3700,0x7f12eac353c0,12076635399444655,12076635399456170,12076635399581449,12076635399584315
|
|
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,937113,937118,4194304,256,0,0,28,24,19904,0x7f141aca3600,0x7f12eac35400,12076635399611585,12076635399623689,12076635399870247,12076635399893239
|
|
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,937113,937118,4194304,256,0,0,28,24,20608,0x7f141aca3500,0x7f12eac35440,12076635399918546,12076635399929606,12076635400177284,12076635400223223
|
|
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,937113,937118,4194304,256,0,0,24,24,21312,0x7f141aca3400,0x7f12eac35480,12076635400245675,12076635400257444,12076635400382403,12076635400385244
|
|
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,937113,937118,4194304,256,0,0,24,24,22016,0x7f141aca3300,0x7f12eac354c0,12076635400412726,12076635400425762,12076635400550881,12076635400554048
|
|
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,937113,937118,4194304,256,0,0,24,24,22720,0x7f141aca3a00,0x7f12eac35500,12076635400591819,12076635400602881,12076635400727040,12076635400730136
|
|
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,937113,937118,4194304,256,0,0,28,24,23680,0x7f141aca3900,0x7f12eac35540,12076635400756735,12076635400768959,12076635401016317,12076635401041185
|
|
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,937113,937118,4194304,256,0,0,28,24,24384,0x7f141aca3800,0x7f12eac35580,12076635401064799,12076635401076317,12076635401318875,12076635401363364
|
|
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,937113,937118,4194304,256,0,0,24,24,25088,0x7f141aca3700,0x7f12eac355c0,12076635401384904,12076635401395994,12076635401520153,12076635401523091
|
|
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,937113,937118,4194304,256,0,0,24,24,25792,0x7f141aca3600,0x7f12eac35600,12076635401549149,12076635401560473,12076635401685592,12076635401688719
|
|
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,937113,937118,4194304,256,0,0,24,24,26496,0x7f141aca3500,0x7f12eac35640,12076635401727772,12076635401738712,12076635401862391,12076635401865458
|
|
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,937113,937118,4194304,256,0,0,28,24,27712,0x7f141aca3400,0x7f12eac35680,12076635401892097,12076635401906710,12076635402152788,12076635402202364
|
|
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,937113,937118,4194304,256,0,0,28,24,28416,0x7f141aca3300,0x7f12eac356c0,12076635402225738,12076635402238868,12076635402483186,12076635402528471
|
|
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,937113,937118,4194304,256,0,0,24,24,29120,0x7f141aca3a00,0x7f12eac35700,12076635402552285,12076635402565585,12076635402689584,12076635402692556
|
|
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,937113,937118,4194304,256,0,0,24,24,30080,0x7f141aca3900,0x7f12eac35740,12076635402719877,12076635402731344,12076635402856303,12076635402859487
|
|
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,937113,937118,4194304,256,0,0,24,24,30784,0x7f141aca3800,0x7f12eac35780,12076635402897117,12076635402908142,12076635403032941,12076635403036506
|
|
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,937113,937118,4194304,256,0,0,28,24,32000,0x7f141aca3700,0x7f12eac357c0,12076635403063136,12076635403075181,12076635403325419,12076635403348526
|
|
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,937113,937118,4194304,256,0,0,28,24,32960,0x7f141aca3600,0x7f12eac35800,12076635403370758,12076635403382378,12076635403629736,12076635403674102
|
|
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,937113,937118,4194304,256,0,0,24,24,33920,0x7f141aca3500,0x7f12eac35840,12076635403695322,12076635403708456,12076635403832775,12076635403835713
|
|
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,937113,937118,4194304,256,0,0,24,24,34880,0x7f141aca3400,0x7f12eac35880,12076635403861561,12076635403873894,12076635403999973,12076635404017561
|
|
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,937113,937118,4194304,256,0,0,24,24,35840,0x7f141aca3300,0x7f12eac358c0,12076635404049080,12076635404060933,12076635404185572,12076635404188699
|
|
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,937113,937118,4194304,256,0,0,28,24,37312,0x7f141aca3a00,0x7f12eac35900,12076635404214627,12076635404226211,12076635404472609,12076635404497944
|
|
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,937113,937118,4194304,256,0,0,28,24,38272,0x7f141aca3900,0x7f12eac35940,12076635404521208,12076635404532769,12076635404779487,12076635404800427
|
|
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,937113,937118,4194304,256,0,0,24,24,39232,0x7f141aca3800,0x7f12eac35980,12076635404822338,12076635404835327,12076635404959806,12076635404962619
|
|
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,937113,937118,4194304,256,0,0,24,24,40192,0x7f141aca3700,0x7f12eac359c0,12076635404990110,12076635405002845,12076635405128444,12076635405131603
|
|
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,937113,937118,4194304,256,0,0,24,24,41152,0x7f141aca3600,0x7f12eac35a00,12076635405168913,12076635405183324,12076635405307323,12076635405310125
|
|
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,937113,937118,4194304,256,0,0,28,24,42624,0x7f141aca3500,0x7f12eac35a40,12076635405337246,12076635405350202,12076635405599000,12076635405648124
|
|
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,937113,937118,4194304,256,0,0,28,24,43584,0x7f141aca3400,0x7f12eac35a80,12076635405670105,12076635405682840,12076635405928118,12076635405950376
|
|
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,937113,937118,4194304,256,0,0,24,24,44544,0x7f141aca3300,0x7f12eac35ac0,12076635405973099,12076635405985877,12076635406110996,12076635406114031
|
|
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,937113,937118,4194304,256,0,0,24,24,45760,0x7f141aca3a00,0x7f12eac35b00,12076635406142003,12076635406154996,12076635406281235,12076635406284337
|
|
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,937113,937118,4194304,256,0,0,24,24,46720,0x7f141aca3900,0x7f12eac35b40,12076635406320164,12076635406332754,12076635406457553,12076635406460555
|
|
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,937113,937118,4194304,256,0,0,28,24,48448,0x7f141aca3800,0x7f12eac35b80,12076635406486964,12076635406499633,12076635406758511,12076635406779148
|
|
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,937113,937118,4194304,256,0,0,28,24,49408,0x7f141aca3700,0x7f12eac35bc0,12076635406801009,12076635406814031,12076635407059469,12076635407081470
|
|
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,937113,937118,4194304,256,0,0,24,24,50368,0x7f141aca3600,0x7f12eac35c00,12076635407105164,12076635407117868,12076635407242507,12076635407245415
|
|
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,937113,937118,4194304,256,0,0,24,24,51584,0x7f141aca3500,0x7f12eac35c40,12076635407272956,12076635407285547,12076635407412426,12076635407415111
|
|
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,937113,937118,4194304,256,0,0,24,24,52544,0x7f141aca3400,0x7f12eac35c80,12076635407453933,12076635407466825,12076635407592104,12076635407594845
|
|
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,937113,937118,4194304,256,0,0,28,24,54272,0x7f141aca3300,0x7f12eac35cc0,12076635407622326,12076635407634984,12076635407894822,12076635407915882
|
|
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,937113,937118,4194304,256,0,0,28,24,55488,0x7f141aca3a00,0x7f12eac35d00,12076635407936881,12076635407950021,12076635408198179,12076635408219407
|
|
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,937113,937118,4194304,256,0,0,24,24,56704,0x7f141aca3900,0x7f12eac35d40,12076635408241548,12076635408253539,12076635408378498,12076635408381258
|
|
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,937113,937118,4194304,256,0,0,24,24,58176,0x7f141aca3800,0x7f12eac35d80,12076635408408118,12076635408420098,12076635408548897,12076635408551755
|
|
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,937113,937118,4194304,256,0,0,24,24,59392,0x7f141aca3700,0x7f12eac35dc0,12076635408587912,12076635408600736,12076635408726175,12076635408729045
|
|
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,937113,937118,4194304,256,0,0,28,24,61376,0x7f141aca3600,0x7f12eac35e00,12076635408756175,12076635408769215,12076635409028413,12076635409055091
|
|
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,937113,937118,4194304,256,0,0,28,24,62592,0x7f141aca3500,0x7f12eac35e40,12076635409078054,12076635409090492,12076635409336090,12076635409357213
|
|
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,937113,937118,4194304,256,0,0,24,24,63808,0x7f141aca3400,0x7f12eac35e80,12076635409381038,12076635409393050,12076635409518009,12076635409521078
|
|
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,937113,937118,4194304,256,0,0,24,24,65280,0x7f141aca3300,0x7f12eac35ec0,12076635409548990,12076635409561048,12076635409691127,12076635409693990
|
|
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,937113,937118,4194304,256,0,0,24,24,66496,0x7f141aca3a00,0x7f12eac35f00,12076635409730868,12076635409743767,12076635409869366,12076635409872251
|
|
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,937113,937118,4194304,256,0,0,28,24,68480,0x7f141aca3900,0x7f12eac35f40,12076635409898220,12076635409911446,12076635410171763,12076635410196424
|
|
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,937113,937118,4194304,256,0,0,28,24,69696,0x7f141aca3800,0x7f12eac35f80,12076635410219377,12076635410232083,12076635410475601,12076635410496182
|
|
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,937113,937118,4194304,256,0,0,24,24,70912,0x7f141aca3700,0x7f12eac35fc0,12076635410518233,12076635410531761,12076635410656720,12076635410659586
|
|
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,937113,937118,4194304,256,0,0,24,24,72384,0x7f141aca3600,0x7f12eac36000,12076635410686656,12076635410698799,12076635410835438,12076635410838318
|
|
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,937113,937118,4194304,256,0,0,24,24,73600,0x7f141aca3500,0x7f12eac36040,12076635410876219,12076635410889358,12076635411013837,12076635411016830
|
|
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,937113,937118,4194304,256,0,0,28,24,75840,0x7f141aca3400,0x7f12eac36080,12076635411045444,12076635411057996,12076635411323434,12076635411347035
|
|
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,937113,937118,4194304,256,0,0,28,24,77056,0x7f141aca3300,0x7f12eac360c0,12076635411368895,12076635411381194,12076635411663431,12076635411684903
|
|
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,937113,937118,4194304,256,0,0,24,24,78272,0x7f141aca3a00,0x7f12eac36100,12076635411706433,12076635411719591,12076635411844870,12076635411848087
|
|
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,937113,937118,4194304,256,0,0,24,24,80000,0x7f141aca3900,0x7f12eac36140,12076635411875357,12076635411888710,12076635412030948,12076635412034073
|
|
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,937113,937118,4194304,256,0,0,24,24,81216,0x7f141aca3800,0x7f12eac36180,12076635412071552,12076635412083908,12076635412208867,12076635412211873
|
|
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,937113,937118,4194304,256,0,0,28,24,83456,0x7f141aca3700,0x7f12eac361c0,12076635412238493,12076635412251267,12076635412509185,12076635412532029
|
|
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,937113,937118,4194304,256,0,0,28,24,84928,0x7f141aca3600,0x7f12eac36200,12076635412553829,12076635412566624,12076635412815422,12076635412838900
|
|
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,937113,937118,4194304,256,0,0,24,24,86400,0x7f141aca3500,0x7f12eac36240,12076635412861842,12076635412874782,12076635413000861,12076635413015598
|
|
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,937113,937118,4194304,256,0,0,24,24,88128,0x7f141aca3400,0x7f12eac36280,12076635413038771,12076635413051260,12076635413201019,12076635413203899
|
|
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,937113,937118,4194304,256,0,0,24,24,89600,0x7f141aca3300,0x7f12eac362c0,12076635413254533,12076635413268058,12076635413393977,12076635413397338
|
|
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,937113,937118,4194304,256,0,0,28,24,92096,0x7f141aca3a00,0x7f12eac36300,12076635413425220,12076635413437177,12076635413692695,12076635413714188
|
|
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,937113,937118,4194304,256,0,0,28,24,93568,0x7f141aca3900,0x7f12eac36340,12076635413736950,12076635413748855,12076635413996053,12076635414023323
|
|
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,937113,937118,4194304,256,0,0,24,24,95040,0x7f141aca3800,0x7f12eac36380,12076635414046696,12076635414059412,12076635414185011,12076635414188169
|
|
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,937113,937118,4194304,256,0,0,24,24,96768,0x7f141aca3700,0x7f12eac363c0,12076635414216081,12076635414228851,12076635414386609,12076635414389504
|
|
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,937113,937118,4194304,256,0,0,24,24,98240,0x7f141aca3600,0x7f12eac36400,12076635414427425,12076635414440049,12076635414564528,12076635414567485
|
|
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,937113,937118,4194304,256,0,0,28,24,100736,0x7f141aca3500,0x7f12eac36440,12076635414594676,12076635414607408,12076635414869965,12076635414894984
|
|
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,937113,937118,4194304,256,0,0,28,24,102208,0x7f141aca3400,0x7f12eac36480,12076635414916214,12076635414928365,12076635415172683,12076635415199030
|
|
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,937113,937118,4194304,256,0,0,24,24,103680,0x7f141aca3300,0x7f12eac364c0,12076635415220600,12076635415233003,12076635415358602,12076635415361933
|
|
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,937113,937118,4194304,256,0,0,24,24,105664,0x7f141aca3a00,0x7f12eac36500,12076635415388332,12076635415401481,12076635415566920,12076635415570130
|
|
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,937113,937118,4194304,256,0,0,24,24,107136,0x7f141aca3900,0x7f12eac36540,12076635415606828,12076635415618919,12076635415744198,12076635415747270
|
|
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,937113,937118,4194304,256,0,0,28,24,109888,0x7f141aca3800,0x7f12eac36580,12076635415776765,12076635415790918,12076635416046596,12076635416067956
|
|
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,937113,937118,4194304,256,0,0,28,24,111360,0x7f141aca3700,0x7f12eac365c0,12076635416090648,12076635416103236,12076635416352994,12076635416374456
|
|
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,937113,937118,4194304,256,0,0,24,24,112832,0x7f141aca3600,0x7f12eac36600,12076635416397138,12076635416410273,12076635416534592,12076635416537670
|
|
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,937113,937118,4194304,256,0,0,24,24,114816,0x7f141aca3500,0x7f12eac36640,12076635416564570,12076635416576672,12076635416748990,12076635416751969
|
|
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,937113,937118,4194304,256,0,0,24,24,116288,0x7f141aca3400,0x7f12eac36680,12076635416789027,12076635416801950,12076635416927389,12076635416930350
|
|
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,937113,937118,4194304,256,0,0,28,24,119040,0x7f141aca3300,0x7f12eac366c0,12076635416957781,12076635416970429,12076635417226906,12076635417249093
|
|
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,937113,937118,4194304,256,0,0,28,24,120768,0x7f141aca3a00,0x7f12eac36700,12076635417270323,12076635417283226,12076635417531864,12076635417553399
|
|
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,937113,937118,4194304,256,0,0,24,24,122496,0x7f141aca3900,0x7f12eac36740,12076635417575741,12076635417587864,12076635417713303,12076635417716332
|
|
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,937113,937118,4194304,256,0,0,24,24,124736,0x7f141aca3800,0x7f12eac36780,12076635417743282,12076635417755862,12076635417938421,12076635417941381
|
|
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,937113,937118,4194304,256,0,0,24,24,126464,0x7f141aca3700,0x7f12eac367c0,12076635417979311,12076635417991540,12076635418116979,12076635418120384
|
|
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,937113,937118,4194304,256,0,0,20,24,127936,0x7f141aca3600,0x7f12eac36800,12076635418147274,12076635418159699,12076635418423217,12076635418446440
|
|
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,937113,937118,4194304,256,0,0,28,24,129664,0x7f141aca3500,0x7f12eac36840,12076635418471607,12076635418484016,12076635418732334,12076635418753562
|
|
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,937113,937118,4194304,256,0,0,24,24,131392,0x7f141aca3400,0x7f12eac36880,12076635418775743,12076635418787854,12076635418914253,12076635418917236
|
|
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,937113,937118,4194304,256,0,0,24,24,133632,0x7f141aca3300,0x7f12eac368c0,12076635418943816,12076635418956812,12076635419147851,12076635419163013
|
|
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,937113,937118,4194304,256,0,0,24,24,135360,0x7f141aca3a00,0x7f12eac36900,12076635419194602,12076635419207370,12076635419333769,12076635419337057
|
|
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,937113,937118,4194304,256,0,0,20,24,136832,0x7f141aca3900,0x7f12eac36940,12076635419364268,12076635419377609,12076635419660647,12076635419684864
|
|
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,937113,937118,4194304,256,0,0,28,24,138560,0x7f141aca3800,0x7f12eac36980,12076635419706344,12076635419718566,12076635419964484,12076635419988038
|
|
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,937113,937118,4194304,256,0,0,24,24,140288,0x7f141aca3700,0x7f12eac369c0,12076635420018034,12076635420031364,12076635420157603,12076635420160659
|
|
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,937113,937118,4194304,256,0,0,24,24,142784,0x7f141aca3600,0x7f12eac36a00,12076635420188791,12076635420201602,12076635420411681,12076635420432535
|
|
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,937113,937118,4194304,256,0,0,24,24,144768,0x7f141aca3500,0x7f12eac36a40,12076635420463543,12076635420476320,12076635420603359,12076635420606388
|
|
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,937113,937118,4194304,256,0,0,20,24,145728,0x7f141aca3400,0x7f12eac36a80,12076635420633869,12076635420647039,12076635420953436,12076635420974854
|
|
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,937113,937118,4194304,256,0,0,28,24,147712,0x7f141aca3300,0x7f12eac36ac0,12076635420996624,12076635421013596,12076635421265754,12076635421288186
|
|
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,937113,937118,4194304,256,0,0,24,24,149696,0x7f141aca3a00,0x7f12eac36b00,12076635421308895,12076635421322073,12076635421450552,12076635421453774
|
|
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,937113,937118,4194304,256,0,0,24,24,152192,0x7f141aca3900,0x7f12eac36b40,12076635421480304,12076635421492792,12076635421720630,12076635421746299
|
|
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,937113,937118,4194304,256,0,0,24,24,154176,0x7f141aca3800,0x7f12eac36b80,12076635421779290,12076635421791990,12076635421919189,12076635421922366
|
|
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,937113,937118,4194304,256,0,0,20,24,155648,0x7f141aca3700,0x7f12eac36bc0,12076635421949787,12076635421962868,12076635422291346,12076635422314596
|
|
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,937113,937118,4194304,256,0,0,28,24,157632,0x7f141aca3600,0x7f12eac36c00,12076635422336677,12076635422349105,12076635422596943,12076635422617269
|
|
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,937113,937118,4194304,256,0,0,24,24,159616,0x7f141aca3500,0x7f12eac36c40,12076635422639530,12076635422651983,12076635422779182,12076635422782316
|
|
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,937113,937118,4194304,256,0,0,24,24,162368,0x7f141aca3400,0x7f12eac36c80,12076635422809646,12076635422822221,12076635423065899,12076635423091801
|
|
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,937113,937118,4194304,256,0,0,24,24,164608,0x7f141aca3300,0x7f12eac36cc0,12076635423124723,12076635423139659,12076635423270058,12076635423273309
|
|
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,937113,937118,4194304,256,0,0,20,24,166336,0x7f141aca3a00,0x7f12eac36d00,12076635423301031,12076635423312777,12076635423687974,12076635423709731
|
|
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,937113,937118,4194304,256,0,0,28,24,168576,0x7f141aca3900,0x7f12eac36d40,12076635423730770,12076635423742694,12076635424001732,12076635424023525
|
|
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,937113,937118,4194304,256,0,0,24,24,170816,0x7f141aca3800,0x7f12eac36d80,12076635424047569,12076635424060451,12076635424190530,12076635424193631
|
|
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,937113,937118,4194304,256,0,0,24,24,174080,0x7f141aca3700,0x7f12eac36dc0,12076635424219148,12076635424231010,12076635424509408,12076635424534595
|
|
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,937113,937118,4194304,256,0,0,24,24,176576,0x7f141aca3600,0x7f12eac36e00,12076635424565022,12076635424577727,12076635424713406,12076635424716554
|
|
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,937113,937118,4194304,256,0,0,20,24,177792,0x7f141aca3500,0x7f12eac36e40,12076635424744405,12076635424757086,12076635425204442,12076635425230269
|
|
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,937113,937118,4194304,256,0,0,28,24,180288,0x7f141aca3400,0x7f12eac36e80,12076635425252380,12076635425264602,12076635425524119,12076635425549924
|
|
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,937113,937118,4194304,256,0,0,24,24,182784,0x7f141aca3300,0x7f12eac36ec0,12076635425572696,12076635425584759,12076635425719318,12076635425722324
|
|
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,937113,937118,4194304,256,0,0,24,24,186304,0x7f141aca3a00,0x7f12eac36f00,12076635425748804,12076635425761078,12076635426074995,12076635426102401
|
|
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,937113,937118,4194304,256,0,0,24,24,189312,0x7f141aca3900,0x7f12eac36f40,12076635426135062,12076635426147634,12076635426299153,12076635426302303
|
|
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,937113,937118,4194304,256,0,0,20,24,190784,0x7f141aca3800,0x7f12eac36f80,12076635426328512,12076635426341713,12076635426859309,12076635426879818
|
|
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,937113,937118,4194304,256,0,0,28,24,193792,0x7f141aca3700,0x7f12eac36fc0,12076635426901057,12076635426913388,12076635427212746,12076635427240078
|
|
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,937113,937118,4194304,256,0,0,24,24,196800,0x7f141aca3600,0x7f12eac37000,12076635427265745,12076635427278665,12076635427434024,12076635427437244
|
|
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,937113,937118,4194304,256,0,0,24,24,201088,0x7f141aca3500,0x7f12eac37040,12076635427463754,12076635427476104,12076635427860741,12076635427886119
|
|
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,937113,937118,4194304,256,0,0,24,24,204608,0x7f141aca3400,0x7f12eac37080,12076635427916947,12076635427930180,12076635428104899,12076635428108794
|
|
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,937113,937118,4194304,256,0,0,20,24,206080,0x7f141aca3300,0x7f12eac370c0,12076635428135433,12076635428147778,12076635428758333,12076635428784581
|
|
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,937113,937118,4194304,256,0,0,28,24,209600,0x7f141aca3a00,0x7f12eac37100,12076635428805870,12076635428818013,12076635429175290,12076635429199422
|
|
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,937113,937118,4194304,256,0,0,24,24,213120,0x7f141aca3900,0x7f12eac37140,12076635429223247,12076635429236089,12076635429413208,12076635429416767
|
|
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,937113,937118,4194304,256,0,0,24,24,218176,0x7f141aca3800,0x7f12eac37180,12076635429444298,12076635429456888,12076635429912884,12076635429938858
|
|
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,937113,937118,4194304,256,0,0,24,24,222208,0x7f141aca3700,0x7f12eac371c0,12076635429972841,12076635429985363,12076635430184402,12076635430205363
|
|
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,937113,937118,4194304,256,0,0,20,24,223936,0x7f141aca3600,0x7f12eac37200,12076635430227164,12076635430240401,12076635430944556,12076635430970617
|
|
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,937113,937118,4194304,256,0,0,28,24,227968,0x7f141aca3500,0x7f12eac37240,12076635430994101,12076635431006155,12076635431378312,12076635431409674
|
|
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,937113,937118,4194304,256,0,0,24,24,232000,0x7f141aca3400,0x7f12eac37280,12076635431433167,12076635431445832,12076635431648870,12076635431673885
|
|
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,937113,937118,4194304,256,0,0,24,24,237824,0x7f141aca3300,0x7f12eac372c0,12076635431696076,12076635431708549,12076635432234465,12076635432258733
|
|
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,937113,937118,4194304,256,0,0,24,24,242368,0x7f141aca3a00,0x7f12eac37300,12076635432296844,12076635432309185,12076635432533183,12076635432559693
|
|
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,937113,937118,4194304,256,0,0,20,24,243584,0x7f141aca3900,0x7f12eac37340,12076635432582325,12076635432595102,12076635433394136,12076635433420905
|
|
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,937113,937118,4194304,256,0,0,28,24,248128,0x7f141aca3800,0x7f12eac37380,12076635433443767,12076635433456215,12076635433877812,12076635433901298
|
|
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,937113,937118,4194304,256,0,0,24,24,252672,0x7f141aca3700,0x7f12eac373c0,12076635433923951,12076635433936851,12076635434162610,12076635434191508
|
|
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,937113,937118,4194304,256,0,0,24,24,259264,0x7f141aca3600,0x7f12eac37400,12076635434215783,12076635434227889,12076635434824844,12076635434854411
|
|
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,937113,937118,4194304,256,0,0,24,24,264832,0x7f141aca3500,0x7f12eac37440,12076635434890048,12076635434903884,12076635435203881,12076635435232575
|
|
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,937113,937118,4194304,256,0,0,20,24,266304,0x7f141aca3400,0x7f12eac37480,12076635435256760,12076635435270281,12076635436256033,12076635436283199
|
|
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,937113,937118,4194304,256,0,0,28,24,271872,0x7f141aca3300,0x7f12eac374c0,12076635436306232,12076635436319232,12076635436835228,12076635436862476
|
|
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,937113,937118,4194304,256,0,0,24,24,277440,0x7f141aca3a00,0x7f12eac37500,12076635436887413,12076635436900028,12076635437171865,12076635437199734
|
|
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,937113,937118,4194304,256,0,0,12,24,279936,0x7f141aca3900,0x7f12eac37540,12076635437222847,12076635437235065,12076635437973619,12076635437994582
|
|
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,937113,937118,4194304,256,0,0,24,24,286528,0x7f141aca3800,0x7f12eac37580,12076635438036270,12076635438049938,12076635438394735,12076635438417038
|
|
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,937113,937118,4194304,256,0,0,20,24,288000,0x7f141aca3700,0x7f12eac375c0,12076635438442155,12076635438454575,12076635439629286,12076635439659199
|
|
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,937113,937118,4194304,256,0,0,32,24,294592,0x7f141aca3600,0x7f12eac37600,12076635439681911,12076635439694245,12076635440303680,12076635440333854
|
|
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,937113,937118,4194304,256,0,0,24,24,301184,0x7f141aca3500,0x7f12eac37640,12076635440356846,12076635440369280,12076635440687677,12076635440715453
|
|
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,937113,937118,4194304,256,0,0,12,24,304960,0x7f141aca3400,0x7f12eac37680,12076635440738787,12076635440751356,12076635441629109,12076635441659079
|
|
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,937113,937118,4194304,256,0,0,24,24,313600,0x7f141aca3300,0x7f12eac376c0,12076635441694455,12076635441707029,12076635442116465,12076635442145554
|
|
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,937113,937118,4194304,256,0,0,20,24,314816,0x7f141aca3a00,0x7f12eac37700,12076635442166994,12076635442179825,12076635443731492,12076635443782178
|
|
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,937113,937118,4194304,256,0,0,20,24,317568,0x7f141aca3900,0x7f12eac37740,12076635443805832,12076635443818496,12076635444614331,12076635444671001
|
|
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,937113,937118,4194304,256,0,0,12,24,320320,0x7f141aca3800,0x7f12eac37780,12076635444692712,12076635444705209,12076635445119766,12076635445169909
|
|
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,937113,937118,4194304,256,0,0,12,24,324096,0x7f141aca3700,0x7f12eac377c0,12076635445192501,12076635445205686,12076635446364558,12076635446415336
|
|
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,937113,937118,4194304,256,0,0,12,24,328896,0x7f141aca3600,0x7f12eac37800,12076635446449770,12076635446462477,12076635447247272,12076635447297717
|
|
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,937113,937118,4194304,256,0,0,20,24,330112,0x7f141aca3500,0x7f12eac37840,12076635447320820,12076635447334311,12076635450390770,12076635450441415
|
|
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,937113,937118,4194304,256,0,0,20,24,332864,0x7f141aca3400,0x7f12eac37880,12076635450465380,12076635450477969,12076635452023558,12076635452074603
|
|
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,937113,937118,4194304,256,0,0,12,24,335616,0x7f141aca3300,0x7f12eac378c0,12076635452099299,12076635452111878,12076635452901312,12076635452951614
|
|
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,937113,937118,4194304,256,0,0,12,24,339392,0x7f141aca3a00,0x7f12eac37900,12076635452975879,12076635452989471,12076635455272336,12076635455325831
|
|
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,937113,937118,4194304,256,0,0,12,24,344192,0x7f141aca3900,0x7f12eac37940,12076635455360435,12076635455373615,12076635456908484,12076635456958598
|
|
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,937113,937118,4194304,256,0,0,20,24,345408,0x7f141aca3800,0x7f12eac37980,12076635456981360,12076635456994724,12076635463054681,12076635463108808
|
|
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,937113,937118,4194304,256,0,0,20,24,348160,0x7f141aca3700,0x7f12eac379c0,12076635463132151,12076635463145081,12076635466191299,12076635466241976
|
|
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,937113,937118,4194304,256,0,0,12,24,350912,0x7f141aca3600,0x7f12eac37a00,12076635466265570,12076635466278339,12076635467816888,12076635467867189
|
|
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,937113,937118,4194304,256,0,0,12,24,0,0x7f141aca3500,0x7f12eac37a40,12076635467890693,12076635467903287,12076635472429176,12076635472482624
|