169 строки
54 KiB
CSV
169 строки
54 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_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,GRBM_COUNT,GRBM_GUI_ACTIVE,TD_TD_BUSY_sum,TD_TC_STALL_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,DispatchNs,BeginNs,EndNs,CompleteNs
|
|
0,__amd_rocclr_fillBuffer.kd,0,0,0,860130,860135,33554432,256,0,0,8,32,6464,0x0,0x7f875ea04180,4026768,3823281,57089627,524288,372083385,503345,503345,55261707,54086759,1048576,1048576,0,1048576,12075073030672697,12075076321956559,12075076322280876,12075073277403934
|
|
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,860130,860135,32768,256,0,0,24,24,12480,0x0,0x7f875ea35100,223144,80823,1099072,512,1174935,27892,27892,638660,618215,4096,4096,0,0,12075073291830284,12075076336906869,12075076336914069,12075073292285439
|
|
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,860130,860135,4194304,256,0,0,24,24,12928,0x7f888eafa900,0x7f875ea35140,1754480,1587646,23501113,65536,129814297,219309,219309,22913864,20742872,524288,524288,0,0,12075073292452770,12075076336979349,12075076337114228,12075073292947069
|
|
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,860130,860135,4194304,256,0,0,36,24,13632,0x7f888eafa800,0x7f875ea35180,3143400,2985490,44514865,65536,269953627,392924,392924,43887368,35494882,0,524288,0,0,12075073293193236,12075076337181427,12075076337431025,12075073293802609
|
|
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,860130,860135,4194304,256,0,0,28,24,14080,0x7f888eafa700,0x7f875ea351c0,3248728,3076282,45754634,65536,277209050,406090,406090,45344040,36950510,0,524288,0,0,12075073293962957,12075076337548464,12075076337795022,12075073294580785
|
|
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,860130,860135,4194304,256,0,0,24,24,14528,0x7f888eafa600,0x7f875ea35200,1756328,1568718,23212252,65536,139814615,219540,219540,22667036,20499310,524288,524288,0,0,12075073294733849,12075076337907821,12075076338033260,12075073295147789
|
|
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,860130,860135,4194304,256,0,0,24,24,14976,0x7f888eafa500,0x7f875ea35240,1769432,1599196,23666738,65536,134395096,221178,221178,23113404,20940987,524288,524288,0,0,12075073295372687,12075076338076779,12075076338201738,12075073295792657
|
|
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,860130,860135,4194304,256,0,0,24,24,15424,0x7f888eafa400,0x7f875ea35280,1734680,1574757,23302995,65536,153576333,216834,216834,22771004,20602057,524288,524288,0,0,12075073296053442,12075076338269898,12075076338394217,12075073296467922
|
|
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,860130,860135,4194304,256,0,0,28,24,16128,0x7f888eafa300,0x7f875ea352c0,3242984,3075206,45802301,65536,302750925,405372,405372,45195388,36802095,0,524288,0,0,12075073296690395,12075076338436136,12075076338680774,12075073297294017
|
|
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,860130,860135,4194304,256,0,0,28,24,16832,0x7f888eafaa00,0x7f875ea35300,3126592,2964325,44255975,65536,348999462,390823,390823,43851492,35458977,0,524288,0,0,12075073297447302,12075076338791013,12075076339036451,12075073298034313
|
|
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,860130,860135,4194304,256,0,0,24,24,17536,0x7f888eafa900,0x7f875ea35340,1730736,1563305,23186458,65536,147262566,216341,216341,22651988,20483627,524288,524288,0,0,12075073298194611,12075076339148290,12075076339273089,12075073298600605
|
|
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,860130,860135,4194304,256,0,0,24,24,18240,0x7f888eafa800,0x7f875ea35380,1723816,1555208,23057833,65536,145981974,215476,215476,22419712,20248309,524288,524288,0,0,12075073298830953,12075076339315649,12075076339440928,12075073299236216
|
|
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,860130,860135,4194304,256,0,0,24,24,18944,0x7f888eafa700,0x7f875ea353c0,1698864,1525359,22595340,65536,157815569,212357,212357,22104156,19922862,524288,524288,0,0,12075073299475231,12075076339494687,12075076339619646,12075073299883740
|
|
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,860130,860135,4194304,256,0,0,28,24,19904,0x7f888eafa600,0x7f875ea35400,3156440,2996075,44727344,65536,357439101,394554,394554,44172732,35780197,0,524288,0,0,12075073300106343,12075076339660766,12075076339906684,12075073300690429
|
|
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,860130,860135,4194304,256,0,0,28,24,20608,0x7f888eafa500,0x7f875ea35440,3217472,3050396,45440835,65536,286587553,402183,402183,45016460,36622390,0,524288,0,0,12075073300846649,12075076339963323,12075076340209081,12075073301444640
|
|
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,860130,860135,4194304,256,0,0,24,24,21312,0x7f888eafa400,0x7f875ea35480,1735272,1573927,23340474,65536,151536793,216908,216908,22826680,20656508,524288,524288,0,0,12075073301604588,12075076340294040,12075076340418359,12075073302006825
|
|
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,860130,860135,4194304,256,0,0,24,24,22016,0x7f888eafa300,0x7f875ea354c0,1735616,1570061,23261613,65536,146192741,216951,216951,22686032,20512511,524288,524288,0,0,12075073302230501,12075076340454999,12075076340580118,12075073302631997
|
|
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,860130,860135,4194304,256,0,0,24,24,22720,0x7f888eafaa00,0x7f875ea35500,1752472,1581157,23370451,65536,154220028,219058,219058,22844228,20673238,524288,524288,0,0,12075073302866082,12075076340634037,12075076340758836,12075073303271395
|
|
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,860130,860135,4194304,256,0,0,28,24,23680,0x7f888eafa900,0x7f875ea35540,3158744,2991312,44661935,65536,356316796,394842,394842,44110620,35718054,0,524288,0,0,12075073303486094,12075076340801556,12075076341049074,12075073304068026
|
|
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,860130,860135,4194304,256,0,0,28,24,24384,0x7f888eafa800,0x7f875ea35580,3210496,3035405,45274275,65536,290540155,401311,401311,44856804,36462980,0,524288,0,0,12075073304232441,12075076341133393,12075076341377071,12075073304822638
|
|
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,860130,860135,4194304,256,0,0,24,24,25088,0x7f888eafa700,0x7f875ea355c0,1755224,1578148,23385555,65536,140096691,219402,219402,22880148,20710628,524288,524288,0,0,12075073304980341,12075076341459790,12075076341584429,12075073305388490
|
|
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,860130,860135,4194304,256,0,0,24,24,25792,0x7f888eafa600,0x7f875ea35600,1739760,1576851,23312551,65536,147447359,217469,217469,22721364,20551588,524288,524288,0,0,12075073305610442,12075076341625709,12075076341750668,12075073306009193
|
|
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,860130,860135,4194304,256,0,0,24,24,26496,0x7f888eafa500,0x7f875ea35640,1702448,1531084,22701831,65536,147848159,212805,212805,22192792,20019144,524288,524288,0,0,12075073306244661,12075076341802987,12075076341927146,12075073306643271
|
|
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,860130,860135,4194304,256,0,0,28,24,27712,0x7f888eafa400,0x7f875ea35680,3245312,3069609,45656349,65536,265081806,405663,405663,45075348,36682424,0,524288,0,0,12075073306856418,12075076341970506,12075076342214824,12075073307455351
|
|
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,860130,860135,4194304,256,0,0,28,24,28416,0x7f888eafa300,0x7f875ea356c0,3211072,3016898,45000604,65536,300384108,401383,401383,44571580,36177400,0,524288,0,0,12075073307608044,12075076342326023,12075076342570341,12075073308191098
|
|
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,860130,860135,4194304,256,0,0,24,24,29120,0x7f888eafaa00,0x7f875ea35700,1768024,1593004,23683685,65536,136019959,221002,221002,23079508,20907966,524288,524288,0,0,12075073308347468,12075076342680740,12075076342805379,12075073308760676
|
|
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,860130,860135,4194304,256,0,0,24,24,30080,0x7f888eafa900,0x7f875ea35740,1761624,1596836,23607504,65536,135191029,220202,220202,22894792,20728857,524288,524288,0,0,12075073308984572,12075076342847138,12075076342971937,12075073309398221
|
|
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,860130,860135,4194304,256,0,0,24,24,30784,0x7f888eafa800,0x7f875ea35780,1679856,1518458,22542200,65536,154818878,209981,209981,21971692,19797201,524288,524288,0,0,12075073309611938,12075076343026657,12075076343151296,12075073310019606
|
|
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,860130,860135,4194304,256,0,0,28,24,32000,0x7f888eafa700,0x7f875ea357c0,3203688,3034375,45283062,65536,361669708,400460,400460,44686940,36294029,0,524288,0,0,12075073310235878,12075076343193855,12075076343440093,12075073310831425
|
|
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,860130,860135,4194304,256,0,0,28,24,32960,0x7f888eafa600,0x7f875ea35800,3136960,2974964,44397031,65536,315456016,392119,392119,43946096,35553229,0,524288,0,0,12075073310987314,12075076343552892,12075076343795770,12075073311576369
|
|
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,860130,860135,4194304,256,0,0,24,24,33920,0x7f888eafa500,0x7f875ea35840,1707440,1541626,22796185,65536,152764143,213429,213429,22267988,20096694,524288,524288,0,0,12075073311733391,12075076343907769,12075076344032248,12075073312138273
|
|
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,860130,860135,4194304,256,0,0,24,24,34880,0x7f888eafa400,0x7f875ea35880,1764656,1594718,23594777,65536,142132181,220581,220581,22900804,20733287,524288,524288,0,0,12075073312357631,12075076344075608,12075076344201367,12075073312761902
|
|
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,860130,860135,4194304,256,0,0,24,24,35840,0x7f888eafa300,0x7f875ea358c0,1721176,1559289,23108617,65536,149180737,215146,215146,22548660,20373567,524288,524288,0,0,12075073312995015,12075076344255766,12075076344380725,12075073313402513
|
|
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,860130,860135,4194304,256,0,0,28,24,37312,0x7f888eafaa00,0x7f875ea35900,3224896,3041758,45343608,65536,308329947,403111,403111,44754848,36361356,0,524288,0,0,12075073313623022,12075076344422005,12075076344673043,12075073314219310
|
|
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,860130,860135,4194304,256,0,0,28,24,38272,0x7f888eafa900,0x7f875ea35940,3214552,3043099,45339057,65536,319359681,401818,401818,44814516,36422009,0,524288,0,0,12075073314377084,12075076344768722,12075076345013360,12075073314965377
|
|
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,860130,860135,4194304,256,0,0,24,24,39232,0x7f888eafa800,0x7f875ea35980,1688432,1523298,22578740,65536,149055581,211053,211053,22030404,19859497,524288,524288,0,0,12075073315123661,12075076345074159,12075076345198798,12075073315515700
|
|
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,860130,860135,4194304,256,0,0,24,24,40192,0x7f888eafa700,0x7f875ea359c0,1843032,1667340,24731593,65536,148643516,230378,230378,23931104,21763577,524288,524288,0,0,12075073315721733,12075076345241518,12075076345366957,12075073316131143
|
|
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,860130,860135,4194304,256,0,0,24,24,41152,0x7f888eafa600,0x7f875ea35a00,1740200,1553352,23011420,65536,144330687,217524,217524,22497156,20324554,524288,524288,0,0,12075073316364768,12075076345418476,12075076345542475,12075073316769830
|
|
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,860130,860135,4194304,256,0,0,28,24,42624,0x7f888eafa500,0x7f875ea35a40,3103720,2929441,43688927,65536,343715483,387964,387964,43087452,34693926,0,524288,0,0,12075073316986132,12075076345584875,12075076345829353,12075073317583593
|
|
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,860130,860135,4194304,256,0,0,28,24,43584,0x7f888eafa400,0x7f875ea35a80,3173360,2999184,44738782,65536,295468865,396669,396669,44278800,35886218,0,524288,0,0,12075073317735264,12075076345886632,12075076346129990,12075073318318398
|
|
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,860130,860135,4194304,256,0,0,24,24,44544,0x7f888eafa300,0x7f875ea35ac0,1716208,1548767,22906578,65536,163297311,214525,214525,22285940,20108510,524288,524288,0,0,12075073318479137,12075076346196229,12075076346321348,12075073318885131
|
|
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,860130,860135,4194304,256,0,0,24,24,45760,0x7f888eafaa00,0x7f875ea35b00,1760432,1594016,23481302,65536,157299877,220053,220053,22695900,20519477,524288,524288,0,0,12075073319115890,12075076346363108,12075076346488707,12075073319520101
|
|
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,860130,860135,4194304,256,0,0,24,24,46720,0x7f888eafa900,0x7f875ea35b40,1772208,1602759,23694987,65536,146021450,221525,221525,23057684,20886837,524288,524288,0,0,12075073319754156,12075076346540546,12075076346665505,12075073320171602
|
|
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,860130,860135,4194304,256,0,0,28,24,48448,0x7f888eafa800,0x7f875ea35b80,3322712,3148791,46778785,65536,343346134,415338,415338,46145132,37747300,0,524288,0,0,12075073320386862,12075076346708225,12075076346963903,12075073320984903
|
|
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,860130,860135,4194304,256,0,0,28,24,49408,0x7f888eafa700,0x7f875ea35bc0,3212056,3040376,45306131,65536,330451057,401506,401506,44775764,36383257,0,524288,0,0,12075073321148998,12075076347023422,12075076347273820,12075073321745096
|
|
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,860130,860135,4194304,256,0,0,24,24,50368,0x7f888eafa600,0x7f875ea35c00,1677040,1508560,22369322,65536,158600125,209629,209629,21730932,19550622,524288,524288,0,0,12075073321884104,12075076347330460,12075076347454939,12075073322295028
|
|
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,860130,860135,4194304,256,0,0,24,24,51584,0x7f888eafa500,0x7f875ea35c40,1802072,1614241,23685921,65536,149549307,225258,225258,22694092,20516057,524288,524288,0,0,12075073322521449,12075076347495738,12075076347622457,12075073322932833
|
|
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,860130,860135,4194304,256,0,0,24,24,52544,0x7f888eafa400,0x7f875ea35c80,1723032,1553613,23011421,65536,152338882,215378,215378,22440040,20264679,524288,524288,0,0,12075073323164023,12075076347674137,12075076347800056,12075073323563315
|
|
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,860130,860135,4194304,256,0,0,28,24,54272,0x7f888eafa300,0x7f875ea35cc0,3357144,3168485,47171870,65536,314260409,419642,419642,46562404,38165094,0,524288,0,0,12075073323778074,12075076347841015,12075076348093973,12075073324385513
|
|
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,860130,860135,4194304,256,0,0,28,24,55488,0x7f888eafaa00,0x7f875ea35d00,3162432,2987567,44621387,65536,265713783,395303,395303,44175696,35783037,0,524288,0,0,12075073324541062,12075076348157173,12075076348400690,12075073325131780
|
|
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,860130,860135,4194304,256,0,0,24,24,56704,0x7f888eafa900,0x7f875ea35d40,1784744,1617517,23963991,65536,140614078,223092,223092,23349552,21181536,524288,524288,0,0,12075073325289543,12075076348457650,12075076348583089,12075073325698363
|
|
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,860130,860135,4194304,256,0,0,24,24,58176,0x7f888eafa800,0x7f875ea35d80,1788568,1615005,23690088,65536,162215833,223570,223570,22424540,20236160,524288,524288,0,0,12075073325925785,12075076348622289,12075076348750767,12075073326335326
|
|
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,860130,860135,4194304,256,0,0,24,24,59392,0x7f888eafa700,0x7f875ea35dc0,1804656,1632789,24177420,65536,141482335,225581,225581,23571960,21406547,524288,524288,0,0,12075073326569311,12075076348801327,12075076348926286,12075073326983741
|
|
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,860130,860135,4194304,256,0,0,28,24,61376,0x7f888eafa600,0x7f875ea35e00,3286576,3114113,46311768,65536,344129908,410821,410821,45631200,37233814,0,524288,0,0,12075073327199412,12075076348966926,12075076349225163,12075073327800579
|
|
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,860130,860135,4194304,256,0,0,28,24,62592,0x7f888eafa500,0x7f875ea35e40,3198720,3028668,45164278,65536,349273006,399839,399839,44708028,36315492,0,524288,0,0,12075073327935821,12075076349288683,12075076349535241,12075073328528472
|
|
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,860130,860135,4194304,256,0,0,24,24,63808,0x7f888eafa400,0x7f875ea35e80,1750832,1585974,23457389,65536,140983830,218853,218853,22840124,20667746,524288,524288,0,0,12075073328689672,12075076349596040,12075076349721799,12075073329093773
|
|
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,860130,860135,4194304,256,0,0,24,24,65280,0x7f888eafa300,0x7f875ea35ec0,1831872,1660399,24324059,65536,170615354,228983,228983,22417584,20213662,524288,524288,0,0,12075073329319242,12075076349764839,12075076349893318,12075073329735706
|
|
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,860130,860135,4194304,256,0,0,24,24,66496,0x7f888eafaa00,0x7f875ea35f00,1712408,1542705,22757559,65536,149932525,214050,214050,22142244,19970380,524288,524288,0,0,12075073329970131,12075076349945477,12075076350070116,12075073330375404
|
|
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,860130,860135,4194304,256,0,0,28,24,68480,0x7f888eafa900,0x7f875ea35f40,3288384,3117714,46354879,65536,348426067,411047,411047,45660196,37262026,0,524288,0,0,12075073330591225,12075076350112196,12075076350370753,12075073331184708
|
|
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,860130,860135,4194304,256,0,0,28,24,69696,0x7f888eafa800,0x7f875ea35f80,3138432,2969567,44333192,65536,355404138,392303,392303,43879240,35486727,0,524288,0,0,12075073331347421,12075076350427873,12075076350674431,12075073331930614
|
|
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,860130,860135,4194304,256,0,0,24,24,70912,0x7f888eafa700,0x7f875ea35fc0,1699288,1527662,22588512,65536,150856870,212410,212410,21988920,19810314,524288,524288,0,0,12075073332086554,12075076350734430,12075076350858909,12075073332483011
|
|
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,860130,860135,4194304,256,0,0,24,24,72384,0x7f888eafa600,0x7f875ea36000,1822360,1646679,24127114,65536,175975175,227794,227794,19717916,17428822,524288,524288,0,0,12075073332701297,12075076350899549,12075076351035708,12075073333108984
|
|
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,860130,860135,4194304,256,0,0,24,24,73600,0x7f888eafa500,0x7f875ea36040,1774576,1603579,23682911,65536,146275181,221821,221821,23051700,20881300,524288,524288,0,0,12075073333344863,12075076351089947,12075076351214746,12075073333747130
|
|
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,860130,860135,4194304,256,0,0,28,24,75840,0x7f888eafa400,0x7f875ea36080,3320512,3144627,46697674,65536,337599379,415063,415063,46024892,37622277,0,524288,0,0,12075073333943575,12075076351255066,12075076351507064,12075073334544542
|
|
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,860130,860135,4194304,256,0,0,28,24,77056,0x7f888eafa300,0x7f875ea360c0,3238616,3061827,45702161,65536,348430254,404826,404826,45233888,36841264,0,524288,0,0,12075073334694861,12075076351563703,12075076351811061,12075073335288895
|
|
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,860130,860135,4194304,256,0,0,24,24,78272,0x7f888eafaa00,0x7f875ea36100,1741592,1572149,23338338,65536,154800054,217698,217698,22767032,20601909,524288,524288,0,0,12075073335450576,12075076351866741,12075076351991860,12075073335859506
|
|
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,860130,860135,4194304,256,0,0,24,24,80000,0x7f888eafa900,0x7f875ea36140,1848128,1678531,24865072,65536,192683550,231015,231015,18948116,16618603,524288,524288,0,0,12075073336086458,12075076352038739,12075076352180978,12075073336496339
|
|
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,860130,860135,4194304,256,0,0,24,24,81216,0x7f888eafa800,0x7f875ea36180,1766256,1597337,23626632,65536,155654646,220781,220781,22967504,20796381,524288,524288,0,0,12075073336725094,12075076352231697,12075076352356816,12075073337136739
|
|
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,860130,860135,4194304,256,0,0,28,24,83456,0x7f888eafa700,0x7f875ea361c0,3307752,3123967,46474212,65536,320334905,413468,413468,45726720,37322038,0,524288,0,0,12075073337350947,12075076352400656,12075076352659694,12075073337957625
|
|
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,860130,860135,4194304,256,0,0,28,24,84928,0x7f888eafa600,0x7f875ea36200,3185960,3018037,44987817,65536,315762277,398244,398244,44484964,36091916,0,524288,0,0,12075073338116580,12075076352719053,12075076352963371,12075073338707088
|
|
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,860130,860135,4194304,256,0,0,24,24,86400,0x7f888eafa500,0x7f875ea36240,1738800,1566045,23186932,65536,147468741,217349,217349,22558016,20389332,524288,524288,0,0,12075073338860723,12075076353032971,12075076353158410,12075073339268421
|
|
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,860130,860135,4194304,256,0,0,24,24,88128,0x7f888eafa400,0x7f875ea36280,1932440,1763518,26132881,65536,207454679,241554,241554,17987972,15616996,524288,524288,0,0,12075073339485454,12075076353200649,12075076353349928,12075073339903461
|
|
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,860130,860135,4194304,256,0,0,24,24,89600,0x7f888eafa300,0x7f875ea362c0,1802600,1628952,24082706,65536,147936607,225324,225324,23417876,21247828,524288,524288,0,0,12075073340154357,12075076353419527,12075076353545606,12075073340566563
|
|
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,860130,860135,4194304,256,0,0,28,24,92096,0x7f888eafaa00,0x7f875ea36300,3343552,3141655,46677520,65536,312817387,417943,417943,45866536,37456643,0,524288,0,0,12075073340759422,12075076353585606,12075076353841124,12075073341368714
|
|
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,860130,860135,4194304,256,0,0,28,24,93568,0x7f888eafa900,0x7f875ea36340,3126192,2961783,44210365,65536,353914216,390773,390773,43711728,35319116,0,524288,0,0,12075073341527920,12075076353900163,12075076354145601,12075073342108158
|
|
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,860130,860135,4194304,256,0,0,24,24,95040,0x7f888eafa800,0x7f875ea36380,1798488,1636138,24203085,65536,152349758,224810,224810,23546092,21380980,524288,524288,0,0,12075073342263487,12075076354210880,12075076354336159,12075073342678077
|
|
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,860130,860135,4194304,256,0,0,24,24,96768,0x7f888eafa700,0x7f875ea363c0,2025704,1852502,27525141,65536,217948994,253212,253212,16553716,14118148,524288,524288,0,0,12075073342956485,12075076354377279,12075076354535038,12075073343395280
|
|
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,860130,860135,4194304,256,0,0,24,24,98240,0x7f888eafa600,0x7f875ea36400,1823528,1629138,24061141,65536,150621155,227940,227940,23324960,21155560,524288,524288,0,0,12075073343623885,12075076354586077,12075076354711196,12075073344028367
|
|
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,860130,860135,4194304,256,0,0,28,24,100736,0x7f888eafa500,0x7f875ea36440,3360560,3167389,47027840,65536,299600456,420069,420069,46049784,37617878,0,524288,0,0,12075073344243066,12075076354751676,12075076355005754,12075073344851927
|
|
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,860130,860135,4194304,256,0,0,28,24,102208,0x7f888eafa400,0x7f875ea36480,3573568,2960192,44130995,65536,345977980,446695,446695,43605468,35212678,0,524288,0,0,12075073345019358,12075076355062073,12075076355310071,12075073345639140
|
|
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,860130,860135,4194304,256,0,0,24,24,103680,0x7f888eafa300,0x7f875ea364c0,1806064,1620790,23942885,65536,150387220,225757,225757,23192756,21022246,524288,524288,0,0,12075073345794779,12075076355366710,12075076355492309,12075073346207166
|
|
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,860130,860135,4194304,256,0,0,24,24,105664,0x7f888eafaa00,0x7f875ea36500,2117992,1945551,28912752,65536,224494534,264748,264748,15435844,12949834,524288,524288,0,0,12075073346431653,12075076355533429,12075076355699188,12075073346866080
|
|
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,860130,860135,4194304,256,0,0,24,24,107136,0x7f888eafa900,0x7f875ea36540,1719040,1542259,22690885,65536,169281318,214879,214879,21956736,19776201,524288,524288,0,0,12075073347101728,12075076355750547,12075076355875826,12075073347509055
|
|
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,860130,860135,4194304,256,0,0,28,24,109888,0x7f888eafa800,0x7f875ea36580,3303280,3116998,46155266,65536,356778496,412909,412909,45242212,36825219,0,524288,0,0,12075073347697275,12075076355916946,12075076356184143,12075073348287492
|
|
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,860130,860135,4194304,256,0,0,28,24,111360,0x7f888eafa700,0x7f875ea365c0,3180888,3006686,44859287,65536,346089159,397610,397610,44303684,35910833,0,524288,0,0,12075073348444594,12075076356245903,12075076356491021,12075073349029471
|
|
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,860130,860135,4194304,256,0,0,24,24,112832,0x7f888eafa600,0x7f875ea36600,1752664,1579404,23397750,65536,159641708,219082,219082,22724772,20553706,524288,524288,0,0,12075073349191872,12075076356553580,12075076356678539,12075073349593218
|
|
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,860130,860135,4194304,256,0,0,24,24,114816,0x7f888eafa500,0x7f875ea36640,2215104,2052009,30521931,65536,247909179,276887,276887,15661860,13167686,524288,524288,0,0,12075073349817204,12075076356720459,12075076356892937,12075073350274775
|
|
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,860130,860135,4194304,256,0,0,24,24,116288,0x7f888eafa400,0x7f875ea36680,1792104,1591640,23480259,65536,144499767,224012,224012,22697932,20521627,524288,524288,0,0,12075073350503650,12075076356944937,12075076357070536,12075073350914353
|
|
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,860130,860135,4194304,256,0,0,28,24,119040,0x7f888eafa300,0x7f875ea366c0,3281896,3095272,45870995,65536,327255766,410236,410236,44089952,35597714,0,524288,0,0,12075073351136767,12075076357111495,12075076357364453,12075073351739908
|
|
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,860130,860135,4194304,256,0,0,28,24,120768,0x7f888eafaa00,0x7f875ea36700,3182592,3000875,44741269,65536,337775661,397823,397823,44213372,35820045,0,524288,0,0,12075073351902590,12075076357426373,12075076357671811,12075073352498036
|
|
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,860130,860135,4194304,256,0,0,24,24,122496,0x7f888eafa900,0x7f875ea36740,1855808,1678073,24812589,65536,157009222,231975,231975,23851084,21679046,524288,524288,0,0,12075073352653906,12075076357727650,12075076357853409,12075073353064409
|
|
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,860130,860135,4194304,256,0,0,24,24,124736,0x7f888eafa800,0x7f875ea36780,2320152,2154903,32042028,65536,257826886,290018,290018,15453372,12948179,524288,524288,0,0,12075073353280450,12075076357894529,12075076358076927,12075073353799475
|
|
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,860130,860135,4194304,256,0,0,24,24,126464,0x7f888eafa700,0x7f875ea367c0,1796592,1616266,23899954,65536,153559920,224573,224573,23138716,20972506,524288,524288,0,0,12075073353969030,12075076358130367,12075076358255646,12075073354390243
|
|
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,860130,860135,4194304,256,0,0,20,24,127936,0x7f888eafa600,0x7f875ea36800,3275304,3105934,46253084,65536,375965168,409412,409412,45722396,37299069,0,524288,0,0,12075073354609049,12075076358296605,12075076358559963,12075073355212280
|
|
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,860130,860135,4194304,256,0,0,28,24,129664,0x7f888eafa500,0x7f875ea36840,3124952,2953928,44070275,65536,355180261,390618,390618,43535372,35142579,0,524288,0,0,12075073355367539,12075076358619962,12075076358866360,12075073355955822
|
|
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,860130,860135,4194304,256,0,0,24,24,131392,0x7f888eafa400,0x7f875ea36880,1771120,1595940,23591989,65536,145432890,221389,221389,22792804,20621654,524288,524288,0,0,12075073356119196,12075076358926520,12075076359052439,12075073356523798
|
|
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,860130,860135,4194304,256,0,0,24,24,133632,0x7f888eafa300,0x7f875ea368c0,2438056,2268379,33718327,65536,275078546,304756,304756,16226860,13706241,524288,524288,0,0,12075073356747854,12075076359095318,12075076359286517,12075073357290122
|
|
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,860130,860135,4194304,256,0,0,24,24,135360,0x7f888eafaa00,0x7f875ea36900,1814104,1644125,24272303,65536,149654579,226762,226762,23428912,21261620,524288,524288,0,0,12075073357456571,12075076359338036,12075076359465715,12075073357863487
|
|
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,860130,860135,4194304,256,0,0,20,24,136832,0x7f888eafa900,0x7f875ea36940,3512640,3336029,49644142,65536,406508565,439079,439079,48995256,40535008,0,524288,0,0,12075073358077335,12075076359507955,12075076359790192,12075073358699531
|
|
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,860130,860135,4194304,256,0,0,28,24,138560,0x7f888eafa800,0x7f875ea36980,3144152,2971290,44266958,65536,355853309,393018,393018,43659352,35266031,0,524288,0,0,12075073358853677,12075076359845232,12075076360093390,12075073359445497
|
|
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,860130,860135,4194304,256,0,0,24,24,140288,0x7f888eafa700,0x7f875ea369c0,1808688,1641042,24108410,65536,152284975,226085,226085,23111756,20934760,524288,524288,0,0,12075073359601247,12075076360155309,12075076360281068,12075073360011579
|
|
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,860130,860135,4194304,256,0,0,24,24,142784,0x7f888eafa600,0x7f875ea36a00,2637272,2469467,36714909,65536,293532898,329658,329658,15047920,12505245,524288,524288,0,0,12075073360230135,12075076360323628,12075076360533226,12075073360774397
|
|
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,860130,860135,4194304,256,0,0,24,24,144768,0x7f888eafa500,0x7f875ea36a40,1801536,1621056,23882037,65536,150469386,225191,225191,22826420,20645940,524288,524288,0,0,12075073360920298,12075076360600905,12075076360728904,12075073361339768
|
|
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,860130,860135,4194304,256,0,0,20,24,145728,0x7f888eafa400,0x7f875ea36a80,3795560,3604439,53735837,65536,439922020,474444,474444,52707880,44150237,0,524288,0,0,12075073361559065,12075076360770184,12075076361077061,12075073362201148
|
|
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,860130,860135,4194304,256,0,0,28,24,147712,0x7f888eafa300,0x7f875ea36ac0,3185048,3004194,44693901,65536,345534058,398130,398130,43979848,35583057,0,524288,0,0,12075073362361065,12075076361137381,12075076361384419,12075073362948808
|
|
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,860130,860135,4194304,256,0,0,24,24,149696,0x7f888eafaa00,0x7f875ea36b00,1826072,1660927,24496167,65536,152928371,228258,228258,23210168,21027579,524288,524288,0,0,12075073363105860,12075076361446658,12075076361573857,12075073363513337
|
|
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,860130,860135,4194304,256,0,0,24,24,152192,0x7f888eafa900,0x7f875ea36b40,2858608,2687171,39920832,65536,324679970,357325,357325,15451712,12899987,524288,524288,0,0,12075073363738054,12075076361614977,12075076361842495,12075073364302032
|
|
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,860130,860135,4194304,256,0,0,24,24,154176,0x7f888eafa800,0x7f875ea36b80,1760216,1586069,23393641,65536,155526284,220026,220026,22197812,20012843,524288,524288,0,0,12075073364473511,12075076361914494,12075076362041693,12075073364875919
|
|
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,860130,860135,4194304,256,0,0,20,24,155648,0x7f888eafa700,0x7f875ea36bc0,4392384,3882390,57821894,65536,473569010,549047,549047,56731568,48128098,0,524288,0,0,12075073365101398,12075076362082653,12075076362410650,12075073365798373
|
|
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,860130,860135,4194304,256,0,0,28,24,157632,0x7f888eafa600,0x7f875ea36c00,3131544,2958322,44032326,65536,349264983,391442,391442,43369948,34975696,0,524288,0,0,12075073365960054,12075076362474809,12075076362725207,12075073366560449
|
|
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,860130,860135,4194304,256,0,0,24,24,159616,0x7f888eafa500,0x7f875ea36c40,1830128,1655167,24369593,65536,154709913,228765,228765,22934096,20750943,524288,524288,0,0,12075073366714466,12075076362784247,12075076362913046,12075073367127163
|
|
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,860130,860135,4194304,256,0,0,24,24,162368,0x7f888eafa400,0x7f875ea36c80,3060328,2894843,43089698,65536,352532119,382540,382540,15588908,13038409,524288,524288,0,0,12075073367351700,12075076362953205,12075076363196723,12075073367911440
|
|
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,860130,860135,4194304,256,0,0,24,24,164608,0x7f888eafa300,0x7f875ea36cc0,1773864,1598496,23446780,65536,155200486,221732,221732,21826948,19626356,524288,524288,0,0,12075073368088760,12075076363265203,12075076363394961,12075073368496728
|
|
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,860130,860135,4194304,256,0,0,20,24,166336,0x7f888eafaa00,0x7f875ea36d00,4905136,4428778,65995437,65536,540262983,613141,613141,64107068,55259207,0,524288,0,0,12075073368716506,12075076363431921,12075076363807118,12075073369455570
|
|
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,860130,860135,4194304,256,0,0,28,24,168576,0x7f888eafa900,0x7f875ea36d40,3280128,3060247,45367821,65536,316771851,410015,410015,44241104,35828308,0,524288,0,0,12075073369612241,12075076363864077,12075076364118955,12075073370220992
|
|
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,860130,860135,4194304,256,0,0,24,24,170816,0x7f888eafa800,0x7f875ea36d80,1829336,1658106,24405856,65536,174680823,228666,228666,22736948,20546456,524288,524288,0,0,12075073370378645,12075076364183595,12075076364313193,12075073370791342
|
|
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,860130,860135,4194304,256,0,0,24,24,174080,0x7f888eafa700,0x7f875ea36dc0,3489240,3304179,49177424,65536,401535406,436154,436154,15352220,12808223,524288,524288,0,0,12075073371019987,12075076364354633,12075076364633191,12075073371631133
|
|
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,860130,860135,4194304,256,0,0,24,24,176576,0x7f888eafa600,0x7f875ea36e00,1791488,1617736,23772712,65536,163294466,223935,223935,21355540,19098902,524288,524288,0,0,12075073371801549,12075076364700710,12075076364835749,12075073372218053
|
|
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,860130,860135,4194304,256,0,0,20,24,177792,0x7f888eafa500,0x7f875ea36e40,5182040,5008529,74657618,65536,613103411,647754,647754,70350212,61169921,0,524288,0,0,12075073372432352,12075076364877829,12075076365300225,12075073373193356
|
|
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,860130,860135,4194304,256,0,0,28,24,180288,0x7f888eafa400,0x7f875ea36e80,3254656,3056284,45299480,65536,292299915,406831,406831,42754256,34287702,0,524288,0,0,12075073373352341,12075076365363744,12075076365619422,12075073373953008
|
|
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,860130,860135,4194304,256,0,0,24,24,182784,0x7f888eafa300,0x7f875ea36ec0,1799336,1624470,24036338,65536,178275487,224916,224916,21447400,19172172,524288,524288,0,0,12075073374108697,12075076365680062,12075076365815421,12075073374521825
|
|
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,860130,860135,4194304,256,0,0,24,24,186304,0x7f888eafaa00,0x7f875ea36f00,3897648,3737316,55631870,65536,454953142,487205,487205,16214260,13627700,524288,524288,0,0,12075073374722347,12075076365856220,12075076366170298,12075073375371073
|
|
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,860130,860135,4194304,256,0,0,24,24,189312,0x7f888eafa900,0x7f875ea36f40,1960424,1780666,26483372,65536,214596363,245052,245052,21353208,18774618,524288,524288,0,0,12075073375539546,12075076366243737,12075076366394136,12075073375962362
|
|
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,860130,860135,4194304,256,0,0,20,24,190784,0x7f888eafa800,0x7f875ea36f80,6496104,6123286,91326848,65536,751074806,812012,812012,82896628,73135566,0,524288,0,0,12075073376185637,12075076366435575,12075076366951891,12075073377053579
|
|
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,860130,860135,4194304,256,0,0,28,24,193792,0x7f888eafa700,0x7f875ea36fc0,3678808,3483952,51625851,65536,383092520,459850,459850,40102984,31418442,0,524288,0,0,12075073377215200,12075076367018290,12075076367315728,12075073377853145
|
|
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,860130,860135,4194304,256,0,0,24,24,196800,0x7f888eafa600,0x7f875ea37000,1970072,1809665,26878631,65536,218320895,246258,246258,22052748,19449535,524288,524288,0,0,12075073378019094,12075076367379567,12075076367533966,12075073378450075
|
|
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,860130,860135,4194304,256,0,0,24,24,201088,0x7f888eafa500,0x7f875ea37040,5057344,4582416,68385161,65536,556794547,632167,632167,15175204,12632671,524288,524288,0,0,12075073378674642,12075076367574925,12075076367958762,12075073379426650
|
|
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,860130,860135,4194304,256,0,0,24,24,204608,0x7f888eafa400,0x7f875ea37080,2236648,2066054,30721130,65536,249842821,279580,279580,21397068,18708535,524288,524288,0,0,12075073379590334,12075076368040041,12075076368216680,12075073380035641
|
|
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,860130,860135,4194304,256,0,0,20,24,206080,0x7f888eafa300,0x7f875ea370c0,7405544,7233598,107963789,65536,889667074,925692,925692,90358212,79844846,0,524288,0,0,12075073380248938,12075076368257640,12075076368866594,12075073381196318
|
|
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,860130,860135,4194304,256,0,0,28,24,209600,0x7f888eafaa00,0x7f875ea37100,4037824,3852346,57286717,65536,454129688,504727,504727,36437892,27510882,0,524288,0,0,12075073381351517,12075076368927714,12075076369255391,12075073382022183
|
|
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,860130,860135,4194304,256,0,0,24,24,213120,0x7f888eafa900,0x7f875ea37140,2268760,2099699,31224805,65536,254052084,283594,283594,22043656,19352511,524288,524288,0,0,12075073382178423,12075076369322910,12075076369500349,12075073382631105
|
|
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,860130,860135,4194304,256,0,0,24,24,218176,0x7f888eafa800,0x7f875ea37180,5583488,5423540,80939539,65536,665992877,697935,697935,16741712,14213083,524288,524288,0,0,12075073382830675,12075076369542268,12075076369997305,12075073383624541
|
|
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,860130,860135,4194304,256,0,0,24,24,222208,0x7f888eafa700,0x7f875ea371c0,2520088,2342996,34828193,65536,281168276,315010,315010,21418824,18682621,524288,524288,0,0,12075073383793515,12075076370070424,12075076370308182,12075073384330653
|
|
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,860130,860135,4194304,256,0,0,20,24,223936,0x7f888eafa600,0x7f875ea37200,8598888,8357287,124762092,65536,1028613580,1074860,1074860,96386396,85426714,0,524288,0,0,12075073384485421,12075076370369301,12075076371071695,12075073385529170
|
|
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,860130,860135,4194304,256,0,0,28,24,227968,0x7f888eafa500,0x7f875ea37240,4548656,4376270,65188259,65536,532788639,568581,568581,34231188,25216385,0,524288,0,0,12075073385691091,12075076371135055,12075076371506572,12075073386402122
|
|
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,860130,860135,4194304,256,0,0,24,24,232000,0x7f888eafa400,0x7f875ea37280,2977840,2378962,35415060,65536,288188305,372229,372229,20930612,18214608,524288,524288,0,0,12075073386559515,12075076371568651,12075076371770729,12075073387134173
|
|
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,860130,860135,4194304,256,0,0,24,24,237824,0x7f888eafa300,0x7f875ea372c0,6641280,6259938,93448287,65536,759551662,830159,830159,15698920,13171057,524288,524288,0,0,12075073387290604,12075076371831049,12075076372356644,12075073388170158
|
|
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,860130,860135,4194304,256,0,0,24,24,242368,0x7f888eafaa00,0x7f875ea37300,3217496,2640453,39281788,65536,321220248,402186,402186,20684120,17960871,524288,524288,0,0,12075073388340294,12075076372436804,12075076372660002,12075073388935310
|
|
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,860130,860135,4194304,256,0,0,20,24,243584,0x7f888eafa900,0x7f875ea37340,9688432,9491992,141741118,65536,1169910386,1211053,1211053,104780276,93288444,0,524288,0,0,12075073389090088,12075076372721281,12075076373518554,12075073390221530
|
|
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,860130,860135,4194304,256,0,0,28,24,248128,0x7f888eafa800,0x7f875ea37380,5106480,4941376,73659647,65536,600312553,638309,638309,35740708,26661626,0,524288,0,0,12075073390382490,12075076373579834,12075076373997110,12075073391142121
|
|
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,860130,860135,4194304,256,0,0,24,24,252672,0x7f888eafa700,0x7f875ea373c0,2831088,2655248,39467637,65536,322169105,353885,353885,21838476,19069987,524288,524288,0,0,12075073391295627,12075076374056630,12075076374281588,12075073391828377
|
|
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,860130,860135,4194304,256,0,0,24,24,259264,0x7f888eafa600,0x7f875ea37400,7275648,7109399,106100271,65536,873324961,909455,909455,17624820,15137045,524288,524288,0,0,12075073391991800,12075076374342387,12075076374938382,12075073392935594
|
|
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,860130,860135,4194304,256,0,0,24,24,264832,0x7f888eafa500,0x7f875ea37440,3342320,3179228,47301815,65536,386797814,417789,417789,17002224,14399156,524288,524288,0,0,12075073393104107,12075076375012301,12075076375280779,12075073393711336
|
|
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,860130,860135,4194304,256,0,0,20,24,266304,0x7f888eafa400,0x7f875ea37480,11904488,11740275,175309950,65536,1447545826,1488060,1488060,111369980,99303227,0,524288,0,0,12075073393867576,12075076375346539,12075076376329570,12075073395200543
|
|
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,860130,860135,4194304,256,0,0,28,24,271872,0x7f888eafa300,0x7f875ea374c0,6426392,6050702,90243407,65536,738546367,803298,803298,32140820,23131229,0,524288,0,0,12075073395355080,12075076376390850,12075076376903805,12075073396226049
|
|
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,860130,860135,4194304,256,0,0,24,24,277440,0x7f888eafaa00,0x7f875ea37500,3392920,3218539,47779410,65536,387946241,424114,424114,17444616,14822426,524288,524288,0,0,12075073396386547,12075076376966525,12075076377237082,12075073396990840
|
|
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,860130,860135,4194304,256,0,0,12,24,279936,0x7f888eafa900,0x7f875ea37540,9016920,8852091,132203781,65536,1091561562,1127114,1127114,100321888,95423745,524288,524288,0,0,12075073397147421,12075076377304602,12075076378040915,12075073398223361
|
|
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,860130,860135,4194304,256,0,0,24,24,286528,0x7f888eafa800,0x7f875ea37580,3909080,3739744,55688345,65536,455016471,488634,488634,17007948,14400830,524288,524288,0,0,12075073398393737,12075076378113555,12075076378456752,12075073399041401
|
|
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,860130,860135,4194304,256,0,0,20,24,288000,0x7f888eafa700,0x7f875ea375c0,14153432,13979711,208799402,65536,1725800112,1769178,1769178,131910312,118727086,0,524288,0,0,12075073399196359,12075076378516911,12075076379685381,12075073400702498
|
|
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,860130,860135,4194304,256,0,0,32,24,294592,0x7f888eafa600,0x7f875ea37600,7365120,7198011,107373932,65536,810900088,920639,920639,36234564,27116853,0,524288,0,0,12075073400863738,12075076379748101,12075076380358975,12075073401819213
|
|
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,860130,860135,4194304,256,0,0,24,24,301184,0x7f888eafa500,0x7f875ea37640,3941680,3770736,56122488,65536,459303818,492709,492709,17080956,14473576,524288,524288,0,0,12075073401971416,12075076380421855,12075076380740252,12075073402626994
|
|
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,860130,860135,4194304,256,0,0,12,24,304960,0x7f888eafa400,0x7f875ea37680,10687280,10527917,157258355,65536,1299168761,1335909,1335909,104056840,98547442,524288,524288,0,0,12075073402765882,12075076380801692,12075076381678644,12075073403994866
|
|
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,860130,860135,4194304,256,0,0,24,24,313600,0x7f888eafa300,0x7f875ea376c0,5025216,4849882,72349608,65536,594029371,628151,628151,16696120,14105580,524288,524288,0,0,12075073404162828,12075076381752403,12075076382163280,12075073404909436
|
|
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,860130,860135,4194304,256,0,0,20,24,314816,0x7f888eafaa00,0x7f875ea37700,18668016,18498220,276321484,65536,2282619338,2333501,2333501,133022284,119247717,0,524288,0,0,12075073405072299,12075076382228239,12075076383777506,12075073406952242
|
|
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,860130,860135,4194304,256,0,0,20,24,317568,0x7f888eafa900,0x7f875ea37740,9620672,9448228,141048261,65536,1161345060,1202583,1202583,113215580,101598421,0,524288,0,0,12075073407108412,12075076383863585,12075076384656698,12075073408240336
|
|
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,860130,860135,4194304,256,0,0,12,24,320320,0x7f888eafa800,0x7f875ea37780,5125144,4961189,73990070,65536,608595549,640642,640642,69224408,66197319,524288,524288,0,0,12075073408395344,12075076384749011,12075076385162288,12075073409144156
|
|
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,860130,860135,4194304,256,0,0,12,24,324096,0x7f888eafa700,0x7f875ea377c0,14070144,13907167,207629515,65536,1714093337,1758767,1758767,117638292,111304649,524288,524288,0,0,12075073409306698,12075076385252366,12075076386410278,12075073410797037
|
|
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,860130,860135,4194304,256,0,0,12,24,328896,0x7f888eafa600,0x7f875ea37800,9585560,9423299,140685779,65536,1161278383,1198194,1198194,97080416,91903264,524288,524288,0,0,12075073410968997,12075076386505797,12075076387291072,12075073412112632
|
|
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,860130,860135,4194304,256,0,0,20,24,330112,0x7f888eafa500,0x7f875ea37840,36670424,36503696,545529091,65536,4515506891,4583802,4583802,174915852,159476753,0,524288,0,0,12075073412236763,12075076387378111,12075076390428329,12075073415853244
|
|
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,860130,860135,4194304,256,0,0,20,24,332864,0x7f888eafa400,0x7f875ea37880,18603096,18432547,275337598,65536,2275767280,2325386,2325386,144669928,129883527,0,524288,0,0,12075073415984157,12075076390513449,12075076392054558,12075073417858901
|
|
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,860130,860135,4194304,256,0,0,12,24,335616,0x7f888eafa300,0x7f875ea378c0,9635800,9463185,141288854,65536,1164249916,1204474,1204474,91788996,87014972,524288,524288,0,0,12075073418026893,12075076392143517,12075076392931831,12075073419137617
|
|
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,860130,860135,4194304,256,0,0,12,24,339392,0x7f888eafaa00,0x7f875ea37900,27556400,27385493,409083666,65536,3384030933,3444549,3444549,146864152,138744338,524288,524288,0,0,12075073419300981,12075076393018871,12075076395300134,12075073421923394
|
|
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,860130,860135,4194304,256,0,0,12,24,344192,0x7f888eafa900,0x7f875ea37940,18594024,18424628,275288834,65536,2276480584,2324252,2324252,126023368,119316380,524288,524288,0,0,12075073422095464,12075076395403654,12075076396938843,12075073423969246
|
|
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,860130,860135,4194304,256,0,0,20,24,345408,0x7f888eafa800,0x7f875ea37980,72696320,72533013,1084093852,65536,8978280433,9087039,9087039,179153896,164424792,0,524288,0,0,12075073424123372,12075076397030682,12075076403085519,12075073430509861
|
|
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,860130,860135,4194304,256,0,0,20,24,348160,0x7f888eafa700,0x7f875ea379c0,36600112,36426707,544226257,65536,4503734907,4575013,4575013,182863248,168392951,0,524288,0,0,12075073430671060,12075076403175438,12075076406216696,12075073434056842
|
|
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,860130,860135,4194304,256,0,0,12,24,350912,0x7f888eafa600,0x7f875ea37a00,18635992,18461539,275771383,65536,2278775389,2329498,2329498,133964716,126489888,524288,524288,0,0,12075073434209717,12075076406308536,12075076407846285,12075073436089039
|
|
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,860130,860135,4194304,256,0,0,12,24,0,0x7f888eafa500,0x7f875ea37a40,54527232,54341249,812101453,65536,6723913800,6815903,6815903,149950428,141914091,524288,524288,0,0,12075073436250108,12075076407934764,12075076412460012,12075073441111493
|