169 lines
41 KiB
CSV
169 lines
41 KiB
CSV
|
|
Index,KernelName,gpu-id,queue-id,queue-index,pid,tid,grd,wgr,lds,scr,vgpr,sgpr,fbar,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,BeginNs,EndNs,CompleteNs
|
||
|
|
0,"__amd_rocclr_fillBufferAligned.kd",0,0,0,207917,207917,33554432,256,0,0,4,32,4160,0x0,0x7ff54c204280,524288,5490003,614888704,17354329285041,17352075152262,17354476649922,17354476742662
|
||
|
|
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,207917,207917,32768,256,0,0,12,24,13888,0x0,0x7ff54c223f80,4096,38964,4359388,17354481900826,17354476649922,17354482028645,17354482033612
|
||
|
|
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,207917,207917,4194304,256,0,0,12,24,14336,0x7ff56a9d1380,0x7ff54c223fc0,524288,10857982,1216044208,17354482068181,17354482028645,17354482412005,17354482414992
|
||
|
|
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,207917,207917,4194304,256,0,0,16,24,15040,0x7ff56a9d1200,0x7ff54c224000,524288,11440844,1281353888,17354482451201,17354482412005,17354482824325,17354482826771
|
||
|
|
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,207917,207917,4194304,256,0,0,16,24,15488,0x7ff56a9d1080,0x7ff54c224040,524288,11563274,1295063352,17354482858941,17354482824325,17354483221606,17354483224051
|
||
|
|
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,207917,207917,4194304,256,0,0,12,24,15936,0x7ff568331f00,0x7ff54c224080,524288,10915927,1222546744,17354483256080,17354483221606,17354483536806,17354483539213
|
||
|
|
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,207917,207917,4194304,256,0,0,12,24,16384,0x7ff568331d80,0x7ff54c2240c0,524288,10662008,1194169692,17354483570782,17354483536806,17354483850246,17354483852814
|
||
|
|
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,207917,207917,4194304,256,0,0,12,24,17088,0x7ff568331c00,0x7ff54c224100,524288,10973678,1229016936,17354483895843,17354483850246,17354484165926,17354484168406
|
||
|
|
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,207917,207917,4194304,256,0,0,16,24,17792,0x7ff568331a80,0x7ff54c224140,524288,11527675,1291088972,17354484199805,17354484165926,17354484564166,17354484566656
|
||
|
|
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,207917,207917,4194304,256,0,0,16,24,18496,0x7ff568331900,0x7ff54c224180,524288,11527101,1291006048,17354484596665,17354484564166,17354484961447,17354484963925
|
||
|
|
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,207917,207917,4194304,256,0,0,16,24,19200,0x7ff568331780,0x7ff54c2241c0,524288,11200150,1254408664,17354484994414,17354484961447,17354485281127,17354485283697
|
||
|
|
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,207917,207917,4194304,256,0,0,16,24,19904,0x7ff568331600,0x7ff54c224200,524288,11034518,1235829080,17354485314786,17354485281127,17354485586727,17354485589099
|
||
|
|
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,207917,207917,4194304,256,0,0,12,24,20608,0x7ff56a9d1480,0x7ff54c224240,524288,11173012,1251342508,17354485628148,17354485586727,17354485891847,17354485894371
|
||
|
|
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,207917,207917,4194304,256,0,0,16,24,21312,0x7ff56a9d1300,0x7ff54c224280,524288,11622798,1301717308,17354485925970,17354485891847,17354486299367,17354486301990
|
||
|
|
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,207917,207917,4194304,256,0,0,16,24,22016,0x7ff56a9d1180,0x7ff54c2242c0,524288,11442532,1281506936,17354486333409,17354486299367,17354486701608,17354486703399
|
||
|
|
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,207917,207917,4194304,256,0,0,16,24,22720,0x7ff56a9d1000,0x7ff54c224300,524288,11364325,1272770828,17354486734538,17354486701608,17354486985608,17354486987322
|
||
|
|
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,207917,207917,4194304,256,0,0,12,24,23424,0x7ff568331e80,0x7ff54c224340,524288,10924955,1223566412,17354487017751,17354486985608,17354487268008,17354487269924
|
||
|
|
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,207917,207917,4194304,256,0,0,12,24,24128,0x7ff568331d00,0x7ff54c224380,524288,11238357,1258667288,17354487307143,17354487268008,17354487549128,17354487550917
|
||
|
|
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,207917,207917,4194304,256,0,0,16,24,24832,0x7ff568331b80,0x7ff54c2243c0,524288,11439307,1281215924,17354487582766,17354487549128,17354487916168,17354487918087
|
||
|
|
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,207917,207917,4194304,256,0,0,16,24,25536,0x7ff568331a00,0x7ff54c224400,524288,11474076,1285068048,17354487948296,17354487916168,17354488290889,17354488292747
|
||
|
|
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,207917,207917,4194304,256,0,0,12,24,26240,0x7ff568331880,0x7ff54c224440,524288,10853660,1215612728,17354488323457,17354488290889,17354488573609,17354488575600
|
||
|
|
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,207917,207917,4194304,256,0,0,12,24,26944,0x7ff568331700,0x7ff54c224480,524288,11131606,1246680240,17354488606069,17354488573609,17354488854409,17354488856263
|
||
|
|
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,207917,207917,4194304,256,0,0,12,24,27648,0x7ff56a9d1580,0x7ff54c2244c0,524288,11001424,1232168916,17354488893692,17354488854409,17354489135049,17354489136925
|
||
|
|
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,207917,207917,4194304,256,0,0,16,24,28608,0x7ff56a9d1400,0x7ff54c224500,524288,11317552,1267548504,17354489167874,17354489135049,17354489501609,17354489503575
|
||
|
|
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,207917,207917,4194304,256,0,0,16,24,29312,0x7ff56a9d1280,0x7ff54c224540,524288,11508613,1288916096,17354489534455,17354489501609,17354489873930,17354489875816
|
||
|
|
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,207917,207917,4194304,256,0,0,12,24,30016,0x7ff56a9d1100,0x7ff54c224580,524288,10981444,1229917704,17354489906525,17354489873930,17354490152970,17354490155418
|
||
|
|
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,207917,207917,4194304,256,0,0,8,24,30976,0x7ff568331f80,0x7ff54c2245c0,524288,10421587,1167141584,17354490185858,17354490152970,17354490436330,17354490438301
|
||
|
|
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,207917,207917,4194304,256,0,0,12,24,31680,0x7ff568331e00,0x7ff54c224600,524288,11185337,1252760760,17354490476260,17354490436330,17354490714410,17354490716254
|
||
|
|
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,207917,207917,4194304,256,0,0,16,24,32640,0x7ff568331c80,0x7ff54c224640,524288,11501667,1288164888,17354490746123,17354490714410,17354491085130,17354491086894
|
||
|
|
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,207917,207917,4194304,256,0,0,12,24,33600,0x7ff568331b00,0x7ff54c224680,524288,11400002,1276790692,17354491117613,17354491085130,17354491448331,17354491450244
|
||
|
|
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,207917,207917,4194304,256,0,0,12,24,34560,0x7ff568331980,0x7ff54c2246c0,524288,10727380,1201429272,17354491481423,17354491448331,17354491727371,17354491729177
|
||
|
|
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,207917,207917,4194304,256,0,0,8,24,35520,0x7ff568331800,0x7ff54c224700,524288,10157877,1137635924,17354491759816,17354491727371,17354492006251,17354492008180
|
||
|
|
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,207917,207917,4194304,256,0,0,12,24,36224,0x7ff568331680,0x7ff54c224740,524288,10859785,1216270712,17354492045729,17354492006251,17354492283051,17354492284932
|
||
|
|
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,207917,207917,4194304,256,0,0,12,24,37184,0x7ff56a9d1500,0x7ff54c224780,524288,11513943,1289558416,17354492316541,17354492283051,17354492648011,17354492649833
|
||
|
|
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,207917,207917,4194304,256,0,0,12,24,38144,0x7ff56a9d1380,0x7ff54c2247c0,524288,11439502,1281205176,17354492680972,17354492648011,17354493015372,17354493017323
|
||
|
|
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,207917,207917,4194304,256,0,0,12,24,39104,0x7ff56a9d1200,0x7ff54c224800,524288,10467232,1172297508,17354493048442,17354493015372,17354493291692,17354493293596
|
||
|
|
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,207917,207917,4194304,256,0,0,8,24,40320,0x7ff56a9d1080,0x7ff54c224840,524288,9840371,1102109956,17354493325715,17354493291692,17354493571692,17354493573438
|
||
|
|
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,207917,207917,4194304,256,0,0,12,24,41280,0x7ff568331f00,0x7ff54c224880,524288,10625621,1190085616,17354493612277,17354493571692,17354493854412,17354493856241
|
||
|
|
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,207917,207917,4194304,256,0,0,12,24,42240,0x7ff568331d80,0x7ff54c2248c0,524288,11513491,1289503816,17354493887880,17354493854412,17354494220972,17354494222961
|
||
|
|
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,207917,207917,4194304,256,0,0,12,24,43200,0x7ff568331c00,0x7ff54c224900,524288,11452299,1282629344,17354494254810,17354494220972,17354494589933,17354494591751
|
||
|
|
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,207917,207917,4194304,256,0,0,8,24,44160,0x7ff568331a80,0x7ff54c224940,524288,10646810,1192423676,17354494622901,17354494589933,17354494871373,17354494873114
|
||
|
|
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,207917,207917,4194304,256,0,0,12,24,45376,0x7ff568331900,0x7ff54c224980,524288,9780940,1095479548,17354494904353,17354494871373,17354495150413,17354495152246
|
||
|
|
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,207917,207917,4194304,256,0,0,12,24,46336,0x7ff568331780,0x7ff54c2249c0,524288,10705375,1199017196,17354495190375,17354495150413,17354495434733,17354495436549
|
||
|
|
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,207917,207917,4194304,256,0,0,12,24,47552,0x7ff568331600,0x7ff54c224a00,524288,11446343,1281959104,17354495468008,17354495434733,17354495799373,17354495801219
|
||
|
|
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,207917,207917,4194304,256,0,0,12,24,48512,0x7ff56a9d1480,0x7ff54c224a40,524288,11401805,1276983340,17354495833638,17354495799373,17354496164014,17354496165930
|
||
|
|
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,207917,207917,4194304,256,0,0,8,24,49472,0x7ff56a9d1300,0x7ff54c224a80,524288,10575191,1184491224,17354496197009,17354496164014,17354496442094,17354496443832
|
||
|
|
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,207917,207917,4194304,256,0,0,12,24,50688,0x7ff56a9d1180,0x7ff54c224ac0,524288,9138510,1023476616,17354496475331,17354496442094,17354496730734,17354496732525
|
||
|
|
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,207917,207917,4194304,256,0,0,12,24,51648,0x7ff56a9d1000,0x7ff54c224b00,524288,10673787,1195411828,17354496771244,17354496730734,17354497008334,17354497010197
|
||
|
|
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,207917,207917,4194304,256,0,0,12,24,52864,0x7ff568331e80,0x7ff54c224b40,524288,11388099,1275417824,17354497040816,17354497008334,17354497376174,17354497378067
|
||
|
|
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,207917,207917,4194304,256,0,0,12,24,54080,0x7ff568331d00,0x7ff54c224b80,524288,11207260,1255135008,17354497408337,17354497376174,17354497745775,17354497747758
|
||
|
|
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,207917,207917,4194304,256,0,0,8,24,55296,0x7ff568331b80,0x7ff54c224bc0,524288,10284526,1151773288,17354497778197,17354497745775,17354498028175,17354498029880
|
||
|
|
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,207917,207917,4194304,256,0,0,12,24,56768,0x7ff568331a00,0x7ff54c224c00,524288,7973345,892949220,17354498061009,17354498028175,17354498322415,17354498324142
|
||
|
|
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,207917,207917,4194304,256,0,0,12,24,57728,0x7ff568331880,0x7ff54c224c40,524288,10962463,1227780352,17354498362511,17354498322415,17354498607375,17354498609145
|
||
|
|
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,207917,207917,4194304,256,0,0,12,24,58944,0x7ff568331700,0x7ff54c224c80,524288,11331266,1269078352,17354498639544,17354498607375,17354498974735,17354498976565
|
||
|
|
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,207917,207917,4194304,256,0,0,12,24,60160,0x7ff56a9d1580,0x7ff54c224cc0,524288,11360197,1272288320,17354499007354,17354498974735,17354499343856,17354499345776
|
||
|
|
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,207917,207917,4194304,256,0,0,8,24,61376,0x7ff56a9d1400,0x7ff54c224d00,524288,10291971,1152557340,17354499376575,17354499343856,17354499631056,17354499632988
|
||
|
|
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,207917,207917,4194304,256,0,0,12,24,62848,0x7ff56a9d1280,0x7ff54c224d40,524288,6009675,673092204,17354499663427,17354499631056,17354499915056,17354499916980
|
||
|
|
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,207917,207917,4194304,256,0,0,12,24,63808,0x7ff56a9d1100,0x7ff54c224d80,524288,10156304,1137428364,17354499955029,17354499915056,17354500196016,17354500197793
|
||
|
|
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,207917,207917,4194304,256,0,0,12,24,65024,0x7ff568331f80,0x7ff54c224dc0,524288,11239424,1258785660,17354500229442,17354500196016,17354500562896,17354500564703
|
||
|
|
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,207917,207917,4194304,256,0,0,12,24,66240,0x7ff568331e00,0x7ff54c224e00,524288,11225938,1257274820,17354500596903,17354500562896,17354500928977,17354500930954
|
||
|
|
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,207917,207917,4194304,256,0,0,8,24,67456,0x7ff568331c80,0x7ff54c224e40,524288,10083755,1129346860,17354500961313,17354500928977,17354501209297,17354501211416
|
||
|
|
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,207917,207917,4194304,256,0,0,12,24,68928,0x7ff568331b00,0x7ff54c224e80,524288,5881424,658724268,17354501241556,17354501209297,17354501499537,17354501501429
|
||
|
|
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,207917,207917,4194304,256,0,0,12,24,70144,0x7ff568331980,0x7ff54c224ec0,524288,10349529,1159138432,17354501539028,17354501499537,17354501780977,17354501782891
|
||
|
|
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,207917,207917,4194304,256,0,0,12,24,71616,0x7ff568331800,0x7ff54c224f00,524288,11282018,1263575728,17354501813561,17354501780977,17354502145617,17354502147902
|
||
|
|
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,207917,207917,4194304,256,0,0,12,24,72832,0x7ff568331680,0x7ff54c224f40,524288,11311141,1266821532,17354502179021,17354502145617,17354502527058,17354502528892
|
||
|
|
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,207917,207917,4194304,256,0,0,8,24,74048,0x7ff56a9d1500,0x7ff54c224f80,524288,9783000,1095601592,17354502559431,17354502527058,17354502808498,17354502810484
|
||
|
|
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,207917,207917,4194304,256,0,0,12,24,75776,0x7ff56a9d1380,0x7ff54c224fc0,524288,4578063,512702672,17354502841603,17354502808498,17354503104658,17354503106506
|
||
|
|
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,207917,207917,4194304,256,0,0,12,24,76992,0x7ff56a9d1200,0x7ff54c225000,524288,10432135,1168436004,17354503144595,17354503104658,17354503383058,17354503385019
|
||
|
|
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,207917,207917,4194304,256,0,0,12,24,78464,0x7ff56a9d1080,0x7ff54c225040,524288,11154898,1249324180,17354503416498,17354503383058,17354503747698,17354503749500
|
||
|
|
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,207917,207917,4194304,256,0,0,12,24,79936,0x7ff568331f00,0x7ff54c225080,524288,11160342,1249947080,17354503780509,17354503747698,17354504114739,17354504116640
|
||
|
|
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,207917,207917,4194304,256,0,0,8,24,81408,0x7ff568331d80,0x7ff54c2250c0,524288,9442052,1057472024,17354504147729,17354504114739,17354504397459,17354504399382
|
||
|
|
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,207917,207917,4194304,256,0,0,12,24,83136,0x7ff568331c00,0x7ff54c225100,524288,3817146,427475904,17354504429942,17354504397459,17354504696979,17354504698824
|
||
|
|
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,207917,207917,4194304,256,0,0,12,24,84352,0x7ff568331a80,0x7ff54c225140,524288,10363380,1160687348,17354504749733,17354504696979,17354504977779,17354504979627
|
||
|
|
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,207917,207917,4194304,256,0,0,12,24,85824,0x7ff568331900,0x7ff54c225180,524288,11137512,1247382600,17354505010026,17354504977779,17354505344659,17354505346597
|
||
|
|
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,207917,207917,4194304,256,0,0,12,24,87296,0x7ff568331780,0x7ff54c2251c0,524288,11318350,1267620944,17354505378167,17354505344659,17354505721140,17354505723118
|
||
|
|
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,207917,207917,4194304,256,0,0,12,24,88768,0x7ff568331600,0x7ff54c225200,524288,9538306,1068261360,17354505754277,17354505721140,17354506005460,17354506007250
|
||
|
|
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,207917,207917,4194304,256,0,0,12,24,90752,0x7ff56a9d1480,0x7ff54c225240,524288,3579973,400942932,17354506038489,17354506005460,17354506325140,17354506327142
|
||
|
|
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,207917,207917,4194304,256,0,0,12,24,91968,0x7ff56a9d1300,0x7ff54c225280,524288,9988094,1118697116,17354506365761,17354506325140,17354506614900,17354506616734
|
||
|
|
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,207917,207917,4194304,256,0,0,12,24,93440,0x7ff56a9d1180,0x7ff54c2252c0,524288,11185722,1252769384,17354506647393,17354506614900,17354506979380,17354506981294
|
||
|
|
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,207917,207917,4194304,256,0,0,12,24,94912,0x7ff56a9d1000,0x7ff54c225300,524288,11261041,1261222636,17354507013354,17354506979380,17354507344821,17354507346575
|
||
|
|
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,207917,207917,4194304,256,0,0,12,24,96384,0x7ff568331e80,0x7ff54c225340,524288,9354010,1047657268,17354507377324,17354507344821,17354507625621,17354507627547
|
||
|
|
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,207917,207917,4194304,256,0,0,12,24,98368,0x7ff568331d00,0x7ff54c225380,524288,3348471,375006432,17354507657777,17354507625621,17354507942261,17354507944179
|
||
|
|
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,207917,207917,4194304,256,0,0,12,24,99584,0x7ff568331b80,0x7ff54c2253c0,524288,10154973,1137331668,17354507982728,17354507942261,17354508229461,17354508231191
|
||
|
|
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,207917,207917,4194304,256,0,0,12,24,101312,0x7ff568331a00,0x7ff54c225400,524288,11235130,1258295356,17354508262381,17354508229461,17354508602261,17354508603972
|
||
|
|
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,207917,207917,4194304,256,0,0,12,24,102784,0x7ff568331880,0x7ff54c225440,524288,11139944,1247645404,17354508634911,17354508602261,17354508968822,17354508970592
|
||
|
|
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,207917,207917,4194304,256,0,0,12,24,104256,0x7ff568331700,0x7ff54c225480,524288,8824237,988253564,17354509001531,17354508968822,17354509250422,17354509252355
|
||
|
|
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,207917,207917,4194304,256,0,0,12,24,106240,0x7ff56a9d1580,0x7ff54c2254c0,524288,3271509,366378940,17354509282894,17354509250422,17354509567542,17354509569426
|
||
|
|
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,207917,207917,4194304,256,0,0,12,24,107712,0x7ff56a9d1400,0x7ff54c225500,524288,9682416,1084359516,17354509608355,17354509567542,17354509845142,17354509847179
|
||
|
|
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,207917,207917,4194304,256,0,0,16,24,109440,0x7ff56a9d1280,0x7ff54c225540,524288,11137183,1247325940,17354509877898,17354509845142,17354510209622,17354510211759
|
||
|
|
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,207917,207917,4194304,256,0,0,16,24,111168,0x7ff56a9d1100,0x7ff54c225580,524288,11196174,1253927888,17354510243428,17354510209622,17354510577623,17354510579590
|
||
|
|
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,207917,207917,4194304,256,0,0,8,24,112896,0x7ff568331f80,0x7ff54c2255c0,524288,8160313,913979400,17354510609859,17354510577623,17354510865303,17354510866972
|
||
|
|
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,207917,207917,4194304,256,0,0,12,24,115136,0x7ff568331e00,0x7ff54c225600,524288,3200783,358418612,17354510898291,17354510865303,17354511193783,17354511195713
|
||
|
|
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,207917,207917,4194304,256,0,0,12,24,116608,0x7ff568331c80,0x7ff54c225640,524288,9667161,1082713760,17354511233662,17354511193783,17354511481143,17354511483006
|
||
|
|
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,207917,207917,4194304,256,0,0,16,24,118336,0x7ff568331b00,0x7ff54c225680,524288,11074463,1240334956,17354511513625,17354511481143,17354511845943,17354511847936
|
||
|
|
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,207917,207917,4194304,256,0,0,16,24,120064,0x7ff568331980,0x7ff54c2256c0,524288,11123849,1245885308,17354511879185,17354511845943,17354512210104,17354512211957
|
||
|
|
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,207917,207917,4194304,256,0,0,12,24,121792,0x7ff568331800,0x7ff54c225700,524288,6820109,763898536,17354512242376,17354512210104,17354512491544,17354512493479
|
||
|
|
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,207917,207917,4194304,256,0,0,12,24,124032,0x7ff568331680,0x7ff54c225740,524288,2956354,331091744,17354512523938,17354512491544,17354512822904,17354512824830
|
||
|
|
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,207917,207917,4194304,256,0,0,12,24,125504,0x7ff56a9d1500,0x7ff54c225780,524288,9383948,1050917980,17354512862889,17354512822904,17354513107064,17354513109003
|
||
|
|
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,207917,207917,4194304,256,0,0,12,24,127488,0x7ff56a9d1380,0x7ff54c2257c0,524288,11098067,1242998220,17354513139792,17354513107064,17354513472024,17354513473923
|
||
|
|
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,207917,207917,4194304,256,0,0,12,24,129216,0x7ff56a9d1200,0x7ff54c225800,524288,11135337,1247129664,17354513505452,17354513472024,17354513836985,17354513838864
|
||
|
|
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,207917,207917,4194304,256,0,0,12,24,130944,0x7ff56a9d1080,0x7ff54c225840,524288,5627169,630163216,17354513870213,17354513836985,17354514125785,17354514128256
|
||
|
|
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,207917,207917,4194304,256,0,0,12,24,133440,0x7ff568331f00,0x7ff54c225880,524288,2892703,323985012,17354514159265,17354514125785,17354514476505,17354514478437
|
||
|
|
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,207917,207917,4194304,256,0,0,12,24,134912,0x7ff568331d80,0x7ff54c2258c0,524288,8313611,931078808,17354514516396,17354514476505,17354514766585,17354514768299
|
||
|
|
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,207917,207917,4194304,256,0,0,12,24,136896,0x7ff568331c00,0x7ff54c225900,524288,11008670,1232933068,17354514798778,17354514766585,17354515133625,17354515135490
|
||
|
|
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,207917,207917,4194304,256,0,0,12,24,138880,0x7ff568331a80,0x7ff54c225940,524288,10971379,1228786656,17354515165939,17354515133625,17354515501306,17354515503200
|
||
|
|
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,207917,207917,4194304,256,0,0,12,24,140864,0x7ff568331900,0x7ff54c225980,524288,4745174,531538900,17354515533789,17354515501306,17354515794106,17354515796032
|
||
|
|
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,207917,207917,4194304,256,0,0,12,24,143616,0x7ff568331780,0x7ff54c2259c0,524288,2870534,321401980,17354515826431,17354515794106,17354516148186,17354516149983
|
||
|
|
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,207917,207917,4194304,256,0,0,12,24,145344,0x7ff568331600,0x7ff54c225a00,524288,7547889,845381688,17354516188372,17354516148186,17354516428986,17354516430815
|
||
|
|
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,207917,207917,4194304,256,0,0,12,24,147584,0x7ff56a9d1480,0x7ff54c225a40,524288,10975381,1229245756,17354516461445,17354516428986,17354516795867,17354516797886
|
||
|
|
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,207917,207917,4194304,256,0,0,12,24,149568,0x7ff56a9d1300,0x7ff54c225a80,524288,10962953,1227833952,17354516828075,17354516795867,17354517161147,17354517163056
|
||
|
|
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,207917,207917,4194304,256,0,0,12,24,151552,0x7ff56a9d1180,0x7ff54c225ac0,524288,3892147,435886824,17354517194135,17354517161147,17354517464187,17354517466058
|
||
|
|
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,207917,207917,4194304,256,0,0,12,24,154304,0x7ff56a9d1000,0x7ff54c225b00,524288,2831528,317114308,17354517497587,17354517464187,17354517832667,17354517834538
|
||
|
|
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,207917,207917,4194304,256,0,0,12,24,156288,0x7ff568331e80,0x7ff54c225b40,524288,5537287,620195024,17354517872517,17354517832667,17354518128027,17354518130081
|
||
|
|
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,207917,207917,4194304,256,0,0,12,24,158784,0x7ff568331d00,0x7ff54c225b80,524288,10590000,1186063380,17354518161800,17354518128027,17354518500988,17354518502971
|
||
|
|
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,207917,207917,4194304,256,0,0,12,24,161024,0x7ff568331b80,0x7ff54c225bc0,524288,10735241,1202321168,17354518533990,17354518500988,17354518871068,17354518872981
|
||
|
|
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,207917,207917,4194304,256,0,0,12,24,163264,0x7ff568331a00,0x7ff54c225c00,524288,3545190,396972964,17354518903200,17354518871068,17354519180348,17354519182333
|
||
|
|
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,207917,207917,4194304,256,0,0,12,24,166528,0x7ff568331880,0x7ff54c225c40,524288,2864075,320711620,17354519213082,17354519180348,17354519574108,17354519597332
|
||
|
|
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,207917,207917,4194304,256,0,0,12,24,168512,0x7ff568331700,0x7ff54c225c80,524288,4095093,458738364,17354519616381,17354519574108,17354519886268,17354519888154
|
||
|
|
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,207917,207917,4194304,256,0,0,12,24,171264,0x7ff56a9d1580,0x7ff54c225cc0,524288,10360306,1160333292,17354519919143,17354519886268,17354520256029,17354520257904
|
||
|
|
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,207917,207917,4194304,256,0,0,12,24,173760,0x7ff56a9d1400,0x7ff54c225d00,524288,10539476,1180359468,17354520288963,17354520256029,17354520634109,17354520635954
|
||
|
|
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,207917,207917,4194304,256,0,0,12,24,176256,0x7ff56a9d1280,0x7ff54c225d40,524288,2771968,310425980,17354520666893,17354520634109,17354520957629,17354520959546
|
||
|
|
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,207917,207917,4194304,256,0,0,12,24,179776,0x7ff56a9d1100,0x7ff54c225d80,524288,2865762,321055172,17354520990335,17354520957629,17354521376669,17354521396174
|
||
|
|
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,207917,207917,4194304,256,0,0,12,24,182272,0x7ff568331f80,0x7ff54c225dc0,524288,3085746,345611312,17354521417163,17354521376669,17354521702910,17354521704786
|
||
|
|
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,207917,207917,4194304,256,0,0,12,24,185536,0x7ff568331e00,0x7ff54c225e00,524288,8316734,931445504,17354521735255,17354521702910,17354522079550,17354522081846
|
||
|
|
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,207917,207917,4194304,256,0,0,12,24,188544,0x7ff568331c80,0x7ff54c225e40,524288,7552083,845816428,17354522113575,17354522079550,17354522465150,17354522487545
|
||
|
|
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,207917,207917,4194304,256,0,0,12,24,191552,0x7ff568331b00,0x7ff54c225e80,524288,2794723,313016060,17354522498995,17354522465150,17354522823390,17354522825246
|
||
|
|
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,207917,207917,4194304,256,0,0,12,24,195840,0x7ff568331980,0x7ff54c225ec0,524288,2860728,320353020,17354522856125,17354522823390,17354523297471,17354523318643
|
||
|
|
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,207917,207917,4194304,256,0,0,12,24,198592,0x7ff568331800,0x7ff54c225f00,524288,2701663,302512976,17354523337783,17354523297471,17354523639231,17354523641245
|
||
|
|
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,207917,207917,4194304,256,0,0,12,24,202368,0x7ff568331680,0x7ff54c225f40,524288,6772520,758493544,17354523672754,17354523639231,17354524040191,17354524061264
|
||
|
|
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,207917,207917,4194304,256,0,0,12,24,205888,0x7ff56a9d1500,0x7ff54c225f80,524288,6215183,696125288,17354524073813,17354524040191,17354524444191,17354524463953
|
||
|
|
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,207917,207917,4194304,256,0,0,12,24,209408,0x7ff56a9d1380,0x7ff54c225fc0,524288,2821370,315970404,17354524477113,17354524444191,17354524825312,17354524827164
|
||
|
|
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,207917,207917,4194304,256,0,0,12,24,214464,0x7ff56a9d1200,0x7ff54c226000,524288,2904656,325311588,17354524858613,17354524825312,17354525346592,17354525364639
|
||
|
|
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,207917,207917,4194304,256,0,0,12,24,217728,0x7ff56a9d1080,0x7ff54c226040,524288,2769298,310165676,17354525388069,17354525346592,17354525705472,17354525707410
|
||
|
|
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,207917,207917,4194304,256,0,0,12,24,222016,0x7ff568331f00,0x7ff54c226080,524288,5757167,644757412,17354525738750,17354525705472,17354526127712,17354526147669
|
||
|
|
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,207917,207917,4194304,256,0,0,12,24,226048,0x7ff568331d80,0x7ff54c2260c0,524288,5207214,583187308,17354526162328,17354526127712,17354526558433,17354526578067
|
||
|
|
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,207917,207917,4194304,256,0,0,12,24,230080,0x7ff568331c00,0x7ff54c226100,524288,2805716,314234204,17354526591537,17354526558433,17354526964833,17354526982737
|
||
|
|
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,207917,207917,4194304,256,0,0,12,24,235904,0x7ff568331a80,0x7ff54c226140,524288,2954352,330941000,17354526997876,17354526964833,17354527546273,17354527563441
|
||
|
|
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,207917,207917,4194304,256,0,0,12,24,239424,0x7ff568331900,0x7ff54c226180,524288,2792449,312711548,17354527587201,17354527546273,17354527929313,17354527931312
|
||
|
|
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,207917,207917,4194304,256,0,0,12,24,244224,0x7ff568331780,0x7ff54c2261c0,524288,5179074,580088928,17354527962151,17354527929313,17354528370114,17354528388260
|
||
|
|
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,207917,207917,4194304,256,0,0,12,24,248768,0x7ff568331600,0x7ff54c226200,524288,3230110,361748540,17354528403219,17354528370114,17354528810914,17354528828948
|
||
|
|
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,207917,207917,4194304,256,0,0,12,24,253312,0x7ff56a9d1480,0x7ff54c226240,524288,2789480,312404204,17354528844128,17354528810914,17354529241154,17354529258727
|
||
|
|
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,207917,207917,4194304,256,0,0,8,24,255552,0x7ff56a9d1300,0x7ff54c226280,524288,2360632,264397680,17354529274366,17354529241154,17354529883395,17354529900840
|
||
|
|
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,207917,207917,4194304,256,0,0,12,24,259840,0x7ff56a9d1180,0x7ff54c2262c0,524288,2731855,305819908,17354529923699,17354529883395,17354530297955,17354530315699
|
||
|
|
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,207917,207917,4194304,256,0,0,12,24,265664,0x7ff56a9d1000,0x7ff54c226300,524288,3142733,351966136,17354530332758,17354530297955,17354530791715,17354530833935
|
||
|
|
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,207917,207917,4194304,256,0,0,12,24,271232,0x7ff568331e80,0x7ff54c226340,524288,3557469,398514760,17354530846255,17354530791715,17354531303876,17354531346052
|
||
|
|
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,207917,207917,4194304,256,0,0,8,24,273216,0x7ff568331d00,0x7ff54c226380,524288,2392305,267879080,17354531356382,17354531303876,17354531815716,17354531857888
|
||
|
|
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,207917,207917,4194304,256,0,0,8,24,275712,0x7ff568331b80,0x7ff54c2263c0,524288,2374051,265832292,17354531869048,17354531815716,17354532593316,17354532611508
|
||
|
|
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,207917,207917,4194304,256,0,0,12,24,280768,0x7ff568331a00,0x7ff54c226400,524288,2635146,295135044,17354532633098,17354532593316,17354533049957,17354533072086
|
||
|
|
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,207917,207917,4194304,256,0,0,12,24,287616,0x7ff568331880,0x7ff54c226440,524288,3623182,405729292,17354533083006,17354533049957,17354533596517,17354533639601
|
||
|
|
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,207917,207917,4194304,256,0,0,12,24,294208,0x7ff568331700,0x7ff54c226480,524288,3411951,382125044,17354533652511,17354533596517,17354534164677,17354534210786
|
||
|
|
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,207917,207917,4194304,256,0,0,8,24,296960,0x7ff56a9d1580,0x7ff54c2264c0,524288,2387113,267390096,17354534223126,17354534164677,17354534740838,17354534785391
|
||
|
|
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,207917,207917,4194304,256,0,0,8,24,299968,0x7ff56a9d1400,0x7ff54c226500,524288,2402290,269079060,17354534796871,17354534740838,17354535618918,17354535661788
|
||
|
|
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,207917,207917,4194304,256,0,0,8,24,302720,0x7ff56a9d1280,0x7ff54c226540,524288,2391548,267702748,17354535680918,17354535618918,17354536281159,17354536324651
|
||
|
|
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,207917,207917,4194304,256,0,0,12,24,305472,0x7ff56a9d1100,0x7ff54c226580,524288,2592892,290390196,17354536335700,17354536281159,17354536966439,17354537009243
|
||
|
|
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,207917,207917,4194304,256,0,0,12,24,308224,0x7ff568331f80,0x7ff54c2265c0,524288,2598578,291001168,17354537021182,17354536966439,17354537642920,17354537685635
|
||
|
|
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,207917,207917,4194304,256,0,0,8,24,310976,0x7ff568331e00,0x7ff54c226600,524288,2405386,269346120,17354537696794,17354537642920,17354538317640,17354538363797
|
||
|
|
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,207917,207917,4194304,256,0,0,8,24,313216,0x7ff568331c80,0x7ff54c226640,524288,2417790,270771896,17354538375387,17354538317498,17354539410778,17354539460378
|
||
|
|
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,207917,207917,4194304,256,0,0,8,24,315968,0x7ff568331b00,0x7ff54c226680,524288,2432389,272436076,17354539480397,17354539410778,17354540487738,17354540530780
|
||
|
|
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,207917,207917,4194304,256,0,0,12,24,318720,0x7ff568331980,0x7ff54c2266c0,524288,2590749,290166744,17354540541880,17354540487738,17354541589818,17354541654180
|
||
|
|
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,207917,207917,4194304,256,0,0,12,24,321472,0x7ff568331800,0x7ff54c226700,524288,2598614,291037564,17354541666540,17354541589818,17354542707099,17354542781361
|
||
|
|
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,207917,207917,4194304,256,0,0,8,24,324224,0x7ff568331680,0x7ff54c226740,524288,2432360,272337216,17354542792300,17354542707099,17354543820539,17354543888851
|
||
|
|
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,207917,207917,4194304,256,0,0,8,24,326464,0x7ff56a9d1500,0x7ff54c226780,524288,2468887,276555488,17354543900581,17354543820539,17354545776220,17354545845160
|
||
|
|
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,207917,207917,4194304,256,0,0,8,24,329216,0x7ff56a9d1380,0x7ff54c2267c0,524288,2448121,274157696,17354545864339,17354545776220,17354547704060,17354547776529
|
||
|
|
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,207917,207917,4194304,256,0,0,12,24,331968,0x7ff56a9d1200,0x7ff54c226800,524288,2624098,293811652,17354547787798,17354547704060,17354549690781,17354549759966
|
||
|
|
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,207917,207917,4194304,256,0,0,12,24,334720,0x7ff56a9d1080,0x7ff54c226840,524288,2628534,294421696,17354549771606,17354549690781,17354551677342,17354551753513
|
||
|
|
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,207917,207917,4194304,256,0,0,8,24,337472,0x7ff568331f00,0x7ff54c226880,524288,2450128,274392520,17354551764853,17354551677342,17354553621502,17354553687413
|
||
|
|
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,207917,207917,4194304,256,0,0,8,24,0,0x7ff568331d80,0x7ff54c2268c0,524288,2462861,275870004,17354553698472,17354553621502,17354557238944,17354557311637
|