169 řádky
48 KiB
CSV
169 řádky
48 KiB
CSV
Index,KernelName,gpu-id,queue-id,queue-index,pid,tid,grd,wgr,lds,scr,vgpr,sgpr,fbar,sig,obj,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,GRBM_COUNT,GRBM_GUI_ACTIVE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,DispatchNs,BeginNs,EndNs,CompleteNs
|
|
0,__amd_rocclr_fillBufferAligned.kd,0,0,0,162887,162887,33554432,256,0,0,4,32,4160,0x0,0x7f0b90204280,3066680,2977166,524288,383334,383334,383334,0,2896,0,0,380125,0,16527598245916,16530446836344,16530447076822,16527746399726
|
|
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,162887,162887,32768,256,0,0,12,24,13888,0x0,0x7f0b90223f80,269736,161104,512,33716,33716,33716,0,1798,0,0,31489,0,16527751557277,16530451863499,16530451877259,16527751693352
|
|
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,162887,162887,4194304,256,0,0,12,24,14336,0x7f0baea38380,0x7f0b90223fc0,1323456,1214693,65536,165431,165431,165431,0,1855,0,0,162564,0,16527751728691,16530451947178,16530452039817,16527752064919
|
|
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,162887,162887,4194304,256,0,0,16,24,15040,0x7f0baea38200,0x7f0b90224000,2475992,2366960,65536,309498,309498,309498,0,1846,0,0,309104,0,16527752103057,16530452073097,16530452252455,16527752473314
|
|
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,162887,162887,4194304,256,0,0,16,24,15488,0x7f0baea38080,0x7f0b90224040,2476240,2374199,65536,309529,309529,309529,0,1823,0,0,307591,0,16527752506633,16530452277895,16530452458533,16527752872929
|
|
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,162887,162887,4194304,256,0,0,12,24,15936,0x7f0bac409f00,0x7f0b90224080,1325480,1216078,65536,165684,165684,165684,0,1786,0,0,162298,0,16527752905488,16530452482533,16530452575972,16527753178638
|
|
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,162887,162887,4194304,256,0,0,12,24,16384,0x7f0bac409d80,0x7f0b902240c0,1322120,1207782,65536,165264,165264,165264,0,1840,0,0,162240,0,16527753211147,16530452602212,16530452694051,16527753487487
|
|
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,162887,162887,4194304,256,0,0,12,24,17088,0x7f0bac409c00,0x7f0b90224100,1303480,1198691,65536,162934,162934,162934,0,1837,0,0,162983,0,16527753532295,16530452734051,16530452826530,16527753792776
|
|
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,162887,162887,4194304,256,0,0,16,24,17792,0x7f0bac409a80,0x7f0b90224140,2476304,2369047,65536,309537,309537,309537,0,1829,0,0,308583,0,16527753825304,16530452858690,16530453039008,16527754190011
|
|
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,162887,162887,4194304,256,0,0,16,24,18496,0x7f0bac409900,0x7f0b90224180,2461080,2353703,65536,307634,307634,307634,0,1839,0,0,307574,0,16527754221890,16530453071648,16530453251806,16527754609176
|
|
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,162887,162887,4194304,256,0,0,16,24,19200,0x7f0bac409780,0x7f0b902241c0,1312632,1205018,65536,164078,164078,164078,0,1846,0,0,162029,0,16527754641315,16530453290206,16530453383645,16527754886496
|
|
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,162887,162887,4194304,256,0,0,16,24,19904,0x7f0bac409600,0x7f0b90224200,1318968,1212892,65536,164870,164870,164870,0,1798,0,0,162759,0,16527754919034,16530453412605,16530453505404,16527755163286
|
|
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,162887,162887,4194304,256,0,0,12,24,20608,0x7f0baea38480,0x7f0b90224240,1324320,1213026,65536,165539,165539,165539,0,1809,0,0,160902,0,16527755204774,16530453537724,16530453630203,16527755441545
|
|
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,162887,162887,4194304,256,0,0,16,24,21312,0x7f0baea38300,0x7f0b90224280,2480872,2371525,65536,310108,310108,310108,0,1891,0,0,307752,0,16527755474674,16530453659643,16530453839321,16527755806902
|
|
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,162887,162887,4194304,256,0,0,16,24,22016,0x7f0baea38180,0x7f0b902242c0,2509328,2391788,65536,313665,313665,313665,0,1804,0,0,305754,0,16527755839161,16530453864921,16530454045879,16527756173949
|
|
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,162887,162887,4194304,256,0,0,16,24,22720,0x7f0baea38000,0x7f0b90224300,1311040,1208082,65536,163879,163879,163879,0,1799,0,0,162021,0,16527756206877,16530454073879,16530454166998,16527756450309
|
|
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,162887,162887,4194304,256,0,0,12,24,23424,0x7f0bac409e80,0x7f0b90224340,1316216,1207008,65536,164526,164526,164526,0,1839,0,0,161639,0,16527756481967,16530454196118,16530454290197,16527756739068
|
|
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,162887,162887,4194304,256,0,0,12,24,24128,0x7f0bac409d00,0x7f0b90224380,1305520,1197448,65536,163189,163189,163189,0,1844,0,0,160576,0,16527756779836,16530454325077,16530454418836,16527757015328
|
|
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,162887,162887,4194304,256,0,0,16,24,24832,0x7f0bac409b80,0x7f0b902243c0,2472464,2362078,65536,309057,309057,309057,0,1829,0,0,306159,0,16527757048047,16530454474036,16530454653874,16527757383154
|
|
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,162887,162887,4194304,256,0,0,16,24,25536,0x7f0bac409a00,0x7f0b90224400,2442224,2333727,65536,305277,305277,305277,0,1868,0,0,305798,0,16527757415683,16530454687154,16530454866512,16527757747371
|
|
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,162887,162887,4194304,256,0,0,12,24,26240,0x7f0bac409880,0x7f0b90224440,1308528,1202335,65536,163565,163565,163565,0,1874,0,0,160937,0,16527757779380,16530454919472,16530455012591,16527758025281
|
|
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,162887,162887,4194304,256,0,0,12,24,26944,0x7f0bac409700,0x7f0b90224480,1306448,1203391,65536,163305,163305,163305,0,1893,0,0,162104,0,16527758057670,16530455038351,16530455131150,16527758309631
|
|
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,162887,162887,4194304,256,0,0,12,24,27648,0x7f0baea38580,0x7f0b902244c0,1308584,1207858,65536,163572,163572,163572,0,1833,0,0,161344,0,16527758349409,16530455165069,16530455257229,16527758588150
|
|
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,162887,162887,4194304,256,0,0,16,24,28608,0x7f0baea38400,0x7f0b90224500,2460280,2355799,65536,307534,307534,307534,0,1839,0,0,305420,0,16527758620939,16530455282508,16530455461387,16527758951537
|
|
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,162887,162887,4194304,256,0,0,16,24,29312,0x7f0baea38280,0x7f0b90224540,2444952,2343679,65536,305618,305618,305618,0,1853,0,0,305982,0,16527758984176,16530455488107,16530455667465,16527759322073
|
|
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,162887,162887,4194304,256,0,0,12,24,30016,0x7f0baea38100,0x7f0b90224580,1300344,1192507,65536,162542,162542,162542,0,1887,0,0,160334,0,16527759355632,16530455690985,16530455782664,16527759598493
|
|
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,162887,162887,4194304,256,0,0,8,24,30976,0x7f0bac409f80,0x7f0b902245c0,1289448,1188425,65536,161180,161180,161180,0,1844,0,0,160308,0,16527759631602,16530455807464,16530455899143,16527759875793
|
|
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,162887,162887,4194304,256,0,0,12,24,31680,0x7f0bac409e00,0x7f0b90224600,1296104,1192899,65536,162012,162012,162012,0,1824,0,0,161086,0,16527759914982,16530455931463,16530456024582,16527760156483
|
|
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,162887,162887,4194304,256,0,0,16,24,32640,0x7f0bac409c80,0x7f0b90224640,2450184,2339341,65536,306272,306272,306272,0,1813,0,0,304030,0,16527760190302,16530456050022,16530456229860,16527760521369
|
|
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,162887,162887,4194304,256,0,0,12,24,33600,0x7f0bac409b00,0x7f0b90224680,2457592,2354784,65536,307198,307198,307198,0,1826,0,0,304150,0,16527760553698,16530456253860,16530456434338,16527760887146
|
|
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,162887,162887,4194304,256,0,0,12,24,34560,0x7f0bac409980,0x7f0b902246c0,1311768,1205947,65536,163970,163970,163970,0,1795,0,0,162588,0,16527760919575,16530456458658,16530456552897,16527761164756
|
|
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,162887,162887,4194304,256,0,0,8,24,35520,0x7f0bac409800,0x7f0b90224700,1305640,1201221,65536,163204,163204,163204,0,1788,0,0,161868,0,16527761197965,16530456578977,16530456673216,16527761458495
|
|
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,162887,162887,4194304,256,0,0,12,24,36224,0x7f0bac409680,0x7f0b90224740,1300232,1199431,65536,162528,162528,162528,0,1829,0,0,160539,0,16527761498824,16530456705216,16530456798335,16527761745634
|
|
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,162887,162887,4194304,256,0,0,12,24,37184,0x7f0baea38500,0x7f0b90224780,2453672,2347680,65536,306708,306708,306708,0,1817,0,0,304868,0,16527761778523,16530456823295,16530457004253,16527762111921
|
|
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,162887,162887,4194304,256,0,0,12,24,38144,0x7f0baea38380,0x7f0b902247c0,2446056,2341406,65536,305756,305756,305756,0,1755,0,0,303816,0,16527762145770,16530457029533,16530457210971,16527762482368
|
|
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,162887,162887,4194304,256,0,0,12,24,39104,0x7f0baea38200,0x7f0b90224800,1300024,1196357,65536,162502,162502,162502,0,1817,0,0,160414,0,16527762514946,16530457236571,16530457330170,16527762760747
|
|
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,162887,162887,4194304,256,0,0,8,24,40320,0x7f0baea38080,0x7f0b90224840,1314040,1207009,65536,164254,164254,164254,0,1799,0,0,160456,0,16527762794086,16530457355610,16530457450489,16527763040557
|
|
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,162887,162887,4194304,256,0,0,12,24,41280,0x7f0bac409f00,0x7f0b90224880,1299352,1198763,65536,162418,162418,162418,0,1801,0,0,160295,0,16527763080456,16530457483129,16530457576888,16527763321727
|
|
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,162887,162887,4194304,256,0,0,12,24,42240,0x7f0bac409d80,0x7f0b902248c0,2456408,2346224,65536,307050,307050,307050,0,1801,0,0,305336,0,16527763354456,16530457602968,16530457781686,16527763689323
|
|
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,162887,162887,4194304,256,0,0,12,24,43200,0x7f0bac409c00,0x7f0b90224900,2434344,2329888,65536,304292,304292,304292,0,1808,0,0,302129,0,16527763722262,16530457806326,16530457987124,16527764053390
|
|
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,162887,162887,4194304,256,0,0,8,24,44160,0x7f0bac409a80,0x7f0b90224940,1302520,1202231,65536,162814,162814,162814,0,1812,0,0,160737,0,16527764085569,16530458013204,16530458107923,16527764335470
|
|
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,162887,162887,4194304,256,0,0,12,24,45376,0x7f0bac409900,0x7f0b90224980,1308584,1200679,65536,163572,163572,163572,0,1807,0,0,162576,0,16527764368019,16530458131443,16530458226162,16527764614420
|
|
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,162887,162887,4194304,256,0,0,12,24,46336,0x7f0bac409780,0x7f0b902249c0,1293928,1191852,65536,161740,161740,161740,0,1798,0,0,159745,0,16527764654558,16530458258802,16530458351761,16527764897509
|
|
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,162887,162887,4194304,256,0,0,12,24,47552,0x7f0bac409600,0x7f0b90224a00,2439496,2332363,65536,304936,304936,304936,0,1811,0,0,305021,0,16527764930478,16530458375921,16530458555279,16527765262346
|
|
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,162887,162887,4194304,256,0,0,12,24,48512,0x7f0baea38480,0x7f0b90224a40,2444888,2335426,65536,305610,305610,305610,0,1861,0,0,302787,0,16527765295745,16530458580239,16530458761997,16527765629273
|
|
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,162887,162887,4194304,256,0,0,8,24,49472,0x7f0baea38300,0x7f0b90224a80,1287416,1182582,65536,160926,160926,160926,0,1776,0,0,160123,0,16527765661981,16530458786477,16530458879116,16527765908292
|
|
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,162887,162887,4194304,256,0,0,12,24,50688,0x7f0baea38180,0x7f0b90224ac0,1298208,1188991,65536,162275,162275,162275,0,1792,0,0,160392,0,16527765940891,16530458904396,16530458998315,16527766198182
|
|
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,162887,162887,4194304,256,0,0,12,24,51648,0x7f0baea38000,0x7f0b90224b00,1287728,1183940,65536,160965,160965,160965,0,1772,0,0,158806,0,16527766239560,16530459030315,16530459122314,16527766489251
|
|
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,162887,162887,4194304,256,0,0,12,24,52864,0x7f0bac409e80,0x7f0b90224b40,2424144,2312053,65536,303017,303017,303017,0,1802,0,0,300809,0,16527766521670,16530459149834,16530459328872,16527766853648
|
|
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,162887,162887,4194304,256,0,0,12,24,54080,0x7f0bac409d00,0x7f0b90224b80,2436288,2330086,65536,304535,304535,304535,0,1784,0,0,301592,0,16527766886827,16530459353672,16530459532871,16527767221304
|
|
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,162887,162887,4194304,256,0,0,8,24,55296,0x7f0bac409b80,0x7f0b90224bc0,1305192,1195223,65536,163148,163148,163148,0,1784,0,0,159731,0,16527767253303,16530459556070,16530459649670,16527767501664
|
|
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,162887,162887,4194304,256,0,0,12,24,56768,0x7f0bac409a00,0x7f0b90224c00,1301600,1196100,65536,162699,162699,162699,0,1808,0,0,160722,0,16527767534403,16530459674309,16530459770308,16527767783294
|
|
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,162887,162887,4194304,256,0,0,12,24,57728,0x7f0bac409880,0x7f0b90224c40,1296672,1185038,65536,162083,162083,162083,0,1786,0,0,160135,0,16527767822372,16530459803268,16530459897347,16527768067613
|
|
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,162887,162887,4194304,256,0,0,12,24,58944,0x7f0bac409700,0x7f0b90224c80,2424752,2313843,65536,303093,303093,303093,0,1808,0,0,300082,0,16527768101762,16530459921987,16530460102466,16527768435460
|
|
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,162887,162887,4194304,256,0,0,12,24,60160,0x7f0baea38580,0x7f0b90224cc0,2406624,2298964,65536,300827,300827,300827,0,1878,0,0,299240,0,16527768468869,16530460127585,16530460309344,16527768801597
|
|
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,162887,162887,4194304,256,0,0,8,24,61376,0x7f0baea38400,0x7f0b90224d00,1298144,1196196,65536,162267,162267,162267,0,1815,0,0,160829,0,16527768834105,16530460335743,16530460430463,16527769084166
|
|
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,162887,162887,4194304,256,0,0,12,24,62848,0x7f0baea38280,0x7f0b90224d40,1357536,1249293,65536,169691,169691,169691,0,1836,0,0,166679,0,16527769116815,16530460457182,16530460556221,16527769368206
|
|
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,162887,162887,4194304,256,0,0,12,24,63808,0x7f0baea38100,0x7f0b90224d80,1297296,1193160,65536,162161,162161,162161,0,1891,0,0,159698,0,16527769408555,16530460588381,16530460681500,16527769651296
|
|
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,162887,162887,4194304,256,0,0,12,24,65024,0x7f0bac409f80,0x7f0b90224dc0,2386576,2281395,65536,298321,298321,298321,0,1812,0,0,297798,0,16527769684994,16530460709660,16530460888539,16527770014252
|
|
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,162887,162887,4194304,256,0,0,12,24,66240,0x7f0bac409e00,0x7f0b90224e00,2398512,2284666,65536,299813,299813,299813,0,1784,0,0,300425,0,16527770046771,16530460914458,16530461092697,16527770392109
|
|
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,162887,162887,4194304,256,0,0,8,24,67456,0x7f0bac409c80,0x7f0b90224e40,1313760,1198132,65536,164219,164219,164219,0,1838,0,0,161229,0,16527770424597,16530461119416,16530461213496,16527770674658
|
|
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,162887,162887,4194304,256,0,0,12,24,68928,0x7f0bac409b00,0x7f0b90224e80,1410672,1306123,65536,176333,176333,176333,0,1797,0,0,173724,0,16527770707057,16530461238135,16530461343254,16527770963248
|
|
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,162887,162887,4194304,256,0,0,12,24,70144,0x7f0bac409980,0x7f0b90224ec0,1292032,1179503,65536,161503,161503,161503,0,1866,0,0,159945,0,16527771002916,16530461375094,16530461468053,16527771242777
|
|
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,162887,162887,4194304,256,0,0,12,24,71616,0x7f0bac409800,0x7f0b90224f00,2418552,2313489,65536,302318,302318,302318,0,1875,0,0,299507,0,16527771274496,16530461493653,16530461673812,16527771613604
|
|
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,162887,162887,4194304,256,0,0,12,24,72832,0x7f0bac409680,0x7f0b90224f40,2426008,2318916,65536,303250,303250,303250,0,1845,0,0,299777,0,16527771645493,16530461700051,16530461880050,16527771980790
|
|
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,162887,162887,4194304,256,0,0,8,24,74048,0x7f0baea38500,0x7f0b90224f80,1297888,1193606,65536,162235,162235,162235,0,1835,0,0,159013,0,16527772013349,16530461904849,16530461998769,16527772260420
|
|
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,162887,162887,4194304,256,0,0,12,24,75776,0x7f0baea38380,0x7f0b90224fc0,1453968,1346302,65536,181745,181745,181745,0,1803,0,0,180334,0,16527772292939,16530462024528,16530462131727,16527772552389
|
|
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,162887,162887,4194304,256,0,0,12,24,76992,0x7f0baea38200,0x7f0b90225000,1287360,1182226,65536,160919,160919,160919,0,1868,0,0,158917,0,16527772605657,16530462166447,16530462259726,16527772834279
|
|
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,162887,162887,4194304,256,0,0,12,24,78464,0x7f0baea38080,0x7f0b90225040,2422880,2310198,65536,302859,302859,302859,0,1845,0,0,300272,0,16527772867338,16530462283726,16530462462925,16527773203295
|
|
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,162887,162887,4194304,256,0,0,12,24,79936,0x7f0bac409f00,0x7f0b90225080,2394384,2285990,65536,299297,299297,299297,0,1862,0,0,298327,0,16527773236424,16530462486604,16530462666283,16527773566512
|
|
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,162887,162887,4194304,256,0,0,8,24,81408,0x7f0bac409d80,0x7f0b902250c0,1295656,1192793,65536,161956,161956,161956,0,1819,0,0,161158,0,16527773599161,16530462690603,16530462785322,16527773845552
|
|
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,162887,162887,4194304,256,0,0,12,24,83136,0x7f0bac409c00,0x7f0b90225100,1536336,1424919,65536,192041,192041,192041,0,1836,0,0,190563,0,16527773877371,16530462808521,16530462923400,16527774148981
|
|
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,162887,162887,4194304,256,0,0,12,24,84352,0x7f0bac409a80,0x7f0b90225140,1288256,1185834,65536,161031,161031,161031,0,1773,0,0,159140,0,16527774188629,16530462968040,16530463061959,16527774443830
|
|
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,162887,162887,4194304,256,0,0,12,24,85824,0x7f0bac409900,0x7f0b90225180,2400184,2288339,65536,300022,300022,300022,0,1866,0,0,299372,0,16527774476389,16530463087399,16530463266917,16527774811556
|
|
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,162887,162887,4194304,256,0,0,12,24,87296,0x7f0bac409780,0x7f0b902251c0,2390472,2279329,65536,298808,298808,298808,0,1819,0,0,298097,0,16527774844695,16530463291877,16530463471236,16527775176203
|
|
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,162887,162887,4194304,256,0,0,12,24,88768,0x7f0bac409600,0x7f0b90225200,1301256,1194316,65536,162656,162656,162656,0,1833,0,0,161632,0,16527775208692,16530463495875,16530463590755,16527775456633
|
|
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,162887,162887,4194304,256,0,0,12,24,90752,0x7f0baea38480,0x7f0b90225240,1616728,1499954,65536,202090,202090,202090,0,1791,0,0,201367,0,16527775489042,16530463618114,16530463738753,16527775762582
|
|
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,162887,162887,4194304,256,0,0,12,24,91968,0x7f0baea38300,0x7f0b90225280,1295312,1190255,65536,161913,161913,161913,0,1772,0,0,159839,0,16527775802350,16530463771073,16530463864032,16527776054071
|
|
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,162887,162887,4194304,256,0,0,12,24,93440,0x7f0baea38180,0x7f0b902252c0,2414648,2310990,65536,301830,301830,301830,0,1784,0,0,302991,0,16527776086020,16530463889952,16530464069470,16527776427767
|
|
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,162887,162887,4194304,256,0,0,12,24,94912,0x7f0baea38000,0x7f0b90225300,2385728,2281424,65536,298215,298215,298215,0,1841,0,0,297111,0,16527776461236,16530464096030,16530464275868,16527776794504
|
|
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,162887,162887,4194304,256,0,0,12,24,96384,0x7f0bac409e80,0x7f0b90225340,1296992,1190427,65536,162123,162123,162123,0,1850,0,0,160782,0,16527776827563,16530464301468,16530464396827,16527777075374
|
|
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,162887,162887,4194304,256,0,0,12,24,98368,0x7f0bac409d00,0x7f0b90225380,1683792,1571279,65536,210473,210473,210473,0,1821,0,0,207574,0,16527777107853,16530464421947,16530464548986,16527777387122
|
|
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,162887,162887,4194304,256,0,0,12,24,99584,0x7f0bac409b80,0x7f0b902253c0,1283648,1181286,65536,160455,160455,160455,0,1806,0,0,159244,0,16527777426691,16530464582586,16530464676665,16527777665992
|
|
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,162887,162887,4194304,256,0,0,12,24,101312,0x7f0bac409a00,0x7f0b90225400,2389984,2282523,65536,298747,298747,298747,0,1816,0,0,294791,0,16527777697341,16530464702105,16530464882263,16527778028879
|
|
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,162887,162887,4194304,256,0,0,12,24,102784,0x7f0bac409880,0x7f0b90225440,2421584,2307908,65536,302697,302697,302697,0,1789,0,0,296888,0,16527778061538,16530464907863,16530465087701,16527778402345
|
|
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,162887,162887,4194304,256,0,0,12,24,104256,0x7f0bac409700,0x7f0b90225480,1287152,1183733,65536,160893,160893,160893,0,1787,0,0,158991,0,16527778434734,16530465112341,16530465206260,16527778683165
|
|
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,162887,162887,4194304,256,0,0,12,24,106240,0x7f0baea38580,0x7f0b902254c0,1754744,1638861,65536,219342,219342,219342,0,1786,0,0,217257,0,16527778715344,16530465232180,16530465362259,16527779002903
|
|
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,162887,162887,4194304,256,0,0,12,24,107712,0x7f0baea38400,0x7f0b90225500,1282096,1179182,65536,160261,160261,160261,0,1761,0,0,159506,0,16527779043492,16530465394578,16530465487698,16527779287273
|
|
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,162887,162887,4194304,256,0,0,16,24,109440,0x7f0baea38280,0x7f0b90225540,2379576,2277689,65536,297446,297446,297446,0,1807,0,0,297971,0,16527779320172,16530465514257,16530465693456,16527779654660
|
|
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,162887,162887,4194304,256,0,0,16,24,111168,0x7f0baea38100,0x7f0b90225580,2397664,2284647,65536,299707,299707,299707,0,1814,0,0,296523,0,16527779687118,16530465718256,16530465897774,16527780031636
|
|
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,162887,162887,4194304,256,0,0,8,24,112896,0x7f0bac409f80,0x7f0b902255c0,1301800,1199807,65536,162724,162724,162724,0,1797,0,0,160398,0,16527780064185,16530465922094,16530466017773,16527780314845
|
|
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,162887,162887,4194304,256,0,0,12,24,115136,0x7f0bac409e00,0x7f0b90225600,1825088,1719381,65536,228135,228135,228135,0,1821,0,0,227100,0,16527780346624,16530466042093,16530466181291,16527780636264
|
|
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,162887,162887,4194304,256,0,0,12,24,116608,0x7f0bac409c80,0x7f0b90225640,1297176,1193665,65536,162146,162146,162146,0,1824,0,0,159182,0,16527780675982,16530466214411,16530466308650,16527780922033
|
|
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,162887,162887,4194304,256,0,0,16,24,118336,0x7f0bac409b00,0x7f0b90225680,2373512,2266418,65536,296688,296688,296688,0,1847,0,0,296044,0,16527780954212,16530466332650,16530466512009,16527781288170
|
|
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,162887,162887,4194304,256,0,0,16,24,120064,0x7f0bac409980,0x7f0b902256c0,2370520,2267903,65536,296314,296314,296314,0,1800,0,0,295087,0,16527781320699,16530466536488,16530466716007,16527781655177
|
|
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,162887,162887,4194304,256,0,0,12,24,121792,0x7f0bac409800,0x7f0b90225700,1302136,1199830,65536,162766,162766,162766,0,1824,0,0,162654,0,16527781687785,16530466740167,16530466836966,16527781936346
|
|
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,162887,162887,4194304,256,0,0,12,24,124032,0x7f0bac409680,0x7f0b90225740,1907560,1801246,65536,238444,238444,238444,0,1803,0,0,236070,0,16527781968525,16530466862085,16530467007364,16527782283894
|
|
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,162887,162887,4194304,256,0,0,12,24,125504,0x7f0baea38500,0x7f0b90225780,1291816,1182027,65536,161476,161476,161476,0,1810,0,0,159400,0,16527782324192,16530467039364,16530467134883,16527782574353
|
|
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,162887,162887,4194304,256,0,0,12,24,127488,0x7f0baea38380,0x7f0b902257c0,2385432,2278586,65536,298178,298178,298178,0,1778,0,0,295898,0,16527782607442,16530467160003,16530467339841,16527782940589
|
|
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,162887,162887,4194304,256,0,0,12,24,129216,0x7f0baea38200,0x7f0b90225800,2398312,2274055,65536,299788,299788,299788,0,1793,0,0,296195,0,16527782973558,16530467365441,16530467546399,16527783304896
|
|
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,162887,162887,4194304,256,0,0,12,24,130944,0x7f0baea38080,0x7f0b90225840,1363800,1257931,65536,170474,170474,170474,0,1787,0,0,168651,0,16527783337305,16530467570719,16530467670558,16527783593535
|
|
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,162887,162887,4194304,256,0,0,12,24,133440,0x7f0bac409f00,0x7f0b90225880,2074040,1959043,65536,259254,259254,259254,0,1814,0,0,257540,0,16527783625904,16530467694398,16530467849757,16527783940403
|
|
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,162887,162887,4194304,256,0,0,12,24,134912,0x7f0bac409d80,0x7f0b902258c0,1286080,1185026,65536,160759,160759,160759,0,1773,0,0,159913,0,16527783980611,16530467882716,16530467977116,16527784223562
|
|
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,162887,162887,4194304,256,0,0,12,24,136896,0x7f0bac409c00,0x7f0b90225900,2371760,2264359,65536,296469,296469,296469,0,1777,0,0,295219,0,16527784255221,16530468001435,16530468180634,16527784589799
|
|
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,162887,162887,4194304,256,0,0,12,24,138880,0x7f0bac409a80,0x7f0b90225940,2367600,2264092,65536,295949,295949,295949,0,1800,0,0,293234,0,16527784621608,16530468205913,16530468386072,16527784953836
|
|
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,162887,162887,4194304,256,0,0,12,24,140864,0x7f0bac409900,0x7f0b90225980,1427304,1318763,65536,178412,178412,178412,0,1833,0,0,176831,0,16527784986194,16530468411032,16530468518551,16527785244245
|
|
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,162887,162887,4194304,256,0,0,12,24,143616,0x7f0bac409780,0x7f0b902259c0,2244928,2132382,65536,280615,280615,280615,0,1878,0,0,278647,0,16527785276814,16530468542870,16530468712789,16527785602102
|
|
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,162887,162887,4194304,256,0,0,12,24,145344,0x7f0bac409600,0x7f0b90225a00,1289632,1183163,65536,161203,161203,161203,0,1787,0,0,160928,0,16527785641970,16530468745749,16530468841908,16527785886321
|
|
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,162887,162887,4194304,256,0,0,12,24,147584,0x7f0baea38480,0x7f0b90225a40,2375648,2261798,65536,296955,296955,296955,0,1890,0,0,294213,0,16527785918370,16530468866548,16530469046866,16527786252948
|
|
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,162887,162887,4194304,256,0,0,12,24,149568,0x7f0baea38300,0x7f0b90225a80,2359552,2251601,65536,294943,294943,294943,0,1788,0,0,295469,0,16527786285807,16530469071346,16530469251504,16527786626104
|
|
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,162887,162887,4194304,256,0,0,12,24,151552,0x7f0baea38180,0x7f0b90225ac0,1498584,1378958,65536,187322,187322,187322,0,1830,0,0,186225,0,16527786658603,16530469275184,16530469385263,16527786924873
|
|
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,162887,162887,4194304,256,0,0,12,24,154304,0x7f0baea38000,0x7f0b90225b00,2397552,2284041,65536,299693,299693,299693,0,1826,0,0,297343,0,16527786957782,16530469408783,16530469590221,16527787292000
|
|
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,162887,162887,4194304,256,0,0,12,24,156288,0x7f0bac409e80,0x7f0b90225b40,1374632,1268032,65536,171828,171828,171828,0,1844,0,0,170310,0,16527787331559,16530469622701,16530469723980,16527787585029
|
|
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,162887,162887,4194304,256,0,0,12,24,158784,0x7f0bac409d00,0x7f0b90225b80,2383088,2258516,65536,297885,297885,297885,0,1823,0,0,298581,0,16527787617228,16530469748620,16530469931818,16527787952116
|
|
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,162887,162887,4194304,256,0,0,12,24,161024,0x7f0bac409b80,0x7f0b90225bc0,2386792,2267076,65536,298348,298348,298348,0,1815,0,0,296575,0,16527787984905,16530469957738,16530470144616,16527788324332
|
|
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,162887,162887,4194304,256,0,0,12,24,163264,0x7f0bac409a00,0x7f0b90225c00,1649936,1537583,65536,206241,206241,206241,0,1789,0,0,204270,0,16527788356881,16530470170216,16530470292935,16527788633861
|
|
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,162887,162887,4194304,256,0,0,12,24,166528,0x7f0bac409880,0x7f0b90225c40,2716352,2606837,65536,339543,339543,339543,0,1791,0,0,338883,0,16527788666410,16530470320935,16530470527653,16527789073955
|
|
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,162887,162887,4194304,256,0,0,12,24,168512,0x7f0bac409700,0x7f0b90225c80,1468272,1359603,65536,183533,183533,183533,0,1786,0,0,182122,0,16527789092584,16530470601412,16530470712931,16527789362094
|
|
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,162887,162887,4194304,256,0,0,12,24,171264,0x7f0baea38580,0x7f0b90225cc0,2375816,2233445,65536,296976,296976,296976,0,1822,0,0,296645,0,16527789397663,16530470738531,16530470923649,16527789731861
|
|
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,162887,162887,4194304,256,0,0,12,24,173760,0x7f0baea38400,0x7f0b90225d00,2392576,2252765,65536,299071,299071,299071,0,1838,0,0,296127,0,16527789765360,16530470947969,16530471133407,16527790102707
|
|
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,162887,162887,4194304,256,0,0,12,24,176256,0x7f0baea38280,0x7f0b90225d40,1803048,1691804,65536,225380,225380,225380,0,1824,0,0,222786,0,16527790135636,16530471159647,16530471294846,16527790426805
|
|
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,162887,162887,4194304,256,0,0,12,24,179776,0x7f0baea38100,0x7f0b90225d80,3055616,2938337,65536,381951,381951,381951,0,1817,0,0,378293,0,16527790459204,16530471318846,16530471551164,16527790891388
|
|
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,162887,162887,4194304,256,0,0,12,24,182272,0x7f0bac409f80,0x7f0b90225dc0,1690168,1577915,65536,211270,211270,211270,0,1824,0,0,208784,0,16527790910098,16530471622043,16530471748762,16527791192417
|
|
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,162887,162887,4194304,256,0,0,12,24,185536,0x7f0bac409e00,0x7f0b90225e00,2440592,2320828,65536,305073,305073,305073,0,1807,0,0,302885,0,16527791224616,16530471775802,16530471967800,16527791566194
|
|
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,162887,162887,4194304,256,0,0,12,24,188544,0x7f0bac409c80,0x7f0b90225e40,2474400,2345412,65536,309299,309299,309299,0,1836,0,0,307924,0,16527791597993,16530471992440,16530472186358,16527791993628
|
|
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,162887,162887,4194304,256,0,0,12,24,191552,0x7f0bac409b00,0x7f0b90225e80,2126368,2016579,65536,265795,265795,265795,0,1785,0,0,263556,0,16527792004488,16530472209238,16530472369716,16527792326546
|
|
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,162887,162887,4194304,256,0,0,12,24,195840,0x7f0bac409980,0x7f0b90225ec0,3694000,3578192,65536,461749,461749,461749,0,1836,0,0,459963,0,16527792359445,16530472394036,16530472677554,16527792838327
|
|
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,162887,162887,4194304,256,0,0,12,24,198592,0x7f0bac409800,0x7f0b90225f00,1944848,1835500,65536,243105,243105,243105,0,1860,0,0,240909,0,16527792856837,16530472748433,16530472897232,16527793159766
|
|
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,162887,162887,4194304,256,0,0,12,24,202368,0x7f0bac409680,0x7f0b90225f40,2675128,2557948,65536,334390,334390,334390,0,1824,0,0,332608,0,16527793194324,16530472923472,16530473131150,16527793596190
|
|
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,162887,162887,4194304,256,0,0,12,24,205888,0x7f0baea38500,0x7f0b90225f80,2649760,2524762,65536,331219,331219,331219,0,1842,0,0,329142,0,16527793606679,16530473170189,16530473380908,16527793994145
|
|
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,162887,162887,4194304,256,0,0,12,24,209408,0x7f0baea38380,0x7f0b90225fc0,2455760,2345421,65536,306969,306969,306969,0,1824,0,0,304352,0,16527794010085,16530473415787,16530473602186,16527794360492
|
|
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,162887,162887,4194304,256,0,0,12,24,214464,0x7f0baea38200,0x7f0b90226000,4337792,4224233,65536,542223,542223,542223,0,1788,0,0,540587,0,16527794394110,16530473626985,16530473961702,16527794924281
|
|
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,162887,162887,4194304,256,0,0,12,24,217728,0x7f0baea38080,0x7f0b90226040,2171880,2063261,65536,271484,271484,271484,0,1828,0,0,269025,0,16527794943060,16530474005862,16530474174500,16527795270488
|
|
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,162887,162887,4194304,256,0,0,12,24,222016,0x7f0bac409f00,0x7f0b90226080,2949160,2828767,65536,368644,368644,368644,0,1817,0,0,363855,0,16527795303537,16530474199620,16530474426338,16527795733491
|
|
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,162887,162887,4194304,256,0,0,12,24,226048,0x7f0bac409d80,0x7f0b902260c0,2935368,2815450,65536,366920,366920,366920,0,1765,0,0,367015,0,16527795743551,16530474466658,16530474695456,16527796181145
|
|
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,162887,162887,4194304,256,0,0,12,24,230080,0x7f0bac409c00,0x7f0b90226100,2784136,2669586,65536,348016,348016,348016,0,1804,0,0,344553,0,16527796191305,16530474754815,16530474966493,16527796609679
|
|
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,162887,162887,4194304,256,0,0,12,24,235904,0x7f0bac409a80,0x7f0b90226140,4992792,4873732,65536,624098,624098,624098,0,1796,0,0,622147,0,16527796620189,16530475025533,16530475411289,16527797212437
|
|
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,162887,162887,4194304,256,0,0,12,24,239424,0x7f0bac409900,0x7f0b90226180,2427656,2317986,65536,303456,303456,303456,0,1774,0,0,300673,0,16527797230476,16530475482009,16530475668887,16527797571884
|
|
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,162887,162887,4194304,256,0,0,12,24,244224,0x7f0bac409780,0x7f0b902261c0,3181192,3068821,65536,397648,397648,397648,0,1770,0,0,394960,0,16527797605443,16530475693527,16530475944405,16527798024897
|
|
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,162887,162887,4194304,256,0,0,12,24,248768,0x7f0bac409600,0x7f0b90226200,3140152,3034625,65536,392518,392518,392518,0,1792,0,0,389147,0,16527798038677,16530476002804,16530476251442,16527798503830
|
|
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,162887,162887,4194304,256,0,0,12,24,253312,0x7f0baea38480,0x7f0b90226240,3099872,2987292,65536,387483,387483,387483,0,1769,0,0,386874,0,16527798514919,16530476311441,16530476548239,16527798970833
|
|
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,162887,162887,4194304,256,0,0,8,24,255552,0x7f0baea38300,0x7f0b90226280,5751768,5629198,65536,718970,718970,718970,0,1800,0,0,716566,0,16527798981762,16530476587279,16530477040395,16527799640678
|
|
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,162887,162887,4194304,256,0,0,12,24,259840,0x7f0baea38180,0x7f0b902262c0,2918232,2798266,65536,364778,364778,364778,0,1793,0,0,360331,0,16527799659878,16530477082795,16530477308873,16527800079562
|
|
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,162887,162887,4194304,256,0,0,12,24,265664,0x7f0baea38000,0x7f0b90226300,3750648,3640401,65536,468830,468830,468830,0,1773,0,0,466601,0,16527800090202,16530477343432,16530477641830,16527800593133
|
|
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,162887,162887,4194304,256,0,0,12,24,271232,0x7f0bac409e80,0x7f0b90226340,3761712,3660866,65536,470213,470213,470213,0,1808,0,0,469296,0,16527800603823,16530477679429,16530477977667,16527801107335
|
|
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,162887,162887,4194304,256,0,0,8,24,273216,0x7f0bac409d00,0x7f0b90226380,3866320,3752679,65536,483289,483289,483289,0,1807,0,0,481518,0,16527801117654,16530478016866,16530478313504,16527801619206
|
|
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,162887,162887,4194304,256,0,0,8,24,275712,0x7f0bac409b80,0x7f0b902263c0,7038448,6934428,65536,879805,879805,879805,0,1794,0,0,877563,0,16527801630076,16530478353183,16530478911418,16527802395128
|
|
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,162887,162887,4194304,256,0,0,12,24,280768,0x7f0bac409a00,0x7f0b90226400,3410752,3301530,65536,426343,426343,426343,0,1795,0,0,424881,0,16527802414347,16530478959258,16530479222456,16527802883190
|
|
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,162887,162887,4194304,256,0,0,12,24,287616,0x7f0bac409880,0x7f0b90226440,4393680,4290125,65536,549209,549209,549209,0,1782,0,0,547587,0,16527802893999,16530479260375,16530479611572,16527803456119
|
|
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,162887,162887,4194304,256,0,0,12,24,294208,0x7f0bac409700,0x7f0b90226480,4400648,4292908,65536,550080,550080,550080,0,1786,0,0,548758,0,16527803466878,16530479660052,16530480010769,16527804019498
|
|
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,162887,162887,4194304,256,0,0,8,24,296960,0x7f0baea38580,0x7f0b902264c0,4508200,4389280,65536,563524,563524,563524,0,1853,0,0,561768,0,16527804030308,16530480057168,16530480404045,16527804581378
|
|
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,162887,162887,4194304,256,0,0,8,24,299968,0x7f0baea38400,0x7f0b90226500,8337736,8220623,65536,1042216,1042216,1042216,0,1820,0,0,1038552,0,16527804592037,16530480444205,16530481105159,16527805456526
|
|
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,162887,162887,4194304,256,0,0,8,24,302720,0x7f0baea38280,0x7f0b90226540,5767376,5656019,65536,720921,720921,720921,0,1827,0,0,718325,0,16527805475945,16530481154118,16530481602754,16527806142821
|
|
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,162887,162887,4194304,256,0,0,12,24,305472,0x7f0baea38100,0x7f0b90226580,5787232,5671957,65536,723403,723403,723403,0,1871,0,0,721443,0,16527806154180,16530481643234,16530482108830,16527806954141
|
|
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,162887,162887,4194304,256,0,0,12,24,308224,0x7f0bac409f80,0x7f0b902265c0,5788928,5665413,65536,723615,723615,723615,0,1819,0,0,720629,0,16527806965461,16530482152190,16530482613625,16527807764771
|
|
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,162887,162887,4194304,256,0,0,8,24,310976,0x7f0bac409e00,0x7f0b90226600,5810256,5692286,65536,726281,726281,726281,0,1799,0,0,723708,0,16527807776401,16530482656985,16530483109141,16527808549212
|
|
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,162887,162887,4194304,256,0,0,8,24,313216,0x7f0bac409c80,0x7f0b90226640,10939624,10815736,65536,1367452,1367452,1367452,0,1791,0,0,1365108,0,16527808561152,16530483149781,16530484018733,16527809751118
|
|
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,162887,162887,4194304,256,0,0,8,24,315968,0x7f0bac409b00,0x7f0b90226680,10965032,10849810,65536,1370628,1370628,1370628,0,1852,0,0,1368282,0,16527809770388,16530484066893,16530484921605,16527810974834
|
|
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,162887,162887,4194304,256,0,0,12,24,318720,0x7f0bac409980,0x7f0b902266c0,10991536,10862608,65536,1373941,1373941,1373941,0,1815,0,0,1372115,0,16527810987553,16530484983684,16530485868797,16527812236547
|
|
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,162887,162887,4194304,256,0,0,12,24,321472,0x7f0bac409800,0x7f0b90226700,10958472,10844711,65536,1369808,1369808,1369808,0,1776,0,0,1369335,0,16527812247837,16530485931036,16530486812148,16527813492222
|
|
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,162887,162887,4194304,256,0,0,8,24,324224,0x7f0bac409680,0x7f0b90226740,11021840,10886750,65536,1377729,1377729,1377729,0,1813,0,0,1373206,0,16527813504591,16530486880468,16530487740460,16527814737736
|
|
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,162887,162887,4194304,256,0,0,8,24,326464,0x7f0baea38500,0x7f0b90226780,21309168,21182928,65536,2663645,2663645,2663645,0,1835,0,0,2658671,0,16527814750506,16530487805419,16530489504604,16527816799321
|
|
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,162887,162887,4194304,256,0,0,8,24,329216,0x7f0baea38380,0x7f0b902267c0,21364368,21225475,65536,2670545,2670545,2670545,0,1858,0,0,2668092,0,16527816818000,16530489604283,16530491270029,16527818790778
|
|
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,162887,162887,4194304,256,0,0,12,24,331968,0x7f0baea38200,0x7f0b90226800,21353920,21239036,65536,2669239,2669239,2669239,0,1789,0,0,2666863,0,16527818802708,16530491359308,16530493085852,16527820846263
|
|
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,162887,162887,4194304,256,0,0,12,24,334720,0x7f0baea38080,0x7f0b90226840,21376880,21237111,65536,2672109,2672109,2672109,0,1780,0,0,2669988,0,16527820857503,16530493174012,16530494890796,16527822898268
|
|
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,162887,162887,4194304,256,0,0,8,24,337472,0x7f0bac409f00,0x7f0b90226880,21371392,21257472,65536,2671423,2671423,2671423,0,1864,0,0,2669733,0,16527822910287,16530494982316,16530496656861,16527824898164
|
|
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,162887,162887,4194304,256,0,0,8,24,0,0x7f0bac409d80,0x7f0b902268c0,42069472,41927427,65536,5258683,5258683,5258683,0,1841,0,0,5256262,0,16527824909134,16530496744540,16530500103390,16527828581890
|