169 خطوط
43 KiB
CSV
169 خطوط
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",0,0,0,880581,880586,33554432,256,0,0,8,32,6464,0x0,0x7fe7ed804180,1048576,11078382,1417971496,12075537965584008,12075538208404486,12075538208731365,12075538208839027
|
||
|
|
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,880581,880586,32768,256,0,0,24,24,12480,0x0,0x7fe7ed835100,4096,117181,14993908,12075538223157086,12075538223463229,12075538223469789,12075538223481179
|
||
|
|
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,880581,880586,4194304,256,0,0,24,24,12928,0x7fe8f94cc900,0x7fe7ed835140,524288,10299796,1318424996,12075538223533306,12075538223749628,12075538223889627,12075538223893285
|
||
|
|
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,880581,880586,4194304,256,0,0,36,24,13632,0x7fe8f94cc800,0x7fe7ed835180,524288,13515734,1729994736,12075538223964246,12075538224140666,12075538224389945,12075538224460459
|
||
|
|
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,880581,880586,4194304,256,0,0,28,24,14080,0x7fe8f94cc700,0x7fe7ed8351c0,524288,13539810,1733036468,12075538224486357,12075538224673464,12075538224928503,12075538224995824
|
||
|
|
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,880581,880586,4194304,256,0,0,24,24,14528,0x7fe8f94cc600,0x7fe7ed835200,524288,12128656,1552412068,12075538225026921,12075538225211702,12075538225344182,12075538225347898
|
||
|
|
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,880581,880586,4194304,256,0,0,24,24,14976,0x7fe8f94cc500,0x7fe7ed835240,524288,9985762,1278178868,12075538225391098,12075538225573301,12075538225715540,12075538225718937
|
||
|
|
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,880581,880586,4194304,256,0,0,24,24,15424,0x7fe8f94cc400,0x7fe7ed835280,524288,12792480,1637432232,12075538225797784,12075538225966099,12075538226096979,12075538226100466
|
||
|
|
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,880581,880586,4194304,256,0,0,28,24,16128,0x7fe8f94cc300,0x7fe7ed8352c0,524288,13498189,1727761312,12075538226150479,12075538226332498,12075538226592497,12075538226634118
|
||
|
|
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,880581,880586,4194304,256,0,0,28,24,16832,0x7fe8f94cca00,0x7fe7ed835300,524288,14083761,1802743240,12075538226661048,12075538226842576,12075538227095215,12075538227136221
|
||
|
|
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,880581,880586,4194304,256,0,0,24,24,17536,0x7fe8f94cc900,0x7fe7ed835340,524288,11635924,1489332172,12075538227160266,12075538227352334,12075538227486414,12075538227489959
|
||
|
|
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,880581,880586,4194304,256,0,0,24,24,18240,0x7fe8f94cc800,0x7fe7ed835380,524288,11995112,1535305724,12075538227539541,12075538227711373,12075538227844172,12075538227847573
|
||
|
|
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,880581,880586,4194304,256,0,0,24,24,18944,0x7fe8f94cc700,0x7fe7ed8353c0,524288,12015895,1538091572,12075538227910180,12075538228080971,12075538228213771,12075538228217441
|
||
|
|
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,880581,880586,4194304,256,0,0,28,24,19904,0x7fe8f94cc600,0x7fe7ed835400,524288,14002035,1792313128,12075538228267895,12075538228440810,12075538228698089,12075538228764748
|
||
|
|
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,880581,880586,4194304,256,0,0,28,24,20608,0x7fe8f94cc500,0x7fe7ed835440,524288,13521213,1730686716,12075538228791608,12075538228972488,12075538229229607,12075538229295865
|
||
|
|
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,880581,880586,4194304,256,0,0,24,24,21312,0x7fe8f94cc400,0x7fe7ed835480,524288,12233259,1565953676,12075538229321473,12075538229512166,12075538229643846,12075538229647318
|
||
|
|
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,880581,880586,4194304,256,0,0,24,24,22016,0x7fe8f94cc300,0x7fe7ed8354c0,524288,12416727,1589334528,12075538229695568,12075538229865765,12075538229997124,12075538230004622
|
||
|
|
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,880581,880586,4194304,256,0,0,24,24,22720,0x7fe8f94cca00,0x7fe7ed835500,524288,11839102,1515427280,12075538230063271,12075538230232003,12075538230365123,12075538230368699
|
||
|
|
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,880581,880586,4194304,256,0,0,28,24,23680,0x7fe8f94cc900,0x7fe7ed835540,524288,13344902,1708166148,12075538230419112,12075538230583362,12075538230841441,12075538230907961
|
||
|
|
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,880581,880586,4194304,256,0,0,28,24,24384,0x7fe8f94cc800,0x7fe7ed835580,524288,14069899,1800935976,12075538230932837,12075538231125120,12075538231372319,12075538231439158
|
||
|
|
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,880581,880586,4194304,256,0,0,24,24,25088,0x7fe8f94cc700,0x7fe7ed8355c0,524288,12674288,1622427104,12075538231463704,12075538231647038,12075538231776798,12075538231780222
|
||
|
|
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,880581,880586,4194304,256,0,0,24,24,25792,0x7fe8f94cc600,0x7fe7ed835600,524288,11064786,1416374964,12075538231830606,12075538231997117,12075538232135196,12075538232138818
|
||
|
|
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,880581,880586,4194304,256,0,0,24,24,26496,0x7fe8f94cc500,0x7fe7ed835640,524288,11800008,1510459044,12075538232200433,12075538232366555,12075538232500315,12075538232504017
|
||
|
|
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,880581,880586,4194304,256,0,0,28,24,27712,0x7fe8f94cc400,0x7fe7ed835680,524288,13482638,1725731196,12075538232552257,12075538232722714,12075538232980153,12075538233046946
|
||
|
|
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,880581,880586,4194304,256,0,0,28,24,28416,0x7fe8f94cc300,0x7fe7ed8356c0,524288,14347090,1836385800,12075538233073816,12075538233254232,12075538233511351,12075538233577893
|
||
|
|
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,880581,880586,4194304,256,0,0,24,24,29120,0x7fe8f94cca00,0x7fe7ed835700,524288,13278725,1699677836,12075538233600805,12075538233779190,12075538233907030,12075538233910441
|
||
|
|
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,880581,880586,4194304,256,0,0,24,24,30080,0x7fe8f94cc900,0x7fe7ed835740,524288,11793425,1509476396,12075538233959492,12075538234131829,12075538234265588,12075538234269148
|
||
|
|
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,880581,880586,4194304,256,0,0,24,24,30784,0x7fe8f94cc800,0x7fe7ed835780,524288,11609859,1486049464,12075538234329951,12075538234494547,12075538234628147,12075538234631922
|
||
|
|
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,880581,880586,4194304,256,0,0,28,24,32000,0x7fe8f94cc700,0x7fe7ed8357c0,524288,13418552,1717623916,12075538234679871,12075538234857426,12075538235123985,12075538235191091
|
||
|
|
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,880581,880586,4194304,256,0,0,28,24,32960,0x7fe8f94cc600,0x7fe7ed835800,524288,13893440,1778324016,12075538235217901,12075538235402704,12075538235661423,12075538235727798
|
||
|
|
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,880581,880586,4194304,256,0,0,24,24,33920,0x7fe8f94cc500,0x7fe7ed835840,524288,13150677,1683354028,12075538235754378,12075538235931502,12075538236060142,12075538236063442
|
||
|
|
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,880581,880586,4194304,256,0,0,24,24,34880,0x7fe8f94cc400,0x7fe7ed835880,524288,11094429,1420051704,12075538236114167,12075538236279661,12075538236417580,12075538236421087
|
||
|
|
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,880581,880586,4194304,256,0,0,24,24,35840,0x7fe8f94cc300,0x7fe7ed8358c0,524288,11713009,1499265528,12075538236482291,12075538236646219,12075538236780779,12075538236784122
|
||
|
|
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,880581,880586,4194304,256,0,0,28,24,37312,0x7fe8f94cca00,0x7fe7ed835900,524288,13700817,1753689604,12075538236832832,12075538237002058,12075538237264137,12075538237330878
|
||
|
|
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,880581,880586,4194304,256,0,0,28,24,38272,0x7fe8f94cc900,0x7fe7ed835940,524288,13526094,1731356060,12075538237355393,12075538237536456,12075538237796455,12075538237865642
|
||
|
|
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,880581,880586,4194304,256,0,0,24,24,39232,0x7fe8f94cc800,0x7fe7ed835980,524288,11563245,1480025456,12075538237888724,12075538238095174,12075538238228933,12075538238232533
|
||
|
|
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,880581,880586,4194304,256,0,0,24,24,40192,0x7fe8f94cc700,0x7fe7ed8359c0,524288,13240486,1694733176,12075538238282236,12075538238464933,12075538238593092,12075538238596650
|
||
|
|
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,880581,880586,4194304,256,0,0,24,24,41152,0x7fe8f94cc600,0x7fe7ed835a00,524288,11290351,1445175700,12075538238657914,12075538238819011,12075538238954851,12075538238958222
|
||
|
|
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,880581,880586,4194304,256,0,0,28,24,42624,0x7fe8f94cc500,0x7fe7ed835a40,524288,13622054,1743564792,12075538239010770,12075538239195970,12075538239457409,12075538239523803
|
||
|
|
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,880581,880586,4194304,256,0,0,28,24,43584,0x7fe8f94cc400,0x7fe7ed835a80,524288,13556919,1735286480,12075538239549912,12075538239728928,12075538239984127,12075538240026578
|
||
|
|
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,880581,880586,4194304,256,0,0,24,24,44544,0x7fe8f94cc300,0x7fe7ed835ac0,524288,11832430,1514566736,12075538240048999,12075538240230206,12075538240364125,12075538240367501
|
||
|
|
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,880581,880586,4194304,256,0,0,24,24,45760,0x7fe8f94cca00,0x7fe7ed835b00,524288,10496991,1343539000,12075538240416622,12075538240584925,12075538240723484,12075538240726989
|
||
|
|
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,880581,880586,4194304,256,0,0,24,24,46720,0x7fe8f94cc900,0x7fe7ed835b40,524288,13097079,1676378156,12075538240787161,12075538240948123,12075538241077563,12075538241080947
|
||
|
|
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,880581,880586,4194304,256,0,0,28,24,48448,0x7fe8f94cc800,0x7fe7ed835b80,524288,13517986,1730265004,12075538241129347,12075538241305402,12075538241575161,12075538241642901
|
||
|
|
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,880581,880586,4194304,256,0,0,28,24,49408,0x7fe8f94cc700,0x7fe7ed835bc0,524288,13255976,1696798632,12075538241665904,12075538241846360,12075538242101399,12075538242168749
|
||
|
|
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,880581,880586,4194304,256,0,0,24,24,50368,0x7fe8f94cc600,0x7fe7ed835c00,524288,12125376,1551974624,12075538242194186,12075538242378358,12075538242510517,12075538242514221
|
||
|
|
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,880581,880586,4194304,256,0,0,24,24,51584,0x7fe8f94cc500,0x7fe7ed835c40,524288,10217239,1307770388,12075538242563983,12075538242733077,12075538242873556,12075538242877005
|
||
|
|
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,880581,880586,4194304,256,0,0,24,24,52544,0x7fe8f94cc400,0x7fe7ed835c80,524288,12568696,1608838688,12075538242937738,12075538243114355,12075538243245715,12075538243249337
|
||
|
|
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,880581,880586,4194304,256,0,0,28,24,54272,0x7fe8f94cc300,0x7fe7ed835cc0,524288,13534572,1732428708,12075538243298849,12075538243468914,12075538243734513,12075538243777338
|
||
|
|
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,880581,880586,4194304,256,0,0,28,24,55488,0x7fe8f94cca00,0x7fe7ed835d00,524288,12879972,1648653104,12075538243804519,12075538243981392,12075538244240911,12075538244309297
|
||
|
|
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,880581,880586,4194304,256,0,0,24,24,56704,0x7fe8f94cc900,0x7fe7ed835d40,524288,12109424,1550021420,12075538244335425,12075538244518670,12075538244650669,12075538244654088
|
||
|
|
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,880581,880586,4194304,256,0,0,24,24,58176,0x7fe8f94cc800,0x7fe7ed835d80,524288,9106859,1165642272,12075538244702728,12075538244873068,12075538245018668,12075538245022282
|
||
|
|
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,880581,880586,4194304,256,0,0,24,24,59392,0x7fe8f94cc700,0x7fe7ed835dc0,524288,12629362,1616553528,12075538245083726,12075538245250027,12075538245380907,12075538245384475
|
||
|
|
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,880581,880586,4194304,256,0,0,28,24,61376,0x7fe8f94cc600,0x7fe7ed835e00,524288,13896745,1778721236,12075538245433767,12075538245601386,12075538245862025,12075538245927374
|
||
|
|
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,880581,880586,4194304,256,0,0,28,24,62592,0x7fe8f94cc500,0x7fe7ed835e40,524288,13948159,1785343032,12075538245951358,12075538246146824,12075538246404423,12075538246471515
|
||
|
|
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,880581,880586,4194304,256,0,0,24,24,63808,0x7fe8f94cc400,0x7fe7ed835e80,524288,12242388,1566990808,12075538246495369,12075538246674982,12075538246807301,12075538246810806
|
||
|
|
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,880581,880586,4194304,256,0,0,24,24,65280,0x7fe8f94cc300,0x7fe7ed835ec0,524288,8572301,1097235336,12075538246857843,12075538247033220,12075538247171780,12075538247175744
|
||
|
|
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,880581,880586,4194304,256,0,0,24,24,66496,0x7fe8f94cca00,0x7fe7ed835f00,524288,11571011,1481026432,12075538247236717,12075538247400419,12075538247535619,12075538247539269
|
||
|
|
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,880581,880586,4194304,256,0,0,28,24,68480,0x7fe8f94cc900,0x7fe7ed835f40,524288,12957802,1658510048,12075538247587649,12075538247758818,12075538248027937,12075538248094992
|
||
|
|
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,880581,880586,4194304,256,0,0,28,24,69696,0x7fe8f94cc800,0x7fe7ed835f80,524288,13777803,1763530176,12075538248119047,12075538248301856,12075538248561215,12075538248628183
|
||
|
|
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,880581,880586,4194304,256,0,0,24,24,70912,0x7fe8f94cc700,0x7fe7ed835fc0,524288,11942537,1528741968,12075538248655815,12075538248838494,12075538248971293,12075538248974777
|
||
|
|
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,880581,880586,4194304,256,0,0,24,24,72384,0x7fe8f94cc600,0x7fe7ed836000,524288,6755736,864700336,12075538249028888,12075538249202972,12075538249341212,12075538249344775
|
||
|
|
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,880581,880586,4194304,256,0,0,24,24,73600,0x7fe8f94cc500,0x7fe7ed836040,524288,12578793,1610117664,12075538249404887,12075538249566811,12075538249696890,12075538249700516
|
||
|
|
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,880581,880586,4194304,256,0,0,28,24,75840,0x7fe8f94cc400,0x7fe7ed836080,524288,13526393,1731379256,12075538249748866,12075538249924090,12075538250193849,12075538250243044
|
||
|
|
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,880581,880586,4194304,256,0,0,28,24,77056,0x7fe8f94cc300,0x7fe7ed8360c0,524288,14060144,1799657108,12075538250267330,12075538250448888,12075538250698327,12075538250747201
|
||
|
|
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,880581,880586,4194304,256,0,0,24,24,78272,0x7fe8f94cca00,0x7fe7ed836100,524288,11510644,1473426664,12075538250770425,12075538250949366,12075538251084885,12075538251088546
|
||
|
|
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,880581,880586,4194304,256,0,0,24,24,80000,0x7fe8f94cc900,0x7fe7ed836140,524288,6948737,889384608,12075538251136515,12075538251308084,12075538251452884,12075538251456249
|
||
|
|
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,880581,880586,4194304,256,0,0,24,24,81216,0x7fe8f94cc800,0x7fe7ed836180,524288,11630910,1488780572,12075538251517773,12075538251678163,12075538251812083,12075538251815417
|
||
|
|
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,880581,880586,4194304,256,0,0,28,24,83456,0x7fe8f94cc700,0x7fe7ed8361c0,524288,13080371,1674332236,12075538251863696,12075538252038962,12075538252306161,12075538252356131
|
||
|
|
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,880581,880586,4194304,256,0,0,28,24,84928,0x7fe8f94cc600,0x7fe7ed836200,524288,13246453,1695572244,12075538252380557,12075538252561200,12075538252818639,12075538252865789
|
||
|
|
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,880581,880586,4194304,256,0,0,24,24,86400,0x7fe8f94cc500,0x7fe7ed836240,524288,10838034,1387264692,12075538252892178,12075538253073678,12075538253211917,12075538253215649
|
||
|
|
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,880581,880586,4194304,256,0,0,24,24,88128,0x7fe8f94cc400,0x7fe7ed836280,524288,6054571,774981876,12075538253268537,12075538253435756,12075538253586636,12075538253589974
|
||
|
|
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,880581,880586,4194304,256,0,0,24,24,89600,0x7fe8f94cc300,0x7fe7ed8362c0,524288,11577572,1482018444,12075538253669162,12075538253830795,12075538253964394,12075538253967977
|
||
|
|
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,880581,880586,4194304,256,0,0,28,24,92096,0x7fe8f94cca00,0x7fe7ed836300,524288,12333488,1578635596,12075538254016567,12075538254195754,12075538254457353,12075538254505626
|
||
|
|
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,880581,880586,4194304,256,0,0,28,24,93568,0x7fe8f94cc900,0x7fe7ed836340,524288,13717317,1755812848,12075538254529591,12075538254707432,12075538254968071,12075538255017588
|
||
|
|
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,880581,880586,4194304,256,0,0,24,24,95040,0x7fe8f94cc800,0x7fe7ed836380,524288,12969537,1660050172,12075538255045770,12075538255225030,12075538255355109,12075538255358451
|
||
|
|
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,880581,880586,4194304,256,0,0,24,24,96768,0x7fe8f94cc700,0x7fe7ed8363c0,524288,4952059,633936224,12075538255406120,12075538255574628,12075538255732708,12075538255736053
|
||
|
|
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,880581,880586,4194304,256,0,0,24,24,98240,0x7fe8f94cc600,0x7fe7ed836400,524288,11531501,1475930216,12075538255797457,12075538255963427,12075538256099106,12075538256102975
|
||
|
|
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,880581,880586,4194304,256,0,0,28,24,100736,0x7fe8f94cc500,0x7fe7ed836440,524288,12754109,1632504360,12075538256151405,12075538256325986,12075538256598625,12075538256646635
|
||
|
|
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,880581,880586,4194304,256,0,0,28,24,102208,0x7fe8f94cc400,0x7fe7ed836480,524288,13766111,1761995412,12075538256669317,12075538256849184,12075538257109023,12075538257160049
|
||
|
|
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,880581,880586,4194304,256,0,0,24,24,103680,0x7fe8f94cc300,0x7fe7ed8364c0,524288,10793443,1381528728,12075538257184745,12075538257365822,12075538257503901,12075538257507525
|
||
|
|
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,880581,880586,4194304,256,0,0,24,24,105664,0x7fe8f94cca00,0x7fe7ed836500,524288,4170107,533710420,12075538257558009,12075538257729020,12075538257896220,12075538257899764
|
||
|
|
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,880581,880586,4194304,256,0,0,24,24,107136,0x7fe8f94cc900,0x7fe7ed836540,524288,12288568,1572936460,12075538257960477,12075538258126459,12075538258259258,12075538258263209
|
||
|
|
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,880581,880586,4194304,256,0,0,28,24,109888,0x7fe8f94cc800,0x7fe7ed836580,524288,9450603,1209613736,12075538258314084,12075538258501017,12075538258769496,12075538258816097
|
||
|
|
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,880581,880586,4194304,256,0,0,28,24,111360,0x7fe8f94cc700,0x7fe7ed8365c0,524288,13599670,1740727580,12075538258841955,12075538259023575,12075538259284055,12075538259333368
|
||
|
|
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,880581,880586,4194304,256,0,0,24,24,112832,0x7fe8f94cc600,0x7fe7ed836600,524288,9689906,1240234732,12075538259357623,12075538259541014,12075538259684533,12075538259688158
|
||
|
|
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,880581,880586,4194304,256,0,0,24,24,114816,0x7fe8f94cc500,0x7fe7ed836640,524288,3686742,472064448,12075538259735766,12075538259904692,12075538260079412,12075538260083112
|
||
|
|
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,880581,880586,4194304,256,0,0,24,24,116288,0x7fe8f94cc400,0x7fe7ed836680,524288,12946752,1657173596,12075538260143434,12075538260306771,12075538260436850,12075538260440356
|
||
|
|
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,880581,880586,4194304,256,0,0,28,24,119040,0x7fe8f94cc300,0x7fe7ed8366c0,524288,8024530,1027197928,12075538260490258,12075538260659889,12075538260924048,12075538260971433
|
||
|
|
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,880581,880586,4194304,256,0,0,28,24,120768,0x7fe8f94cca00,0x7fe7ed836700,524288,13433917,1719555236,12075538260993153,12075538261186767,12075538261447246,12075538261496819
|
||
|
|
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,880581,880586,4194304,256,0,0,24,24,122496,0x7fe8f94cc900,0x7fe7ed836740,524288,10615056,1358701312,12075538261526083,12075538261709325,12075538261850605,12075538261854323
|
||
|
|
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,880581,880586,4194304,256,0,0,24,24,124736,0x7fe8f94cc800,0x7fe7ed836780,524288,3236298,414279112,12075538261902463,12075538262077324,12075538262260203,12075538262263905
|
||
|
|
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,880581,880586,4194304,256,0,0,24,24,126464,0x7fe8f94cc700,0x7fe7ed8367c0,524288,10341404,1323623228,12075538262325689,12075538262489323,12075538262630762,12075538262634553
|
||
|
|
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,880581,880586,4194304,256,0,0,20,24,127936,0x7fe8f94cc600,0x7fe7ed836800,524288,4170318,533715716,12075538262683034,12075538262849641,12075538263116520,12075538263164268
|
||
|
|
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,880581,880586,4194304,256,0,0,28,24,129664,0x7fe8f94cc500,0x7fe7ed836840,524288,13329490,1706180724,12075538263188533,12075538263368999,12075538263630438,12075538263652976
|
||
|
|
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,880581,880586,4194304,256,0,0,24,24,131392,0x7fe8f94cc400,0x7fe7ed836880,524288,11674332,1494365856,12075538263695064,12075538263853477,12075538263987397,12075538263991044
|
||
|
|
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,880581,880586,4194304,256,0,0,24,24,133632,0x7fe8f94cc300,0x7fe7ed8368c0,524288,3649303,467044868,12075538264039214,12075538264209636,12075538264401475,12075538264448725
|
||
|
|
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,880581,880586,4194304,256,0,0,24,24,135360,0x7fe8f94cca00,0x7fe7ed836900,524288,11043812,1413632884,12075538264487036,12075538264650754,12075538264787074,12075538264790450
|
||
|
|
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,880581,880586,4194304,256,0,0,20,24,136832,0x7fe8f94cc900,0x7fe7ed836940,524288,2851585,364933772,12075538264840082,12075538265023233,12075538265339712,12075538265390285
|
||
|
|
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,880581,880586,4194304,256,0,0,28,24,138560,0x7fe8f94cc800,0x7fe7ed836980,524288,13543167,1733456544,12075538265413829,12075538265598591,12075538265861150,12075538265907897
|
||
|
|
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,880581,880586,4194304,256,0,0,24,24,140288,0x7fe8f94cc700,0x7fe7ed8369c0,524288,10611757,1358261568,12075538265933394,12075538266114749,12075538266252348,12075538266256244
|
||
|
|
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,880581,880586,4194304,256,0,0,24,24,142784,0x7fe8f94cc600,0x7fe7ed836a00,524288,3486357,446270808,12075538266307239,12075538266473628,12075538266684027,12075538266730656
|
||
|
|
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,880581,880586,4194304,256,0,0,24,24,144768,0x7fe8f94cc500,0x7fe7ed836a40,524288,10919982,1397777428,12075538266768356,12075538266931066,12075538267069465,12075538267073102
|
||
|
|
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,880581,880586,4194304,256,0,0,20,24,145728,0x7fe8f94cc400,0x7fe7ed836a80,524288,2582214,330570008,12075538267120971,12075538267295064,12075538267602423,12075538267623866
|
||
|
|
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,880581,880586,4194304,256,0,0,28,24,147712,0x7fe8f94cc300,0x7fe7ed836ac0,524288,12550142,1606399800,12075538267665363,12075538267824503,12075538268089142,12075538268137551
|
||
|
|
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,880581,880586,4194304,256,0,0,24,24,149696,0x7fe8f94cca00,0x7fe7ed836b00,524288,9872914,1263623684,12075538268164691,12075538268341941,12075538268484660,12075538268488152
|
||
|
|
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,880581,880586,4194304,256,0,0,24,24,152192,0x7fe8f94cc900,0x7fe7ed836b40,524288,3450026,441564000,12075538268535851,12075538268704819,12075538268933138,12075538268979545
|
||
|
|
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,880581,880586,4194304,256,0,0,24,24,154176,0x7fe8f94cc800,0x7fe7ed836b80,524288,10405505,1331887932,12075538269020501,12075538269195057,12075538269336657,12075538269340516
|
||
|
|
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,880581,880586,4194304,256,0,0,20,24,155648,0x7fe8f94cc700,0x7fe7ed836bc0,524288,2479070,317293448,12075538269388295,12075538269560176,12075538269890735,12075538269937546
|
||
|
|
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,880581,880586,4194304,256,0,0,28,24,157632,0x7fe8f94cc600,0x7fe7ed836c00,524288,12556680,1607255908,12075538269960929,12075538270146574,12075538270411053,12075538270457813
|
||
|
|
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,880581,880586,4194304,256,0,0,24,24,159616,0x7fe8f94cc500,0x7fe7ed836c40,524288,9450258,1209662264,12075538270481617,12075538270662092,12075538270807371,12075538270810748
|
||
|
|
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,880581,880586,4194304,256,0,0,24,24,162368,0x7fe8f94cc400,0x7fe7ed836c80,524288,3343420,427818300,12075538270858397,12075538271030251,12075538271274890,12075538271323511
|
||
|
|
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,880581,880586,4194304,256,0,0,24,24,164608,0x7fe8f94cc300,0x7fe7ed836cc0,524288,8853184,1133245404,12075538271363005,12075538271527720,12075538271671080,12075538271678211
|
||
|
|
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,880581,880586,4194304,256,0,0,20,24,166336,0x7fe8f94cca00,0x7fe7ed836d00,524288,2388875,305746140,12075538271723244,12075538271893158,12075538272270117,12075538272320514
|
||
|
|
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,880581,880586,4194304,256,0,0,28,24,168576,0x7fe8f94cc900,0x7fe7ed836d40,524288,12274089,1571095772,12075538272345060,12075538272526596,12075538272793155,12075538272839940
|
||
|
|
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,880581,880586,4194304,256,0,0,24,24,170816,0x7fe8f94cc800,0x7fe7ed836d80,524288,10270306,1314476200,12075538272865718,12075538273047714,12075538273224993,12075538273228312
|
||
|
|
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,880581,880586,4194304,256,0,0,24,24,174080,0x7fe8f94cc700,0x7fe7ed836dc0,524288,3230888,413598372,12075538273278134,12075538273453633,12075538273732992,12075538273780107
|
||
|
|
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,880581,880586,4194304,256,0,0,24,24,176576,0x7fe8f94cc600,0x7fe7ed836e00,524288,8071992,1033320108,12075538273816595,12075538273978111,12075538274116510,12075538274120249
|
||
|
|
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,880581,880586,4194304,256,0,0,20,24,177792,0x7fe8f94cc500,0x7fe7ed836e40,524288,2349301,300724132,12075538274168449,12075538274338430,12075538274762908,12075538274809320
|
||
|
|
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,880581,880586,4194304,256,0,0,28,24,180288,0x7fe8f94cc400,0x7fe7ed836e80,524288,11425784,1462437888,12075538274833244,12075538275021787,12075538275291707,12075538275338954
|
||
|
|
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,880581,880586,4194304,256,0,0,24,24,182784,0x7fe8f94cc300,0x7fe7ed836ec0,524288,7525653,963250540,12075538275364922,12075538275545786,12075538275686905,12075538275690287
|
||
|
|
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,880581,880586,4194304,256,0,0,24,24,186304,0x7fe8f94cca00,0x7fe7ed836f00,524288,3420603,437881172,12075538275738577,12075538275908025,12075538276224503,12075538276245769
|
||
|
|
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,880581,880586,4194304,256,0,0,24,24,189312,0x7fe8f94cc900,0x7fe7ed836f40,524288,3747134,479579236,12075538276300912,12075538276466263,12075538276619222,12075538276622910
|
||
|
|
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,880581,880586,4194304,256,0,0,20,24,190784,0x7fe8f94cc800,0x7fe7ed836f80,524288,2302690,294757108,12075538276671651,12075538276850581,12075538277368500,12075538277418990
|
||
|
|
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,880581,880586,4194304,256,0,0,28,24,193792,0x7fe8f94cc700,0x7fe7ed836fc0,524288,7323634,937388332,12075538277446962,12075538277628659,12075538277927698,12075538277974262
|
||
|
|
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,880581,880586,4194304,256,0,0,24,24,196800,0x7fe8f94cc600,0x7fe7ed837000,524288,3213051,411245724,12075538277996202,12075538278194897,12075538278349456,12075538278352865
|
||
|
|
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,880581,880586,4194304,256,0,0,24,24,201088,0x7fe8f94cc500,0x7fe7ed837040,524288,3298433,422134684,12075538278403529,12075538278568016,12075538278954254,12075538279008544
|
||
|
|
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,880581,880586,4194304,256,0,0,24,24,204608,0x7fe8f94cc400,0x7fe7ed837080,524288,3288006,420769328,12075538279045723,12075538279210094,12075538279386093,12075538279389752
|
||
|
|
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,880581,880586,4194304,256,0,0,20,24,206080,0x7fe8f94cc300,0x7fe7ed8370c0,524288,2298394,294074560,12075538279437461,12075538279608972,12075538280219370,12075538280266682
|
||
|
|
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,880581,880586,4194304,256,0,0,28,24,209600,0x7fe8f94cca00,0x7fe7ed837100,524288,4781605,612030980,12075538280290336,12075538280480489,12075538280810728,12075538280857700
|
||
|
|
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,880581,880586,4194304,256,0,0,24,24,213120,0x7fe8f94cc900,0x7fe7ed837140,524288,3282753,420220424,12075538280882707,12075538281066887,12075538281246567,12075538281250110
|
||
|
|
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,880581,880586,4194304,256,0,0,24,24,218176,0x7fe8f94cc800,0x7fe7ed837180,524288,3276207,419414052,12075538281299942,12075538281470086,12075538281949285,12075538281970058
|
||
|
|
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,880581,880586,4194304,256,0,0,24,24,222208,0x7fe8f94cc700,0x7fe7ed8371c0,524288,3272232,418774584,12075538282032323,12075538282198884,12075538282437443,12075538282485195
|
||
|
|
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,880581,880586,4194304,256,0,0,20,24,223936,0x7fe8f94cc600,0x7fe7ed837200,524288,2300455,294361112,12075538282515401,12075538282695842,12075538283400320,12075538283449407
|
||
|
|
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,880581,880586,4194304,256,0,0,28,24,227968,0x7fe8f94cc500,0x7fe7ed837240,524288,3261262,417346256,12075538283482799,12075538283667839,12075538284040958,12075538284089276
|
||
|
|
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,880581,880586,4194304,256,0,0,24,24,232000,0x7fe8f94cc400,0x7fe7ed837280,524288,3006999,384809976,12075538284124582,12075538284290557,12075538284494396,12075538284545334
|
||
|
|
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,880581,880586,4194304,256,0,0,24,24,237824,0x7fe8f94cc300,0x7fe7ed8372c0,524288,4217045,539777276,12075538284573947,12075538284748315,12075538285275034,12075538285323470
|
||
|
|
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,880581,880586,4194304,256,0,0,24,24,242368,0x7fe8f94cca00,0x7fe7ed837300,524288,3117373,398998832,12075538285362512,12075538285527193,12075538285751032,12075538285798763
|
||
|
|
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,880581,880586,4194304,256,0,0,20,24,243584,0x7fe8f94cc900,0x7fe7ed837340,524288,2295760,293807032,12075538285821966,12075538286001751,12075538286801269,12075538286850768
|
||
|
|
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,880581,880586,4194304,256,0,0,28,24,248128,0x7fe8f94cc800,0x7fe7ed837380,524288,3561967,455877500,12075538286874142,12075538287074548,12075538287494706,12075538287543426
|
||
|
|
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,880581,880586,4194304,256,0,0,24,24,252672,0x7fe8f94cc700,0x7fe7ed8373c0,524288,3149993,403278548,12075538287569875,12075538287748945,12075538287975505,12075538288022676
|
||
|
|
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,880581,880586,4194304,256,0,0,24,24,259264,0x7fe8f94cc600,0x7fe7ed837400,524288,4541016,581279992,12075538288048184,12075538288227184,12075538288824782,12075538288872646
|
||
|
|
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,880581,880586,4194304,256,0,0,24,24,264832,0x7fe8f94cc500,0x7fe7ed837440,524288,3321321,425138340,12075538288908753,12075538289086061,12075538289355820,12075538289404915
|
||
|
|
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,880581,880586,4194304,256,0,0,20,24,266304,0x7fe8f94cc400,0x7fe7ed837480,524288,2314982,296356232,12075538289428098,12075538289607179,12075538290591816,12075538290658324
|
||
|
|
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,880581,880586,4194304,256,0,0,28,24,271872,0x7fe8f94cc300,0x7fe7ed8374c0,524288,3283440,420295240,12075538290682189,12075538290869735,12075538291401893,12075538291471185
|
||
|
|
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,880581,880586,4194304,256,0,0,24,24,277440,0x7fe8f94cca00,0x7fe7ed837500,524288,3319124,424818248,12075538291495340,12075538291682052,12075538291955652,12075538292022850
|
||
|
|
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,880581,880586,4194304,256,0,0,12,24,279936,0x7fe8f94cc900,0x7fe7ed837540,524288,2195363,281030824,12075538292046604,12075538292227171,12075538292965728,12075538293032677
|
||
|
|
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,880581,880586,4194304,256,0,0,24,24,286528,0x7fe8f94cc800,0x7fe7ed837580,524288,3354097,429406732,12075538293071259,12075538293235167,12075538293553086,12075538293619818
|
||
|
|
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,880581,880586,4194304,256,0,0,20,24,288000,0x7fe8f94cc700,0x7fe7ed8375c0,524288,2302540,294668300,12075538293644244,12075538293821085,12075538294991961,12075538295062299
|
||
|
|
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,880581,880586,4194304,256,0,0,32,24,294592,0x7fe8f94cc600,0x7fe7ed837600,524288,3323371,425325808,12075538295093196,12075538295271161,12075538295882039,12075538295949147
|
||
|
|
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,880581,880586,4194304,256,0,0,24,24,301184,0x7fe8f94cc500,0x7fe7ed837640,524288,3307813,423367784,12075538295976829,12075538296159318,12075538296478997,12075538296547649
|
||
|
|
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,880581,880586,4194304,256,0,0,12,24,304960,0x7fe8f94cc400,0x7fe7ed837680,524288,2208284,282699436,12075538296572245,12075538296760916,12075538297639793,12075538297707775
|
||
|
|
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,880581,880586,4194304,256,0,0,24,24,313600,0x7fe8f94cc300,0x7fe7ed8376c0,524288,3227702,413195708,12075538297750735,12075538297915792,12075538298330190,12075538298399180
|
||
|
|
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,880581,880586,4194304,256,0,0,20,24,314816,0x7fe8f94cca00,0x7fe7ed837700,524288,2303504,294748972,12075538298431230,12075538298608910,12075538300158984,12075538300227548
|
||
|
|
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,880581,880586,4194304,256,0,0,20,24,317568,0x7fe8f94cc900,0x7fe7ed837740,524288,2289871,293145808,12075538300258766,12075538300438343,12075538301235301,12075538301303608
|
||
|
|
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,880581,880586,4194304,256,0,0,12,24,320320,0x7fe8f94cc800,0x7fe7ed837780,524288,2183494,279448200,12075538301332772,12075538301515940,12075538301954498,12075538302022975
|
||
|
|
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,880581,880586,4194304,256,0,0,12,24,324096,0x7fe8f94cc700,0x7fe7ed8377c0,524288,2246089,287416056,12075538302052550,12075538302234978,12075538303393374,12075538303460978
|
||
|
|
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,880581,880586,4194304,256,0,0,12,24,328896,0x7fe8f94cc600,0x7fe7ed837800,524288,2176668,278443144,12075538303501884,12075538303665053,12075538304450970,12075538304518603
|
||
|
|
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,880581,880586,4194304,256,0,0,20,24,330112,0x7fe8f94cc500,0x7fe7ed837840,524288,2640228,338021012,12075538304548909,12075538304729209,12075538307781839,12075538307850656
|
||
|
|
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,880581,880586,4194304,256,0,0,20,24,332864,0x7fe8f94cc400,0x7fe7ed837880,524288,2332401,298620460,12075538307882104,12075538308075118,12075538309617993,12075538309687389
|
||
|
|
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,880581,880586,4194304,256,0,0,12,24,335616,0x7fe8f94cc300,0x7fe7ed8378c0,524288,2205918,282289836,12075538309710001,12075538309908392,12075538310698950,12075538310768398
|
||
|
|
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,880581,880586,4194304,256,0,0,12,24,339392,0x7fe8f94cca00,0x7fe7ed837900,524288,2506859,320833128,12075538310798885,12075538310984069,12075538313266621,12075538313335759
|
||
|
|
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,880581,880586,4194304,256,0,0,12,24,344192,0x7fe8f94cc900,0x7fe7ed837940,524288,2476188,316960976,12075538313378389,12075538313548540,12075538315084695,12075538315152115
|
||
|
|
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,880581,880586,4194304,256,0,0,20,24,345408,0x7fe8f94cc800,0x7fe7ed837980,524288,2914494,373030972,12075538315183433,12075538315366134,12075538321421634,12075538321490264
|
||
|
|
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,880581,880586,4194304,256,0,0,20,24,348160,0x7fe8f94cc700,0x7fe7ed8379c0,524288,3375357,431959268,12075538321519348,12075538321702113,12075538324746103,12075538324817207
|
||
|
|
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,880581,880586,4194304,256,0,0,12,24,350912,0x7fe8f94cc600,0x7fe7ed837a00,524288,2315649,296435636,12075538324844087,12075538325036822,12075538326577137,12075538326647749
|
||
|
|
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,880581,880586,4194304,256,0,0,12,24,0,0x7fe8f94cc500,0x7fe7ed837a40,524288,2548695,326234092,12075538326677284,12075538326859696,12075538331387041,12075538331456095
|