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",0,0,0,183214,183214,33554432,256,0,0,4,32,4160,0x0,0x7f2f90604280,524288,5470219,612567120,16923739028927,16921436568901,16923886206421,16923886320630
|
||
|
|
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,183214,183214,32768,256,0,0,12,24,13888,0x0,0x7f2f90623f80,4096,35703,3996116,16923891496516,16923886206421,16923891629922,16923891634782
|
||
|
|
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,183214,183214,4194304,256,0,0,12,24,14336,0x7f2f936bd380,0x7f2f90623fc0,524288,10698602,1198180000,16923891669571,16923891629922,16923892002401,16923892005181
|
||
|
|
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,183214,183214,4194304,256,0,0,16,24,15040,0x7f2f936bd200,0x7f2f90624000,524288,11529386,1291264640,16923892040270,16923892002401,16923892412639,16923892415079
|
||
|
|
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,183214,183214,4194304,256,0,0,16,24,15488,0x7f2f936bd080,0x7f2f90624040,524288,11442936,1281565832,16923892448068,16923892412639,16923892814878,16923892817157
|
||
|
|
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,183214,183214,4194304,256,0,0,12,24,15936,0x7f2f9108ff00,0x7f2f90624080,524288,10934300,1224616700,16923892851016,16923892814878,16923893121117,16923893123608
|
||
|
|
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,183214,183214,4194304,256,0,0,12,24,16384,0x7f2f9108fd80,0x7f2f906240c0,524288,10557223,1182474508,16923893156947,16923893121117,16923893429436,16923893431919
|
||
|
|
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,183214,183214,4194304,256,0,0,12,24,17088,0x7f2f9108fc00,0x7f2f90624100,524288,11097227,1242868304,16923893477218,16923893429436,16923893739355,16923893741650
|
||
|
|
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,183214,183214,4194304,256,0,0,16,24,17792,0x7f2f9108fa80,0x7f2f90624140,524288,11441631,1281472260,16923893774109,16923893739355,16923894134714,16923894137648
|
||
|
|
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,183214,183214,4194304,256,0,0,16,24,18496,0x7f2f9108f900,0x7f2f90624180,524288,11499863,1287956944,16923894170747,16923894134714,16923894550552,16923894552166
|
||
|
|
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,183214,183214,4194304,256,0,0,16,24,19200,0x7f2f9108f780,0x7f2f906241c0,524288,10933021,1224442028,16923894583345,16923894550552,16923894836151,16923894837707
|
||
|
|
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,183214,183214,4194304,256,0,0,16,24,19904,0x7f2f9108f600,0x7f2f90624200,524288,10968252,1228513156,16923894869036,16923894836151,16923895111670,16923895113459
|
||
|
|
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,183214,183214,4194304,256,0,0,12,24,20608,0x7f2f936bd480,0x7f2f90624240,524288,10941851,1225438900,16923895153898,16923895111670,16923895401590,16923895403320
|
||
|
|
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,183214,183214,4194304,256,0,0,16,24,21312,0x7f2f936bd300,0x7f2f90624280,524288,11367872,1273151504,16923895436189,16923895401590,16923895766228,16923895768120
|
||
|
|
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,183214,183214,4194304,256,0,0,16,24,22016,0x7f2f936bd180,0x7f2f906242c0,524288,11445712,1281925420,16923895800209,16923895766228,16923896131507,16923896133209
|
||
|
|
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,183214,183214,4194304,256,0,0,16,24,22720,0x7f2f936bd000,0x7f2f90624300,524288,10804371,1210090636,16923896165538,16923896131507,16923896410066,16923896411900
|
||
|
|
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,183214,183214,4194304,256,0,0,12,24,23424,0x7f2f9108fe80,0x7f2f90624340,524288,10860169,1216343880,16923896442980,16923896410066,16923896688945,16923896690672
|
||
|
|
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,183214,183214,4194304,256,0,0,12,24,24128,0x7f2f9108fd00,0x7f2f90624380,524288,11104952,1243729624,16923896730161,16923896688945,16923896976624,16923896978414
|
||
|
|
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,183214,183214,4194304,256,0,0,16,24,24832,0x7f2f9108fb80,0x7f2f906243c0,524288,11448157,1282181496,16923897011663,16923896976624,16923897340623,16923897342433
|
||
|
|
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,183214,183214,4194304,256,0,0,16,24,25536,0x7f2f9108fa00,0x7f2f90624400,524288,11348007,1270962080,16923897374622,16923897340623,16923897713422,16923897715002
|
||
|
|
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,183214,183214,4194304,256,0,0,12,24,26240,0x7f2f9108f880,0x7f2f90624440,524288,10940611,1225366456,16923897746171,16923897713422,16923897992301,16923897993863
|
||
|
|
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,183214,183214,4194304,256,0,0,12,24,26944,0x7f2f9108f700,0x7f2f90624480,524288,11047617,1237243540,16923898026233,16923897992301,16923898282060,16923898283785
|
||
|
|
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,183214,183214,4194304,256,0,0,12,24,27648,0x7f2f936bd580,0x7f2f906244c0,524288,10965745,1228109740,16923898323824,16923898282060,16923898561419,16923898563016
|
||
|
|
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,183214,183214,4194304,256,0,0,16,24,28608,0x7f2f936bd400,0x7f2f90624500,524288,11229845,1257672884,16923898595106,16923898561419,16923898927338,16923898929116
|
||
|
|
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,183214,183214,4194304,256,0,0,16,24,29312,0x7f2f936bd280,0x7f2f90624540,524288,11543877,1292916508,16923898960575,16923898927338,16923899295177,16923899296905
|
||
|
|
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,183214,183214,4194304,256,0,0,12,24,30016,0x7f2f936bd100,0x7f2f90624580,524288,10848522,1215015748,16923899328974,16923899295177,16923899573896,16923899575686
|
||
|
|
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,183214,183214,4194304,256,0,0,8,24,30976,0x7f2f9108ff80,0x7f2f906245c0,524288,10565199,1183266632,16923899607195,16923899573896,16923899849895,16923899851858
|
||
|
|
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,183214,183214,4194304,256,0,0,12,24,31680,0x7f2f9108fe00,0x7f2f90624600,524288,11140288,1247629732,16923899889887,16923899849895,16923900128134,16923900129700
|
||
|
|
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,183214,183214,4194304,256,0,0,16,24,32640,0x7f2f9108fc80,0x7f2f90624640,524288,11404324,1277206740,16923900161229,16923900128134,16923900496453,16923900498279
|
||
|
|
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,183214,183214,4194304,256,0,0,12,24,33600,0x7f2f9108fb00,0x7f2f90624680,524288,11334422,1269438248,16923900529968,16923900496453,16923900859332,16923900861138
|
||
|
|
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,183214,183214,4194304,256,0,0,12,24,34560,0x7f2f9108f980,0x7f2f906246c0,524288,10664204,1194370884,16923900892447,16923900859332,16923901133731,16923901135320
|
||
|
|
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,183214,183214,4194304,256,0,0,8,24,35520,0x7f2f9108f800,0x7f2f90624700,524288,10390289,1163667992,16923901167609,16923901133731,16923901410690,16923901412431
|
||
|
|
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,183214,183214,4194304,256,0,0,12,24,36224,0x7f2f9108f680,0x7f2f90624740,524288,10899535,1220731728,16923901450750,16923901410690,16923901690689,16923901692343
|
||
|
|
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,183214,183214,4194304,256,0,0,12,24,37184,0x7f2f936bd500,0x7f2f90624780,524288,11460318,1283521932,16923901724062,16923901690689,16923902058208,16923902059902
|
||
|
|
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,183214,183214,4194304,256,0,0,12,24,38144,0x7f2f936bd380,0x7f2f906247c0,524288,11366458,1273023084,16923902094841,16923902058208,16923902434366,16923902436341
|
||
|
|
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,183214,183214,4194304,256,0,0,12,24,39104,0x7f2f936bd200,0x7f2f90624800,524288,10607712,1188049924,16923902467950,16923902434366,16923902710685,16923902712403
|
||
|
|
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,183214,183214,4194304,256,0,0,8,24,40320,0x7f2f936bd080,0x7f2f90624840,524288,9845378,1102652808,16923902743672,16923902710685,16923902989725,16923902991534
|
||
|
|
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,183214,183214,4194304,256,0,0,12,24,41280,0x7f2f9108ff00,0x7f2f90624880,524288,10737438,1202544424,16923903030523,16923902989725,16923903278044,16923903279756
|
||
|
|
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,183214,183214,4194304,256,0,0,12,24,42240,0x7f2f9108fd80,0x7f2f906248c0,524288,11313154,1267075332,16923903311125,16923903278044,16923903642522,16923903644245
|
||
|
|
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,183214,183214,4194304,256,0,0,12,24,43200,0x7f2f9108fc00,0x7f2f90624900,524288,11282300,1263618072,16923903675274,16923903642522,16923904005561,16923904007254
|
||
|
|
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,183214,183214,4194304,256,0,0,8,24,44160,0x7f2f9108fa80,0x7f2f90624940,524288,10612846,1188589388,16923904038783,16923904005561,16923904284600,16923904286316
|
||
|
|
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,183214,183214,4194304,256,0,0,12,24,45376,0x7f2f9108f900,0x7f2f90624980,524288,9629482,1078423556,16923904317505,16923904284600,16923904564119,16923904565868
|
||
|
|
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,183214,183214,4194304,256,0,0,12,24,46336,0x7f2f9108f780,0x7f2f906249c0,524288,10768594,1206031112,16923904604977,16923904564119,16923904850998,16923904852659
|
||
|
|
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,183214,183214,4194304,256,0,0,12,24,47552,0x7f2f9108f600,0x7f2f90624a00,524288,11440995,1281347308,16923904884388,16923904850998,16923905214837,16923905216598
|
||
|
|
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,183214,183214,4194304,256,0,0,12,24,48512,0x7f2f936bd480,0x7f2f90624a40,524288,11297452,1265302732,16923905248427,16923905214837,16923905575956,16923905577758
|
||
|
|
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,183214,183214,4194304,256,0,0,8,24,49472,0x7f2f936bd300,0x7f2f90624a80,524288,10246218,1147480628,16923905610257,16923905575956,16923905851955,16923905853589
|
||
|
|
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,183214,183214,4194304,256,0,0,12,24,50688,0x7f2f936bd180,0x7f2f90624ac0,524288,9154629,1025306384,16923905885829,16923905851955,16923906135474,16923906137471
|
||
|
|
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,183214,183214,4194304,256,0,0,12,24,51648,0x7f2f936bd000,0x7f2f90624b00,524288,10500827,1175990968,16923906176850,16923906135474,16923906418833,16923906420393
|
||
|
|
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,183214,183214,4194304,256,0,0,12,24,52864,0x7f2f9108fe80,0x7f2f90624b40,524288,11299614,1265545808,16923906451582,16923906418833,16923906785392,16923906787022
|
||
|
|
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,183214,183214,4194304,256,0,0,12,24,54080,0x7f2f9108fd00,0x7f2f90624b80,524288,11309041,1266623096,16923906819841,16923906785392,16923907151951,16923907153691
|
||
|
|
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,183214,183214,4194304,256,0,0,8,24,55296,0x7f2f9108fb80,0x7f2f90624bc0,524288,10106766,1131924304,16923907184870,16923907151951,16923907431630,16923907433413
|
||
|
|
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,183214,183214,4194304,256,0,0,12,24,56768,0x7f2f9108fa00,0x7f2f90624c00,524288,7780594,871418352,16923907464222,16923907431630,16923907712589,16923907714334
|
||
|
|
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,183214,183214,4194304,256,0,0,12,24,57728,0x7f2f9108f880,0x7f2f90624c40,524288,10669848,1195051916,16923907752293,16923907712589,16923907993068,16923907994886
|
||
|
|
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,183214,183214,4194304,256,0,0,12,24,58944,0x7f2f9108f700,0x7f2f90624c80,524288,11326619,1268550228,16923908026555,16923907993068,16923908358667,16923908360335
|
||
|
|
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,183214,183214,4194304,256,0,0,12,24,60160,0x7f2f936bd580,0x7f2f90624cc0,524288,11267449,1261905356,16923908392784,16923908358667,16923908723626,16923908725454
|
||
|
|
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,183214,183214,4194304,256,0,0,8,24,61376,0x7f2f936bd400,0x7f2f90624d00,524288,10247179,1147729480,16923908756913,16923908723626,16923909007945,16923909009656
|
||
|
|
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,183214,183214,4194304,256,0,0,12,24,62848,0x7f2f936bd280,0x7f2f90624d40,524288,6289260,704355100,16923909041155,16923909007945,16923909290984,16923909292787
|
||
|
|
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,183214,183214,4194304,256,0,0,12,24,63808,0x7f2f936bd100,0x7f2f90624d80,524288,10383982,1163086976,16923909331986,16923909290984,16923909570183,16923909571969
|
||
|
|
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,183214,183214,4194304,256,0,0,12,24,65024,0x7f2f9108ff80,0x7f2f90624dc0,524288,11195283,1253831588,16923909605028,16923909570183,16923909938022,16923909939778
|
||
|
|
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,183214,183214,4194304,256,0,0,12,24,66240,0x7f2f9108fe00,0x7f2f90624e00,524288,11269221,1262106940,16923909970907,16923909938022,16923910307940,16923910309797
|
||
|
|
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,183214,183214,4194304,256,0,0,8,24,67456,0x7f2f9108fc80,0x7f2f90624e40,524288,10031547,1123517176,16923910341266,16923910307940,16923910591459,16923910593099
|
||
|
|
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,183214,183214,4194304,256,0,0,12,24,68928,0x7f2f9108fb00,0x7f2f90624e80,524288,5635151,631104564,16923910624538,16923910591459,16923910878658,16923910880220
|
||
|
|
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,183214,183214,4194304,256,0,0,12,24,70144,0x7f2f9108f980,0x7f2f90624ec0,524288,10151446,1136935336,16923910919239,16923910878658,16923911155298,16923911157092
|
||
|
|
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,183214,183214,4194304,256,0,0,12,24,71616,0x7f2f9108f800,0x7f2f90624f00,524288,11190899,1253364328,16923911189231,16923911155298,16923911515776,16923911517451
|
||
|
|
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,183214,183214,4194304,256,0,0,12,24,72832,0x7f2f9108f680,0x7f2f90624f40,524288,11237673,1258599096,16923911548740,16923911515776,16923911884575,16923911886320
|
||
|
|
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,183214,183214,4194304,256,0,0,8,24,74048,0x7f2f936bd500,0x7f2f90624f80,524288,9847209,1102897672,16923911917160,16923911884575,16923912162014,16923912163662
|
||
|
|
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,183214,183214,4194304,256,0,0,12,24,75776,0x7f2f936bd380,0x7f2f90624fc0,524288,4463374,499862796,16923912195851,16923912162014,16923912451453,16923912453214
|
||
|
|
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,183214,183214,4194304,256,0,0,12,24,76992,0x7f2f936bd200,0x7f2f90625000,524288,10245626,1147506896,16923912491522,16923912451453,16923912730012,16923912731845
|
||
|
|
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,183214,183214,4194304,256,0,0,12,24,78464,0x7f2f936bd080,0x7f2f90625040,524288,11227052,1257425504,16923912763224,16923912730012,16923913095291,16923913097274
|
||
|
|
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,183214,183214,4194304,256,0,0,12,24,79936,0x7f2f9108ff00,0x7f2f90625080,524288,11144682,1248213964,16923913129504,16923913095291,16923913458170,16923913460034
|
||
|
|
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,183214,183214,4194304,256,0,0,8,24,81408,0x7f2f9108fd80,0x7f2f906250c0,524288,9381009,1050578556,16923913490983,16923913458170,16923913735129,16923913736955
|
||
|
|
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,183214,183214,4194304,256,0,0,12,24,83136,0x7f2f9108fc00,0x7f2f90625100,524288,3959244,443420484,16923913767995,16923913735129,16923914031608,16923914033367
|
||
|
|
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,183214,183214,4194304,256,0,0,12,24,84352,0x7f2f9108fa80,0x7f2f90625140,524288,10572479,1184117028,16923914091165,16923914031608,16923914320407,16923914322458
|
||
|
|
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,183214,183214,4194304,256,0,0,12,24,85824,0x7f2f9108f900,0x7f2f90625180,524288,11133722,1246948012,16923914352837,16923914320407,16923914692886,16923914694827
|
||
|
|
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,183214,183214,4194304,256,0,0,12,24,87296,0x7f2f9108f780,0x7f2f906251c0,524288,11308838,1266570296,16923914726686,16923914692886,16923915062805,16923915064526
|
||
|
|
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,183214,183214,4194304,256,0,0,12,24,88768,0x7f2f9108f600,0x7f2f90625200,524288,9390068,1051635120,16923915095575,16923915062805,16923915339764,16923915341418
|
||
|
|
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,183214,183214,4194304,256,0,0,12,24,90752,0x7f2f936bd480,0x7f2f90625240,524288,3591290,402237984,16923915373107,16923915339764,16923915643283,16923915645019
|
||
|
|
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,183214,183214,4194304,256,0,0,12,24,91968,0x7f2f936bd300,0x7f2f90625280,524288,10072425,1128055460,16923915683128,16923915643283,16923915920082,16923915921951
|
||
|
|
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,183214,183214,4194304,256,0,0,12,24,93440,0x7f2f936bd180,0x7f2f906252c0,524288,11163849,1250299640,16923915953250,16923915920082,16923916281841,16923916283560
|
||
|
|
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,183214,183214,4194304,256,0,0,12,24,94912,0x7f2f936bd000,0x7f2f90625300,524288,11196891,1254049068,16923916315029,16923916281841,16923916647439,16923916649199
|
||
|
|
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,183214,183214,4194304,256,0,0,12,24,96384,0x7f2f9108fe80,0x7f2f90625340,524288,9374310,1049866452,16923916680408,16923916647439,16923916926959,16923916928661
|
||
|
|
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,183214,183214,4194304,256,0,0,12,24,98368,0x7f2f9108fd00,0x7f2f90625380,524288,3618455,405292444,16923916960340,16923916926959,16923917234158,16923917235862
|
||
|
|
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,183214,183214,4194304,256,0,0,12,24,99584,0x7f2f9108fb80,0x7f2f906253c0,524288,9977671,1117463660,16923917274970,16923917234158,16923917509997,16923917511823
|
||
|
|
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,183214,183214,4194304,256,0,0,12,24,101312,0x7f2f9108fa00,0x7f2f90625400,524288,11131345,1246712856,16923917542453,16923917509997,16923917877995,16923917879823
|
||
|
|
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,183214,183214,4194304,256,0,0,12,24,102784,0x7f2f9108f880,0x7f2f90625440,524288,11072313,1240095928,16923917910672,16923917877995,16923918247114,16923918248772
|
||
|
|
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,183214,183214,4194304,256,0,0,12,24,104256,0x7f2f9108f700,0x7f2f90625480,524288,8763748,981467992,16923918280751,16923918247114,16923918529513,16923918531213
|
||
|
|
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,183214,183214,4194304,256,0,0,12,24,106240,0x7f2f936bd580,0x7f2f906254c0,524288,3139086,351497052,16923918563102,16923918529513,16923918843592,16923918845184
|
||
|
|
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,183214,183214,4194304,256,0,0,12,24,107712,0x7f2f936bd400,0x7f2f90625500,524288,9674164,1083498616,16923918884683,16923918843592,16923919122311,16923919124025
|
||
|
|
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,183214,183214,4194304,256,0,0,16,24,109440,0x7f2f936bd280,0x7f2f90625540,524288,11106945,1243912384,16923919155464,16923919122311,16923919485990,16923919487785
|
||
|
|
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,183214,183214,4194304,256,0,0,16,24,111168,0x7f2f936bd100,0x7f2f90625580,524288,11141262,1247813272,16923919520124,16923919485990,16923919847909,16923919849564
|
||
|
|
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,183214,183214,4194304,256,0,0,8,24,112896,0x7f2f9108ff80,0x7f2f906255c0,524288,8238403,922668680,16923919882263,16923919847909,16923920126788,16923920128295
|
||
|
|
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,183214,183214,4194304,256,0,0,12,24,115136,0x7f2f9108fe00,0x7f2f90625600,524288,3012372,337341924,16923920159964,16923920126788,16923920447427,16923920449296
|
||
|
|
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,183214,183214,4194304,256,0,0,12,24,116608,0x7f2f9108fc80,0x7f2f90625640,524288,9930498,1112222344,16923920487985,16923920447427,16923920732706,16923920734347
|
||
|
|
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,183214,183214,4194304,256,0,0,16,24,118336,0x7f2f9108fb00,0x7f2f90625680,524288,11131971,1246746940,16923920764996,16923920732706,16923921097025,16923921098946
|
||
|
|
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,183214,183214,4194304,256,0,0,16,24,120064,0x7f2f9108f980,0x7f2f906256c0,524288,11038121,1236249248,16923921129976,16923921097025,16923921460064,16923921461696
|
||
|
|
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,183214,183214,4194304,256,0,0,12,24,121792,0x7f2f9108f800,0x7f2f90625700,524288,6974774,781111188,16923921492795,16923921460064,16923921739423,16923921741237
|
||
|
|
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,183214,183214,4194304,256,0,0,12,24,124032,0x7f2f9108f680,0x7f2f90625740,524288,2998475,335802132,16923921772466,16923921739423,16923922066142,16923922067868
|
||
|
|
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,183214,183214,4194304,256,0,0,12,24,125504,0x7f2f936bd500,0x7f2f90625780,524288,9093250,1018394076,16923922107336,16923922066142,16923922354941,16923922356779
|
||
|
|
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,183214,183214,4194304,256,0,0,12,24,127488,0x7f2f936bd380,0x7f2f906257c0,524288,10981701,1229959168,16923922387038,16923922354941,16923922718619,16923922720408
|
||
|
|
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,183214,183214,4194304,256,0,0,12,24,129216,0x7f2f936bd200,0x7f2f90625800,524288,11108635,1244141220,16923922751417,16923922718619,16923923082458,16923923084167
|
||
|
|
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,183214,183214,4194304,256,0,0,12,24,130944,0x7f2f936bd080,0x7f2f90625840,524288,6552181,733839340,16923923116106,16923923082458,16923923371257,16923923373049
|
||
|
|
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,183214,183214,4194304,256,0,0,12,24,133440,0x7f2f9108ff00,0x7f2f90625880,524288,2895014,324230272,16923923404598,16923923371257,16923923718456,16923923720578
|
||
|
|
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,183214,183214,4194304,256,0,0,12,24,134912,0x7f2f9108fd80,0x7f2f906258c0,524288,8568077,959486372,16923923759097,16923923718456,16923924003575,16923924005170
|
||
|
|
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,183214,183214,4194304,256,0,0,12,24,136896,0x7f2f9108fc00,0x7f2f90625900,524288,10997414,1231693544,16923924036139,16923924003575,16923924367094,16923924369059
|
||
|
|
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,183214,183214,4194304,256,0,0,12,24,138880,0x7f2f9108fa80,0x7f2f90625940,524288,11003905,1232429616,16923924399848,16923924367094,16923924733333,16923924734978
|
||
|
|
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,183214,183214,4194304,256,0,0,12,24,140864,0x7f2f9108f900,0x7f2f90625980,524288,4732039,529928600,16923924765917,16923924733333,16923925024052,16923925025750
|
||
|
|
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,183214,183214,4194304,256,0,0,12,24,143616,0x7f2f9108f780,0x7f2f906259c0,524288,2837024,317711700,16923925056729,16923925024052,16923925378451,16923925380339
|
||
|
|
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,183214,183214,4194304,256,0,0,12,24,145344,0x7f2f9108f600,0x7f2f90625a00,524288,7410307,830035864,16923925418678,16923925378451,16923925658930,16923925660561
|
||
|
|
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,183214,183214,4194304,256,0,0,12,24,147584,0x7f2f936bd480,0x7f2f90625a40,524288,10949222,1226342500,16923925692300,16923925658930,16923926024689,16923926026300
|
||
|
|
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,183214,183214,4194304,256,0,0,12,24,149568,0x7f2f936bd300,0x7f2f90625a80,524288,10938559,1225105876,16923926057929,16923926024689,16923926395727,16923926397599
|
||
|
|
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,183214,183214,4194304,256,0,0,12,24,151552,0x7f2f936bd180,0x7f2f90625ac0,524288,3715180,416105624,16923926429638,16923926395727,16923926696046,16923926697670
|
||
|
|
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,183214,183214,4194304,256,0,0,12,24,154304,0x7f2f936bd000,0x7f2f90625b00,524288,2846387,318766152,16923926729439,16923926696046,16923927059885,16923927061649
|
||
|
|
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,183214,183214,4194304,256,0,0,12,24,156288,0x7f2f9108fe80,0x7f2f90625b40,524288,5712074,639742572,16923927100758,16923927059885,16923927345964,16923927347951
|
||
|
|
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,183214,183214,4194304,256,0,0,12,24,158784,0x7f2f9108fd00,0x7f2f90625b80,524288,9849219,1103094656,16923927379160,16923927345964,16923927711723,16923927713320
|
||
|
|
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,183214,183214,4194304,256,0,0,12,24,161024,0x7f2f9108fb80,0x7f2f90625bc0,524288,10642757,1191979440,16923927745319,16923927711723,16923928077162,16923928078959
|
||
|
|
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,183214,183214,4194304,256,0,0,12,24,163264,0x7f2f9108fa00,0x7f2f90625c00,524288,3754319,420480140,16923928110838,16923928077162,16923928385001,16923928386590
|
||
|
|
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,183214,183214,4194304,256,0,0,12,24,166528,0x7f2f9108f880,0x7f2f90625c40,524288,2817466,315457464,16923928417769,16923928385001,16923928778119,16923928824247
|
||
|
|
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,183214,183214,4194304,256,0,0,12,24,168512,0x7f2f9108f700,0x7f2f90625c80,524288,3979765,445682976,16923928844456,16923928778119,16923929110438,16923929112268
|
||
|
|
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,183214,183214,4194304,256,0,0,12,24,171264,0x7f2f936bd580,0x7f2f90625cc0,524288,9683318,1084516040,16923929142868,16923929110438,16923929480677,16923929482467
|
||
|
|
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,183214,183214,4194304,256,0,0,12,24,173760,0x7f2f936bd400,0x7f2f90625d00,524288,10015535,1121753368,16923929515786,16923929480677,16923929855076,16923929856826
|
||
|
|
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,183214,183214,4194304,256,0,0,12,24,176256,0x7f2f936bd280,0x7f2f90625d40,524288,2808746,314489532,16923929888245,16923929855076,16923930176035,16923930177917
|
||
|
|
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,183214,183214,4194304,256,0,0,12,24,179776,0x7f2f936bd100,0x7f2f90625d80,524288,2856483,319978764,16923930210646,16923930176035,16923930597953,16923930645543
|
||
|
|
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,183214,183214,4194304,256,0,0,12,24,182272,0x7f2f9108ff80,0x7f2f90625dc0,524288,3029455,339233288,16923930665272,16923930597953,16923930945472,16923930947134
|
||
|
|
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,183214,183214,4194304,256,0,0,12,24,185536,0x7f2f9108fe00,0x7f2f90625e00,524288,8229965,921714152,16923930977903,16923930945472,16923931322591,16923931324013
|
||
|
|
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,183214,183214,4194304,256,0,0,12,24,188544,0x7f2f9108fc80,0x7f2f90625e40,524288,7994346,895360960,16923931356582,16923931322591,16923931701790,16923931748080
|
||
|
|
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,183214,183214,4194304,256,0,0,12,24,191552,0x7f2f9108fb00,0x7f2f90625e80,524288,2788926,312384220,16923931760060,16923931701790,16923932081949,16923932083840
|
||
|
|
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,183214,183214,4194304,256,0,0,12,24,195840,0x7f2f9108f980,0x7f2f90625ec0,524288,2840716,318161684,16923932115559,16923932081949,16923932549147,16923932593985
|
||
|
|
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,183214,183214,4194304,256,0,0,12,24,198592,0x7f2f9108f800,0x7f2f90625f00,524288,2751459,307999692,16923932613334,16923932549147,16923932915546,16923932917195
|
||
|
|
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,183214,183214,4194304,256,0,0,12,24,202368,0x7f2f9108f680,0x7f2f90625f40,524288,6677150,747804784,16923932948205,16923932915546,16923933315064,16923933334983
|
||
|
|
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,183214,183214,4194304,256,0,0,12,24,205888,0x7f2f936bd500,0x7f2f90625f80,524288,6177194,691789016,16923933349263,16923933315064,16923933713943,16923933731541
|
||
|
|
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,183214,183214,4194304,256,0,0,12,24,209408,0x7f2f936bd380,0x7f2f90625fc0,524288,2784399,311861204,16923933746401,16923933713943,16923934087862,16923934089671
|
||
|
|
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,183214,183214,4194304,256,0,0,12,24,214464,0x7f2f936bd200,0x7f2f90626000,524288,2899375,324702144,16923934121580,16923934087862,16923934611700,16923934629575
|
||
|
|
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,183214,183214,4194304,256,0,0,12,24,217728,0x7f2f936bd080,0x7f2f90626040,524288,2793178,312802464,16923934652984,16923934611700,16923934975539,16923934977294
|
||
|
|
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,183214,183214,4194304,256,0,0,12,24,222016,0x7f2f9108ff00,0x7f2f90626080,524288,5988150,670644644,16923935008883,16923934975539,16923935390738,16923935409421
|
||
|
|
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,183214,183214,4194304,256,0,0,12,24,226048,0x7f2f9108fd80,0x7f2f906260c0,524288,5039978,564419632,16923935424401,16923935390738,16923935810576,16923935827819
|
||
|
|
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,183214,183214,4194304,256,0,0,12,24,230080,0x7f2f9108fc00,0x7f2f90626100,524288,2726155,305302876,16923935843399,16923935810576,16923936216015,16923936233077
|
||
|
|
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,183214,183214,4194304,256,0,0,12,24,235904,0x7f2f9108fa80,0x7f2f90626140,524288,2890146,323699616,16923936249297,16923936216015,16923936793613,16923936811790
|
||
|
|
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,183214,183214,4194304,256,0,0,12,24,239424,0x7f2f9108f900,0x7f2f90626180,524288,2839494,317996948,16923936833729,16923936793613,16923937176172,16923937177929
|
||
|
|
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,183214,183214,4194304,256,0,0,12,24,244224,0x7f2f9108f780,0x7f2f906261c0,524288,5072352,568030040,16923937209288,16923937176172,16923937612010,16923937630796
|
||
|
|
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,183214,183214,4194304,256,0,0,12,24,248768,0x7f2f9108f600,0x7f2f90626200,524288,3162817,354208888,16923937644805,16923937612010,16923938051849,16923938069233
|
||
|
|
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,183214,183214,4194304,256,0,0,12,24,253312,0x7f2f936bd480,0x7f2f90626240,524288,2704066,302749868,16923938091912,16923938051849,16923938495527,16923938514419
|
||
|
|
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,183214,183214,4194304,256,0,0,8,24,255552,0x7f2f936bd300,0x7f2f90626280,524288,2362588,264571708,16923938528949,16923938495527,16923939140005,16923939157110
|
||
|
|
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,183214,183214,4194304,256,0,0,12,24,259840,0x7f2f936bd180,0x7f2f906262c0,524288,2716828,304202000,16923939181349,16923939140005,16923939561444,16923939578827
|
||
|
|
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,183214,183214,4194304,256,0,0,12,24,265664,0x7f2f936bd000,0x7f2f90626300,524288,3178873,356027700,16923939594687,16923939561444,16923940050242,16923940067583
|
||
|
|
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,183214,183214,4194304,256,0,0,12,24,271232,0x7f2f9108fe80,0x7f2f90626340,524288,3483767,390214828,16923940085732,16923940050242,16923940539521,16923940557088
|
||
|
|
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,183214,183214,4194304,256,0,0,8,24,273216,0x7f2f9108fd00,0x7f2f90626380,524288,2392512,267983256,16923940572378,16923940539521,16923941027519,16923941044654
|
||
|
|
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,183214,183214,4194304,256,0,0,8,24,275712,0x7f2f9108fb80,0x7f2f906263c0,524288,2379757,266499144,16923941061263,16923941027519,16923941776797,16923941794611
|
||
|
|
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,183214,183214,4194304,256,0,0,12,24,280768,0x7f2f9108fa00,0x7f2f90626400,524288,2639943,295600496,16923941817601,16923941776797,16923942232475,16923942254298
|
||
|
|
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,183214,183214,4194304,256,0,0,12,24,287616,0x7f2f9108f880,0x7f2f90626440,524288,3542729,396771320,16923942265767,16923942232475,16923942786233,16923942830001
|
||
|
|
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,183214,183214,4194304,256,0,0,12,24,294208,0x7f2f9108f700,0x7f2f90626480,524288,3552647,397812908,16923942842630,16923942786233,16923943353111,16923943394704
|
||
|
|
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,183214,183214,4194304,256,0,0,8,24,296960,0x7f2f936bd580,0x7f2f906264c0,524288,2382617,266848948,16923943406903,16923943353111,16923943917110,16923943959587
|
||
|
|
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,183214,183214,4194304,256,0,0,8,24,299968,0x7f2f936bd400,0x7f2f90626500,524288,2393751,268115604,16923943972347,16923943917110,16923944795027,16923944837001
|
||
|
|
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,183214,183214,4194304,256,0,0,8,24,302720,0x7f2f936bd280,0x7f2f90626540,524288,2385477,267172344,16923944856660,16923944795027,16923945467824,16923945509861
|
||
|
|
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,183214,183214,4194304,256,0,0,12,24,305472,0x7f2f936bd100,0x7f2f90626580,524288,2589607,289932688,16923945522051,16923945467824,16923946151822,16923946196081
|
||
|
|
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,183214,183214,4194304,256,0,0,12,24,308224,0x7f2f9108ff80,0x7f2f906265c0,524288,2591280,290165428,16923946208200,16923946151822,16923946839020,16923946882450
|
||
|
|
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,183214,183214,4194304,256,0,0,8,24,310976,0x7f2f9108fe00,0x7f2f90626600,524288,2388871,267616580,16923946894340,16923946839020,16923947512458,16923947556330
|
||
|
|
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,183214,183214,4194304,256,0,0,8,24,313216,0x7f2f9108fc80,0x7f2f90626640,524288,2394885,268229260,16923947568820,16923947512458,16923948613414,16923948657278
|
||
|
|
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,183214,183214,4194304,256,0,0,8,24,315968,0x7f2f9108fb00,0x7f2f90626680,524288,2436865,272900800,16923948678817,16923948613300,16923949697776,16923949766365
|
||
|
|
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,183214,183214,4194304,256,0,0,12,24,318720,0x7f2f9108f980,0x7f2f906266c0,524288,2591434,290197500,16923949777874,16923949697776,16923950838091,16923950907691
|
||
|
|
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,183214,183214,4194304,256,0,0,12,24,321472,0x7f2f9108f800,0x7f2f90626700,524288,2599579,291105736,16923950920020,16923950838091,16923951977767,16923952043447
|
||
|
|
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,183214,183214,4194304,256,0,0,8,24,324224,0x7f2f9108f680,0x7f2f90626740,524288,2430326,272176296,16923952055857,16923951977767,16923953091203,16923953157344
|
||
|
|
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,183214,183214,4194304,256,0,0,8,24,326464,0x7f2f936bd500,0x7f2f90626780,524288,2456352,275123564,16923953169254,16923953091203,16923955042236,16923955118356
|
||
|
|
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,183214,183214,4194304,256,0,0,8,24,329216,0x7f2f936bd380,0x7f2f906267c0,524288,2455635,274975472,16923955138515,16923955042236,16923956979349,16923957045889
|
||
|
|
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,183214,183214,4194304,256,0,0,12,24,331968,0x7f2f936bd200,0x7f2f90626800,524288,2626971,294234500,16923957057708,16923956979349,16923958956462,16923959027290
|
||
|
|
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,183214,183214,4194304,256,0,0,12,24,334720,0x7f2f936bd080,0x7f2f90626840,524288,2621382,293578144,16923959039459,16923958956462,16923960945415,16923961012260
|
||
|
|
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,183214,183214,4194304,256,0,0,8,24,337472,0x7f2f9108ff00,0x7f2f90626880,524288,2458137,275300464,16923961025250,16923960945415,16923962872288,16923962939053
|
||
|
|
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,183214,183214,4194304,256,0,0,8,24,0,0x7f2f9108fd80,0x7f2f906268c0,524288,2461763,275726776,16923962951763,16923962872288,16923966494836,16923966573005
|