169 lines
44 KiB
CSV
169 lines
44 KiB
CSV
|
|
Index,KernelName,gpu-id,queue-id,queue-index,pid,tid,grd,wgr,lds,scr,vgpr,sgpr,fbar,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,BeginNs,EndNs,CompleteNs
|
||
|
|
0,"__amd_rocclr_fillBufferAligned.kd",0,0,0,200200,200200,33554432,256,0,0,4,32,4160,0x0,0x7f3043a04280,380449,380449,524288,4718592,680823,76291444,17230491852189,17229803716158,17230639935378,17230640050298
|
||
|
|
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,200200,200200,32768,256,0,0,12,24,13888,0x0,0x7f3043a23f80,33388,33388,512,8192,6035,679208,17230645228208,17230639935378,17230645362261,17230645367004
|
||
|
|
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,200200,200200,4194304,256,0,0,12,24,14336,0x7f304aaf0380,0x7f3043a23fc0,164997,164997,65536,917504,142337,15939976,17230645404843,17230645362261,17230645745301,17230645747704
|
||
|
|
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,200200,200200,4194304,256,0,0,16,24,15040,0x7f304aaf0200,0x7f3043a24000,310782,310782,65536,1114112,169402,18938872,17230645790383,17230645745301,17230646166581,17230646169192
|
||
|
|
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,200200,200200,4194304,256,0,0,16,24,15488,0x7f304aaf0080,0x7f3043a24040,309055,309055,65536,917504,138787,15597044,17230646205871,17230646166581,17230646586741,17230646589191
|
||
|
|
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,200200,200200,4194304,256,0,0,12,24,15936,0x7f304844df00,0x7f3043a24080,166664,166664,65536,1048576,158657,17789628,17230646626190,17230646586741,17230646911542,17230646913782
|
||
|
|
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,200200,200200,4194304,256,0,0,12,24,16384,0x7f304844dd80,0x7f3043a240c0,165207,165207,65536,983040,146870,16529420,17230646951031,17230646911542,17230647232022,17230647234284
|
||
|
|
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,200200,200200,4194304,256,0,0,12,24,17088,0x7f304844dc00,0x7f3043a24100,163382,163382,65536,1114112,164070,18310496,17230647281852,17230647232022,17230647550902,17230647553285
|
||
|
|
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,200200,200200,4194304,256,0,0,16,24,17792,0x7f304844da80,0x7f3043a24140,310746,310746,65536,1310720,195675,21954640,17230647589284,17230647550902,17230647959222,17230647961684
|
||
|
|
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,200200,200200,4194304,256,0,0,16,24,18496,0x7f304844d900,0x7f3043a24180,309955,309955,65536,1179648,178000,19980700,17230647996103,17230647959222,17230648379382,17230648381793
|
||
|
|
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,200200,200200,4194304,256,0,0,16,24,19200,0x7f304844d780,0x7f3043a241c0,164552,164552,65536,1245184,187310,20956568,17230648415772,17230648379382,17230648705623,17230648707924
|
||
|
|
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,200200,200200,4194304,256,0,0,16,24,19904,0x7f304844d600,0x7f3043a24200,164868,164868,65536,1245184,186472,20881924,17230648744363,17230648705623,17230649029783,17230649032455
|
||
|
|
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,200200,200200,4194304,256,0,0,12,24,20608,0x7f304aaf0480,0x7f3043a24240,164240,164240,65536,1245184,189435,21222580,17230649076614,17230649029783,17230649349303,17230649351576
|
||
|
|
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,200200,200200,4194304,256,0,0,16,24,21312,0x7f304aaf0300,0x7f3043a24280,309929,309929,65536,1441792,215034,24095384,17230649387685,17230649349303,17230649759863,17230649762185
|
||
|
|
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,200200,200200,4194304,256,0,0,16,24,22016,0x7f304aaf0180,0x7f3043a242c0,307647,307647,65536,1310720,200666,22434260,17230649797864,17230649759863,17230650170904,17230650173514
|
||
|
|
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,200200,200200,4194304,256,0,0,16,24,22720,0x7f304aaf0000,0x7f3043a24300,163586,163586,65536,1376256,207773,23238464,17230650209263,17230650170904,17230650504024,17230650506475
|
||
|
|
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,200200,200200,4194304,256,0,0,12,24,23424,0x7f304844de80,0x7f3043a24340,164942,164942,65536,1441792,216749,24287348,17230650541944,17230650504024,17230650826104,17230650827996
|
||
|
|
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,200200,200200,4194304,256,0,0,12,24,24128,0x7f304844dd00,0x7f3043a24380,164520,164520,65536,1310720,195726,21940208,17230650871035,17230650826104,17230651127224,17230651128918
|
||
|
|
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,200200,200200,4194304,256,0,0,16,24,24832,0x7f304844db80,0x7f3043a243c0,307882,307882,65536,1572864,234252,26307684,17230651165997,17230651127224,17230651504984,17230651506828
|
||
|
|
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,200200,200200,4194304,256,0,0,16,24,25536,0x7f304844da00,0x7f3043a24400,310896,310896,65536,1441792,208880,23368856,17230651542017,17230651504984,17230651887545,17230651889357
|
||
|
|
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,200200,200200,4194304,256,0,0,12,24,26240,0x7f304844d880,0x7f3043a24440,164810,164810,65536,1507328,224531,25131788,17230651924537,17230651887545,17230652179545,17230652181240
|
||
|
|
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,200200,200200,4194304,256,0,0,12,24,26944,0x7f304844d700,0x7f3043a24480,163294,163294,65536,1638400,245619,27507160,17230652216799,17230652179545,17230652471065,17230652472682
|
||
|
|
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,200200,200200,4194304,256,0,0,12,24,27648,0x7f304aaf0580,0x7f3043a244c0,163210,163210,65536,1441792,216004,24124144,17230652514850,17230652471065,17230652763225,17230652765074
|
||
|
|
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,200200,200200,4194304,256,0,0,16,24,28608,0x7f304aaf0400,0x7f3043a24500,307768,307768,65536,1703936,252732,28277064,17230652802083,17230652763225,17230653140985,17230653142663
|
||
|
|
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,200200,200200,4194304,256,0,0,16,24,29312,0x7f304aaf0280,0x7f3043a24540,304086,304086,65536,1572864,234321,26218088,17230653179082,17230653140985,17230653518746,17230653520613
|
||
|
|
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,200200,200200,4194304,256,0,0,12,24,30016,0x7f304aaf0100,0x7f3043a24580,162989,162989,65536,1638400,246650,27623476,17230653556662,17230653518746,17230653813146,17230653814835
|
||
|
|
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,200200,200200,4194304,256,0,0,8,24,30976,0x7f304844df80,0x7f3043a245c0,163674,163674,65536,1835008,273034,30556028,17230653850624,17230653813146,17230654106426,17230654108447
|
||
|
|
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,200200,200200,4194304,256,0,0,12,24,31680,0x7f304844de00,0x7f3043a24600,162781,162781,65536,1507328,227231,25455360,17230654151736,17230654106426,17230654405306,17230654407189
|
||
|
|
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,200200,200200,4194304,256,0,0,16,24,32640,0x7f304844dc80,0x7f3043a24640,303999,303999,65536,1835008,275944,30880412,17230654443658,17230654405306,17230654781466,17230654783359
|
||
|
|
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,200200,200200,4194304,256,0,0,12,24,33600,0x7f304844db00,0x7f3043a24680,305947,305947,65536,1703936,248084,27796728,17230654818368,17230654781466,17230655160027,17230655161799
|
||
|
|
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,200200,200200,4194304,256,0,0,12,24,34560,0x7f304844d980,0x7f3043a246c0,163816,163816,65536,1769472,263321,29449376,17230655196958,17230655160027,17230655450907,17230655452751
|
||
|
|
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,200200,200200,4194304,256,0,0,8,24,35520,0x7f304844d800,0x7f3043a24700,164381,164381,65536,2031616,310346,34842180,17230655488450,17230655450907,17230655744187,17230655745903
|
||
|
|
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,200200,200200,4194304,256,0,0,12,24,36224,0x7f304844d680,0x7f3043a24740,162393,162393,65536,1638400,246872,27689624,17230655788202,17230655744187,17230656034587,17230656036355
|
||
|
|
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,200200,200200,4194304,256,0,0,12,24,37184,0x7f304aaf0500,0x7f3043a24780,305063,305063,65536,1966080,288906,32364660,17230656072214,17230656034587,17230656417947,17230656419925
|
||
|
|
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,200200,200200,4194304,256,0,0,12,24,38144,0x7f304aaf0380,0x7f3043a247c0,304605,304605,65536,1835008,272048,30506216,17230656454504,17230656417947,17230656796988,17230656798675
|
||
|
|
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,200200,200200,4194304,256,0,0,12,24,39104,0x7f304aaf0200,0x7f3043a24800,164055,164055,65536,1900544,283345,31762032,17230656833994,17230656796988,17230657089468,17230657091257
|
||
|
|
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,200200,200200,4194304,256,0,0,8,24,40320,0x7f304aaf0080,0x7f3043a24840,163927,163927,65536,2228224,330805,36976876,17230657127006,17230657089468,17230657381468,17230657383129
|
||
|
|
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,200200,200200,4194304,256,0,0,12,24,41280,0x7f304844df00,0x7f3043a24880,163689,163689,65536,1703936,254761,28566444,17230657425918,17230657381468,17230657678908,17230657680561
|
||
|
|
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,200200,200200,4194304,256,0,0,12,24,42240,0x7f304844dd80,0x7f3043a248c0,306597,306597,65536,2097152,309252,34620448,17230657716940,17230657678908,17230658071068,17230658072750
|
||
|
|
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,200200,200200,4194304,256,0,0,12,24,43200,0x7f304844dc00,0x7f3043a24900,303101,303101,65536,1966080,284071,31845608,17230658110509,17230658071068,17230658459389,17230658461080
|
||
|
|
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,200200,200200,4194304,256,0,0,8,24,44160,0x7f304844da80,0x7f3043a24940,163274,163274,65536,2031616,303814,34025836,17230658497439,17230658459389,17230658753789,17230658755552
|
||
|
|
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,200200,200200,4194304,256,0,0,12,24,45376,0x7f304844d900,0x7f3043a24980,163078,163078,65536,2424832,362779,40615960,17230658790871,17230658753789,17230659053149,17230659054954
|
||
|
|
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,200200,200200,4194304,256,0,0,12,24,46336,0x7f304844d780,0x7f3043a249c0,162814,162814,65536,1835008,282713,31710248,17230659096182,17230659053149,17230659344669,17230659346466
|
||
|
|
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,200200,200200,4194304,256,0,0,12,24,47552,0x7f304844d600,0x7f3043a24a00,305186,305186,65536,2228224,330869,37059636,17230659383245,17230659344669,17230659723549,17230659725415
|
||
|
|
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,200200,200200,4194304,256,0,0,12,24,48512,0x7f304aaf0480,0x7f3043a24a40,303044,303044,65536,2097152,319154,35718512,17230659761174,17230659723549,17230660105309,17230660107065
|
||
|
|
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,200200,200200,4194304,256,0,0,8,24,49472,0x7f304aaf0300,0x7f3043a24a80,162398,162398,65536,2162688,318541,35680988,17230660143284,17230660105309,17230660399070,17230660400817
|
||
|
|
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,200200,200200,4194304,256,0,0,12,24,50688,0x7f304aaf0180,0x7f3043a24ac0,162390,162390,65536,2621440,387979,43293004,17230660436996,17230660399070,17230660692510,17230660694419
|
||
|
|
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,200200,200200,4194304,256,0,0,12,24,51648,0x7f304aaf0000,0x7f3043a24b00,162254,162254,65536,1966080,293781,32887184,17230660737358,17230660692510,17230660993950,17230660995671
|
||
|
|
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,200200,200200,4194304,256,0,0,12,24,52864,0x7f304844de80,0x7f3043a24b40,304381,304381,65536,2359296,362011,40537000,17230661032060,17230660993950,17230661376030,17230661377821
|
||
|
|
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,200200,200200,4194304,256,0,0,12,24,54080,0x7f304844dd00,0x7f3043a24b80,300824,300824,65536,2228224,340641,38086916,17230661413910,17230661376030,17230661758750,17230661760430
|
||
|
|
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,200200,200200,4194304,256,0,0,8,24,55296,0x7f304844db80,0x7f3043a24bc0,163739,163739,65536,2293760,340272,38150796,17230661796869,17230661758750,17230662052671,17230662054293
|
||
|
|
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,200200,200200,4194304,256,0,0,12,24,56768,0x7f304844da00,0x7f3043a24c00,163150,163150,65536,2752512,416212,46578968,17230662102681,17230662052671,17230662361471,17230662363224
|
||
|
|
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,200200,200200,4194304,256,0,0,12,24,57728,0x7f304844d880,0x7f3043a24c40,162519,162519,65536,2031616,302684,33874464,17230662406313,17230662361471,17230662656511,17230662658476
|
||
|
|
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,200200,200200,4194304,256,0,0,12,24,58944,0x7f304844d700,0x7f3043a24c80,301350,301350,65536,2490368,371291,41560636,17230662696145,17230662656511,17230663033311,17230663034976
|
||
|
|
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,200200,200200,4194304,256,0,0,12,24,60160,0x7f304aaf0580,0x7f3043a24cc0,301811,301811,65536,2359296,367035,41186144,17230663070665,17230663033311,17230663412511,17230663414456
|
||
|
|
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,200200,200200,4194304,256,0,0,8,24,61376,0x7f304aaf0400,0x7f3043a24d00,164426,164426,65536,2424832,366459,40976124,17230663449875,17230663412511,17230663704512,17230663706208
|
||
|
|
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,200200,200200,4194304,256,0,0,12,24,62848,0x7f304aaf0280,0x7f3043a24d40,169254,169254,65536,2949120,447367,50132076,17230663742167,17230663704512,17230664002432,17230664004220
|
||
|
|
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,200200,200200,4194304,256,0,0,12,24,63808,0x7f304aaf0100,0x7f3043a24d80,161622,161622,65536,2162688,321182,35976040,17230664047569,17230664002432,17230664304512,17230664306512
|
||
|
|
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,200200,200200,4194304,256,0,0,12,24,65024,0x7f304844df80,0x7f3043a24dc0,301543,301543,65536,2621440,394729,44272664,17230664341681,17230664304512,17230664684352,17230664686001
|
||
|
|
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,200200,200200,4194304,256,0,0,12,24,66240,0x7f304844de00,0x7f3043a24e00,300674,300674,65536,2490368,361140,40421676,17230664723490,17230664684352,17230665063232,17230665065011
|
||
|
|
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,200200,200200,4194304,256,0,0,8,24,67456,0x7f304844dc80,0x7f3043a24e40,163561,163561,65536,2555904,388626,43548832,17230665099380,17230665063232,17230665356673,17230665358453
|
||
|
|
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,200200,200200,4194304,256,0,0,12,24,68928,0x7f304844db00,0x7f3043a24e80,176658,176658,65536,3145728,467697,52363120,17230665395112,17230665356673,17230665664833,17230665666525
|
||
|
|
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,200200,200200,4194304,256,0,0,12,24,70144,0x7f304844d980,0x7f3043a24ec0,162061,162061,65536,2228224,332411,37227340,17230665708934,17230665664833,17230665959873,17230665961677
|
||
|
|
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,200200,200200,4194304,256,0,0,12,24,71616,0x7f304844d800,0x7f3043a24f00,301757,301757,65536,2752512,405992,45449776,17230665997696,17230665959873,17230666347393,17230666349206
|
||
|
|
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,200200,200200,4194304,256,0,0,12,24,72832,0x7f304844d680,0x7f3043a24f40,302163,302163,65536,2621440,394241,44213880,17230666384636,17230666347393,17230666728833,17230666730596
|
||
|
|
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,200200,200200,4194304,256,0,0,8,24,74048,0x7f304aaf0500,0x7f3043a24f80,163134,163134,65536,2686976,395671,44328660,17230666766365,17230666728833,17230667027234,17230667029048
|
||
|
|
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,200200,200200,4194304,256,0,0,12,24,75776,0x7f304aaf0380,0x7f3043a24fc0,183085,183085,65536,3342336,502790,56305908,17230667064927,17230667027234,17230667335874,17230667337880
|
||
|
|
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,200200,200200,4194304,256,0,0,12,24,76992,0x7f304aaf0200,0x7f3043a25000,162329,162329,65536,2359296,358568,40040196,17230667393358,17230667335874,17230667630914,17230667632782
|
||
|
|
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,200200,200200,4194304,256,0,0,12,24,78464,0x7f304aaf0080,0x7f3043a25040,302855,302855,65536,2883584,428430,47990568,17230667668321,17230667630914,17230668015554,17230668017351
|
||
|
|
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,200200,200200,4194304,256,0,0,12,24,79936,0x7f304844df00,0x7f3043a25080,302573,302573,65536,2686976,427643,47905088,17230668053640,17230668015554,17230668395394,17230668397261
|
||
|
|
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,200200,200200,4194304,256,0,0,8,24,81408,0x7f304844dd80,0x7f3043a250c0,163165,163165,65536,2818048,424049,47520680,17230668431830,17230668395394,17230668690435,17230668692053
|
||
|
|
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,200200,200200,4194304,256,0,0,12,24,83136,0x7f304844dc00,0x7f3043a25100,192377,192377,65536,3538944,530344,59415628,17230668727422,17230668690435,17230669004035,17230669005804
|
||
|
|
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,200200,200200,4194304,256,0,0,12,24,84352,0x7f304844da80,0x7f3043a25140,162189,162189,65536,2424832,359056,40180288,17230669048283,17230669004035,17230669299715,17230669301546
|
||
|
|
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,200200,200200,4194304,256,0,0,12,24,85824,0x7f304844d900,0x7f3043a25180,299148,299148,65536,3014656,466159,52162984,17230669335955,17230669299715,17230669681795,17230669683546
|
||
|
|
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,200200,200200,4194304,256,0,0,12,24,87296,0x7f304844d780,0x7f3043a251c0,299390,299390,65536,2818048,418846,46990864,17230669719155,17230669681795,17230670063235,17230670065055
|
||
|
|
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,200200,200200,4194304,256,0,0,12,24,88768,0x7f304844d600,0x7f3043a25200,162379,162379,65536,2949120,439976,49337992,17230670100845,17230670063235,17230670376196,17230670377997
|
||
|
|
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,200200,200200,4194304,256,0,0,12,24,90752,0x7f304aaf0480,0x7f3043a25240,203013,203013,65536,3735552,554541,62113364,17230670414786,17230670376196,17230670697796,17230670699488
|
||
|
|
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,200200,200200,4194304,256,0,0,12,24,91968,0x7f304aaf0300,0x7f3043a25280,161987,161987,65536,2555904,386413,43254120,17230670742367,17230670697796,17230670997476,17230670999210
|
||
|
|
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,200200,200200,4194304,256,0,0,12,24,93440,0x7f304aaf0180,0x7f3043a252c0,300535,300535,65536,3145728,469581,52538292,17230671036439,17230670997476,17230671375876,17230671377540
|
||
|
|
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,200200,200200,4194304,256,0,0,12,24,94912,0x7f304aaf0000,0x7f3043a25300,301427,301427,65536,2949120,433291,48543928,17230671414069,17230671375876,17230671755236,17230671756960
|
||
|
|
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,200200,200200,4194304,256,0,0,12,24,96384,0x7f304844de80,0x7f3043a25340,162561,162561,65536,3080192,460079,51475600,17230671791419,17230671755236,17230672054917,17230672056482
|
||
|
|
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,200200,200200,4194304,256,0,0,12,24,98368,0x7f304844dd00,0x7f3043a25380,212409,212409,65536,3932160,591570,66242416,17230672093141,17230672054917,17230672387877,17230672389493
|
||
|
|
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,200200,200200,4194304,256,0,0,12,24,99584,0x7f304844db80,0x7f3043a253c0,161719,161719,65536,2621440,389122,43596944,17230672431242,17230672387877,17230672688837,17230672690605
|
||
|
|
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,200200,200200,4194304,256,0,0,12,24,101312,0x7f304844da00,0x7f3043a25400,300379,300379,65536,3276800,488517,54738508,17230672727604,17230672688837,17230673072037,17230673073624
|
||
|
|
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,200200,200200,4194304,256,0,0,12,24,102784,0x7f304844d880,0x7f3043a25440,297883,297883,65536,3080192,449765,50356596,17230673108833,17230673072037,17230673450117,17230673451924
|
||
|
|
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,200200,200200,4194304,256,0,0,12,24,104256,0x7f304844d700,0x7f3043a25480,161493,161493,65536,3211264,477024,53370300,17230673486713,17230673450117,17230673745318,17230673746986
|
||
|
|
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,200200,200200,4194304,256,0,0,12,24,106240,0x7f304aaf0580,0x7f3043a254c0,220023,220023,65536,4128768,617828,69239336,17230673782235,17230673745318,17230674076518,17230674081927
|
||
|
|
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,200200,200200,4194304,256,0,0,12,24,107712,0x7f304aaf0400,0x7f3043a25500,161459,161459,65536,2752512,411465,46098152,17230674122916,17230674076518,17230674379718,17230674381509
|
||
|
|
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,200200,200200,4194304,256,0,0,16,24,109440,0x7f304aaf0280,0x7f3043a25540,298409,298409,65536,3407872,517724,57935876,17230674418868,17230674379718,17230674760678,17230674762419
|
||
|
|
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,200200,200200,4194304,256,0,0,16,24,111168,0x7f304aaf0100,0x7f3043a25580,299541,299541,65536,3211264,476616,53414416,17230674798338,17230674760678,17230675144838,17230675146528
|
||
|
|
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,200200,200200,4194304,256,0,0,8,24,112896,0x7f304844df80,0x7f3043a255c0,163815,163815,65536,3276800,497035,55670300,17230675182997,17230675144838,17230675439719,17230675441320
|
||
|
|
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,200200,200200,4194304,256,0,0,12,24,115136,0x7f304844de00,0x7f3043a25600,229685,229685,65536,4325376,657224,73555604,17230675476389,17230675439719,17230675776839,17230675778431
|
||
|
|
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,200200,200200,4194304,256,0,0,12,24,116608,0x7f304844dc80,0x7f3043a25640,163348,163348,65536,2818048,466414,52258272,17230675820340,17230675776839,17230676072039,17230676073653
|
||
|
|
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,200200,200200,4194304,256,0,0,16,24,118336,0x7f304844db00,0x7f3043a25680,297423,297423,65536,3538944,528267,59108136,17230676110572,17230676072039,17230676450759,17230676452353
|
||
|
|
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,200200,200200,4194304,256,0,0,16,24,120064,0x7f304844d980,0x7f3043a256c0,299630,299630,65536,3407872,501737,56223044,17230676487242,17230676450759,17230676832679,17230676834373
|
||
|
|
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,200200,200200,4194304,256,0,0,12,24,121792,0x7f304844d800,0x7f3043a25700,164756,164756,65536,3407872,509975,57161456,17230676869312,17230676832679,17230677127080,17230677128875
|
||
|
|
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,200200,200200,4194304,256,0,0,12,24,124032,0x7f304844d680,0x7f3043a25740,239809,239809,65536,4521984,679768,76194020,17230677164144,17230677127080,17230677470600,17230677472145
|
||
|
|
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,200200,200200,4194304,256,0,0,12,24,125504,0x7f304aaf0500,0x7f3043a25780,161248,161248,65536,3014656,453378,50786952,17230677514114,17230677470600,17230677764520,17230677766227
|
||
|
|
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,200200,200200,4194304,256,0,0,12,24,127488,0x7f304aaf0380,0x7f3043a257c0,298955,298955,65536,3801088,564090,63207388,17230677800826,17230677764520,17230678149640,17230678151547
|
||
|
|
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,200200,200200,4194304,256,0,0,12,24,129216,0x7f304aaf0200,0x7f3043a25800,299656,299656,65536,3670016,545992,61167132,17230678188766,17230678149640,17230678540841,17230678542636
|
||
|
|
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,200200,200200,4194304,256,0,0,12,24,130944,0x7f304aaf0080,0x7f3043a25840,172181,172181,65536,3670016,570741,63968428,17230678578805,17230678540841,17230678842761,17230678844518
|
||
|
|
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,200200,200200,4194304,256,0,0,12,24,133440,0x7f304844df00,0x7f3043a25880,259422,259422,65536,4915200,770619,86269040,17230678881027,17230678842761,17230679198601,17230679200469
|
||
|
|
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,200200,200200,4194304,256,0,0,12,24,134912,0x7f304844dd80,0x7f3043a258c0,162327,162327,65536,3145728,480589,53960940,17230679243087,17230679198601,17230679492841,17230679494691
|
||
|
|
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,200200,200200,4194304,256,0,0,12,24,136896,0x7f304844dc00,0x7f3043a25900,296872,296872,65536,4063232,606108,67854676,17230679531400,17230679492841,17230679871081,17230679872640
|
||
|
|
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,200200,200200,4194304,256,0,0,12,24,138880,0x7f304844da80,0x7f3043a25940,300515,300515,65536,3932160,598661,67125152,17230679908579,17230679871081,17230680252682,17230680254480
|
||
|
|
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,200200,200200,4194304,256,0,0,12,24,140864,0x7f304844d900,0x7f3043a25980,181020,181020,65536,3932160,593125,66408984,17230680289629,17230680252682,17230680562602,17230680564271
|
||
|
|
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,200200,200200,4194304,256,0,0,12,24,143616,0x7f304844d780,0x7f3043a259c0,281027,281027,65536,5308416,795368,89012436,17230680598680,17230680562602,17230680933002,17230680934611
|
||
|
|
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,200200,200200,4194304,256,0,0,12,24,145344,0x7f304844d600,0x7f3043a25a00,162936,162936,65536,3342336,497839,55836584,17230680978600,17230680933002,17230681227722,17230681229463
|
||
|
|
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,200200,200200,4194304,256,0,0,12,24,147584,0x7f304aaf0480,0x7f3043a25a40,295625,295625,65536,4325376,663755,74413072,17230681264482,17230681227722,17230681607082,17230681608843
|
||
|
|
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,200200,200200,4194304,256,0,0,12,24,149568,0x7f304aaf0300,0x7f3043a25a80,296196,296196,65536,4194304,659883,73927896,17230681644582,17230681607082,17230681992363,17230681993963
|
||
|
|
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,200200,200200,4194304,256,0,0,12,24,151552,0x7f304aaf0180,0x7f3043a25ac0,188119,188119,65536,4194304,620549,69584384,17230682029472,17230681992363,17230682309003,17230682310714
|
||
|
|
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,200200,200200,4194304,256,0,0,12,24,154304,0x7f304aaf0000,0x7f3043a25b00,300049,300049,65536,5701632,853908,95480540,17230682347393,17230682309003,17230682692683,17230682694384
|
||
|
|
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,200200,200200,4194304,256,0,0,12,24,156288,0x7f304844de80,0x7f3043a25b40,172721,172721,65536,3735552,567893,63563072,17230682737242,17230682692683,17230682999723,17230683001475
|
||
|
|
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,200200,200200,4194304,256,0,0,12,24,158784,0x7f304844dd00,0x7f3043a25b80,303224,303224,65536,4849664,748988,83987644,17230683036704,17230682999723,17230683386763,17230683388445
|
||
|
|
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,200200,200200,4194304,256,0,0,12,24,161024,0x7f304844db80,0x7f3043a25bc0,297249,297249,65536,4718592,733006,82116460,17230683423594,17230683386763,17230683773324,17230683775034
|
||
|
|
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,200200,200200,4194304,256,0,0,12,24,163264,0x7f304844da00,0x7f3043a25c00,206320,206320,65536,4718592,709591,79526156,17230683809714,17230683773324,17230684095884,17230684097576
|
||
|
|
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,200200,200200,4194304,256,0,0,12,24,166528,0x7f304844d880,0x7f3043a25c40,341017,341017,65536,6488064,976130,109319488,17230684132555,17230684095884,17230684502444,17230684549074
|
||
|
|
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,200200,200200,4194304,256,0,0,12,24,168512,0x7f304844d700,0x7f3043a25c80,185361,185361,65536,4128768,620699,69464476,17230684568933,17230684502444,17230684845964,17230684847625
|
||
|
|
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,200200,200200,4194304,256,0,0,12,24,171264,0x7f304aaf0580,0x7f3043a25cc0,298934,298934,65536,5373952,839012,93967904,17230684884214,17230684845964,17230685228045,17230685229855
|
||
|
|
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,200200,200200,4194304,256,0,0,12,24,173760,0x7f304aaf0400,0x7f3043a25d00,297658,297658,65536,5242880,827941,92748532,17230685266134,17230685228045,17230685611085,17230685612635
|
||
|
|
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,200200,200200,4194304,256,0,0,12,24,176256,0x7f304aaf0280,0x7f3043a25d40,225782,225782,65536,5242880,788154,88196292,17230685648704,17230685611085,17230685949805,17230685951706
|
||
|
|
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,200200,200200,4194304,256,0,0,12,24,179776,0x7f304aaf0100,0x7f3043a25d80,380606,380606,65536,7274496,1119811,125408736,17230685987655,17230685949805,17230686400525,17230686425383
|
||
|
|
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,200200,200200,4194304,256,0,0,12,24,182272,0x7f304844df80,0x7f3043a25dc0,211722,211722,65536,4915200,738025,82566040,17230686445972,17230686400525,17230686747565,17230686749344
|
||
|
|
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,200200,200200,4194304,256,0,0,12,24,185536,0x7f304844de00,0x7f3043a25e00,307320,307320,65536,6422528,1032859,115627544,17230686786353,17230686747565,17230687137966,17230687183222
|
||
|
|
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,200200,200200,4194304,256,0,0,12,24,188544,0x7f304844dc80,0x7f3043a25e40,312244,312244,65536,6291456,1020415,114243404,17230687194732,17230687137966,17230687561166,17230687605971
|
||
|
|
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,200200,200200,4194304,256,0,0,12,24,191552,0x7f304844db00,0x7f3043a25e80,266393,266393,65536,6291456,947568,106119276,17230687618091,17230687561166,17230687949326,17230687950952
|
||
|
|
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,200200,200200,4194304,256,0,0,12,24,195840,0x7f304844d980,0x7f3043a25ec0,462715,462715,65536,8847360,1337508,149786796,17230687986441,17230687949326,17230688435566,17230688480557
|
||
|
|
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,200200,200200,4194304,256,0,0,12,24,198592,0x7f304844d800,0x7f3043a25f00,242937,242937,65536,5701632,866738,97080748,17230688501227,17230688435566,17230688816527,17230688818288
|
||
|
|
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,200200,200200,4194304,256,0,0,12,24,202368,0x7f304844d680,0x7f3043a25f40,335015,335015,65536,7471104,1186058,132734668,17230688854437,17230688816527,17230689224687,17230689267066
|
||
|
|
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,200200,200200,4194304,256,0,0,12,24,205888,0x7f304aaf0500,0x7f3043a25f80,331471,331471,65536,7340032,1151742,128884656,17230689278556,17230689224687,17230689664847,17230689683735
|
||
|
|
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,200200,200200,4194304,256,0,0,12,24,209408,0x7f304aaf0380,0x7f3043a25fc0,309825,309825,65536,7340032,1115054,124938416,17230689701474,17230689664847,17230690056527,17230690059505
|
||
|
|
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,200200,200200,4194304,256,0,0,12,24,214464,0x7f304aaf0200,0x7f3043a26000,543503,543503,65536,10420224,1588316,177868940,17230690095644,17230690056527,17230690599248,17230690645039
|
||
|
|
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,200200,200200,4194304,256,0,0,12,24,217728,0x7f304aaf0080,0x7f3043a26040,271372,271372,65536,6488064,974536,109116672,17230690665948,17230690599248,17230690996208,17230690997919
|
||
|
|
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,200200,200200,4194304,256,0,0,12,24,222016,0x7f304844df00,0x7f3043a26080,365683,365683,65536,8519680,1376984,154240176,17230691035068,17230690996208,17230691425328,17230691467866
|
||
|
|
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,200200,200200,4194304,256,0,0,12,24,226048,0x7f304844dd80,0x7f3043a260c0,365976,365976,65536,8388608,1305082,146148728,17230691480616,17230691425328,17230691884369,17230691926394
|
||
|
|
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,200200,200200,4194304,256,0,0,12,24,230080,0x7f304844dc00,0x7f3043a26100,348124,348124,65536,8388608,1291298,144662364,17230691939354,17230691884369,17230692323889,17230692366332
|
||
|
|
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,200200,200200,4194304,256,0,0,12,24,235904,0x7f304844da80,0x7f3043a26140,623980,623980,65536,11993088,1836605,205591236,17230692378292,17230692323889,17230692935889,17230692977705
|
||
|
|
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,200200,200200,4194304,256,0,0,12,24,239424,0x7f304844d900,0x7f3043a26180,304951,304951,65536,7274496,1110533,124392372,17230692997505,17230692935889,17230693353169,17230693354805
|
||
|
|
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,200200,200200,4194304,256,0,0,12,24,244224,0x7f304844d780,0x7f3043a261c0,400586,400586,65536,9568256,1541178,172764392,17230693391124,17230693353169,17230693805970,17230693825372
|
||
|
|
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,200200,200200,4194304,256,0,0,12,24,248768,0x7f304844d600,0x7f3043a26200,392332,392332,65536,9437184,1529711,171376408,17230693845912,17230693805970,17230694257170,17230694303339
|
||
|
|
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,200200,200200,4194304,256,0,0,12,24,253312,0x7f304aaf0480,0x7f3043a26240,388146,388146,65536,9437184,1469648,164484344,17230694316019,17230694257170,17230694731090,17230694778807
|
||
|
|
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,200200,200200,4194304,256,0,0,8,24,255552,0x7f304aaf0300,0x7f3043a26280,719766,719766,65536,16056320,2303086,257967128,17230694790756,17230694731090,17230695417171,17230695459498
|
||
|
|
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,200200,200200,4194304,256,0,0,12,24,259840,0x7f304aaf0180,0x7f3043a262c0,364701,364701,65536,8847360,1382246,154853484,17230695479888,17230695417171,17230695872531,17230695915166
|
||
|
|
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,200200,200200,4194304,256,0,0,12,24,265664,0x7f304aaf0000,0x7f3043a26300,470110,470110,65536,11665408,1844660,206507712,17230695926416,17230695872531,17230696401011,17230696443062
|
||
|
|
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,200200,200200,4194304,256,0,0,12,24,271232,0x7f304844de80,0x7f3043a26340,471545,471545,65536,11468800,1851812,207409196,17230696455551,17230696401011,17230696928692,17230696970847
|
||
|
|
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,200200,200200,4194304,256,0,0,8,24,273216,0x7f304844dd00,0x7f3043a26380,483811,483811,65536,14090240,2021606,226338528,17230696982547,17230696928692,17230697458292,17230697501033
|
||
|
|
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,200200,200200,4194304,256,0,0,8,24,275712,0x7f304844db80,0x7f3043a263c0,879889,879889,65536,19202048,2753994,308599076,17230697512613,17230697458292,17230698241972,17230698286822
|
||
|
|
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,200200,200200,4194304,256,0,0,12,24,280768,0x7f304844da00,0x7f3043a26400,427708,427708,65536,10420224,1591607,178282556,17230698308131,17230698241972,17230698742933,17230698787318
|
||
|
|
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,200200,200200,4194304,256,0,0,12,24,287616,0x7f304844d880,0x7f3043a26440,549980,549980,65536,13762560,2197575,246241116,17230698799068,17230698742933,17230699326133,17230699368713
|
||
|
|
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,200200,200200,4194304,256,0,0,12,24,294208,0x7f304844d700,0x7f3043a26480,552478,552478,65536,13565952,2185166,244649428,17230699382012,17230699326133,17230699903573,17230699945657
|
||
|
|
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,200200,200200,4194304,256,0,0,8,24,296960,0x7f304aaf0580,0x7f3043a264c0,564914,564914,65536,15466496,2224895,249406804,17230699957527,17230699903573,17230700478614,17230700520701
|
||
|
|
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,200200,200200,4194304,256,0,0,8,24,299968,0x7f304aaf0400,0x7f3043a26500,1043124,1043124,65536,22347776,3216547,360080408,17230700532951,17230700478614,17230701364534,17230701406957
|
||
|
|
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,200200,200200,4194304,256,0,0,8,24,302720,0x7f304aaf0280,0x7f3043a26540,722212,722212,65536,20250624,2908543,325873304,17230701427787,17230701364534,17230702037015,17230702055460
|
||
|
|
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,200200,200200,4194304,256,0,0,12,24,305472,0x7f304aaf0100,0x7f3043a26580,723510,723510,65536,20447232,2936703,328893760,17230702073769,17230702036702,17230702718462,17230702767021
|
||
|
|
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,200200,200200,4194304,256,0,0,12,24,308224,0x7f304844df80,0x7f3043a265c0,723272,723272,65536,19595264,2818913,315632604,17230702781000,17230702718462,17230703413820,17230703459832
|
||
|
|
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,200200,200200,4194304,256,0,0,8,24,310976,0x7f304844de00,0x7f3043a26600,726348,726348,65536,20381696,2930925,328342788,17230703472271,17230703413820,17230704094780,17230704138993
|
||
|
|
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,200200,200200,4194304,256,0,0,8,24,313216,0x7f304844dc80,0x7f3043a26640,1369640,1369640,65536,31522816,4519909,506148692,17230704150533,17230704094780,17230705206300,17230705252483
|
||
|
|
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,200200,200200,4194304,256,0,0,8,24,315968,0x7f304844db00,0x7f3043a26680,1370938,1370938,65536,38993920,5592869,626095372,17230705271823,17230705206300,17230706304380,17230706371203
|
||
|
|
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,200200,200200,4194304,256,0,0,12,24,318720,0x7f304844d980,0x7f3043a266c0,1373390,1373390,65536,39124992,5610953,628252916,17230706384022,17230706304380,17230707461020,17230707528141
|
||
|
|
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,200200,200200,4194304,256,0,0,12,24,321472,0x7f304844d800,0x7f3043a26700,1372439,1372439,65536,38469632,5509836,617207136,17230707540731,17230707461020,17230708605660,17230708675150
|
||
|
|
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,200200,200200,4194304,256,0,0,8,24,324224,0x7f304844d680,0x7f3043a26740,1377380,1377380,65536,39059456,5596109,626891208,17230708687160,17230708605660,17230709732060,17230709797290
|
||
|
|
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,200200,200200,4194304,256,0,0,8,24,326464,0x7f304aaf0500,0x7f3043a26780,2663674,2663674,65536,60489728,8650049,968941056,17230709808880,17230709732060,17230711703260,17230711780507
|
||
|
|
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,200200,200200,4194304,256,0,0,8,24,329216,0x7f304aaf0380,0x7f3043a267c0,2671394,2671394,65536,77266944,11058204,1238333104,17230711799986,17230711703260,17230713656380,17230713724154
|
||
|
|
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,200200,200200,4194304,256,0,0,12,24,331968,0x7f304aaf0200,0x7f3043a26800,2670519,2670519,65536,77398016,11074576,1240054236,17230713736004,17230713656380,17230715655900,17230715729250
|
||
|
|
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,200200,200200,4194304,256,0,0,12,24,334720,0x7f304aaf0080,0x7f3043a26840,2669734,2669734,65536,76218368,10908447,1221550176,17230715742109,17230715655900,17230717653820,17230717718866
|
||
|
|
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,200200,200200,4194304,256,0,0,8,24,337472,0x7f304844df00,0x7f3043a26880,2674843,2674843,65536,77332480,11063591,1239190112,17230717730885,17230717653820,17230719594140,17230719666533
|
||
|
|
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,200200,200200,4194304,256,0,0,8,24,0,0x7f304844dd80,0x7f3043a268c0,5257525,5257525,65536,120258560,17185373,1925585988,17230719679693,17230719594140,17230723230300,17230723302965
|