169 righe
39 KiB
CSV
169 righe
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",0,0,0,932098,932103,33554432,256,0,0,8,32,6464,0x0,0x7fa24b804180,12076540386173827,12076540386221406,12076540386544923,12076540386650935
|
|
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,932098,932103,32768,256,0,0,24,24,12480,0x0,0x7fa24b835100,12076540401083130,12076540401193523,12076540401200243,12076540401205969
|
|
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,932098,932103,4194304,256,0,0,24,24,12928,0x7fa37b76c900,0x7fa24b835140,12076540401247406,12076540401262003,12076540401399282,12076540401402695
|
|
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,932098,932103,4194304,256,0,0,36,24,13632,0x7fa37b76c800,0x7fa24b835180,12076540401444472,12076540401457521,12076540401703919,12076540401799793
|
|
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,932098,932103,4194304,256,0,0,28,24,14080,0x7fa37b76c700,0x7fa24b8351c0,12076540401826413,12076540401838798,12076540402084556,12076540402186092
|
|
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,932098,932103,4194304,256,0,0,24,24,14528,0x7fa37b76c600,0x7fa24b835200,12076540402210087,12076540402221835,12076540402347114,12076540402350528
|
|
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,932098,932103,4194304,256,0,0,24,24,14976,0x7fa37b76c500,0x7fa24b835240,12076540402377959,12076540402389514,12076540402514153,12076540402517328
|
|
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,932098,932103,4194304,256,0,0,24,24,15424,0x7fa37b76c400,0x7fa24b835280,12076540402573472,12076540402591432,12076540402714951,12076540402718081
|
|
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,932098,932103,4194304,256,0,0,28,24,16128,0x7fa37b76c300,0x7fa24b8352c0,12076540402744971,12076540402757991,12076540403006309,12076540403102807
|
|
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,932098,932103,4194304,256,0,0,28,24,16832,0x7fa37b76ca00,0x7fa24b835300,12076540403124207,12076540403136068,12076540403378626,12076540403474108
|
|
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,932098,932103,4194304,256,0,0,24,24,17536,0x7fa37b76c900,0x7fa24b835340,12076540403501368,12076540403513344,12076540403637983,12076540403641259
|
|
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,932098,932103,4194304,256,0,0,24,24,18240,0x7fa37b76c800,0x7fa24b835380,12076540403671585,12076540403683423,12076540403808062,12076540403811215
|
|
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,932098,932103,4194304,256,0,0,24,24,18944,0x7fa37b76c700,0x7fa24b8353c0,12076540403853794,12076540403865982,12076540403990941,12076540403994165
|
|
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,932098,932103,4194304,256,0,0,28,24,19904,0x7fa37b76c600,0x7fa24b835400,12076540404030533,12076540404041500,12076540404291578,12076540404388158
|
|
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,932098,932103,4194304,256,0,0,28,24,20608,0x7fa37b76c500,0x7fa24b835440,12076540404410650,12076540404422137,12076540404668375,12076540404734953
|
|
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,932098,932103,4194304,256,0,0,24,24,21312,0x7fa37b76c400,0x7fa24b835480,12076540404756443,12076540404768374,12076540404892693,12076540404895913
|
|
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,932098,932103,4194304,256,0,0,24,24,22016,0x7fa37b76c300,0x7fa24b8354c0,12076540404924496,12076540404936053,12076540405061492,12076540405064686
|
|
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,932098,932103,4194304,256,0,0,24,24,22720,0x7fa37b76ca00,0x7fa24b835500,12076540405102136,12076540405113491,12076540405238610,12076540405241916
|
|
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,932098,932103,4194304,256,0,0,28,24,23680,0x7fa37b76c900,0x7fa24b835540,12076540405267634,12076540405279410,12076540405525328,12076540405568243
|
|
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,932098,932103,4194304,256,0,0,28,24,24384,0x7fa37b76c800,0x7fa24b835580,12076540405589843,12076540405601168,12076540405847246,12076540405887176
|
|
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,932098,932103,4194304,256,0,0,24,24,25088,0x7fa37b76c700,0x7fa24b8355c0,12076540405908506,12076540405920365,12076540406045004,12076540406048446
|
|
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,932098,932103,4194304,256,0,0,24,24,25792,0x7fa37b76c600,0x7fa24b835600,12076540406075627,12076540406087084,12076540406212363,12076540406215527
|
|
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,932098,932103,4194304,256,0,0,24,24,26496,0x7fa37b76c500,0x7fa24b835640,12076540406251805,12076540406265642,12076540406390441,12076540406393769
|
|
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,932098,932103,4194304,256,0,0,28,24,27712,0x7fa37b76c400,0x7fa24b835680,12076540406420258,12076540406433641,12076540406681959,12076540406747416
|
|
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,932098,932103,4194304,256,0,0,28,24,28416,0x7fa37b76c300,0x7fa24b8356c0,12076540406767334,12076540406780518,12076540407025476,12076540407091987
|
|
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,932098,932103,4194304,256,0,0,24,24,29120,0x7fa37b76ca00,0x7fa24b835700,12076540407114048,12076540407127075,12076540407251714,12076540407254860
|
|
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,932098,932103,4194304,256,0,0,24,24,30080,0x7fa37b76c900,0x7fa24b835740,12076540407280919,12076540407292194,12076540407417153,12076540407420338
|
|
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,932098,932103,4194304,256,0,0,24,24,30784,0x7fa37b76c800,0x7fa24b835780,12076540407456515,12076540407468672,12076540407593311,12076540407596656
|
|
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,932098,932103,4194304,256,0,0,28,24,32000,0x7fa37b76c700,0x7fa24b8357c0,12076540407621933,12076540407633951,12076540407880669,12076540407901854
|
|
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,932098,932103,4194304,256,0,0,28,24,32960,0x7fa37b76c600,0x7fa24b835800,12076540407922542,12076540407934109,12076540408178267,12076540408225095
|
|
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,932098,932103,4194304,256,0,0,24,24,33920,0x7fa37b76c500,0x7fa24b835840,12076540408245032,12076540408258746,12076540408384185,12076540408387197
|
|
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,932098,932103,4194304,256,0,0,24,24,34880,0x7fa37b76c400,0x7fa24b835880,12076540408412634,12076540408424185,12076540408549784,12076540408552995
|
|
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,932098,932103,4194304,256,0,0,24,24,35840,0x7fa37b76c300,0x7fa24b8358c0,12076540408589162,12076540408602103,12076540408727062,12076540408730535
|
|
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,932098,932103,4194304,256,0,0,28,24,37312,0x7fa37b76ca00,0x7fa24b835900,12076540408756053,12076540408768662,12076540409019380,12076540409046954
|
|
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,932098,932103,4194304,256,0,0,28,24,38272,0x7fa37b76c900,0x7fa24b835940,12076540409066591,12076540409079699,12076540409323057,12076540409399740
|
|
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,932098,932103,4194304,256,0,0,24,24,39232,0x7fa37b76c800,0x7fa24b835980,12076540409420138,12076540409432816,12076540409557615,12076540409561211
|
|
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,932098,932103,4194304,256,0,0,24,24,40192,0x7fa37b76c700,0x7fa24b8359c0,12076540409587960,12076540409599215,12076540409724974,12076540409728361
|
|
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,932098,932103,4194304,256,0,0,24,24,41152,0x7fa37b76c600,0x7fa24b835a00,12076540409763156,12076540409776494,12076540409900493,12076540409903898
|
|
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,932098,932103,4194304,256,0,0,28,24,42624,0x7fa37b76c500,0x7fa24b835a40,12076540409930127,12076540409943852,12076540410191850,12076540410228722
|
|
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,932098,932103,4194304,256,0,0,28,24,43584,0x7fa37b76c400,0x7fa24b835a80,12076540410249972,12076540410262890,12076540410511208,12076540410540242
|
|
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,932098,932103,4194304,256,0,0,24,24,44544,0x7fa37b76c300,0x7fa24b835ac0,12076540410562503,12076540410576007,12076540410700646,12076540410703886
|
|
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,932098,932103,4194304,256,0,0,24,24,45760,0x7fa37b76ca00,0x7fa24b835b00,12076540410728812,12076540410741126,12076540410867365,12076540410870506
|
|
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,932098,932103,4194304,256,0,0,24,24,46720,0x7fa37b76c900,0x7fa24b835b40,12076540410904900,12076540410916324,12076540411041283,12076540411044530
|
|
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,932098,932103,4194304,256,0,0,28,24,48448,0x7fa37b76c800,0x7fa24b835b80,12076540411071279,12076540411084003,12076540411343361,12076540411367771
|
|
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,932098,932103,4194304,256,0,0,28,24,49408,0x7fa37b76c700,0x7fa24b835bc0,12076540411388309,12076540411400640,12076540411648958,12076540411672698
|
|
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,932098,932103,4194304,256,0,0,24,24,50368,0x7fa37b76c600,0x7fa24b835c00,12076540411692495,12076540411705598,12076540411830557,12076540411833758
|
|
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,932098,932103,4194304,256,0,0,24,24,51584,0x7fa37b76c500,0x7fa24b835c40,12076540411860127,12076540411871997,12076540411998396,12076540412004345
|
|
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,932098,932103,4194304,256,0,0,24,24,52544,0x7fa37b76c400,0x7fa24b835c80,12076540412038969,12076540412052315,12076540412178074,12076540412181254
|
|
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,932098,932103,4194304,256,0,0,28,24,54272,0x7fa37b76c300,0x7fa24b835cc0,12076540412207333,12076540412219994,12076540412475992,12076540412499686
|
|
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,932098,932103,4194304,256,0,0,28,24,55488,0x7fa37b76ca00,0x7fa24b835d00,12076540412521808,12076540412534231,12076540412777589,12076540412805065
|
|
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,932098,932103,4194304,256,0,0,24,24,56704,0x7fa37b76c900,0x7fa24b835d40,12076540412826154,12076540412839349,12076540412964628,12076540412967787
|
|
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,932098,932103,4194304,256,0,0,24,24,58176,0x7fa37b76c800,0x7fa24b835d80,12076540412992724,12076540413005427,12076540413133906,12076540413137202
|
|
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,932098,932103,4194304,256,0,0,24,24,59392,0x7fa37b76c700,0x7fa24b835dc0,12076540413173951,12076540413186226,12076540413310865,12076540413313921
|
|
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,932098,932103,4194304,256,0,0,28,24,61376,0x7fa37b76c600,0x7fa24b835e00,12076540413340140,12076540413353905,12076540413617902,12076540413645127
|
|
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,932098,932103,4194304,256,0,0,28,24,62592,0x7fa37b76c500,0x7fa24b835e40,12076540413665505,12076540413678382,12076540413923980,12076540413943142
|
|
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,932098,932103,4194304,256,0,0,24,24,63808,0x7fa37b76c400,0x7fa24b835e80,12076540413970773,12076540413984299,12076540414109578,12076540414112957
|
|
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,932098,932103,4194304,256,0,0,24,24,65280,0x7fa37b76c300,0x7fa24b835ec0,12076540414141060,12076540414153738,12076540414283337,12076540414286610
|
|
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,932098,932103,4194304,256,0,0,24,24,66496,0x7fa37b76ca00,0x7fa24b835f00,12076540414322748,12076540414334057,12076540414459176,12076540414462327
|
|
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,932098,932103,4194304,256,0,0,28,24,68480,0x7fa37b76c900,0x7fa24b835f40,12076540414488045,12076540414500615,12076540414756933,12076540414779597
|
|
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,932098,932103,4194304,256,0,0,28,24,69696,0x7fa37b76c800,0x7fa24b835f80,12076540414800396,12076540414811653,12076540415061731,12076540415089103
|
|
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,932098,932103,4194304,256,0,0,24,24,70912,0x7fa37b76c700,0x7fa24b835fc0,12076540415111024,12076540415122850,12076540415247489,12076540415250674
|
|
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,932098,932103,4194304,256,0,0,24,24,72384,0x7fa37b76c600,0x7fa24b836000,12076540415277353,12076540415290369,12076540415427488,12076540415430729
|
|
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,932098,932103,4194304,256,0,0,24,24,73600,0x7fa37b76c500,0x7fa24b836040,12076540415467918,12076540415480447,12076540415604606,12076540415607708
|
|
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,932098,932103,4194304,256,0,0,28,24,75840,0x7fa37b76c400,0x7fa24b836080,12076540415633856,12076540415646686,12076540415902844,12076540415925509
|
|
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,932098,932103,4194304,256,0,0,28,24,77056,0x7fa37b76c300,0x7fa24b8360c0,12076540415946348,12076540415959163,12076540416203801,12076540416230777
|
|
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,932098,932103,4194304,256,0,0,24,24,78272,0x7fa37b76ca00,0x7fa24b836100,12076540416251545,12076540416264121,12076540416389400,12076540416392588
|
|
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,932098,932103,4194304,256,0,0,24,24,80000,0x7fa37b76c900,0x7fa24b836140,12076540416417754,12076540416430680,12076540416572758,12076540416576059
|
|
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,932098,932103,4194304,256,0,0,24,24,81216,0x7fa37b76c800,0x7fa24b836180,12076540416610393,12076540416622518,12076540416747157,12076540416750413
|
|
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,932098,932103,4194304,256,0,0,28,24,83456,0x7fa37b76c700,0x7fa24b8361c0,12076540416775430,12076540416787477,12076540417050355,12076540417074186
|
|
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,932098,932103,4194304,256,0,0,28,24,84928,0x7fa37b76c600,0x7fa24b836200,12076540417096307,12076540417108434,12076540417356112,12076540417382219
|
|
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,932098,932103,4194304,256,0,0,24,24,86400,0x7fa37b76c500,0x7fa24b836240,12076540417405532,12076540417418352,12076540417543470,12076540417547145
|
|
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,932098,932103,4194304,256,0,0,24,24,88128,0x7fa37b76c400,0x7fa24b836280,12076540417573023,12076540417584270,12076540417734669,12076540417737900
|
|
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,932098,932103,4194304,256,0,0,24,24,89600,0x7fa37b76c300,0x7fa24b8362c0,12076540417788534,12076540417802188,12076540417927627,12076540417931210
|
|
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,932098,932103,4194304,256,0,0,28,24,92096,0x7fa37b76ca00,0x7fa24b836300,12076540417957489,12076540417969707,12076540418227945,12076540418255663
|
|
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,932098,932103,4194304,256,0,0,28,24,93568,0x7fa37b76c900,0x7fa24b836340,12076540418276923,12076540418289544,12076540418536422,12076540418562494
|
|
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,932098,932103,4194304,256,0,0,24,24,95040,0x7fa37b76c800,0x7fa24b836380,12076540418583633,12076540418596902,12076540418722661,12076540418725888
|
|
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,932098,932103,4194304,256,0,0,24,24,96768,0x7fa37b76c700,0x7fa24b8363c0,12076540418752057,12076540418763141,12076540418920419,12076540418923536
|
|
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,932098,932103,4194304,256,0,0,24,24,98240,0x7fa37b76c600,0x7fa24b836400,12076540418959793,12076540418972259,12076540419097538,12076540419101066
|
|
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,932098,932103,4194304,256,0,0,28,24,100736,0x7fa37b76c500,0x7fa24b836440,12076540419127214,12076540419138658,12076540419401215,12076540419427723
|
|
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,932098,932103,4194304,256,0,0,28,24,102208,0x7fa37b76c400,0x7fa24b836480,12076540419448182,12076540419460575,12076540419708093,12076540419730847
|
|
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,932098,932103,4194304,256,0,0,24,24,103680,0x7fa37b76c300,0x7fa24b8364c0,12076540419751025,12076540419764252,12076540419890811,12076540419893941
|
|
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,932098,932103,4194304,256,0,0,24,24,105664,0x7fa37b76ca00,0x7fa24b836500,12076540419918857,12076540419930171,12076540420095290,12076540420098742
|
|
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,932098,932103,4194304,256,0,0,24,24,107136,0x7fa37b76c900,0x7fa24b836540,12076540420135400,12076540420150489,12076540420276408,12076540420279859
|
|
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,932098,932103,4194304,256,0,0,28,24,109888,0x7fa37b76c800,0x7fa24b836580,12076540420305276,12076540420318008,12076540420571606,12076540420594534
|
|
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,932098,932103,4194304,256,0,0,28,24,111360,0x7fa37b76c700,0x7fa24b8365c0,12076540420615002,12076540420627125,12076540420872403,12076540420899311
|
|
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,932098,932103,4194304,256,0,0,24,24,112832,0x7fa37b76c600,0x7fa24b836600,12076540420921983,12076540420934803,12076540421060082,12076540421063877
|
|
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,932098,932103,4194304,256,0,0,24,24,114816,0x7fa37b76c500,0x7fa24b836640,12076540421090587,12076540421101842,12076540421274480,12076540421277594
|
|
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,932098,932103,4194304,256,0,0,24,24,116288,0x7fa37b76c400,0x7fa24b836680,12076540421312720,12076540421326160,12076540421451599,12076540421454754
|
|
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,932098,932103,4194304,256,0,0,28,24,119040,0x7fa37b76c300,0x7fa24b8366c0,12076540421479440,12076540421492718,12076540421745036,12076540421764159
|
|
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,932098,932103,4194304,256,0,0,28,24,120768,0x7fa37b76ca00,0x7fa24b836700,12076540421789136,12076540421801516,12076540422047274,12076540422072483
|
|
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,932098,932103,4194304,256,0,0,24,24,122496,0x7fa37b76c900,0x7fa24b836740,12076540422092781,12076540422107593,12076540422233032,12076540422236468
|
|
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,932098,932103,4194304,256,0,0,24,24,124736,0x7fa37b76c800,0x7fa24b836780,12076540422261475,12076540422272872,12076540422455431,12076540422458691
|
|
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,932098,932103,4194304,256,0,0,24,24,126464,0x7fa37b76c700,0x7fa24b8367c0,12076540422494809,12076540422509830,12076540422635589,12076540422639247
|
|
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,932098,932103,4194304,256,0,0,20,24,127936,0x7fa37b76c600,0x7fa24b836800,12076540422664795,12076540422677989,12076540422941027,12076540422968189
|
|
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,932098,932103,4194304,256,0,0,28,24,129664,0x7fa37b76c500,0x7fa24b836840,12076540422988697,12076540423001026,12076540423247904,12076540423272044
|
|
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,932098,932103,4194304,256,0,0,24,24,131392,0x7fa37b76c400,0x7fa24b836880,12076540423292362,12076540423305184,12076540423432543,12076540423435899
|
|
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,932098,932103,4194304,256,0,0,24,24,133632,0x7fa37b76c300,0x7fa24b8368c0,12076540423460936,12076540423472062,12076540423663261,12076540423666969
|
|
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,932098,932103,4194304,256,0,0,24,24,135360,0x7fa37b76ca00,0x7fa24b836900,12076540423701824,12076540423713980,12076540423841019,12076540423844219
|
|
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,932098,932103,4194304,256,0,0,20,24,136832,0x7fa37b76c900,0x7fa24b836940,12076540423869045,12076540423882779,12076540424197336,12076540424219978
|
|
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,932098,932103,4194304,256,0,0,28,24,138560,0x7fa37b76c800,0x7fa24b836980,12076540424241117,12076540424254136,12076540424502614,12076540424528902
|
|
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,932098,932103,4194304,256,0,0,24,24,140288,0x7fa37b76c700,0x7fa24b8369c0,12076540424550693,12076540424564053,12076540424690292,12076540424693298
|
|
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,932098,932103,4194304,256,0,0,24,24,142784,0x7fa37b76c600,0x7fa24b836a00,12076540424719276,12076540424731732,12076540424941170,12076540424966687
|
|
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,932098,932103,4194304,256,0,0,24,24,144768,0x7fa37b76c500,0x7fa24b836a40,12076540424996853,12076540425013650,12076540425141489,12076540425145038
|
|
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,932098,932103,4194304,256,0,0,20,24,145728,0x7fa37b76c400,0x7fa24b836a80,12076540425170345,12076540425182928,12076540425489166,12076540425516479
|
|
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,932098,932103,4194304,256,0,0,28,24,147712,0x7fa37b76c300,0x7fa24b836ac0,12076540425536857,12076540425549485,12076540425802283,12076540425829051
|
|
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,932098,932103,4194304,256,0,0,24,24,149696,0x7fa37b76ca00,0x7fa24b836b00,12076540425850601,12076540425863243,12076540425990602,12076540425993707
|
|
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,932098,932103,4194304,256,0,0,24,24,152192,0x7fa37b76c900,0x7fa24b836b40,12076540426023062,12076540426034922,12076540426261800,12076540426292042
|
|
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,932098,932103,4194304,256,0,0,24,24,154176,0x7fa37b76c800,0x7fa24b836b80,12076540426323901,12076540426335399,12076540426461798,12076540426465004
|
|
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,932098,932103,4194304,256,0,0,20,24,155648,0x7fa37b76c700,0x7fa24b836bc0,12076540426490080,12076540426502598,12076540426831075,12076540426849509
|
|
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,932098,932103,4194304,256,0,0,28,24,157632,0x7fa37b76c600,0x7fa24b836c00,12076540426871049,12076540426883715,12076540427132353,12076540427159325
|
|
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,932098,932103,4194304,256,0,0,24,24,159616,0x7fa37b76c500,0x7fa24b836c40,12076540427179653,12076540427192352,12076540427322111,12076540427325344
|
|
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,932098,932103,4194304,256,0,0,24,24,162368,0x7fa37b76c400,0x7fa24b836c80,12076540427351443,12076540427362911,12076540427606749,12076540427632766
|
|
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,932098,932103,4194304,256,0,0,24,24,164608,0x7fa37b76c300,0x7fa24b836cc0,12076540427663042,12076540427675548,12076540427806107,12076540427809485
|
|
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,932098,932103,4194304,256,0,0,20,24,166336,0x7fa37b76ca00,0x7fa24b836d00,12076540427835373,12076540427848667,12076540428224024,12076540428247239
|
|
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,932098,932103,4194304,256,0,0,28,24,168576,0x7fa37b76c900,0x7fa24b836d40,12076540428267787,12076540428279863,12076540428534101,12076540428556244
|
|
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,932098,932103,4194304,256,0,0,24,24,170816,0x7fa37b76c800,0x7fa24b836d80,12076540428579327,12076540428592341,12076540428722260,12076540428725839
|
|
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,932098,932103,4194304,256,0,0,24,24,174080,0x7fa37b76c700,0x7fa24b836dc0,12076540428750745,12076540428761939,12076540429041137,12076540429067414
|
|
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,932098,932103,4194304,256,0,0,24,24,176576,0x7fa37b76c600,0x7fa24b836e00,12076540429097460,12076540429108497,12076540429243695,12076540429246908
|
|
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,932098,932103,4194304,256,0,0,20,24,177792,0x7fa37b76c500,0x7fa24b836e40,12076540429272255,12076540429285135,12076540429707852,12076540429726500
|
|
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,932098,932103,4194304,256,0,0,28,24,180288,0x7fa37b76c400,0x7fa24b836e80,12076540429746588,12076540429759051,12076540430020489,12076540430046846
|
|
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,932098,932103,4194304,256,0,0,24,24,182784,0x7fa37b76c300,0x7fa24b836ec0,12076540430068987,12076540430081449,12076540430217128,12076540430220489
|
|
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,932098,932103,4194304,256,0,0,24,24,186304,0x7fa37b76ca00,0x7fa24b836f00,12076540430246458,12076540430258727,12076540430573285,12076540430599134
|
|
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,932098,932103,4194304,256,0,0,24,24,189312,0x7fa37b76c900,0x7fa24b836f40,12076540430630261,12076540430643364,12076540430795203,12076540430798444
|
|
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,932098,932103,4194304,256,0,0,20,24,190784,0x7fa37b76c800,0x7fa24b836f80,12076540430823852,12076540430836642,12076540431353438,12076540431386388
|
|
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,932098,932103,4194304,256,0,0,28,24,193792,0x7fa37b76c700,0x7fa24b836fc0,12076540431407147,12076540431419678,12076540431716955,12076540431742490
|
|
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,932098,932103,4194304,256,0,0,24,24,196800,0x7fa37b76c600,0x7fa24b837000,12076540431762678,12076540431775195,12076540431929434,12076540431932754
|
|
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,932098,932103,4194304,256,0,0,24,24,201088,0x7fa37b76c500,0x7fa24b837040,12076540431958202,12076540431969273,12076540432354710,12076540432381479
|
|
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,932098,932103,4194304,256,0,0,24,24,204608,0x7fa37b76c400,0x7fa24b837080,12076540432412286,12076540432424310,12076540432599988,12076540432603392
|
|
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,932098,932103,4194304,256,0,0,20,24,206080,0x7fa37b76c300,0x7fa24b8370c0,12076540432628438,12076540432641588,12076540433252303,12076540433279840
|
|
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,932098,932103,4194304,256,0,0,28,24,209600,0x7fa37b76ca00,0x7fa24b837100,12076540433301510,12076540433313902,12076540433639820,12076540433666018
|
|
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,932098,932103,4194304,256,0,0,24,24,213120,0x7fa37b76c900,0x7fa24b837140,12076540433689081,12076540433701739,12076540433879178,12076540433882511
|
|
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,932098,932103,4194304,256,0,0,24,24,218176,0x7fa37b76c800,0x7fa24b837180,12076540433907898,12076540433919017,12076540434373894,12076540434404552
|
|
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,932098,932103,4194304,256,0,0,24,24,222208,0x7fa37b76c700,0x7fa24b8371c0,12076540434437033,12076540434450213,12076540434649572,12076540434675256
|
|
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,932098,932103,4194304,256,0,0,20,24,223936,0x7fa37b76c600,0x7fa24b837200,12076540434693860,12076540434706371,12076540435410365,12076540435438014
|
|
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,932098,932103,4194304,256,0,0,28,24,227968,0x7fa37b76c500,0x7fa24b837240,12076540435460607,12076540435473085,12076540435846522,12076540435869407
|
|
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,932098,932103,4194304,256,0,0,24,24,232000,0x7fa37b76c400,0x7fa24b837280,12076540435891328,12076540435904121,12076540436106360,12076540436138077
|
|
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,932098,932103,4194304,256,0,0,24,24,237824,0x7fa37b76c300,0x7fa24b8372c0,12076540436158855,12076540436171479,12076540436714355,12076540436742832
|
|
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,932098,932103,4194304,256,0,0,24,24,242368,0x7fa37b76ca00,0x7fa24b837300,12076540436774420,12076540436787314,12076540437011632,12076540437038902
|
|
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,932098,932103,4194304,256,0,0,20,24,243584,0x7fa37b76c900,0x7fa24b837340,12076540437060412,12076540437072272,12076540437872265,12076540437898561
|
|
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,932098,932103,4194304,256,0,0,28,24,248128,0x7fa37b76c800,0x7fa24b837380,12076540437919691,12076540437931145,12076540438350181,12076540438380418
|
|
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,932098,932103,4194304,256,0,0,24,24,252672,0x7fa37b76c700,0x7fa24b8373c0,12076540438401136,12076540438412901,12076540438637379,12076540438663264
|
|
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,932098,932103,4194304,256,0,0,24,24,259264,0x7fa37b76c600,0x7fa24b837400,12076540438684584,12076540438695619,12076540439292894,12076540439320246
|
|
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,932098,932103,4194304,256,0,0,24,24,264832,0x7fa37b76c500,0x7fa24b837440,12076540439351434,12076540439364733,12076540439634811,12076540439660890
|
|
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,932098,932103,4194304,256,0,0,20,24,266304,0x7fa37b76c400,0x7fa24b837480,12076540439682540,12076540439694491,12076540440680723,12076540440708128
|
|
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,932098,932103,4194304,256,0,0,28,24,271872,0x7fa37b76c300,0x7fa24b8374c0,12076540440730229,12076540440742482,12076540441257678,12076540441285702
|
|
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,932098,932103,4194304,256,0,0,24,24,277440,0x7fa37b76ca00,0x7fa24b837500,12076540441310839,12076540441323597,12076540441595435,12076540441621757
|
|
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,932098,932103,4194304,256,0,0,12,24,279936,0x7fa37b76c900,0x7fa24b837540,12076540441641935,12076540441654155,12076540442393029,12076540442420723
|
|
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,932098,932103,4194304,256,0,0,24,24,286528,0x7fa37b76c800,0x7fa24b837580,12076540442451310,12076540442463748,12076540442778625,12076540442805529
|
|
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,932098,932103,4194304,256,0,0,20,24,288000,0x7fa37b76c700,0x7fa24b8375c0,12076540442827770,12076540442840545,12076540444014135,12076540444047469
|
|
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,932098,932103,4194304,256,0,0,32,24,294592,0x7fa37b76c600,0x7fa24b837600,12076540444068769,12076540444081335,12076540444690290,12076540444716133
|
|
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,932098,932103,4194304,256,0,0,24,24,301184,0x7fa37b76c500,0x7fa24b837640,12076540444737002,12076540444749649,12076540445069967,12076540445095158
|
|
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,932098,932103,4194304,256,0,0,12,24,304960,0x7fa37b76c400,0x7fa24b837680,12076540445118341,12076540445131086,12076540446008519,12076540446032892
|
|
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,932098,932103,4194304,256,0,0,24,24,313600,0x7fa37b76c300,0x7fa24b8376c0,12076540446066705,12076540446078759,12076540446489155,12076540446512805
|
|
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,932098,932103,4194304,256,0,0,20,24,314816,0x7fa37b76ca00,0x7fa24b837700,12076540446535387,12076540446547075,12076540448097782,12076540448147035
|
|
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,932098,932103,4194304,256,0,0,20,24,317568,0x7fa37b76c900,0x7fa24b837740,12076540448168445,12076540448180982,12076540448976495,12076540449047079
|
|
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,932098,932103,4194304,256,0,0,12,24,320320,0x7fa37b76c800,0x7fa24b837780,12076540449065874,12076540449078198,12076540449492275,12076540449566515
|
|
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,932098,932103,4194304,256,0,0,12,24,324096,0x7fa37b76c700,0x7fa24b8377c0,12076540449589047,12076540449600913,12076540450760106,12076540450830276
|
|
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,932098,932103,4194304,256,0,0,12,24,328896,0x7fa37b76c600,0x7fa24b837800,12076540450862266,12076540450874185,12076540451659780,12076540451733727
|
|
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,932098,932103,4194304,256,0,0,20,24,330112,0x7fa37b76c500,0x7fa24b837840,12076540451755287,12076540451767779,12076540454823280,12076540454894306
|
|
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,932098,932103,4194304,256,0,0,20,24,332864,0x7fa37b76c400,0x7fa24b837880,12076540454915335,12076540454928399,12076540456472549,12076540456546870
|
|
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,932098,932103,4194304,256,0,0,12,24,335616,0x7fa37b76c300,0x7fa24b8378c0,12076540456570103,12076540456583108,12076540457375103,12076540457446192
|
|
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,932098,932103,4194304,256,0,0,12,24,339392,0x7fa37b76ca00,0x7fa24b837900,12076540457467352,12076540457480382,12076540459761328,12076540459831249
|
|
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,932098,932103,4194304,256,0,0,12,24,344192,0x7fa37b76c900,0x7fa24b837940,12076540459862988,12076540459876527,12076540461412197,12076540461485726
|
|
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,932098,932103,4194304,256,0,0,20,24,345408,0x7fa37b76c800,0x7fa24b837980,12076540461508910,12076540461520996,12076540467578557,12076540467648971
|
|
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,932098,932103,4194304,256,0,0,20,24,348160,0x7fa37b76c700,0x7fa24b8379c0,12076540467671022,12076540467683676,12076540470728457,12076540470798379
|
|
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,932098,932103,4194304,256,0,0,12,24,350912,0x7fa37b76c600,0x7fa24b837a00,12076540470819829,12076540470833096,12076540472372606,12076540472447206
|
|
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,932098,932103,4194304,256,0,0,12,24,0,0x7fa37b76c500,0x7fa24b837a40,12076540472467394,12076540472478525,12076540477004736,12076540477075495
|