169 lines
39 KiB
CSV
169 lines
39 KiB
CSV
Index,KernelName,gpu-id,queue-id,queue-index,pid,tid,grd,wgr,lds,scr,vgpr,sgpr,fbar,sig,obj,DispatchNs,BeginNs,EndNs,CompleteNs
|
|
0,"__amd_rocclr_fillBuffer.kd",0,0,0,911558,911563,33554432,256,0,0,8,32,6464,0x0,0x7f7f1e004180,12076136765385269,12076136765433491,12076136765754608,12076136765859220
|
|
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,911558,911563,32768,256,0,0,24,24,12480,0x0,0x7f7f1e035100,12076136780811589,12076136780918025,12076136780924425,12076136780930219
|
|
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,911558,911563,4194304,256,0,0,24,24,12928,0x7f8029b71900,0x7f7f1e035140,12076136780976144,12076136780988904,12076136781126183,12076136781129860
|
|
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,911558,911563,4194304,256,0,0,36,24,13632,0x7f8029b71800,0x7f7f1e035180,12076136781177198,12076136781195782,12076136781442660,12076136781540152
|
|
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,911558,911563,4194304,256,0,0,28,24,14080,0x7f8029b71700,0x7f7f1e0351c0,12076136781565259,12076136781577379,12076136781824896,12076136781920469
|
|
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,911558,911563,4194304,256,0,0,24,24,14528,0x7f8029b71600,0x7f7f1e035200,12076136781944915,12076136781956575,12076136782082494,12076136782086147
|
|
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,911558,911563,4194304,256,0,0,24,24,14976,0x7f8029b71500,0x7f7f1e035240,12076136782108268,12076136782119613,12076136782243772,12076136782247056
|
|
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,911558,911563,4194304,256,0,0,24,24,15424,0x7f8029b71400,0x7f7f1e035280,12076136782301107,12076136782315292,12076136782439130,12076136782442309
|
|
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,911558,911563,4194304,256,0,0,28,24,16128,0x7f8029b71300,0x7f7f1e0352c0,12076136782467877,12076136782481530,12076136782727288,12076136782823057
|
|
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,911558,911563,4194304,256,0,0,28,24,16832,0x7f8029b71a00,0x7f7f1e035300,12076136782843565,12076136782858167,12076136783102964,12076136783199496
|
|
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,911558,911563,4194304,256,0,0,24,24,17536,0x7f8029b71900,0x7f7f1e035340,12076136783220766,12076136783233843,12076136783359122,12076136783362469
|
|
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,911558,911563,4194304,256,0,0,24,24,18240,0x7f8029b71800,0x7f7f1e035380,12076136783389379,12076136783400561,12076136783525360,12076136783528648
|
|
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,911558,911563,4194304,256,0,0,24,24,18944,0x7f8029b71700,0x7f7f1e0353c0,12076136783565376,12076136783577360,12076136783702159,12076136783705407
|
|
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,911558,911563,4194304,256,0,0,28,24,19904,0x7f8029b71600,0x7f7f1e035400,12076136783731074,12076136783742478,12076136783990636,12076136784069082
|
|
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,911558,911563,4194304,256,0,0,28,24,20608,0x7f8029b71500,0x7f7f1e035440,12076136784091033,12076136784102635,12076136784347272,12076136784414715
|
|
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,911558,911563,4194304,256,0,0,24,24,21312,0x7f8029b71400,0x7f7f1e035480,12076136784435333,12076136784447432,12076136784572230,12076136784575433
|
|
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,911558,911563,4194304,256,0,0,24,24,22016,0x7f8029b71300,0x7f7f1e0354c0,12076136784600981,12076136784612550,12076136784737989,12076136784741292
|
|
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,911558,911563,4194304,256,0,0,24,24,22720,0x7f8029b71a00,0x7f7f1e035500,12076136784776657,12076136784789028,12076136784913667,12076136784916848
|
|
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,911558,911563,4194304,256,0,0,28,24,23680,0x7f8029b71900,0x7f7f1e035540,12076136784942235,12076136784953987,12076136785199104,12076136785267440
|
|
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,911558,911563,4194304,256,0,0,28,24,24384,0x7f8029b71800,0x7f7f1e035580,12076136785289040,12076136785301984,12076136785548381,12076136785614775
|
|
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,911558,911563,4194304,256,0,0,24,24,25088,0x7f8029b71700,0x7f7f1e0355c0,12076136785634682,12076136785648380,12076136785773339,12076136785776425
|
|
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,911558,911563,4194304,256,0,0,24,24,25792,0x7f8029b71600,0x7f7f1e035600,12076136785802334,12076136785814619,12076136785940217,12076136785943466
|
|
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,911558,911563,4194304,256,0,0,24,24,26496,0x7f8029b71500,0x7f7f1e035640,12076136785979383,12076136785992537,12076136786117016,12076136786120345
|
|
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,911558,911563,4194304,256,0,0,28,24,27712,0x7f8029b71400,0x7f7f1e035680,12076136786148026,12076136786159895,12076136786410293,12076136786451179
|
|
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,911558,911563,4194304,256,0,0,28,24,28416,0x7f8029b71300,0x7f7f1e0356c0,12076136786472750,12076136786484532,12076136786728690,12076136786793936
|
|
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,911558,911563,4194304,256,0,0,24,24,29120,0x7f8029b71a00,0x7f7f1e035700,12076136786814655,12076136786828209,12076136786952688,12076136786955727
|
|
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,911558,911563,4194304,256,0,0,24,24,30080,0x7f8029b71900,0x7f7f1e035740,12076136786982697,12076136786994128,12076136787119726,12076136787123148
|
|
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,911558,911563,4194304,256,0,0,24,24,30784,0x7f8029b71800,0x7f7f1e035780,12076136787160548,12076136787171566,12076136787295885,12076136787299125
|
|
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,911558,911563,4194304,256,0,0,28,24,32000,0x7f8029b71700,0x7f7f1e0357c0,12076136787324312,12076136787335884,12076136787585482,12076136787640921
|
|
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,911558,911563,4194304,256,0,0,28,24,32960,0x7f8029b71600,0x7f7f1e035800,12076136787660908,12076136787672361,12076136787921639,12076136787998034
|
|
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,911558,911563,4194304,256,0,0,24,24,33920,0x7f8029b71500,0x7f7f1e035840,12076136788022720,12076136788041158,12076136788165797,12076136788169503
|
|
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,911558,911563,4194304,256,0,0,24,24,34880,0x7f8029b71400,0x7f7f1e035880,12076136788194459,12076136788206116,12076136788331715,12076136788335101
|
|
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,911558,911563,4194304,256,0,0,24,24,35840,0x7f8029b71300,0x7f7f1e0358c0,12076136788371037,12076136788384194,12076136788508513,12076136788511809
|
|
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,911558,911563,4194304,256,0,0,28,24,37312,0x7f8029b71a00,0x7f7f1e035900,12076136788536615,12076136788549153,12076136788801151,12076136788853183
|
|
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,911558,911563,4194304,256,0,0,28,24,38272,0x7f8029b71900,0x7f7f1e035940,12076136788873491,12076136788891710,12076136789137467,12076136789218813
|
|
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,911558,911563,4194304,256,0,0,24,24,39232,0x7f8029b71800,0x7f7f1e035980,12076136789239351,12076136789250746,12076136789376345,12076136789379652
|
|
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,911558,911563,4194304,256,0,0,24,24,40192,0x7f8029b71700,0x7f7f1e0359c0,12076136789404749,12076136789416185,12076136789541784,12076136789545270
|
|
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,911558,911563,4194304,256,0,0,24,24,41152,0x7f8029b71600,0x7f7f1e035a00,12076136789580185,12076136789592823,12076136789717302,12076136789720385
|
|
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,911558,911563,4194304,256,0,0,28,24,42624,0x7f8029b71500,0x7f7f1e035a40,12076136789748517,12076136789762102,12076136790009619,12076136790085995
|
|
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,911558,911563,4194304,256,0,0,28,24,43584,0x7f8029b71400,0x7f7f1e035a80,12076136790107194,12076136790118258,12076136790361456,12076136790408454
|
|
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,911558,911563,4194304,256,0,0,24,24,44544,0x7f8029b71300,0x7f7f1e035ac0,12076136790429323,12076136790440975,12076136790566414,12076136790569653
|
|
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,911558,911563,4194304,256,0,0,24,24,45760,0x7f8029b71a00,0x7f7f1e035b00,12076136790595812,12076136790606894,12076136790733292,12076136790736574
|
|
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,911558,911563,4194304,256,0,0,24,24,46720,0x7f8029b71900,0x7f7f1e035b40,12076136790772320,12076136790785292,12076136790910571,12076136790913543
|
|
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,911558,911563,4194304,256,0,0,28,24,48448,0x7f8029b71800,0x7f7f1e035b80,12076136790938900,12076136790951530,12076136791213768,12076136791238136
|
|
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,911558,911563,4194304,256,0,0,28,24,49408,0x7f8029b71700,0x7f7f1e035bc0,12076136791258754,12076136791271687,12076136791522085,12076136791541329
|
|
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,911558,911563,4194304,256,0,0,24,24,50368,0x7f8029b71600,0x7f7f1e035c00,12076136791560445,12076136791572964,12076136791697283,12076136791700465
|
|
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,911558,911563,4194304,256,0,0,24,24,51584,0x7f8029b71500,0x7f7f1e035c40,12076136791726904,12076136791739203,12076136791865762,12076136791868788
|
|
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,911558,911563,4194304,256,0,0,24,24,52544,0x7f8029b71400,0x7f7f1e035c80,12076136791906318,12076136791918401,12076136792043040,12076136792046328
|
|
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,911558,911563,4194304,256,0,0,28,24,54272,0x7f8029b71300,0x7f7f1e035cc0,12076136792074400,12076136792085920,12076136792342077,12076136792370290
|
|
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,911558,911563,4194304,256,0,0,28,24,55488,0x7f8029b71a00,0x7f7f1e035d00,12076136792390287,12076136792401757,12076136792652154,12076136792679645
|
|
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,911558,911563,4194304,256,0,0,24,24,56704,0x7f8029b71900,0x7f7f1e035d40,12076136792700584,12076136792711994,12076136792836953,12076136792839943
|
|
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,911558,911563,4194304,256,0,0,24,24,58176,0x7f8029b71800,0x7f7f1e035d80,12076136792865099,12076136792876632,12076136793005111,12076136793008015
|
|
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,911558,911563,4194304,256,0,0,24,24,59392,0x7f8029b71700,0x7f7f1e035dc0,12076136793044924,12076136793057591,12076136793182709,12076136793185745
|
|
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,911558,911563,4194304,256,0,0,28,24,61376,0x7f8029b71600,0x7f7f1e035e00,12076136793212074,12076136793223989,12076136793479987,12076136793507593
|
|
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,911558,911563,4194304,256,0,0,28,24,62592,0x7f8029b71500,0x7f7f1e035e40,12076136793527430,12076136793540146,12076136793786064,12076136793808913
|
|
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,911558,911563,4194304,256,0,0,24,24,63808,0x7f8029b71400,0x7f7f1e035e80,12076136793832587,12076136793845263,12076136793970222,12076136793973309
|
|
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,911558,911563,4194304,256,0,0,24,24,65280,0x7f8029b71300,0x7f7f1e035ec0,12076136793999708,12076136794016621,12076136794146060,12076136794149446
|
|
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,911558,911563,4194304,256,0,0,24,24,66496,0x7f8029b71a00,0x7f7f1e035f00,12076136794185283,12076136794196940,12076136794322219,12076136794325313
|
|
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,911558,911563,4194304,256,0,0,28,24,68480,0x7f8029b71900,0x7f7f1e035f40,12076136794351772,12076136794364778,12076136794621416,12076136794644366
|
|
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,911558,911563,4194304,256,0,0,28,24,69696,0x7f8029b71800,0x7f7f1e035f80,12076136794664343,12076136794677095,12076136794921413,12076136794943231
|
|
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,911558,911563,4194304,256,0,0,24,24,70912,0x7f8029b71700,0x7f7f1e035fc0,12076136794963880,12076136794976452,12076136795101251,12076136795104461
|
|
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,911558,911563,4194304,256,0,0,24,24,72384,0x7f8029b71600,0x7f7f1e036000,12076136795130940,12076136795142211,12076136795278850,12076136795281931
|
|
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,911558,911563,4194304,256,0,0,24,24,73600,0x7f8029b71500,0x7f7f1e036040,12076136795319180,12076136795332929,12076136795457888,12076136795461064
|
|
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,911558,911563,4194304,256,0,0,28,24,75840,0x7f8029b71400,0x7f7f1e036080,12076136795485870,12076136795498528,12076136795753085,12076136795771320
|
|
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,911558,911563,4194304,256,0,0,28,24,77056,0x7f8029b71300,0x7f7f1e0360c0,12076136795791037,12076136795803965,12076136796052602,12076136796084703
|
|
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,911558,911563,4194304,256,0,0,24,24,78272,0x7f8029b71a00,0x7f7f1e036100,12076136796105401,12076136796118362,12076136796242841,12076136796245993
|
|
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,911558,911563,4194304,256,0,0,24,24,80000,0x7f8029b71900,0x7f7f1e036140,12076136796270568,12076136796283480,12076136796425079,12076136796428221
|
|
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,911558,911563,4194304,256,0,0,24,24,81216,0x7f8029b71800,0x7f7f1e036180,12076136796464128,12076136796476598,12076136796601877,12076136796605050
|
|
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,911558,911563,4194304,256,0,0,28,24,83456,0x7f8029b71700,0x7f7f1e0361c0,12076136796630537,12076136796643637,12076136796901874,12076136796928140
|
|
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,911558,911563,4194304,256,0,0,28,24,84928,0x7f8029b71600,0x7f7f1e036200,12076136796948629,12076136796961394,12076136797208111,12076136797235351
|
|
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,911558,911563,4194304,256,0,0,24,24,86400,0x7f8029b71500,0x7f7f1e036240,12076136797258514,12076136797272271,12076136797397710,12076136797400849
|
|
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,911558,911563,4194304,256,0,0,24,24,88128,0x7f8029b71400,0x7f7f1e036280,12076136797426837,12076136797439309,12076136797590188,12076136797593437
|
|
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,911558,911563,4194304,256,0,0,24,24,89600,0x7f8029b71300,0x7f7f1e0362c0,12076136797645033,12076136797656107,12076136797781066,12076136797784382
|
|
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,911558,911563,4194304,256,0,0,28,24,92096,0x7f8029b71a00,0x7f7f1e036300,12076136797809048,12076136797820586,12076136798079623,12076136798108394
|
|
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,911558,911563,4194304,256,0,0,28,24,93568,0x7f8029b71900,0x7f7f1e036340,12076136798128291,12076136798141063,12076136798385380,12076136798409724
|
|
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,911558,911563,4194304,256,0,0,24,24,95040,0x7f8029b71800,0x7f7f1e036380,12076136798429881,12076136798442980,12076136798568099,12076136798571414
|
|
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,911558,911563,4194304,256,0,0,24,24,96768,0x7f8029b71700,0x7f7f1e0363c0,12076136798596591,12076136798609538,12076136798767777,12076136798771065
|
|
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,911558,911563,4194304,256,0,0,24,24,98240,0x7f8029b71600,0x7f7f1e036400,12076136798807062,12076136798820416,12076136798945375,12076136798948866
|
|
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,911558,911563,4194304,256,0,0,28,24,100736,0x7f8029b71500,0x7f7f1e036440,12076136798973622,12076136798986335,12076136799243132,12076136799270774
|
|
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,911558,911563,4194304,256,0,0,28,24,102208,0x7f8029b71400,0x7f7f1e036480,12076136799290330,12076136799301692,12076136799547609,12076136799569970
|
|
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,911558,911563,4194304,256,0,0,24,24,103680,0x7f8029b71300,0x7f7f1e0364c0,12076136799589627,12076136799602329,12076136799727448,12076136799730619
|
|
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,911558,911563,4194304,256,0,0,24,24,105664,0x7f8029b71a00,0x7f7f1e036500,12076136799755936,12076136799769047,12076136799933686,12076136799937102
|
|
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,911558,911563,4194304,256,0,0,24,24,107136,0x7f8029b71900,0x7f7f1e036540,12076136799972979,12076136799985525,12076136800111124,12076136800114542
|
|
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,911558,911563,4194304,256,0,0,28,24,109888,0x7f8029b71800,0x7f7f1e036580,12076136800140070,12076136800151124,12076136800406161,12076136800428886
|
|
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,911558,911563,4194304,256,0,0,28,24,111360,0x7f8029b71700,0x7f7f1e0365c0,12076136800448202,12076136800459761,12076136800705679,12076136800731839
|
|
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,911558,911563,4194304,256,0,0,24,24,112832,0x7f8029b71600,0x7f7f1e036600,12076136800754642,12076136800767598,12076136800893037,12076136800896325
|
|
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,911558,911563,4194304,256,0,0,24,24,114816,0x7f8029b71500,0x7f7f1e036640,12076136800920590,12076136800931916,12076136801104555,12076136801107848
|
|
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,911558,911563,4194304,256,0,0,24,24,116288,0x7f8029b71400,0x7f7f1e036680,12076136801143695,12076136801155274,12076136801280713,12076136801284046
|
|
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,911558,911563,4194304,256,0,0,28,24,119040,0x7f8029b71300,0x7f7f1e0366c0,12076136801308491,12076136801323273,12076136801576230,12076136801599592
|
|
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,911558,911563,4194304,256,0,0,28,24,120768,0x7f8029b71a00,0x7f7f1e036700,12076136801618096,12076136801630950,12076136801878787,12076136801901663
|
|
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,911558,911563,4194304,256,0,0,24,24,122496,0x7f8029b71900,0x7f7f1e036740,12076136801921410,12076136801932547,12076136802057826,12076136802060990
|
|
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,911558,911563,4194304,256,0,0,24,24,124736,0x7f8029b71800,0x7f7f1e036780,12076136802087068,12076136802098305,12076136802280544,12076136802284064
|
|
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,911558,911563,4194304,256,0,0,24,24,126464,0x7f8029b71700,0x7f7f1e0367c0,12076136802320271,12076136802331583,12076136802457822,12076136802461063
|
|
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,911558,911563,4194304,256,0,0,20,24,127936,0x7f8029b71600,0x7f7f1e036800,12076136802486240,12076136802499262,12076136802762939,12076136802785636
|
|
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,911558,911563,4194304,256,0,0,28,24,129664,0x7f8029b71500,0x7f7f1e036840,12076136802805714,12076136802817819,12076136803071256,12076136803094791
|
|
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,911558,911563,4194304,256,0,0,24,24,131392,0x7f8029b71400,0x7f7f1e036880,12076136803114568,12076136803127096,12076136803253335,12076136803256582
|
|
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,911558,911563,4194304,256,0,0,24,24,133632,0x7f8029b71300,0x7f7f1e0368c0,12076136803280576,12076136803293654,12076136803483892,12076136803487200
|
|
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,911558,911563,4194304,256,0,0,24,24,135360,0x7f8029b71a00,0x7f7f1e036900,12076136803523187,12076136803535572,12076136803662771,12076136803666012
|
|
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,911558,911563,4194304,256,0,0,20,24,136832,0x7f8029b71900,0x7f7f1e036940,12076136803691279,12076136803702770,12076136803985328,12076136804012336
|
|
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,911558,911563,4194304,256,0,0,28,24,138560,0x7f8029b71800,0x7f7f1e036980,12076136804033034,12076136804045647,12076136804296365,12076136804319467
|
|
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,911558,911563,4194304,256,0,0,24,24,140288,0x7f8029b71700,0x7f7f1e0369c0,12076136804339604,12076136804351084,12076136804477643,12076136804480837
|
|
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,911558,911563,4194304,256,0,0,24,24,142784,0x7f8029b71600,0x7f7f1e036a00,12076136804505352,12076136804518763,12076136804727241,12076136804748975
|
|
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,911558,911563,4194304,256,0,0,24,24,144768,0x7f8029b71500,0x7f7f1e036a40,12076136804778851,12076136804791560,12076136804919399,12076136804922658
|
|
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,911558,911563,4194304,256,0,0,20,24,145728,0x7f8029b71400,0x7f7f1e036a80,12076136804947394,12076136804961158,12076136805267556,12076136805293116
|
|
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,911558,911563,4194304,256,0,0,28,24,147712,0x7f8029b71300,0x7f7f1e036ac0,12076136805312412,12076136805325315,12076136805577153,12076136805602742
|
|
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,911558,911563,4194304,256,0,0,24,24,149696,0x7f8029b71a00,0x7f7f1e036b00,12076136805622889,12076136805635712,12076136805762271,12076136805765574
|
|
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,911558,911563,4194304,256,0,0,24,24,152192,0x7f8029b71900,0x7f7f1e036b40,12076136805790220,12076136805803231,12076136806030588,12076136806053640
|
|
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,911558,911563,4194304,256,0,0,24,24,154176,0x7f8029b71800,0x7f7f1e036b80,12076136806085830,12076136806098748,12076136806225467,12076136806228685
|
|
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,911558,911563,4194304,256,0,0,20,24,155648,0x7f8029b71700,0x7f7f1e036bc0,12076136806252519,12076136806263226,12076136806591543,12076136806613380
|
|
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,911558,911563,4194304,256,0,0,28,24,157632,0x7f8029b71600,0x7f7f1e036c00,12076136806632616,12076136806643863,12076136806894580,12076136806916433
|
|
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,911558,911563,4194304,256,0,0,24,24,159616,0x7f8029b71500,0x7f7f1e036c40,12076136806936140,12076136806949140,12076136807077619,12076136807081159
|
|
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,911558,911563,4194304,256,0,0,24,24,162368,0x7f8029b71400,0x7f7f1e036c80,12076136807106587,12076136807117938,12076136807361616,12076136807387789
|
|
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,911558,911563,4194304,256,0,0,24,24,164608,0x7f8029b71300,0x7f7f1e036cc0,12076136807417855,12076136807430255,12076136807560014,12076136807563195
|
|
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,911558,911563,4194304,256,0,0,20,24,166336,0x7f8029b71a00,0x7f7f1e036d00,12076136807587600,12076136807600014,12076136807974570,12076136807996711
|
|
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,911558,911563,4194304,256,0,0,28,24,168576,0x7f8029b71900,0x7f7f1e036d40,12076136808021206,12076136808033610,12076136808285607,12076136808312408
|
|
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,911558,911563,4194304,256,0,0,24,24,170816,0x7f8029b71800,0x7f7f1e036d80,12076136808334679,12076136808347687,12076136808476485,12076136808479939
|
|
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,911558,911563,4194304,256,0,0,24,24,174080,0x7f8029b71700,0x7f7f1e036dc0,12076136808504765,12076136808517125,12076136808795362,12076136808821083
|
|
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,911558,911563,4194304,256,0,0,24,24,176576,0x7f8029b71600,0x7f7f1e036e00,12076136808850548,12076136808863362,12076136808998080,12076136809005415
|
|
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,911558,911563,4194304,256,0,0,20,24,177792,0x7f8029b71500,0x7f7f1e036e40,12076136809028428,12076136809039520,12076136809461436,12076136809491769
|
|
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,911558,911563,4194304,256,0,0,28,24,180288,0x7f8029b71400,0x7f7f1e036e80,12076136809511947,12076136809523036,12076136809785433,12076136809810923
|
|
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,911558,911563,4194304,256,0,0,24,24,182784,0x7f8029b71300,0x7f7f1e036ec0,12076136809830118,12076136809842873,12076136809978231,12076136809981580
|
|
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,911558,911563,4194304,256,0,0,24,24,186304,0x7f8029b71a00,0x7f7f1e036f00,12076136810011095,12076136810023671,12076136810337908,12076136810360624
|
|
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,911558,911563,4194304,256,0,0,24,24,189312,0x7f8029b71900,0x7f7f1e036f40,12076136810392874,12076136810405427,12076136810557266,12076136810560506
|
|
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,911558,911563,4194304,256,0,0,20,24,190784,0x7f8029b71800,0x7f7f1e036f80,12076136810585502,12076136810598385,12076136811114701,12076136811141355
|
|
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,911558,911563,4194304,256,0,0,28,24,193792,0x7f8029b71700,0x7f7f1e036fc0,12076136811161512,12076136811174220,12076136811474857,12076136811500983
|
|
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,911558,911563,4194304,256,0,0,24,24,196800,0x7f8029b71600,0x7f7f1e037000,12076136811520389,12076136811531977,12076136811685895,12076136811689163
|
|
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,911558,911563,4194304,256,0,0,24,24,201088,0x7f8029b71500,0x7f7f1e037040,12076136811714610,12076136811727495,12076136812112291,12076136812139380
|
|
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,911558,911563,4194304,256,0,0,24,24,204608,0x7f8029b71400,0x7f7f1e037080,12076136812170868,12076136812184291,12076136812359649,12076136812363046
|
|
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,911558,911563,4194304,256,0,0,20,24,206080,0x7f8029b71300,0x7f7f1e0370c0,12076136812388393,12076136812399488,12076136813009083,12076136813036076
|
|
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,911558,911563,4194304,256,0,0,28,24,209600,0x7f8029b71a00,0x7f7f1e037100,12076136813056985,12076136813069562,12076136813397079,12076136813422865
|
|
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,911558,911563,4194304,256,0,0,24,24,213120,0x7f8029b71900,0x7f7f1e037140,12076136813445297,12076136813458359,12076136813636117,12076136813639598
|
|
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,911558,911563,4194304,256,0,0,24,24,218176,0x7f8029b71800,0x7f7f1e037180,12076136813664644,12076136813677396,12076136814131792,12076136814158743
|
|
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,911558,911563,4194304,256,0,0,24,24,222208,0x7f8029b71700,0x7f7f1e0371c0,12076136814189470,12076136814202832,12076136814402350,12076136814428003
|
|
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,911558,911563,4194304,256,0,0,20,24,223936,0x7f8029b71600,0x7f7f1e037200,12076136814447059,12076136814459789,12076136815161862,12076136815188456
|
|
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,911558,911563,4194304,256,0,0,28,24,227968,0x7f8029b71500,0x7f7f1e037240,12076136815210678,12076136815221702,12076136815591618,12076136815618686
|
|
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,911558,911563,4194304,256,0,0,24,24,232000,0x7f8029b71400,0x7f7f1e037280,12076136815639755,12076136815650818,12076136815852736,12076136815878849
|
|
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,911558,911563,4194304,256,0,0,24,24,237824,0x7f8029b71300,0x7f7f1e0372c0,12076136815898266,12076136815911615,12076136816454490,12076136816487210
|
|
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,911558,911563,4194304,256,0,0,24,24,242368,0x7f8029b71a00,0x7f7f1e037300,12076136816518789,12076136816532250,12076136816756087,12076136816778211
|
|
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,911558,911563,4194304,256,0,0,20,24,243584,0x7f8029b71900,0x7f7f1e037340,12076136816800322,12076136816813367,12076136817611439,12076136817644681
|
|
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,911558,911563,4194304,256,0,0,28,24,248128,0x7f8029b71800,0x7f7f1e037380,12076136817663596,12076136817676399,12076136818095275,12076136818123100
|
|
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,911558,911563,4194304,256,0,0,24,24,252672,0x7f8029b71700,0x7f7f1e0373c0,12076136818142486,12076136818156074,12076136818381832,12076136818407799
|
|
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,911558,911563,4194304,256,0,0,24,24,259264,0x7f8029b71600,0x7f7f1e037400,12076136818428227,12076136818441032,12076136819036706,12076136819063778
|
|
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,911558,911563,4194304,256,0,0,24,24,264832,0x7f8029b71500,0x7f7f1e037440,12076136819095247,12076136819106625,12076136819374783,12076136819401206
|
|
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,911558,911563,4194304,256,0,0,20,24,266304,0x7f8029b71400,0x7f7f1e037480,12076136819420862,12076136819433822,12076136820417333,12076136820445436
|
|
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,911558,911563,4194304,256,0,0,28,24,271872,0x7f8029b71300,0x7f7f1e0374c0,12076136820465033,12076136820476212,12076136820992208,12076136821020164
|
|
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,911558,911563,4194304,256,0,0,24,24,277440,0x7f8029b71a00,0x7f7f1e037500,12076136821042947,12076136821054447,12076136821324844,12076136821355147
|
|
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,911558,911563,4194304,256,0,0,12,24,279936,0x7f8029b71900,0x7f7f1e037540,12076136821375605,12076136821387404,12076136822124037,12076136822151848
|
|
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,911558,911563,4194304,256,0,0,24,24,286528,0x7f8029b71800,0x7f7f1e037580,12076136822182424,12076136822195236,12076136822511553,12076136822537675
|
|
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,911558,911563,4194304,256,0,0,20,24,288000,0x7f8029b71700,0x7f7f1e0375c0,12076136822557662,12076136822571393,12076136823741142,12076136823768773
|
|
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,911558,911563,4194304,256,0,0,32,24,294592,0x7f8029b71600,0x7f7f1e037600,12076136823788319,12076136823799541,12076136824411695,12076136824445971
|
|
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,911558,911563,4194304,256,0,0,24,24,301184,0x7f8029b71500,0x7f7f1e037640,12076136824466259,12076136824479215,12076136824797292,12076136824826789
|
|
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,911558,911563,4194304,256,0,0,12,24,304960,0x7f8029b71400,0x7f7f1e037680,12076136824849010,12076136824862571,12076136825739363,12076136825773298
|
|
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,911558,911563,4194304,256,0,0,24,24,313600,0x7f8029b71300,0x7f7f1e0376c0,12076136825806419,12076136825819522,12076136826227838,12076136826257628
|
|
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,911558,911563,4194304,256,0,0,20,24,314816,0x7f8029b71a00,0x7f7f1e037700,12076136826278407,12076136826291358,12076136827839023,12076136827910119
|
|
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,911558,911563,4194304,256,0,0,20,24,317568,0x7f8029b71900,0x7f7f1e037740,12076136827930627,12076136827942928,12076136828735882,12076136828810623
|
|
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,911558,911563,4194304,256,0,0,12,24,320320,0x7f8029b71800,0x7f7f1e037780,12076136828829067,12076136828840840,12076136829254437,12076136829327914
|
|
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,911558,911563,4194304,256,0,0,12,24,324096,0x7f8029b71700,0x7f7f1e0377c0,12076136829351257,12076136829363236,12076136830520827,12076136830591482
|
|
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,911558,911563,4194304,256,0,0,12,24,328896,0x7f8029b71600,0x7f7f1e037800,12076136830622179,12076136830635386,12076136831420020,12076136831490473
|
|
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,911558,911563,4194304,256,0,0,20,24,330112,0x7f8029b71500,0x7f7f1e037840,12076136831511752,12076136831525299,12076136834575035,12076136834645236
|
|
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,911558,911563,4194304,256,0,0,20,24,332864,0x7f8029b71400,0x7f7f1e037880,12076136834665644,12076136834679195,12076136836219662,12076136836289812
|
|
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,911558,911563,4194304,256,0,0,12,24,335616,0x7f8029b71300,0x7f7f1e0378c0,12076136836312615,12076136836325102,12076136837113415,12076136837183283
|
|
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,911558,911563,4194304,256,0,0,12,24,339392,0x7f8029b71a00,0x7f7f1e037900,12076136837205194,12076136837217095,12076136839497557,12076136839567955
|
|
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,911558,911563,4194304,256,0,0,12,24,344192,0x7f8029b71900,0x7f7f1e037940,12076136839599433,12076136839611636,12076136841146504,12076136841216729
|
|
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,911558,911563,4194304,256,0,0,20,24,345408,0x7f8029b71800,0x7f7f1e037980,12076136841237658,12076136841249863,12076136847301816,12076136847372038
|
|
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,911558,911563,4194304,256,0,0,20,24,348160,0x7f8029b71700,0x7f7f1e0379c0,12076136847392226,12076136847404055,12076136850443231,12076136850514588
|
|
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,911558,911563,4194304,256,0,0,12,24,350912,0x7f8029b71600,0x7f7f1e037a00,12076136850534836,12076136850546910,12076136852085938,12076136852157191
|
|
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,911558,911563,4194304,256,0,0,12,24,0,0x7f8029b71500,0x7f7f1e037a40,12076136852176898,12076136852189297,12076136856715982,12076136856786244
|