169 行
37 KiB
CSV
169 行
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",0,0,0,149096,149096,33554432,256,0,0,4,32,4160,0x0,0x7fd2ec604280,16152833461627,16152833487509,16152833727350,16152833816800
|
|
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,149096,149096,32768,256,0,0,12,24,13888,0x0,0x7fd2ec623f80,16152838510616,16152838526258,16152838539378,16152838557375
|
|
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,149096,149096,4194304,256,0,0,12,24,14336,0x7fd2ef6ec380,0x7fd2ec623fc0,16152838562854,16152838607859,16152838700339,16152838702261
|
|
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,149096,149096,4194304,256,0,0,16,24,15040,0x7fd2ef6ec200,0x7fd2ec624000,16152838723461,16152838733299,16152838912180,16152838913967
|
|
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,149096,149096,4194304,256,0,0,16,24,15488,0x7fd2ef6ec080,0x7fd2ec624040,16152838929396,16152838937461,16152839117622,16152839119462
|
|
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,149096,149096,4194304,256,0,0,12,24,15936,0x7fd2ed04df00,0x7fd2ec624080,16152839133722,16152839142422,16152839236182,16152839237990
|
|
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,149096,149096,4194304,256,0,0,12,24,16384,0x7fd2ed04dd80,0x7fd2ec6240c0,16152839253689,16152839261943,16152839354423,16152839356137
|
|
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,149096,149096,4194304,256,0,0,12,24,17088,0x7fd2ed04dc00,0x7fd2ec624100,16152839382936,16152839393463,16152839485144,16152839486914
|
|
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,149096,149096,4194304,256,0,0,16,24,17792,0x7fd2ed04da80,0x7fd2ec624140,16152839511314,16152839521144,16152839701145,16152839702879
|
|
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,149096,149096,4194304,256,0,0,16,24,18496,0x7fd2ed04d900,0x7fd2ec624180,16152839724139,16152839734745,16152839914427,16152839916245
|
|
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,149096,149096,4194304,256,0,0,16,24,19200,0x7fd2ed04d780,0x7fd2ec6241c0,16152839934614,16152839952187,16152840045307,16152840047372
|
|
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,149096,149096,4194304,256,0,0,16,24,19904,0x7fd2ed04d600,0x7fd2ec624200,16152840061881,16152840070907,16152840164348,16152840166029
|
|
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,149096,149096,4194304,256,0,0,12,24,20608,0x7fd2ef6ec480,0x7fd2ec624240,16152840185859,16152840196188,16152840289149,16152840291046
|
|
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,149096,149096,4194304,256,0,0,16,24,21312,0x7fd2ef6ec300,0x7fd2ec624280,16152840309606,16152840318269,16152840497950,16152840499772
|
|
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,149096,149096,4194304,256,0,0,16,24,22016,0x7fd2ef6ec180,0x7fd2ec6242c0,16152840520221,16152840529150,16152840708831,16152840710547
|
|
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,149096,149096,4194304,256,0,0,16,24,22720,0x7fd2ef6ec000,0x7fd2ec624300,16152840726257,16152840734431,16152840827872,16152840829605
|
|
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,149096,149096,4194304,256,0,0,12,24,23424,0x7fd2ed04de80,0x7fd2ec624340,16152840849744,16152840859232,16152840952833,16152840954762
|
|
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,149096,149096,4194304,256,0,0,12,24,24128,0x7fd2ed04dd00,0x7fd2ec624380,16152840975221,16152840985473,16152841078434,16152841080059
|
|
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,149096,149096,4194304,256,0,0,16,24,24832,0x7fd2ed04db80,0x7fd2ec6243c0,16152841096089,16152841104354,16152841284035,16152841285804
|
|
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,149096,149096,4194304,256,0,0,16,24,25536,0x7fd2ed04da00,0x7fd2ec624400,16152841301334,16152841309635,16152841490756,16152841492540
|
|
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,149096,149096,4194304,256,0,0,12,24,26240,0x7fd2ed04d880,0x7fd2ec624440,16152841515429,16152841524676,16152841618437,16152841620027
|
|
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,149096,149096,4194304,256,0,0,12,24,26944,0x7fd2ed04d700,0x7fd2ec624480,16152841641847,16152841652677,16152841746438,16152841748104
|
|
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,149096,149096,4194304,256,0,0,12,24,27648,0x7fd2ef6ec580,0x7fd2ec6244c0,16152841769894,16152841780518,16152841872678,16152841874332
|
|
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,149096,149096,4194304,256,0,0,16,24,28608,0x7fd2ef6ec400,0x7fd2ec624500,16152841891221,16152841899559,16152842079720,16152842102526
|
|
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,149096,149096,4194304,256,0,0,16,24,29312,0x7fd2ef6ec280,0x7fd2ec624540,16152842113026,16152842139400,16152842318761,16152842320472
|
|
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,149096,149096,4194304,256,0,0,12,24,30016,0x7fd2ef6ec100,0x7fd2ec624580,16152842337091,16152842346921,16152842438922,16152842440729
|
|
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,149096,149096,4194304,256,0,0,8,24,30976,0x7fd2ed04df80,0x7fd2ec6245c0,16152842454849,16152842464202,16152842556363,16152842557636
|
|
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,149096,149096,4194304,256,0,0,12,24,31680,0x7fd2ed04de00,0x7fd2ec624600,16152842578066,16152842589163,16152842682443,16152842683654
|
|
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,149096,149096,4194304,256,0,0,16,24,32640,0x7fd2ed04dc80,0x7fd2ec624640,16152842700193,16152842709323,16152842889805,16152842891099
|
|
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,149096,149096,4194304,256,0,0,12,24,33600,0x7fd2ed04db00,0x7fd2ec624680,16152842905339,16152842913165,16152843093646,16152843094894
|
|
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,149096,149096,4194304,256,0,0,12,24,34560,0x7fd2ed04d980,0x7fd2ec6246c0,16152843109654,16152843117486,16152843210767,16152843211902
|
|
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,149096,149096,4194304,256,0,0,8,24,35520,0x7fd2ed04d800,0x7fd2ec624700,16152843227162,16152843235087,16152843329167,16152843330579
|
|
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,149096,149096,4194304,256,0,0,12,24,36224,0x7fd2ed04d680,0x7fd2ec624740,16152843351289,16152843361327,16152843453968,16152843455186
|
|
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,149096,149096,4194304,256,0,0,12,24,37184,0x7fd2ef6ec500,0x7fd2ec624780,16152843469466,16152843477168,16152843657169,16152843658322
|
|
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,149096,149096,4194304,256,0,0,12,24,38144,0x7fd2ef6ec380,0x7fd2ec6247c0,16152843673632,16152843682129,16152843863730,16152843864957
|
|
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,149096,149096,4194304,256,0,0,12,24,39104,0x7fd2ef6ec200,0x7fd2ec624800,16152843880097,16152843887891,16152843982131,16152843983485
|
|
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,149096,149096,4194304,256,0,0,8,24,40320,0x7fd2ef6ec080,0x7fd2ec624840,16152843998004,16152844005811,16152844100372,16152844101712
|
|
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,149096,149096,4194304,256,0,0,12,24,41280,0x7fd2ed04df00,0x7fd2ec624880,16152844122732,16152844133172,16152844226293,16152844227529
|
|
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,149096,149096,4194304,256,0,0,12,24,42240,0x7fd2ed04dd80,0x7fd2ec6248c0,16152844244319,16152844252373,16152844431574,16152844432755
|
|
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,149096,149096,4194304,256,0,0,12,24,43200,0x7fd2ed04dc00,0x7fd2ec624900,16152844448374,16152844457174,16152844637815,16152844639170
|
|
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,149096,149096,4194304,256,0,0,8,24,44160,0x7fd2ed04da80,0x7fd2ec624940,16152844653980,16152844662775,16152844756536,16152844757758
|
|
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,149096,149096,4194304,256,0,0,12,24,45376,0x7fd2ed04d900,0x7fd2ec624980,16152844772457,16152844781016,16152844875417,16152844876505
|
|
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,149096,149096,4194304,256,0,0,12,24,46336,0x7fd2ed04d780,0x7fd2ec6249c0,16152844896995,16152844907577,16152845001977,16152845003262
|
|
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,149096,149096,4194304,256,0,0,12,24,47552,0x7fd2ed04d600,0x7fd2ec624a00,16152845018252,16152845026778,16152845205179,16152845206358
|
|
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,149096,149096,4194304,256,0,0,12,24,48512,0x7fd2ef6ec480,0x7fd2ec624a40,16152845220947,16152845229659,16152845409500,16152845410653
|
|
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,149096,149096,4194304,256,0,0,8,24,49472,0x7fd2ef6ec300,0x7fd2ec624a80,16152845425753,16152845434300,16152845527101,16152845528381
|
|
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,149096,149096,4194304,256,0,0,12,24,50688,0x7fd2ef6ec180,0x7fd2ec624ac0,16152845542580,16152845551901,16152845645341,16152845646448
|
|
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,149096,149096,4194304,256,0,0,12,24,51648,0x7fd2ef6ec000,0x7fd2ec624b00,16152845667157,16152845678302,16152845769822,16152845771125
|
|
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,149096,149096,4194304,256,0,0,12,24,52864,0x7fd2ed04de80,0x7fd2ec624b40,16152845788175,16152845796862,16152845975583,16152845976861
|
|
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,149096,149096,4194304,256,0,0,12,24,54080,0x7fd2ed04dd00,0x7fd2ec624b80,16152845990910,16152845999903,16152846179265,16152846180466
|
|
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,149096,149096,4194304,256,0,0,8,24,55296,0x7fd2ed04db80,0x7fd2ec624bc0,16152846194656,16152846202785,16152846296385,16152846297793
|
|
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,149096,149096,4194304,256,0,0,12,24,56768,0x7fd2ed04da00,0x7fd2ec624c00,16152846312133,16152846320225,16152846415906,16152846417191
|
|
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,149096,149096,4194304,256,0,0,12,24,57728,0x7fd2ed04d880,0x7fd2ec624c40,16152846437750,16152846448386,16152846541667,16152846543048
|
|
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,149096,149096,4194304,256,0,0,12,24,58944,0x7fd2ed04d700,0x7fd2ec624c80,16152846556878,16152846564867,16152846742948,16152846744494
|
|
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,149096,149096,4194304,256,0,0,12,24,60160,0x7fd2ef6ec580,0x7fd2ec624cc0,16152846759263,16152846767428,16152846947269,16152846948589
|
|
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,149096,149096,4194304,256,0,0,8,24,61376,0x7fd2ef6ec400,0x7fd2ec624d00,16152846962879,16152846971109,16152847065990,16152847067376
|
|
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,149096,149096,4194304,256,0,0,12,24,62848,0x7fd2ef6ec280,0x7fd2ec624d40,16152847083506,16152847091590,16152847190791,16152847192204
|
|
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,149096,149096,4194304,256,0,0,12,24,63808,0x7fd2ef6ec100,0x7fd2ec624d80,16152847213563,16152847224231,16152847317511,16152847318711
|
|
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,149096,149096,4194304,256,0,0,12,24,65024,0x7fd2ed04df80,0x7fd2ec624dc0,16152847334440,16152847343272,16152847522793,16152847524256
|
|
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,149096,149096,4194304,256,0,0,12,24,66240,0x7fd2ed04de00,0x7fd2ec624e00,16152847539276,16152847547753,16152847728874,16152847730232
|
|
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,149096,149096,4194304,256,0,0,8,24,67456,0x7fd2ed04dc80,0x7fd2ec624e40,16152847744341,16152847752234,16152847847275,16152847848629
|
|
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,149096,149096,4194304,256,0,0,12,24,68928,0x7fd2ed04db00,0x7fd2ec624e80,16152847863269,16152847871755,16152847976555,16152847977906
|
|
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,149096,149096,4194304,256,0,0,12,24,70144,0x7fd2ed04d980,0x7fd2ec624ec0,16152847998736,16152848009516,16152848102476,16152848103873
|
|
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,149096,149096,4194304,256,0,0,12,24,71616,0x7fd2ed04d800,0x7fd2ec624f00,16152848119633,16152848127436,16152848307437,16152848308749
|
|
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,149096,149096,4194304,256,0,0,12,24,72832,0x7fd2ed04d680,0x7fd2ec624f40,16152848324599,16152848333838,16152848513039,16152848514244
|
|
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,149096,149096,4194304,256,0,0,8,24,74048,0x7fd2ef6ec500,0x7fd2ec624f80,16152848528384,16152848537039,16152848630639,16152848631912
|
|
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,149096,149096,4194304,256,0,0,12,24,75776,0x7fd2ef6ec380,0x7fd2ec624fc0,16152848646421,16152848654960,16152848762000,16152848763189
|
|
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,149096,149096,4194304,256,0,0,12,24,76992,0x7fd2ef6ec200,0x7fd2ec625000,16152848784168,16152848794800,16152848888881,16152848890126
|
|
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,149096,149096,4194304,256,0,0,12,24,78464,0x7fd2ef6ec080,0x7fd2ec625040,16152848906666,16152848914321,16152849094962,16152849096111
|
|
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,149096,149096,4194304,256,0,0,12,24,79936,0x7fd2ed04df00,0x7fd2ec625080,16152849111891,16152849120722,16152849300563,16152849301807
|
|
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,149096,149096,4194304,256,0,0,8,24,81408,0x7fd2ed04dd80,0x7fd2ec6250c0,16152849315987,16152849324724,16152849419444,16152849420574
|
|
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,149096,149096,4194304,256,0,0,12,24,83136,0x7fd2ed04dc00,0x7fd2ec625100,16152849434754,16152849443124,16152849558325,16152849559501
|
|
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,149096,149096,4194304,256,0,0,12,24,84352,0x7fd2ed04da80,0x7fd2ec625140,16152849594610,16152849604405,16152849697846,16152849699138
|
|
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,149096,149096,4194304,256,0,0,12,24,85824,0x7fd2ed04d900,0x7fd2ec625180,16152849714208,16152849722006,16152849902007,16152849903174
|
|
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,149096,149096,4194304,256,0,0,12,24,87296,0x7fd2ed04d780,0x7fd2ec6251c0,16152849919183,16152849927127,16152850108248,16152850109759
|
|
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,149096,149096,4194304,256,0,0,12,24,88768,0x7fd2ed04d600,0x7fd2ec625200,16152850125549,16152850133529,16152850229049,16152850230186
|
|
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,149096,149096,4194304,256,0,0,12,24,90752,0x7fd2ef6ec480,0x7fd2ec625240,16152850245926,16152850254649,16152850374970,16152850376333
|
|
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,149096,149096,4194304,256,0,0,12,24,91968,0x7fd2ef6ec300,0x7fd2ec625280,16152850401782,16152850412250,16152850506011,16152850507270
|
|
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,149096,149096,4194304,256,0,0,12,24,93440,0x7fd2ef6ec180,0x7fd2ec6252c0,16152850523030,16152850530971,16152850710652,16152850711746
|
|
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,149096,149096,4194304,256,0,0,12,24,94912,0x7fd2ef6ec000,0x7fd2ec625300,16152850726355,16152850734332,16152850915773,16152850916971
|
|
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,149096,149096,4194304,256,0,0,12,24,96384,0x7fd2ed04de80,0x7fd2ec625340,16152850931631,16152850939133,16152851034654,16152851036098
|
|
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,149096,149096,4194304,256,0,0,12,24,98368,0x7fd2ed04dd00,0x7fd2ec625380,16152851051148,16152851059454,16152851185695,16152851187085
|
|
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,149096,149096,4194304,256,0,0,12,24,99584,0x7fd2ed04db80,0x7fd2ec6253c0,16152851206275,16152851219135,16152851313536,16152851314922
|
|
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,149096,149096,4194304,256,0,0,12,24,101312,0x7fd2ed04da00,0x7fd2ec625400,16152851330212,16152851338016,16152851517057,16152851518358
|
|
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,149096,149096,4194304,256,0,0,12,24,102784,0x7fd2ed04d880,0x7fd2ec625440,16152851531707,16152851539617,16152851718338,16152851719723
|
|
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,149096,149096,4194304,256,0,0,12,24,104256,0x7fd2ed04d700,0x7fd2ec625480,16152851735843,16152851743778,16152851837699,16152851838971
|
|
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,149096,149096,4194304,256,0,0,12,24,106240,0x7fd2ef6ec580,0x7fd2ec6254c0,16152851854440,16152851862499,16152851992900,16152851994127
|
|
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,149096,149096,4194304,256,0,0,12,24,107712,0x7fd2ef6ec400,0x7fd2ec625500,16152852015427,16152852026180,16152852119141,16152852120374
|
|
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,149096,149096,4194304,256,0,0,16,24,109440,0x7fd2ef6ec280,0x7fd2ec625540,16152852135504,16152852143941,16152852323622,16152852324870
|
|
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,149096,149096,4194304,256,0,0,16,24,111168,0x7fd2ef6ec100,0x7fd2ec625580,16152852341059,16152852348742,16152852528423,16152852529675
|
|
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,149096,149096,4194304,256,0,0,8,24,112896,0x7fd2ed04df80,0x7fd2ec6255c0,16152852545085,16152852553063,16152852648424,16152852649773
|
|
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,149096,149096,4194304,256,0,0,12,24,115136,0x7fd2ed04de00,0x7fd2ec625600,16152852665522,16152852673544,16152852812905,16152852814089
|
|
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,149096,149096,4194304,256,0,0,12,24,116608,0x7fd2ed04dc80,0x7fd2ec625640,16152852833679,16152852844745,16152852939146,16152852940436
|
|
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,149096,149096,4194304,256,0,0,16,24,118336,0x7fd2ed04db00,0x7fd2ec625680,16152852955136,16152852963146,16152853142027,16152853143232
|
|
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,149096,149096,4194304,256,0,0,16,24,120064,0x7fd2ed04d980,0x7fd2ec6256c0,16152853157051,16152853166507,16152853346348,16152853347537
|
|
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,149096,149096,4194304,256,0,0,12,24,121792,0x7fd2ed04d800,0x7fd2ec625700,16152853360867,16152853370028,16152853468269,16152853469484
|
|
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,149096,149096,4194304,256,0,0,12,24,124032,0x7fd2ed04d680,0x7fd2ec625740,16152853485814,16152853492909,16152853638510,16152853639671
|
|
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,149096,149096,4194304,256,0,0,12,24,125504,0x7fd2ef6ec500,0x7fd2ec625780,16152853660520,16152853671310,16152853765711,16152853766828
|
|
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,149096,149096,4194304,256,0,0,12,24,127488,0x7fd2ef6ec380,0x7fd2ec6257c0,16152853783077,16152853790991,16152853971952,16152853973173
|
|
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,149096,149096,4194304,256,0,0,12,24,129216,0x7fd2ef6ec200,0x7fd2ec625800,16152853988203,16152853996432,16152854176593,16152854177919
|
|
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,149096,149096,4194304,256,0,0,12,24,130944,0x7fd2ef6ec080,0x7fd2ec625840,16152854192328,16152854200913,16152854300914,16152854302156
|
|
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,149096,149096,4194304,256,0,0,12,24,133440,0x7fd2ed04df00,0x7fd2ec625880,16152854318386,16152854326354,16152854481715,16152854483322
|
|
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,149096,149096,4194304,256,0,0,12,24,134912,0x7fd2ed04dd80,0x7fd2ec6258c0,16152854504221,16152854515155,16152854610036,16152854611429
|
|
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,149096,149096,4194304,256,0,0,12,24,136896,0x7fd2ed04dc00,0x7fd2ec625900,16152854626689,16152854634996,16152854813557,16152854814985
|
|
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,149096,149096,4194304,256,0,0,12,24,138880,0x7fd2ed04da80,0x7fd2ec625940,16152854830104,16152854838197,16152855018358,16152855019800
|
|
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,149096,149096,4194304,256,0,0,12,24,140864,0x7fd2ed04d900,0x7fd2ec625980,16152855032890,16152855040598,16152855147959,16152855149187
|
|
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,149096,149096,4194304,256,0,0,12,24,143616,0x7fd2ed04d780,0x7fd2ec6259c0,16152855162497,16152855170519,16152855341400,16152855342713
|
|
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,149096,149096,4194304,256,0,0,12,24,145344,0x7fd2ed04d600,0x7fd2ec625a00,16152855364252,16152855374520,16152855469881,16152855470990
|
|
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,149096,149096,4194304,256,0,0,12,24,147584,0x7fd2ef6ec480,0x7fd2ec625a40,16152855487260,16152855495161,16152855675322,16152855676845
|
|
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,149096,149096,4194304,256,0,0,12,24,149568,0x7fd2ef6ec300,0x7fd2ec625a80,16152855691305,16152855699162,16152855882523,16152855884021
|
|
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,149096,149096,4194304,256,0,0,12,24,151552,0x7fd2ef6ec180,0x7fd2ec625ac0,16152855898111,16152855906204,16152856017084,16152856018378
|
|
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,149096,149096,4194304,256,0,0,12,24,154304,0x7fd2ef6ec000,0x7fd2ec625b00,16152856032528,16152856040444,16152856221085,16152856222473
|
|
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,149096,149096,4194304,256,0,0,12,24,156288,0x7fd2ed04de80,0x7fd2ec625b40,16152856244533,16152856254046,16152856354526,16152856356060
|
|
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,149096,149096,4194304,256,0,0,12,24,158784,0x7fd2ed04dd00,0x7fd2ec625b80,16152856371980,16152856380126,16152856565088,16152856566236
|
|
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,149096,149096,4194304,256,0,0,12,24,161024,0x7fd2ed04db80,0x7fd2ec625bc0,16152856581185,16152856589568,16152856773729,16152856774921
|
|
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,149096,149096,4194304,256,0,0,12,24,163264,0x7fd2ed04da00,0x7fd2ec625c00,16152856788361,16152856797089,16152856919330,16152856920538
|
|
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,149096,149096,4194304,256,0,0,12,24,166528,0x7fd2ed04d880,0x7fd2ec625c40,16152856934478,16152856943010,16152857149571,16152857170092
|
|
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,149096,149096,4194304,256,0,0,12,24,168512,0x7fd2ed04d700,0x7fd2ec625c80,16152857184842,16152857196931,16152857308772,16152857309999
|
|
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,149096,149096,4194304,256,0,0,12,24,171264,0x7fd2ef6ec580,0x7fd2ec625cc0,16152857326459,16152857335012,16152857518053,16152857519285
|
|
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,149096,149096,4194304,256,0,0,12,24,173760,0x7fd2ef6ec400,0x7fd2ec625d00,16152857534624,16152857542694,16152857728615,16152857729860
|
|
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,149096,149096,4194304,256,0,0,12,24,176256,0x7fd2ef6ec280,0x7fd2ec625d40,16152857743850,16152857753095,16152857887816,16152857889116
|
|
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,149096,149096,4194304,256,0,0,12,24,179776,0x7fd2ef6ec100,0x7fd2ec625d80,16152857903036,16152857911016,16152858143177,16152858189080
|
|
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,149096,149096,4194304,256,0,0,12,24,182272,0x7fd2ed04df80,0x7fd2ec625dc0,16152858204809,16152858215338,16152858342058,16152858343236
|
|
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,149096,149096,4194304,256,0,0,12,24,185536,0x7fd2ed04de00,0x7fd2ec625e00,16152858358216,16152858366219,16152858557420,16152858558612
|
|
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,149096,149096,4194304,256,0,0,12,24,188544,0x7fd2ed04dc80,0x7fd2ec625e40,16152858574021,16152858583020,16152858778701,16152858779857
|
|
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,149096,149096,4194304,256,0,0,12,24,191552,0x7fd2ed04db00,0x7fd2ec625e80,16152858794426,16152858802701,16152858962862,16152858964143
|
|
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,149096,149096,4194304,256,0,0,12,24,195840,0x7fd2ed04d980,0x7fd2ec625ec0,16152858979122,16152858987182,16152859271184,16152859290665
|
|
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,149096,149096,4194304,256,0,0,12,24,198592,0x7fd2ed04d800,0x7fd2ec625f00,16152859306545,16152859317264,16152859466385,16152859467801
|
|
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,149096,149096,4194304,256,0,0,12,24,202368,0x7fd2ed04d680,0x7fd2ec625f40,16152859485761,16152859494545,16152859704627,16152859724346
|
|
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,149096,149096,4194304,256,0,0,12,24,205888,0x7fd2ef6ec500,0x7fd2ec625f80,16152859733066,16152859742707,16152859952148,16152859970410
|
|
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,149096,149096,4194304,256,0,0,12,24,209408,0x7fd2ef6ec380,0x7fd2ec625fc0,16152859980140,16152859990388,16152860175990,16152860177246
|
|
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,149096,149096,4194304,256,0,0,12,24,214464,0x7fd2ef6ec200,0x7fd2ec626000,16152860193255,16152860202070,16152860536792,16152860552537
|
|
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,149096,149096,4194304,256,0,0,12,24,217728,0x7fd2ef6ec080,0x7fd2ec626040,16152860568077,16152860578872,16152860746553,16152860747793
|
|
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,149096,149096,4194304,256,0,0,12,24,222016,0x7fd2ed04df00,0x7fd2ec626080,16152860763873,16152860772313,16152861001115,16152861016807
|
|
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,149096,149096,4194304,256,0,0,12,24,226048,0x7fd2ed04dd80,0x7fd2ec6260c0,16152861024217,16152861034715,16152861263836,16152861280851
|
|
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,149096,149096,4194304,256,0,0,12,24,230080,0x7fd2ed04dc00,0x7fd2ec626100,16152861289341,16152861299676,16152861510398,16152861526036
|
|
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,149096,149096,4194304,256,0,0,12,24,235904,0x7fd2ed04da80,0x7fd2ec626140,16152861535296,16152861544478,16152861929760,16152861944987
|
|
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,149096,149096,4194304,256,0,0,12,24,239424,0x7fd2ed04d900,0x7fd2ec626180,16152861961406,16152861971680,16152862158722,16152862160272
|
|
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,149096,149096,4194304,256,0,0,12,24,244224,0x7fd2ed04d780,0x7fd2ec6261c0,16152862176561,16152862184802,16152862434243,16152862475775
|
|
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,149096,149096,4194304,256,0,0,12,24,248768,0x7fd2ed04d600,0x7fd2ec626200,16152862483115,16152862493604,16152862740325,16152862785168
|
|
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,149096,149096,4194304,256,0,0,12,24,253312,0x7fd2ef6ec480,0x7fd2ec626240,16152862793358,16152862803685,16152863040487,16152863083291
|
|
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,149096,149096,4194304,256,0,0,8,24,255552,0x7fd2ef6ec300,0x7fd2ec626280,16152863091701,16152863102087,16152863554730,16152863594710
|
|
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,149096,149096,4194304,256,0,0,12,24,259840,0x7fd2ef6ec180,0x7fd2ec6262c0,16152863611570,16152863622570,16152863848492,16152863888064
|
|
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,149096,149096,4194304,256,0,0,12,24,265664,0x7fd2ef6ec000,0x7fd2ec626300,16152863896404,16152863906732,16152864204974,16152864247676
|
|
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,149096,149096,4194304,256,0,0,12,24,271232,0x7fd2ed04de80,0x7fd2ec626340,16152864258076,16152864267534,16152864566416,16152864609298
|
|
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,149096,149096,4194304,256,0,0,8,24,273216,0x7fd2ed04dd00,0x7fd2ec626380,16152864619828,16152864630257,16152864926578,16152864966330
|
|
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,149096,149096,4194304,256,0,0,8,24,275712,0x7fd2ed04db80,0x7fd2ec6263c0,16152864974580,16152864984979,16152865542582,16152865558127
|
|
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,149096,149096,4194304,256,0,0,12,24,280768,0x7fd2ed04da00,0x7fd2ec626400,16152865575317,16152865585942,16152865849304,16152865864400
|
|
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,149096,149096,4194304,256,0,0,12,24,287616,0x7fd2ed04d880,0x7fd2ec626440,16152865872190,16152865882744,16152866233786,16152866280261
|
|
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,149096,149096,4194304,256,0,0,12,24,294208,0x7fd2ed04d700,0x7fd2ec626480,16152866288211,16152866303227,16152866652829,16152866697372
|
|
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,149096,149096,4194304,256,0,0,8,24,296960,0x7fd2ef6ec580,0x7fd2ec6264c0,16152866706782,16152866717309,16152867064351,16152867104123
|
|
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,149096,149096,4194304,256,0,0,8,24,299968,0x7fd2ef6ec400,0x7fd2ec626500,16152867113003,16152867122912,16152867784516,16152867827027
|
|
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,149096,149096,4194304,256,0,0,8,24,302720,0x7fd2ef6ec280,0x7fd2ec626540,16152867843806,16152867853636,16152868300999,16152868345115
|
|
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,149096,149096,4194304,256,0,0,12,24,305472,0x7fd2ef6ec100,0x7fd2ec626580,16152868353865,16152868363879,16152868827882,16152868872064
|
|
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,149096,149096,4194304,256,0,0,12,24,308224,0x7fd2ed04df80,0x7fd2ec6265c0,16152868883563,16152868898762,16152869359725,16152869404262
|
|
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,149096,149096,4194304,256,0,0,8,24,310976,0x7fd2ed04de00,0x7fd2ec626600,16152869412392,16152869423406,16152869874928,16152869891551
|
|
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,149096,149096,4194304,256,0,0,8,24,313216,0x7fd2ed04dc80,0x7fd2ec626640,16152869900981,16152869911089,16152870780054,16152870826350
|
|
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,149096,149096,4194304,256,0,0,8,24,315968,0x7fd2ed04db00,0x7fd2ec626680,16152870843390,16152870854134,16152871707099,16152871753650
|
|
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,149096,149096,4194304,256,0,0,12,24,318720,0x7fd2ed04d980,0x7fd2ec6266c0,16152871763479,16152871773340,16152872657345,16152872701779
|
|
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,149096,149096,4194304,256,0,0,12,24,321472,0x7fd2ed04d800,0x7fd2ec626700,16152872712618,16152872727586,16152873607591,16152873652098
|
|
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,149096,149096,4194304,256,0,0,8,24,324224,0x7fd2ed04d680,0x7fd2ec626740,16152873660307,16152873677671,16152874536397,16152874584117
|
|
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,149096,149096,4194304,256,0,0,8,24,326464,0x7fd2ef6ec500,0x7fd2ec626780,16152874593087,16152874603917,16152876302327,16152876375057
|
|
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,149096,149096,4194304,256,0,0,8,24,329216,0x7fd2ef6ec380,0x7fd2ec6267c0,16152876391507,16152876402328,16152878066338,16152878140668
|
|
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,149096,149096,4194304,256,0,0,12,24,331968,0x7fd2ef6ec200,0x7fd2ec626800,16152878149588,16152878159939,16152879883949,16152879951118
|
|
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,149096,149096,4194304,256,0,0,12,24,334720,0x7fd2ef6ec080,0x7fd2ec626840,16152879962078,16152879977390,16152881692920,16152881760338
|
|
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,149096,149096,4194304,256,0,0,8,24,337472,0x7fd2ed04df00,0x7fd2ec626880,16152881770538,16152881779321,16152883454211,16152883523129
|
|
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,149096,149096,4194304,256,0,0,8,24,0,0x7fd2ed04dd80,0x7fd2ec6268c0,16152883531449,16152883541891,16152886898872,16152886973513
|