169 lines
43 KiB
CSV
169 lines
43 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_fillBuffer.kd",0,0,0,901123,901128,33554432,256,0,0,8,32,6464,0x0,0x7f34bac04180,1048576,11105144,1422096704,12075941073738305,12075941319842027,12075941320166985,12075941320278178
|
||
|
|
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,901123,901128,32768,256,0,0,24,24,12480,0x0,0x7f34bac35100,4096,114185,14602220,12075941334761004,12075941335062034,12075941335068594,12075941335073605
|
||
|
|
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,901123,901128,4194304,256,0,0,24,24,12928,0x7f35ead59900,0x7f34bac35140,524288,12413352,1588891204,12075941335135089,12075941335348753,12075941335481872,12075941335485801
|
||
|
|
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,901123,901128,4194304,256,0,0,36,24,13632,0x7f35ead59800,0x7f34bac35180,524288,13402692,1715511820,12075941335555170,12075941335724591,12075941335975470,12075941336049198
|
||
|
|
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,901123,901128,4194304,256,0,0,28,24,14080,0x7f35ead59700,0x7f34bac351c0,524288,13545990,1733904120,12075941336080867,12075941336269389,12075941336523788,12075941336590725
|
||
|
|
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,901123,901128,4194304,256,0,0,24,24,14528,0x7f35ead59600,0x7f34bac35200,524288,11846202,1516289108,12075941336618556,12075941336803946,12075941336938026,12075941336941276
|
||
|
|
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,901123,901128,4194304,256,0,0,24,24,14976,0x7f35ead59500,0x7f34bac35240,524288,12320378,1576894116,12075941336992060,12075941337166665,12075941337297384,12075941337300834
|
||
|
|
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,901123,901128,4194304,256,0,0,24,24,15424,0x7f35ead59400,0x7f34bac35280,524288,12661711,1620725488,12075941337380412,12075941337551623,12075941337681702,12075941337685018
|
||
|
|
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,901123,901128,4194304,256,0,0,28,24,16128,0x7f35ead59300,0x7f34bac352c0,524288,13923625,1782206516,12075941337740571,12075941337902021,12075941338156260,12075941338224401
|
||
|
|
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,901123,901128,4194304,256,0,0,28,24,16832,0x7f35ead59a00,0x7f34bac35300,524288,14364290,1838601808,12075941338250970,12075941338430339,12075941338681058,12075941338721194
|
||
|
|
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,901123,901128,4194304,256,0,0,24,24,17536,0x7f35ead59900,0x7f34bac35340,524288,12121934,1551545080,12075941338745309,12075941338934976,12075941339066496,12075941339070293
|
||
|
|
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,901123,901128,4194304,256,0,0,24,24,18240,0x7f35ead59800,0x7f34bac35380,524288,12295928,1573961776,12075941339121768,12075941339296575,12075941339429054,12075941339432706
|
||
|
|
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,901123,901128,4194304,256,0,0,24,24,18944,0x7f35ead59700,0x7f34bac353c0,524288,12754550,1632620856,12075941339495172,12075941339656733,12075941339786332,12075941339789439
|
||
|
|
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,901123,901128,4194304,256,0,0,28,24,19904,0x7f35ead59600,0x7f34bac35400,524288,13435440,1719754172,12075941339840194,12075941340002171,12075941340257370,12075941340324974
|
||
|
|
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,901123,901128,4194304,256,0,0,28,24,20608,0x7f35ead59500,0x7f34bac35440,524288,13925867,1782592428,12075941340349891,12075941340534169,12075941340786008,12075941340852705
|
||
|
|
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,901123,901128,4194304,256,0,0,24,24,21312,0x7f35ead59400,0x7f34bac35480,524288,12809035,1639523772,12075941340879635,12075941341068086,12075941341198006,12075941341201373
|
||
|
|
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,901123,901128,4194304,256,0,0,24,24,22016,0x7f35ead59300,0x7f34bac354c0,524288,12558038,1607355812,12075941341250775,12075941341416085,12075941341546484,12075941341549961
|
||
|
|
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,901123,901128,4194304,256,0,0,24,24,22720,0x7f35ead59a00,0x7f34bac35500,524288,13017882,1666221916,12075941341610984,12075941341772083,12075941341901202,12075941341904690
|
||
|
|
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,901123,901128,4194304,256,0,0,28,24,23680,0x7f35ead59900,0x7f34bac35540,524288,14287812,1828820564,12075941341953000,12075941342132081,12075941342385680,12075941342454352
|
||
|
|
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,901123,901128,4194304,256,0,0,28,24,24384,0x7f35ead59800,0x7f34bac35580,524288,13836888,1771164088,12075941342478867,12075941342666159,12075941342920238,12075941342961484
|
||
|
|
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,901123,901128,4194304,256,0,0,24,24,25088,0x7f35ead59700,0x7f34bac355c0,524288,12824198,1641489492,12075941342988815,12075941343179916,12075941343309516,12075941343313208
|
||
|
|
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,901123,901128,4194304,256,0,0,24,24,25792,0x7f35ead59600,0x7f34bac35600,524288,12501384,1600220792,12075941343358482,12075941343545195,12075941343677194,12075941343680671
|
||
|
|
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,901123,901128,4194304,256,0,0,24,24,26496,0x7f35ead59500,0x7f34bac35640,524288,13061932,1671874556,12075941343743187,12075941343905513,12075941344033032,12075941344036502
|
||
|
|
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,901123,901128,4194304,256,0,0,28,24,27712,0x7f35ead59400,0x7f34bac35680,524288,14229473,1821327376,12075941344086746,12075941344259751,12075941344513510,12075941344580523
|
||
|
|
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,901123,901128,4194304,256,0,0,28,24,28416,0x7f35ead59300,0x7f34bac356c0,524288,14281620,1828091580,12075941344606992,12075941344786789,12075941345039108,12075941345110338
|
||
|
|
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,901123,901128,4194304,256,0,0,24,24,29120,0x7f35ead59a00,0x7f34bac35700,524288,12216801,1563868688,12075941345135484,12075941345317506,12075941345448546,12075941345451953
|
||
|
|
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,901123,901128,4194304,256,0,0,24,24,30080,0x7f35ead59900,0x7f34bac35740,524288,11178209,1430796288,12075941345501034,12075941345663105,12075941345800384,12075941345803857
|
||
|
|
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,901123,901128,4194304,256,0,0,24,24,30784,0x7f35ead59800,0x7f34bac35780,524288,12957083,1658486552,12075941345867355,12075941346034303,12075941346164063,12075941346168144
|
||
|
|
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,901123,901128,4194304,256,0,0,28,24,32000,0x7f35ead59700,0x7f34bac357c0,524288,14211379,1819014236,12075941346218127,12075941346397021,12075941346652700,12075941346695053
|
||
|
|
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,901123,901128,4194304,256,0,0,28,24,32960,0x7f35ead59600,0x7f34bac35800,524288,14173967,1814269816,12075941346720981,12075941346896379,12075941347143258,12075941347212885
|
||
|
|
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,901123,901128,4194304,256,0,0,24,24,33920,0x7f35ead59500,0x7f34bac35840,524288,11387218,1457420568,12075941347239234,12075941347417817,12075941347553176,12075941347556664
|
||
|
|
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,901123,901128,4194304,256,0,0,24,24,34880,0x7f35ead59400,0x7f34bac35880,524288,13140501,1681986640,12075941347605104,12075941347773015,12075941347902134,12075941347905623
|
||
|
|
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,901123,901128,4194304,256,0,0,24,24,35840,0x7f35ead59300,0x7f34bac358c0,524288,12083419,1546626624,12075941347966917,12075941348131893,12075941348264853,12075941348268838
|
||
|
|
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,901123,901128,4194304,256,0,0,28,24,37312,0x7f35ead59a00,0x7f34bac35900,524288,13812879,1768101904,12075941348317608,12075941348489812,12075941348745010,12075941348812318
|
||
|
|
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,901123,901128,4194304,256,0,0,28,24,38272,0x7f35ead59900,0x7f34bac35940,524288,13663026,1748803952,12075941348838547,12075941349013329,12075941349271088,12075941349341632
|
||
|
|
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,901123,901128,4194304,256,0,0,24,24,39232,0x7f35ead59800,0x7f34bac35980,524288,11935524,1527683272,12075941349368131,12075941349545967,12075941349678766,12075941349682425
|
||
|
|
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,901123,901128,4194304,256,0,0,24,24,40192,0x7f35ead59700,0x7f34bac359c0,524288,11997706,1535696976,12075941349732328,12075941349901965,12075941350035884,12075941350039729
|
||
|
|
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,901123,901128,4194304,256,0,0,24,24,41152,0x7f35ead59600,0x7f34bac35a00,524288,12513785,1601718828,12075941350101924,12075941350265643,12075941350396683,12075941350400159
|
||
|
|
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,901123,901128,4194304,256,0,0,28,24,42624,0x7f35ead59500,0x7f34bac35a40,524288,13045409,1669837856,12075941350449450,12075941350612362,12075941350870761,12075941350912601
|
||
|
|
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,901123,901128,4194304,256,0,0,28,24,43584,0x7f35ead59400,0x7f34bac35a80,524288,13718177,1755951836,12075941350937588,12075941351116839,12075941351405798,12075941351474485
|
||
|
|
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,901123,901128,4194304,256,0,0,24,24,44544,0x7f35ead59300,0x7f34bac35ac0,524288,12607261,1613586480,12075941351501345,12075941351677157,12075941351809316,12075941351812824
|
||
|
|
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,901123,901128,4194304,256,0,0,24,24,45760,0x7f35ead59a00,0x7f34bac35b00,524288,12281335,1572113032,12075941351862026,12075941352036355,12075941352168834,12075941352172513
|
||
|
|
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,901123,901128,4194304,256,0,0,24,24,46720,0x7f35ead59900,0x7f34bac35b40,524288,12200786,1561792864,12075941352233295,12075941352393953,12075941352525953,12075941352529586
|
||
|
|
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,901123,901128,4194304,256,0,0,28,24,48448,0x7f35ead59800,0x7f34bac35b80,524288,14159216,1812328088,12075941352578637,12075941352737152,12075941352992191,12075941353060603
|
||
|
|
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,901123,901128,4194304,256,0,0,28,24,49408,0x7f35ead59700,0x7f34bac35bc0,524288,14265797,1826001812,12075941353084708,12075941353263389,12075941353514268,12075941353582122
|
||
|
|
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,901123,901128,4194304,256,0,0,24,24,50368,0x7f35ead59600,0x7f34bac35c00,524288,11014339,1409820884,12075941353600697,12075941353785147,12075941353921946,12075941353925510
|
||
|
|
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,901123,901128,4194304,256,0,0,24,24,51584,0x7f35ead59500,0x7f34bac35c40,524288,11574756,1481574580,12075941353974652,12075941354144185,12075941354280985,12075941354284748
|
||
|
|
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,901123,901128,4194304,256,0,0,24,24,52544,0x7f35ead59400,0x7f34bac35c80,524288,12231612,1565600244,12075941354347685,12075941354511064,12075941354643063,12075941354646540
|
||
|
|
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,901123,901128,4194304,256,0,0,28,24,54272,0x7f35ead59300,0x7f34bac35cc0,524288,13401925,1715406044,12075941354698657,12075941354858102,12075941355126261,12075941355195771
|
||
|
|
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,901123,901128,4194304,256,0,0,28,24,55488,0x7f35ead59a00,0x7f34bac35d00,524288,14241911,1822943244,12075941355220868,12075941355403219,12075941355656338,12075941355724794
|
||
|
|
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,901123,901128,4194304,256,0,0,24,24,56704,0x7f35ead59900,0x7f34bac35d40,524288,12877435,1648285668,12075941355750542,12075941355924337,12075941356053616,12075941356057392
|
||
|
|
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,901123,901128,4194304,256,0,0,24,24,58176,0x7f35ead59800,0x7f34bac35d80,524288,11153587,1427696540,12075941356099621,12075941356273615,12075941356407855,12075941356411521
|
||
|
|
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,901123,901128,4194304,256,0,0,24,24,59392,0x7f35ead59700,0x7f34bac35dc0,524288,11663651,1492993708,12075941356473666,12075941356631694,12075941356766413,12075941356769957
|
||
|
|
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,901123,901128,4194304,256,0,0,28,24,61376,0x7f35ead59600,0x7f34bac35e00,524288,13892877,1778318404,12075941356818317,12075941356984332,12075941357251371,12075941357320410
|
||
|
|
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,901123,901128,4194304,256,0,0,28,24,62592,0x7f35ead59500,0x7f34bac35e40,524288,14207833,1818629776,12075941357344054,12075941357531689,12075941357777768,12075941357845085
|
||
|
|
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,901123,901128,4194304,256,0,0,24,24,63808,0x7f35ead59400,0x7f34bac35e80,524288,12370766,1583575676,12075941357868378,12075941358049927,12075941358180646,12075941358184395
|
||
|
|
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,901123,901128,4194304,256,0,0,24,24,65280,0x7f35ead59300,0x7f34bac35ec0,524288,8879272,1136491052,12075941358232565,12075941358399845,12075941358535045,12075941358538463
|
||
|
|
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,901123,901128,4194304,256,0,0,24,24,66496,0x7f35ead59a00,0x7f34bac35f00,524288,11394146,1458491948,12075941358599867,12075941358757444,12075941358892963,12075941358896459
|
||
|
|
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,901123,901128,4194304,256,0,0,28,24,68480,0x7f35ead59900,0x7f34bac35f40,524288,12986316,1662175360,12075941358944428,12075941359112642,12075941359375521,12075941359427145
|
||
|
|
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,901123,901128,4194304,256,0,0,28,24,69696,0x7f35ead59800,0x7f34bac35f80,524288,14111739,1806299644,12075941359449336,12075941359626560,12075941359874718,12075941359924229
|
||
|
|
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,901123,901128,4194304,256,0,0,24,24,70912,0x7f35ead59700,0x7f34bac35fc0,524288,11823209,1513326296,12075941359950057,12075941360129757,12075941360263517,12075941360267226
|
||
|
|
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,901123,901128,4194304,256,0,0,24,24,72384,0x7f35ead59600,0x7f34bac36000,524288,7359701,942000352,12075941360316488,12075941360482396,12075941360620635,12075941360624270
|
||
|
|
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,901123,901128,4194304,256,0,0,24,24,73600,0x7f35ead59500,0x7f34bac36040,524288,11046478,1413963584,12075941360683881,12075941360843834,12075941360980953,12075941360984720
|
||
|
|
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,901123,901128,4194304,256,0,0,28,24,75840,0x7f35ead59400,0x7f34bac36080,524288,11790360,1509148136,12075941361031456,12075941361210072,12075941361476791,12075941361526426
|
||
|
|
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,901123,901128,4194304,256,0,0,28,24,77056,0x7f35ead59300,0x7f34bac360c0,524288,13937127,1783918532,12075941361549469,12075941361726710,12075941361981589,12075941362031685
|
||
|
|
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,901123,901128,4194304,256,0,0,24,24,78272,0x7f35ead59a00,0x7f34bac36100,524288,11716925,1499760940,12075941362057884,12075941362233107,12075941362365747,12075941362369323
|
||
|
|
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,901123,901128,4194304,256,0,0,24,24,80000,0x7f35ead59900,0x7f34bac36140,524288,7304085,935115064,12075941362423103,12075941362584306,12075941362729425,12075941362732838
|
||
|
|
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,901123,901128,4194304,256,0,0,24,24,81216,0x7f35ead59800,0x7f34bac36180,524288,11969279,1531964272,12075941362793601,12075941362953104,12075941363086063,12075941363089822
|
||
|
|
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,901123,901128,4194304,256,0,0,28,24,83456,0x7f35ead59700,0x7f34bac361c0,524288,14020291,1794568384,12075941363139394,12075941363308942,12075941363574861,12075941363626339
|
||
|
|
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,901123,901128,4194304,256,0,0,28,24,84928,0x7f35ead59600,0x7f34bac36200,524288,14135678,1809359296,12075941363656044,12075941363829100,12075941364077579,12075941364126238
|
||
|
|
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,901123,901128,4194304,256,0,0,24,24,86400,0x7f35ead59500,0x7f34bac36240,524288,12516572,1602146548,12075941364151946,12075941364333418,12075941364464297,12075941364467993
|
||
|
|
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,901123,901128,4194304,256,0,0,24,24,88128,0x7f35ead59400,0x7f34bac36280,524288,5999343,767927368,12075941364517275,12075941364680776,12075941364831015,12075941364834604
|
||
|
|
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,901123,901128,4194304,256,0,0,24,24,89600,0x7f35ead59300,0x7f34bac362c0,524288,13160509,1684571980,12075941364911708,12075941365079334,12075941365207334,12075941365211204
|
||
|
|
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,901123,901128,4194304,256,0,0,28,24,92096,0x7f35ead59a00,0x7f34bac36300,524288,12382816,1585020452,12075941365258943,12075941365427973,12075941365694051,12075941365741590
|
||
|
|
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,901123,901128,4194304,256,0,0,28,24,93568,0x7f35ead59900,0x7f34bac36340,524288,14119658,1807288388,12075941365765014,12075941365943010,12075941366226529,12075941366276825
|
||
|
|
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,901123,901128,4194304,256,0,0,24,24,95040,0x7f35ead59800,0x7f34bac36380,524288,11111074,1422209636,12075941366300308,12075941366480928,12075941366615327,12075941366619031
|
||
|
|
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,901123,901128,4194304,256,0,0,24,24,96768,0x7f35ead59700,0x7f34bac363c0,524288,4567073,584458584,12075941366667932,12075941366833246,12075941366990685,12075941366994198
|
||
|
|
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,901123,901128,4194304,256,0,0,24,24,98240,0x7f35ead59600,0x7f34bac36400,524288,11072032,1417247668,12075941367055732,12075941367216764,12075941367352764,12075941367356722
|
||
|
|
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,901123,901128,4194304,256,0,0,28,24,100736,0x7f35ead59500,0x7f34bac36440,524288,10940691,1400432356,12075941367400794,12075941367570043,12075941367836761,12075941367884002
|
||
|
|
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,901123,901128,4194304,256,0,0,28,24,102208,0x7f35ead59400,0x7f34bac36480,524288,14150327,1811202328,12075941367910451,12075941368090680,12075941368344759,12075941368395372
|
||
|
|
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,901123,901128,4194304,256,0,0,24,24,103680,0x7f35ead59300,0x7f34bac364c0,524288,12556595,1607181392,12075941368422262,12075941368597238,12075941368729237,12075941368733029
|
||
|
|
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,901123,901128,4194304,256,0,0,24,24,105664,0x7f35ead59a00,0x7f34bac36500,524288,3619555,463195720,12075941368781099,12075941368953716,12075941369120435,12075941369124347
|
||
|
|
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,901123,901128,4194304,256,0,0,24,24,107136,0x7f35ead59900,0x7f34bac36540,524288,11346463,1452246776,12075941369185841,12075941369344274,12075941369480594,12075941369484175
|
||
|
|
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,901123,901128,4194304,256,0,0,28,24,109888,0x7f35ead59800,0x7f34bac36580,524288,9861627,1262405588,12075941369533167,12075941369693073,12075941369957071,12075941370011806
|
||
|
|
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,901123,901128,4194304,256,0,0,28,24,111360,0x7f35ead59700,0x7f34bac365c0,524288,13578265,1737987808,12075941370039077,12075941370215630,12075941370470669,12075941370521183
|
||
|
|
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,901123,901128,4194304,256,0,0,24,24,112832,0x7f35ead59600,0x7f34bac36600,524288,10862889,1390332780,12075941370545758,12075941370719628,12075941370856747,12075941370860213
|
||
|
|
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,901123,901128,4194304,256,0,0,24,24,114816,0x7f35ead59500,0x7f34bac36640,524288,3768399,482466372,12075941370908963,12075941371068586,12075941371243625,12075941371247322
|
||
|
|
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,901123,901128,4194304,256,0,0,24,24,116288,0x7f35ead59400,0x7f34bac36680,524288,11125523,1424189248,12075941371310259,12075941371470184,12075941371606024,12075941371609836
|
||
|
|
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,901123,901128,4194304,256,0,0,28,24,119040,0x7f35ead59300,0x7f34bac366c0,524288,10166911,1301412412,12075941371658025,12075941371823783,12075941372092421,12075941372143728
|
||
|
|
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,901123,901128,4194304,256,0,0,28,24,120768,0x7f35ead59a00,0x7f34bac36700,524288,14193603,1816787272,12075941372162573,12075941372350340,12075941372604739,12075941372652243
|
||
|
|
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,901123,901128,4194304,256,0,0,24,24,122496,0x7f35ead59900,0x7f34bac36740,524288,11340321,1451512340,12075941372678592,12075941372850978,12075941372987297,12075941372990913
|
||
|
|
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,901123,901128,4194304,256,0,0,24,24,124736,0x7f35ead59800,0x7f34bac36780,524288,3504091,448482292,12075941373041597,12075941373209856,12075941373393055,12075941373396667
|
||
|
|
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,901123,901128,4194304,256,0,0,24,24,126464,0x7f35ead59700,0x7f34bac367c0,524288,10317857,1320505200,12075941373457229,12075941373614334,12075941373755614,12075941373759341
|
||
|
|
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,901123,901128,4194304,256,0,0,20,24,127936,0x7f35ead59600,0x7f34bac36800,524288,4101828,524956188,12075941373808222,12075941373971933,12075941374238011,12075941374285769
|
||
|
|
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,901123,901128,4194304,256,0,0,28,24,129664,0x7f35ead59500,0x7f34bac36840,524288,12508930,1601156888,12075941374312719,12075941374491930,12075941374748889,12075941374769799
|
||
|
|
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,901123,901128,4194304,256,0,0,24,24,131392,0x7f35ead59400,0x7f34bac36880,524288,11711559,1499006932,12075941374817227,12075941374974648,12075941375109687,12075941375113568
|
||
|
|
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,901123,901128,4194304,256,0,0,24,24,133632,0x7f35ead59300,0x7f34bac368c0,524288,3653621,467870008,12075941375153953,12075941375333206,12075941375525525,12075941375575596
|
||
|
|
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,901123,901128,4194304,256,0,0,24,24,135360,0x7f35ead59a00,0x7f34bac36900,524288,10432998,1335562824,12075941375611563,12075941375770644,12075941375909204,12075941375912863
|
||
|
|
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,901123,901128,4194304,256,0,0,20,24,136832,0x7f35ead59900,0x7f34bac36940,524288,2885035,369285468,12075941375962936,12075941376138162,12075941376423921,12075941376472032
|
||
|
|
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,901123,901128,4194304,256,0,0,28,24,138560,0x7f35ead59800,0x7f34bac36980,524288,13860509,1774178164,12075941376500756,12075941376672400,12075941376929839,12075941376977942
|
||
|
|
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,901123,901128,4194304,256,0,0,24,24,140288,0x7f35ead59700,0x7f34bac369c0,524288,11868610,1518994548,12075941377006776,12075941377180878,12075941377316397,12075941377319938
|
||
|
|
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,901123,901128,4194304,256,0,0,24,24,142784,0x7f35ead59600,0x7f34bac36a00,524288,3277846,419504484,12075941377362196,12075941377531596,12075941377742795,12075941377790993
|
||
|
|
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,901123,901128,4194304,256,0,0,24,24,144768,0x7f35ead59500,0x7f34bac36a40,524288,10948403,1401520460,12075941377828162,12075941377985034,12075941378122473,12075941378126647
|
||
|
|
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,901123,901128,4194304,256,0,0,20,24,145728,0x7f35ead59400,0x7f34bac36a80,524288,2539792,325196848,12075941378174306,12075941378342152,12075941378650791,12075941378675718
|
||
|
|
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,901123,901128,4194304,256,0,0,28,24,147712,0x7f35ead59300,0x7f34bac36ac0,524288,13250388,1696016800,12075941378718527,12075941378876550,12075941379136708,12075941379165287
|
||
|
|
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,901123,901128,4194304,256,0,0,24,24,149696,0x7f35ead59a00,0x7f34bac36b00,524288,10710142,1370961328,12075941379205863,12075941379363907,12075941379503427,12075941379507223
|
||
|
|
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,901123,901128,4194304,256,0,0,24,24,152192,0x7f35ead59900,0x7f34bac36b40,524288,3120835,399334568,12075941379554831,12075941379718466,12075941379945505,12075941379970494
|
||
|
|
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,901123,901128,4194304,256,0,0,24,24,154176,0x7f35ead59800,0x7f34bac36b80,524288,11216129,1435653884,12075941380032038,12075941380192384,12075941380328223,12075941380332046
|
||
|
|
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,901123,901128,4194304,256,0,0,20,24,155648,0x7f35ead59700,0x7f34bac36bc0,524288,2493114,319246408,12075941380380325,12075941380553182,12075941380883580,12075941380907776
|
||
|
|
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,901123,901128,4194304,256,0,0,28,24,157632,0x7f35ead59600,0x7f34bac36c00,524288,14094306,1804076396,12075941380954984,12075941381120699,12075941381379418,12075941381407685
|
||
|
|
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,901123,901128,4194304,256,0,0,24,24,159616,0x7f35ead59500,0x7f34bac36c40,524288,10111014,1294254764,12075941381449422,12075941381604697,12075941381746296,12075941381749951
|
||
|
|
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,901123,901128,4194304,256,0,0,24,24,162368,0x7f35ead59400,0x7f34bac36c80,524288,3436745,439760088,12075941381798130,12075941381960855,12075941382206134,12075941382231466
|
||
|
|
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,901123,901128,4194304,256,0,0,24,24,164608,0x7f35ead59300,0x7f34bac36cc0,524288,9693626,1240839820,12075941382288051,12075941382446933,12075941382589332,12075941382593068
|
||
|
|
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,901123,901128,4194304,256,0,0,20,24,166336,0x7f35ead59a00,0x7f34bac36d00,524288,2360670,302228600,12075941382641207,12075941382808702,12075941383184701,12075941383219211
|
||
|
|
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,901123,901128,4194304,256,0,0,28,24,168576,0x7f35ead59900,0x7f34bac36d40,524288,13997276,1791629420,12075941383254647,12075941383416379,12075941383676858,12075941383700696
|
||
|
|
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,901123,901128,4194304,256,0,0,24,24,170816,0x7f35ead59800,0x7f34bac36d80,524288,9437555,1207951892,12075941383744728,12075941383901337,12075941384046296,12075941384049735
|
||
|
|
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,901123,901128,4194304,256,0,0,24,24,174080,0x7f35ead59700,0x7f34bac36dc0,524288,3461187,443081552,12075941384099047,12075941384270615,12075941384581174,12075941384605047
|
||
|
|
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,901123,901128,4194304,256,0,0,24,24,176576,0x7f35ead59600,0x7f34bac36e00,524288,7941659,1016697620,12075941384662484,12075941384823253,12075941384964372,12075941384967761
|
||
|
|
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,901123,901128,4194304,256,0,0,20,24,177792,0x7f35ead59500,0x7f34bac36e40,524288,2340566,299456684,12075941385023475,12075941385184052,12075941385608050,12075941385635833
|
||
|
|
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,901123,901128,4194304,256,0,0,28,24,180288,0x7f35ead59400,0x7f34bac36e80,524288,12630735,1616795204,12075941385677660,12075941385834929,12075941386104208,12075941386133127
|
||
|
|
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,901123,901128,4194304,256,0,0,24,24,182784,0x7f35ead59300,0x7f34bac36ec0,524288,7344495,940088460,12075941386176097,12075941386339407,12075941386479566,12075941386482907
|
||
|
|
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,901123,901128,4194304,256,0,0,24,24,186304,0x7f35ead59a00,0x7f34bac36f00,524288,3462569,443232556,12075941386532158,12075941386691085,12075941387007724,12075941387032769
|
||
|
|
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,901123,901128,4194304,256,0,0,24,24,189312,0x7f35ead59900,0x7f34bac36f40,524288,3511513,449361624,12075941387092670,12075941387254763,12075941387406923,12075941387410230
|
||
|
|
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,901123,901128,4194304,256,0,0,20,24,190784,0x7f35ead59800,0x7f34bac36f80,524288,2304428,295010200,12075941387461906,12075941387619722,12075941388137320,12075941388162919
|
||
|
|
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,901123,901128,4194304,256,0,0,28,24,193792,0x7f35ead59700,0x7f34bac36fc0,524288,7922407,1014020540,12075941388205629,12075941388363239,12075941388660517,12075941388684398
|
||
|
|
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,901123,901128,4194304,256,0,0,24,24,196800,0x7f35ead59600,0x7f34bac37000,524288,3634989,465362128,12075941388732738,12075941388890277,12075941389046276,12075941389049647
|
||
|
|
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,901123,901128,4194304,256,0,0,24,24,201088,0x7f35ead59500,0x7f34bac37040,524288,3264320,417970424,12075941389101774,12075941389261315,12075941389646593,12075941389673356
|
||
|
|
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,901123,901128,4194304,256,0,0,24,24,204608,0x7f35ead59400,0x7f34bac37080,524288,3419795,437808280,12075941389730973,12075941389890432,12075941390068032,12075941390071316
|
||
|
|
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,901123,901128,4194304,256,0,0,20,24,206080,0x7f35ead59300,0x7f34bac370c0,524288,2342972,300028836,12075941390119265,12075941390299231,12075941390909788,12075941390934560
|
||
|
|
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,901123,901128,4194304,256,0,0,28,24,209600,0x7f35ead59a00,0x7f34bac37100,524288,4239022,542724156,12075941390978792,12075941391141467,12075941391469306,12075941391497476
|
||
|
|
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,901123,901128,4194304,256,0,0,24,24,213120,0x7f35ead59900,0x7f34bac37140,524288,3156831,404335252,12075941391537831,12075941391694265,12075941391874424,12075941391877753
|
||
|
|
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,901123,901128,4194304,256,0,0,24,24,218176,0x7f35ead59800,0x7f34bac37180,524288,3527636,451606824,12075941391926033,12075941392094584,12075941392551062,12075941392576111
|
||
|
|
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,901123,901128,4194304,256,0,0,24,24,222208,0x7f35ead59700,0x7f34bac371c0,524288,3123762,399628880,12075941392632325,12075941392793301,12075941392993300,12075941393018132
|
||
|
|
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,901123,901128,4194304,256,0,0,20,24,223936,0x7f35ead59600,0x7f34bac37200,524288,2318630,296929744,12075941393067013,12075941393225939,12075941393929616,12075941393979940
|
||
|
|
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,901123,901128,4194304,256,0,0,28,24,227968,0x7f35ead59500,0x7f34bac37240,524288,3723177,476514456,12075941394010046,12075941394187855,12075941394563374,12075941394611393
|
||
|
|
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,901123,901128,4194304,256,0,0,24,24,232000,0x7f35ead59400,0x7f34bac37280,524288,3027860,387429044,12075941394638474,12075941394813132,12075941395016492,12075941395064505
|
||
|
|
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,901123,901128,4194304,256,0,0,24,24,237824,0x7f35ead59300,0x7f34bac372c0,524288,3271517,418710948,12075941395091606,12075941395266091,12075941395792809,12075941395840247
|
||
|
|
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,901123,901128,4194304,256,0,0,24,24,242368,0x7f35ead59a00,0x7f34bac37300,524288,3191215,408404284,12075941395880592,12075941396046407,12075941396271687,12075941396319047
|
||
|
|
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,901123,901128,4194304,256,0,0,20,24,243584,0x7f35ead59900,0x7f34bac37340,524288,2296875,294173120,12075941396345706,12075941396521286,12075941397320162,12075941397369589
|
||
|
|
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,901123,901128,4194304,256,0,0,28,24,248128,0x7f35ead59800,0x7f34bac37380,524288,3684102,471608300,12075941397393574,12075941397572641,12075941398015680,12075941398041819
|
||
|
|
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,901123,901128,4194304,256,0,0,24,24,252672,0x7f35ead59700,0x7f34bac373c0,524288,3239223,414548536,12075941398090679,12075941398266878,12075941398528157,12075941398577294
|
||
|
|
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,901123,901128,4194304,256,0,0,24,24,259264,0x7f35ead59600,0x7f34bac37400,524288,3722152,476358204,12075941398606488,12075941398775836,12075941399373114,12075941399422695
|
||
|
|
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,901123,901128,4194304,256,0,0,24,24,264832,0x7f35ead59500,0x7f34bac37440,524288,3279408,419684984,12075941399458271,12075941399628153,12075941399896952,12075941399946949
|
||
|
|
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,901123,901128,4194304,256,0,0,20,24,266304,0x7f35ead59400,0x7f34bac37480,524288,2305992,295057208,12075941399968670,12075941400159991,12075941401144467,12075941401214194
|
||
|
|
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,901123,901128,4194304,256,0,0,28,24,271872,0x7f35ead59300,0x7f34bac374c0,524288,3454546,442318960,12075941401242968,12075941401423666,12075941401939344,12075941402013450
|
||
|
|
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,901123,901128,4194304,256,0,0,24,24,277440,0x7f35ead59a00,0x7f34bac37500,524288,3233069,413736316,12075941402046701,12075941402220302,12075941402492461,12075941402560186
|
||
|
|
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,901123,901128,4194304,256,0,0,12,24,279936,0x7f35ead59900,0x7f34bac37540,524288,2208117,282588208,12075941402585062,12075941402758060,12075941403496777,12075941403564622
|
||
|
|
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,901123,901128,4194304,256,0,0,24,24,286528,0x7f35ead59800,0x7f34bac37580,524288,3121979,399732712,12075941403601481,12075941403761896,12075941404078375,12075941404147235
|
||
|
|
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,901123,901128,4194304,256,0,0,20,24,288000,0x7f35ead59700,0x7f34bac375c0,524288,2276762,291266148,12075941404176329,12075941404353254,12075941405523809,12075941405593203
|
||
|
|
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,901123,901128,4194304,256,0,0,32,24,294592,0x7f35ead59600,0x7f34bac37600,524288,3470031,444046844,12075941405624671,12075941405805728,12075941406416285,12075941406487715
|
||
|
|
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,901123,901128,4194304,256,0,0,24,24,301184,0x7f35ead59500,0x7f34bac37640,524288,3216318,411644140,12075941406514144,12075941406689564,12075941407009083,12075941407076649
|
||
|
|
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,901123,901128,4194304,256,0,0,12,24,304960,0x7f35ead59400,0x7f34bac37680,524288,2210352,282859868,12075941407101796,12075941407292922,12075941408171318,12075941408240462
|
||
|
|
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,901123,901128,4194304,256,0,0,24,24,313600,0x7f35ead59300,0x7f34bac376c0,524288,3134829,401167460,12075941408285486,12075941408448917,12075941408880595,12075941408948408
|
||
|
|
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,901123,901128,4194304,256,0,0,20,24,314816,0x7f35ead59a00,0x7f34bac37700,524288,2304562,294814896,12075941408979766,12075941409160594,12075941410708908,12075941410778710
|
||
|
|
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,901123,901128,4194304,256,0,0,20,24,317568,0x7f35ead59900,0x7f34bac37740,524288,2256011,288722584,12075941410809577,12075941410988267,12075941411783944,12075941411854970
|
||
|
|
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,901123,901128,4194304,256,0,0,12,24,320320,0x7f35ead59800,0x7f34bac37780,524288,2165744,277297756,12075941411885597,12075941412060903,12075941412476101,12075941412543139
|
||
|
|
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,901123,901128,4194304,256,0,0,12,24,324096,0x7f35ead59700,0x7f34bac377c0,524288,2268843,290249632,12075941412569468,12075941412745060,12075941413905055,12075941413972776
|
||
|
|
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,901123,901128,4194304,256,0,0,12,24,328896,0x7f35ead59600,0x7f34bac37800,524288,2183015,279412272,12075941414017429,12075941414179294,12075941414965531,12075941415035310
|
||
|
|
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,901123,901128,4194304,256,0,0,20,24,330112,0x7f35ead59500,0x7f34bac37840,524288,2607429,333886484,12075941415065987,12075941415242650,12075941418292237,12075941418360760
|
||
|
|
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,901123,901128,4194304,256,0,0,20,24,332864,0x7f35ead59400,0x7f34bac37880,524288,2305239,295018316,12075941418397589,12075941418560716,12075941420102790,12075941420171956
|
||
|
|
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,901123,901128,4194304,256,0,0,12,24,335616,0x7f35ead59300,0x7f34bac378c0,524288,2212707,283063448,12075941420205950,12075941420385029,12075941421175426,12075941421243638
|
||
|
|
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,901123,901128,4194304,256,0,0,12,24,339392,0x7f35ead59a00,0x7f34bac37900,524288,2543016,325743776,12075941421275077,12075941421454465,12075941423737015,12075941423805660
|
||
|
|
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,901123,901128,4194304,256,0,0,12,24,344192,0x7f35ead59900,0x7f34bac37940,524288,2356147,301682824,12075941423852016,12075941424013654,12075941425549008,12075941425619971
|
||
|
|
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,901123,901128,4194304,256,0,0,20,24,345408,0x7f35ead59800,0x7f34bac37980,524288,2916112,373306396,12075941425649997,12075941425827567,12075941431883222,12075941431952370
|
||
|
|
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,901123,901128,4194304,256,0,0,20,24,348160,0x7f35ead59700,0x7f34bac379c0,524288,3345927,428390632,12075941431982816,12075941432162581,12075941435206089,12075941435276628
|
||
|
|
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,901123,901128,4194304,256,0,0,12,24,350912,0x7f35ead59600,0x7f34bac37a00,524288,2278656,291716872,12075941435308106,12075941435487208,12075941437026241,12075941437095168
|
||
|
|
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,901123,901128,4194304,256,0,0,12,24,0,0x7f35ead59500,0x7f34bac37a40,524288,2546903,326018512,12075941437125083,12075941437302400,12075941441829102,12075941441898384
|