169 lines
63 KiB
CSV
169 lines
63 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,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,DispatchNs,BeginNs,EndNs,CompleteNs
|
|
0,__amd_rocclr_fillBuffer.kd,0,0,0,855764,855769,33554432,256,0,0,8,32,6464,0x0,0x7fb575604180,4036048,3830361,57276432,524288,368613040,336,144,0,504505,504505,0,0,480,0,6291456,6289559,96,2065,2135034,0,0,4194304,4189868,144,4292,2097152,524288,1572864,12074964410272267,12074968630893202,12074968631219119,12074964656414640
|
|
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,855764,855769,32768,256,0,0,24,24,12480,0x0,0x7fb575635100,222552,77206,1085921,512,1157151,432,48,0,27818,27818,0,0,480,0,8192,6581,48,1563,1092,0,0,512,0,48,464,0,512,0,12074964670870775,12074968646292397,12074968646299117,12074964671216828
|
|
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,855764,855769,4194304,256,0,0,24,24,12928,0x7fb681303900,0x7fb575635140,1758432,1592376,23570750,65536,137358092,384,48,0,219803,219803,0,0,432,0,917504,914195,71,5918,183298,0,0,65536,64048,48,1440,0,65536,0,12074964671293881,12074968646365997,12074968646499116,12074964671663969
|
|
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,855764,855769,4194304,256,0,0,36,24,13632,0x7fb681303800,0x7fb575635180,3224720,3064797,45523838,65536,218882707,480,48,0,403089,403089,0,0,528,0,1245184,1240523,48,7640,173776,0,0,65536,64048,48,1440,0,65536,0,12074964671747344,12074968646563435,12074968646810313,12074964672272169
|
|
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,855764,855769,4194304,256,0,0,28,24,14080,0x7fb681303700,0x7fb5756351c0,3130656,2955075,44101137,65536,350097458,384,48,0,391331,391331,0,0,432,0,983040,978377,48,4779,202588,0,0,65536,64048,48,1440,0,65536,0,12074964672308887,12074968646927592,12074968647170950,12074964672826089
|
|
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,855764,855769,4194304,256,0,0,24,24,14528,0x7fb681303600,0x7fb575635200,1752848,1591069,23543179,65536,130067352,432,48,0,219105,219105,0,0,480,0,1048576,1045867,48,7366,203005,0,0,65536,64048,48,1440,0,65536,0,12074964672852488,12074968647293989,12074968647419428,12074964673204512
|
|
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,855764,855769,4194304,256,0,0,24,24,14976,0x7fb681303500,0x7fb575635240,1820896,1659110,24459637,65536,114697604,432,48,0,227611,227611,0,0,480,0,983040,979976,48,8208,142525,0,0,65536,64048,48,1440,0,65536,0,12074964673270254,12074968647459428,12074968647583907,12074964673609665
|
|
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,855764,855769,4194304,256,0,0,24,24,15424,0x7fb681303400,0x7fb575635280,1738896,1577594,23319889,65536,142911781,432,48,0,217361,217361,0,0,480,0,1048576,1046278,48,4472,197327,0,0,131072,129584,48,1440,65536,65536,0,12074964673701736,12074968647655107,12074968647778626,12074964674019587
|
|
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,855764,855769,4194304,256,0,0,28,24,16128,0x7fb681303300,0x7fb5756352c0,3234592,3056611,45441412,65536,258011868,624,48,0,404323,404323,0,0,672,0,1572864,1568147,114,6922,174805,0,0,131072,129584,48,1440,0,131072,0,12074964674081962,12074968647821665,12074968648068863,12074964674588714
|
|
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,855764,855769,4194304,256,0,0,28,24,16832,0x7fb681303a00,0x7fb575635300,3188688,3030571,45269984,65536,348889442,480,48,0,398585,398585,0,0,528,0,1179648,1177442,48,3647,179464,0,0,65536,64048,48,1440,0,0,65536,12074964674624871,12074968648185022,12074968648427580,12074964675141001
|
|
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,855764,855769,4194304,256,0,0,24,24,17536,0x7fb681303900,0x7fb575635340,1728992,1562563,23128870,65536,155670465,480,48,0,216123,216123,0,0,528,0,1114112,1111738,48,4924,194348,0,0,131072,129584,48,1440,65536,65536,0,12074964675165847,12074968648539739,12074968648664058,12074964675518252
|
|
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,855764,855769,4194304,256,0,0,24,24,18240,0x7fb681303800,0x7fb575635380,1784848,1600451,23688956,65536,126015548,480,48,0,223105,223105,0,0,528,0,1114112,1111576,48,4706,200355,0,0,131072,129584,48,1440,65536,65536,0,12074964675582130,12074968648708058,12074968648832377,12074964675919026
|
|
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,855764,855769,4194304,256,0,0,24,24,18944,0x7fb681303700,0x7fb5756353c0,1725920,1558943,23069098,65536,156334516,480,48,0,215739,215739,0,0,528,0,1179648,1177217,48,4594,198553,0,0,131072,129584,48,1440,65536,65536,0,12074964675998123,12074968648891737,12074968649016216,12074964676320242
|
|
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,855764,855769,4194304,256,0,0,28,24,19904,0x7fb681303600,0x7fb575635400,3233680,3069736,45775917,65536,321436087,720,48,0,404209,404209,0,0,768,0,1835008,1831699,118,5938,174961,0,0,131072,129584,48,1440,0,131072,0,12074964676384551,12074968649059895,12074968649310133,12074964676906722
|
|
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,855764,855769,4194304,256,0,0,28,24,20608,0x7fb681303500,0x7fb575635440,3180256,3011304,44794710,65536,229965881,528,48,0,397531,397531,0,0,576,0,1310720,1308534,48,3442,177185,0,0,65536,64048,48,1440,0,0,65536,12074964676931388,12074968649398133,12074968649647891,12074964677473044
|
|
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,855764,855769,4194304,256,0,0,24,24,21312,0x7fb681303400,0x7fb575635480,1730832,1572793,23309074,65536,149712617,528,48,0,216353,216353,0,0,576,0,1245184,1241915,48,6030,190123,0,0,131072,129584,48,1440,65536,65536,0,12074964677497309,12074968649729810,12074968649854289,12074964677841018
|
|
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,855764,855769,4194304,256,0,0,24,24,22016,0x7fb681303300,0x7fb5756354c0,1746144,1581885,23436597,65536,138504884,528,48,0,218267,218267,0,0,576,0,1310720,1308091,48,4714,166951,0,0,131072,129584,48,1440,65536,65536,0,12074964677906059,12074968649895729,12074968650021328,12074964678240090
|
|
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,855764,855769,4194304,256,0,0,24,24,22720,0x7fb681303a00,0x7fb575635500,1688080,1529413,22690753,65536,164117570,528,48,0,211009,211009,0,0,576,0,1310720,1308229,48,4685,193330,0,0,131072,129584,48,1440,65536,65536,0,12074964678317323,12074968650076207,12074968650200686,12074964678635234
|
|
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,855764,855769,4194304,256,0,0,28,24,23680,0x7fb681303900,0x7fb575635540,3118816,2944330,43918600,65536,348945966,816,48,0,389851,389851,0,0,864,0,2097152,2093032,96,8444,177770,0,0,131072,129584,48,1440,0,131072,0,12074964678698932,12074968650243886,12074968650489004,12074964679212908
|
|
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,855764,855769,4194304,256,0,0,28,24,24384,0x7fb681303800,0x7fb575635580,3211792,3023729,45069239,65536,223059142,576,48,0,401473,401473,0,0,624,0,1441792,1439509,48,3619,179187,0,0,65536,64048,48,1440,0,0,65536,12074964679238445,12074968650544843,12074968650790281,12074964679740789
|
|
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,855764,855769,4194304,256,0,0,24,24,25088,0x7fb681303700,0x7fb5756355c0,1740896,1567237,23229025,65536,152828434,576,48,0,217611,217611,0,0,624,0,1376256,1373602,48,5230,196164,0,0,131072,129584,48,1440,65536,65536,0,12074964679782065,12074968650872841,12074968650997800,12074964680099475
|
|
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,855764,855769,4194304,256,0,0,24,24,25792,0x7fb681303600,0x7fb575635600,1760976,1599279,23688735,65536,135706447,624,48,0,220121,220121,0,0,672,0,1507328,1504330,48,5143,201431,0,0,131072,129584,48,1440,65536,65536,0,12074964680161821,12074968651042279,12074968651167718,12074964680499398
|
|
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,855764,855769,4194304,256,0,0,24,24,26496,0x7fb681303500,0x7fb575635640,1787616,1616780,23913364,65536,133806081,576,48,0,223451,223451,0,0,624,0,1441792,1439137,48,5156,198252,0,0,131072,129584,48,1440,65536,65536,0,12074964680575780,12074968651223718,12074968651348357,12074964680889373
|
|
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,855764,855769,4194304,256,0,0,28,24,27712,0x7fb681303400,0x7fb575635680,3232592,3070978,45752594,65536,341095472,912,48,0,404073,404073,0,0,960,0,2359296,2355536,118,6273,204002,0,0,131072,129584,48,1440,0,131072,0,12074964680951779,12074968651390917,12074968651647235,12074964681473789
|
|
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,855764,855769,4194304,256,0,0,28,24,28416,0x7fb681303300,0x7fb5756356c0,3213152,3041350,45302210,65536,295357039,624,48,0,401643,401643,0,0,672,0,1572864,1570137,48,3802,179815,0,0,65536,64048,48,1440,0,0,65536,12074964681498245,12074968651704674,12074968651985152,12074964682026406
|
|
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,855764,855769,4194304,256,0,0,24,24,29120,0x7fb681303a00,0x7fb575635700,1706576,1544758,22831973,65536,142141854,624,48,0,213321,213321,0,0,672,0,1507328,1504641,48,4939,190234,0,0,131072,129584,48,1440,65536,65536,0,12074964682049239,12074968652069311,12074968652193950,12074964682388810
|
|
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,855764,855769,4194304,256,0,0,24,24,30080,0x7fb681303900,0x7fb575635740,1717344,1540782,22769055,65536,145789233,672,48,0,214667,214667,0,0,720,0,1703936,1700490,48,5580,191555,0,0,131072,129584,48,1440,65536,65536,0,12074964682452067,12074968652236990,12074968652362749,12074964682778323
|
|
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,855764,855769,4194304,256,0,0,24,24,30784,0x7fb681303800,0x7fb575635780,1700304,1542277,22813677,65536,147557013,576,48,0,212537,212537,0,0,624,0,1572864,1569758,48,5328,192139,0,0,131072,129584,48,1440,65536,65536,0,12074964682852561,12074968652417148,12074968652541627,12074964683173889
|
|
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,855764,855769,4194304,256,0,0,28,24,32000,0x7fb681303700,0x7fb5756357c0,3188384,3007110,44754203,65536,307360649,1008,48,0,398547,398547,0,0,1056,0,2621440,2617549,48,8491,180493,0,0,131072,129584,48,1440,0,131072,0,12074964683239100,12074968652583707,12074968652830585,12074964683755920
|
|
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,855764,855769,4194304,256,0,0,28,24,32960,0x7fb681303600,0x7fb575635800,3166992,2985439,44526586,65536,264822204,672,48,0,395873,395873,0,0,720,0,1703936,1701156,48,3786,180209,0,0,65536,64048,48,1440,0,0,65536,12074964683780636,12074968652918424,12074968653165622,12074964684302105
|
|
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,855764,855769,4194304,256,0,0,24,24,33920,0x7fb681303500,0x7fb575635840,1685280,1517209,22495042,65536,160524310,672,48,0,210659,210659,0,0,720,0,1638400,1634918,48,5689,196225,0,0,131072,129584,48,1440,65536,65536,0,12074964684327342,12074968653279861,12074968653404020,12074964684656654
|
|
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,855764,855769,4194304,256,0,0,24,24,34880,0x7fb681303400,0x7fb575635880,2244816,1558967,23045840,65536,150629964,768,48,0,280601,280601,0,0,816,0,1900544,1894205,96,8561,191027,0,0,131072,129584,48,1440,65536,65536,0,12074964684719691,12074968653445140,12074968653570899,12074964685086904
|
|
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,855764,855769,4194304,256,0,0,24,24,35840,0x7fb681303300,0x7fb5756358c0,1766944,1593054,23566933,65536,132015965,672,48,0,220867,220867,0,0,720,0,1703936,1700987,48,5072,196881,0,0,131072,129584,48,1440,65536,65536,0,12074964685189174,12074968653623859,12074968653748818,12074964685506904
|
|
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,855764,855769,4194304,256,0,0,28,24,37312,0x7fb681303a00,0x7fb575635900,3219024,3063820,45618851,65536,339639539,1104,48,0,402377,402377,0,0,1152,0,2883584,2878239,48,10377,172347,0,0,131072,129584,48,1440,0,131072,0,12074964685571765,12074968653792657,12074968654045935,12074964686085379
|
|
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,855764,855769,4194304,256,0,0,28,24,38272,0x7fb681303900,0x7fb575635940,3193184,3028925,45149746,65536,311805076,720,48,0,399147,399147,0,0,768,0,1835008,1832250,48,4424,182746,0,0,65536,64048,48,1440,0,0,65536,12074964686108041,12074968654164654,12074968654413772,12074964686636323
|
|
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,855764,855769,4194304,256,0,0,24,24,39232,0x7fb681303800,0x7fb575635980,1744208,1587601,23492165,65536,141938758,720,48,0,218025,218025,0,0,768,0,1769472,1764267,96,8662,189859,0,0,131072,129584,48,1440,65536,65536,0,12074964686659787,12074968654522892,12074968654647531,12074964687005048
|
|
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,855764,855769,4194304,256,0,0,24,24,40192,0x7fb681303700,0x7fb5756359c0,1752416,1579007,23285004,65536,148442791,816,48,0,219051,219051,0,0,864,0,2097152,2090654,48,8983,158336,0,0,131072,129584,48,1440,65536,65536,0,12074964687067043,12074968654689130,12074968654815369,12074964687403849
|
|
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,855764,855769,4194304,256,0,0,24,24,41152,0x7fb681303600,0x7fb575635a00,1734928,1572056,23290555,65536,143718085,720,48,0,216865,216865,0,0,768,0,1835008,1831446,48,5693,198181,0,0,131072,129584,48,1440,65536,65536,0,12074964687479570,12074968654868969,12074968654993448,12074964687790839
|
|
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,855764,855769,4194304,256,0,0,28,24,42624,0x7fb681303500,0x7fb575635a40,3182048,3009092,44782789,65536,323300900,1200,48,0,397755,397755,0,0,1248,0,3145728,3140607,117,7725,182704,0,0,131072,129584,48,1440,0,131072,0,12074964687854096,12074968655041927,12074968655291045,12074964688373301
|
|
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,855764,855769,4194304,256,0,0,28,24,43584,0x7fb681303400,0x7fb575635a80,3187024,3032695,45203067,65536,240700847,768,48,0,398377,398377,0,0,816,0,1966080,1962918,48,4801,173854,0,0,65536,64048,48,1440,0,0,65536,12074964688396935,12074968655380165,12074968655625603,12074964688923604
|
|
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,855764,855769,4194304,256,0,0,24,24,44544,0x7fb681303300,0x7fb575635ac0,1686624,1512136,22385282,65536,163757532,768,48,0,210827,210827,0,0,816,0,1900544,1897098,48,5806,196875,0,0,131072,129584,48,1440,65536,65536,0,12074964688947378,12074968655708962,12074968655834241,12074964689286418
|
|
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,855764,855769,4194304,256,0,0,24,24,45760,0x7fb681303a00,0x7fb575635b00,1782352,1598003,23537980,65536,157049144,912,48,0,222793,222793,0,0,960,0,2293760,2288158,48,7844,195748,0,0,131072,129584,48,1440,65536,65536,0,12074964689352972,12074968655877601,12074968656003040,12074964689679749
|
|
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,855764,855769,4194304,256,0,0,24,24,46720,0x7fb681303900,0x7fb575635b40,1711904,1550470,22931198,65536,150461668,768,48,0,213987,213987,0,0,816,0,1966080,1962002,96,6213,168078,0,0,131072,129584,48,1440,65536,65536,0,12074964689757263,12074968656054879,12074968656179518,12074964690066998
|
|
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,855764,855769,4194304,256,0,0,28,24,48448,0x7fb681303800,0x7fb575635b80,3342096,3169009,47138863,65536,348590918,1296,48,0,417761,417761,0,0,1344,0,3407872,3401766,49,11139,179864,0,0,131072,129584,48,1440,0,131072,0,12074964690130336,12074968656222078,12074968656481276,12074964690655953
|
|
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,855764,855769,4194304,256,0,0,28,24,49408,0x7fb681303700,0x7fb575635bc0,3237792,3064091,45611450,65536,269944544,816,48,0,404723,404723,0,0,864,0,2097152,2094398,48,3983,177200,0,0,65536,64048,48,1440,0,0,65536,12074964690679386,12074968656536635,12074968656784473,12074964691208420
|
|
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,855764,855769,4194304,256,0,0,24,24,50368,0x7fb681303600,0x7fb575635c00,1727376,1572724,23276226,65536,143698935,816,48,0,215921,215921,0,0,864,0,2031616,2024811,96,9148,198863,0,0,131072,129584,48,1440,65536,65536,0,12074964691232064,12074968656840473,12074968656965112,12074964691567988
|
|
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,855764,855769,4194304,256,0,0,24,24,51584,0x7fb681303500,0x7fb575635c40,1826976,1646103,24254220,65536,135942786,960,48,0,228371,228371,0,0,1008,0,2490368,2485112,48,8619,199106,0,0,131072,129584,48,1440,65536,65536,0,12074964691624132,12074968657013272,12074968657139511,12074964691961309
|
|
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,855764,855769,4194304,256,0,0,24,24,52544,0x7fb681303400,0x7fb575635c80,1741136,1580449,23375040,65536,149214750,816,48,0,217641,217641,0,0,864,0,2097152,2092261,48,7086,193856,0,0,131072,129584,48,1440,65536,65536,0,12074964692042640,12074968657194230,12074968657319189,12074964692355992
|
|
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,855764,855769,4194304,256,0,0,28,24,54272,0x7fb681303300,0x7fb575635cc0,3326688,3143429,46738029,65536,276872363,1392,48,0,415835,415835,0,0,1440,0,3670016,3665400,97,9233,175017,0,0,131072,129584,48,1440,0,131072,0,12074964692418238,12074968657361429,12074968657615347,12074964692943043
|
|
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,855764,855769,4194304,256,0,0,28,24,55488,0x7fb681303a00,0x7fb575635d00,3191312,3010603,44808268,65536,223461491,864,48,0,398913,398913,0,0,912,0,2228224,2224235,48,5276,174120,0,0,65536,64048,48,1440,0,0,65536,12074964692965956,12074968657671506,12074968657918064,12074964693494378
|
|
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,855764,855769,4194304,256,0,0,24,24,56704,0x7fb681303900,0x7fb575635d40,1739104,1576304,23284500,65536,154608983,864,48,0,217387,217387,0,0,912,0,2162688,2156590,48,8325,197195,0,0,131072,129584,48,1440,65536,65536,0,12074964693518182,12074968657973104,12074968658097743,12074964693851231
|
|
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,855764,855769,4194304,256,0,0,24,24,58176,0x7fb681303800,0x7fb575635d80,1825680,1643440,24199994,65536,154623494,1056,48,0,228209,228209,0,0,1104,0,2686976,2676334,96,13067,193043,0,0,131072,129584,48,1440,65536,65536,0,12074964693913947,12074968658139983,12074968658267182,12074964694260622
|
|
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,855764,855769,4194304,256,0,0,24,24,59392,0x7fb681303700,0x7fb575635dc0,1727776,1557283,23059558,65536,142823402,864,48,0,215971,215971,0,0,912,0,2228224,2222068,48,8997,194634,0,0,131072,129584,48,1440,65536,65536,0,12074964694339128,12074968658320941,12074968658446220,12074964694651538
|
|
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,855764,855769,4194304,256,0,0,28,24,61376,0x7fb681303600,0x7fb575635e00,3305872,3134177,46547556,65536,302918270,1488,48,0,413233,413233,0,0,1536,0,3932160,3926378,48,10270,195601,0,0,131072,129584,48,1440,0,131072,0,12074964694717551,12074968658489260,12074968658743658,12074964695246163
|
|
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,855764,855769,4194304,256,0,0,28,24,62592,0x7fb681303500,0x7fb575635e40,3236128,3067294,45721963,65536,264049311,912,48,0,404515,404515,0,0,960,0,2359296,2356129,96,4441,178387,0,0,65536,64048,48,1440,0,0,65536,12074964695271320,12074968658800137,12074968659044295,12074964695796326
|
|
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,855764,855769,4194304,256,0,0,24,24,63808,0x7fb681303400,0x7fb575635e80,1772560,1590541,23529976,65536,155263760,912,48,0,221569,221569,0,0,960,0,2293760,2288945,48,7943,190032,0,0,131072,129584,48,1440,65536,65536,0,12074964695820050,12074968659109255,12074968659234694,12074964696155734
|
|
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,855764,855769,4194304,256,0,0,24,24,65280,0x7fb681303300,0x7fb575635ec0,1757408,1586317,23231720,65536,174715330,1104,48,0,219675,219675,0,0,1152,0,2883584,2874852,48,10355,193456,0,0,131072,129584,48,1440,65536,65536,0,12074964696221826,12074968659274053,12074968659401892,12074964696548954
|
|
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,855764,855769,4194304,256,0,0,24,24,66496,0x7fb681303a00,0x7fb575635f00,1812240,1652154,24476343,65536,139719907,912,48,0,226529,226529,0,0,960,0,2359296,2353093,96,8901,191792,0,0,131072,129584,48,1440,65536,65536,0,12074964696625837,12074968659453892,12074968659579331,12074964696943948
|
|
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,855764,855769,4194304,256,0,0,28,24,68480,0x7fb681303900,0x7fb575635f40,3306784,3134602,46645719,65536,339132649,1584,48,0,413347,413347,0,0,1632,0,4194304,4185547,48,13950,199967,0,0,131072,129584,48,1440,0,131072,0,12074964697012556,12074968659622371,12074968659874209,12074964697535938
|
|
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,855764,855769,4194304,256,0,0,28,24,69696,0x7fb681303800,0x7fb575635f80,3240144,3058852,45471146,65536,262870252,960,48,0,405017,405017,0,0,1008,0,2490368,2486943,48,4453,196060,0,0,65536,64048,48,1440,0,0,65536,12074964697560704,12074968659930208,12074968660178686,12074964698087253
|
|
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,855764,855769,4194304,256,0,0,24,24,70912,0x7fb681303700,0x7fb575635fc0,1723936,1539212,22842676,65536,162487110,960,48,0,215491,215491,0,0,1008,0,2424832,2418485,48,9685,195709,0,0,131072,129584,48,1440,65536,65536,0,12074964698110636,12074968660239166,12074968660363965,12074964698457060
|
|
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,855764,855769,4194304,256,0,0,24,24,72384,0x7fb681303600,0x7fb575636000,1808464,1635454,24105834,65536,167168103,1200,48,0,226057,226057,0,0,1248,0,3080192,3068446,48,14401,220441,0,0,131072,129584,48,1440,65536,65536,0,12074964698521049,12074968660405404,12074968660543003,12074964698851884
|
|
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,855764,855769,4194304,256,0,0,24,24,73600,0x7fb681303500,0x7fb575636040,1801504,1623147,23986122,65536,138343377,960,48,0,225187,225187,0,0,1008,0,2490368,2484290,48,9226,193946,0,0,131072,129584,48,1440,65536,65536,0,12074964698927124,12074968660596443,12074968660722202,12074964699257758
|
|
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,855764,855769,4194304,256,0,0,28,24,75840,0x7fb681303400,0x7fb575636080,3376336,3183494,47281416,65536,317148975,1680,48,0,422041,422041,0,0,1728,0,4456448,4450726,49,11159,189172,0,0,131072,129584,48,1440,0,131072,0,12074964699321627,12074968660759642,12074968661027799,12074964699826054
|
|
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,855764,855769,4194304,256,0,0,28,24,77056,0x7fb681303300,0x7fb5756360c0,3198176,2994182,44659426,65536,294465831,1008,48,0,399771,399771,0,0,1056,0,2621440,2617134,48,5380,179980,0,0,65536,64048,48,1440,0,0,65536,12074964699862552,12074968661089399,12074968661337237,12074964700371418
|
|
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,855764,855769,4194304,256,0,0,24,24,78272,0x7fb681303a00,0x7fb575636100,1784016,1615455,23861918,65536,142501405,1008,48,0,223001,223001,0,0,1056,0,2555904,2548764,96,9625,196470,0,0,131072,129584,48,1440,65536,65536,0,12074964700395142,12074968661396276,12074968661521075,12074964700737779
|
|
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,855764,855769,4194304,256,0,0,24,24,80000,0x7fb681303900,0x7fb575636140,1842464,1675545,24808891,65536,198675803,1248,48,0,230307,230307,0,0,1296,0,3276800,3266028,57,18915,181153,0,0,131072,129584,48,1440,65536,65536,0,12074964700802429,12074968661562195,12074968661705234,12074964701146769
|
|
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,855764,855769,4194304,256,0,0,24,24,81216,0x7fb681303800,0x7fb575636180,1766800,1575448,23309614,65536,155998739,1008,48,0,220849,220849,0,0,1056,0,2621440,2611653,49,13296,192070,0,0,131072,129584,48,1440,65536,65536,0,12074964701225405,12074968661756274,12074968661881393,12074964701540560
|
|
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,855764,855769,4194304,256,0,0,28,24,83456,0x7fb681303700,0x7fb5756361c0,3347680,3166967,47061802,65536,325274117,1776,48,0,418459,418459,0,0,1824,0,4718592,4709031,96,13865,179915,0,0,131072,129584,48,1440,0,131072,0,12074964701607725,12074968661924752,12074968662177070,12074964702107734
|
|
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,855764,855769,4194304,256,0,0,28,24,84928,0x7fb681303600,0x7fb575636200,3219024,3046854,45340584,65536,292581072,1056,48,0,402377,402377,0,0,1104,0,2752512,2749271,49,4554,176357,0,0,65536,64048,48,1440,0,0,65536,12074964702144052,12074968662238510,12074968662484748,12074964702632550
|
|
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,855764,855769,4194304,256,0,0,24,24,86400,0x7fb681303500,0x7fb575636240,1777632,1605148,23695839,65536,143501280,1056,48,0,222203,222203,0,0,1104,0,2686976,2678495,96,11133,176033,0,0,131072,129584,48,1440,65536,65536,0,12074964702674888,12074968662545867,12074968662671306,12074964702990896
|
|
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,855764,855769,4194304,256,0,0,24,24,88128,0x7fb681303400,0x7fb575636280,1924240,1763140,26185017,65536,208804862,1344,48,0,240529,240529,0,0,1392,0,3473408,3463102,48,13910,190696,0,0,131072,129584,48,1440,65536,65536,0,12074964703055125,12074968662713226,12074968662862825,12074964703395989
|
|
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,855764,855769,4194304,256,0,0,24,24,89600,0x7fb681303300,0x7fb5756362c0,1752288,1580380,23357955,65536,144890177,1056,48,0,219035,219035,0,0,1104,0,2752512,2743407,96,12927,191527,0,0,131072,129584,48,1440,65536,65536,0,12074964703490665,12074968662930184,12074968663055143,12074964703803857
|
|
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,855764,855769,4194304,256,0,0,28,24,92096,0x7fb681303a00,0x7fb575636300,3304016,3094228,46023385,65536,325951209,1872,48,0,413001,413001,0,0,1920,0,4980736,4971745,49,13119,174443,0,0,131072,129584,48,1440,0,131072,0,12074964703869519,12074968663101543,12074968663353541,12074964704410314
|
|
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,855764,855769,4194304,256,0,0,28,24,93568,0x7fb681303900,0x7fb575636340,3220384,3023580,44968504,65536,246433890,1104,48,0,402547,402547,0,0,1152,0,2883584,2879645,96,5001,178368,0,0,65536,64048,48,1440,0,0,65536,12074964704435991,12074968663414340,12074968663658498,12074964704959164
|
|
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,855764,855769,4194304,256,0,0,24,24,95040,0x7fb681303800,0x7fb575636380,1744400,1573087,23250941,65536,155217462,1104,48,0,218049,218049,0,0,1152,0,2818048,2809305,49,12801,197857,0,0,131072,129584,48,1440,65536,65536,0,12074964704984391,12074968663715778,12074968663841217,12074964705330464
|
|
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,855764,855769,4194304,256,0,0,24,24,96768,0x7fb681303700,0x7fb5756363c0,2027616,1858700,27619278,65536,222423756,1392,48,0,253451,253451,0,0,1440,0,3670016,3652339,48,23143,193326,0,0,131072,129584,48,1440,65536,65536,0,12074964705394072,12074968663884257,12074968664041375,12074964705749873
|
|
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,855764,855769,4194304,256,0,0,24,24,98240,0x7fb681303600,0x7fb575636400,1732496,1574154,23226890,65536,157985411,1104,48,0,216561,216561,0,0,1152,0,2883584,2874987,96,11243,201951,0,0,131072,129584,48,1440,65536,65536,0,12074964705825253,12074968664095455,12074968664220574,12074964706140759
|
|
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,855764,855769,4194304,256,0,0,28,24,100736,0x7fb681303500,0x7fb575636440,3300832,3109531,46086868,65536,320891515,1968,48,0,412603,412603,0,0,2016,0,5177344,5169574,48,11123,179320,0,0,131072,129584,48,1440,0,131072,0,12074964706204117,12074968664263773,12074968664518811,12074964706705759
|
|
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,855764,855769,4194304,256,0,0,28,24,102208,0x7fb681303400,0x7fb575636480,3188176,3023958,44962896,65536,290037277,1152,48,0,398521,398521,0,0,1200,0,3014656,3010181,96,5723,196581,0,0,65536,64048,48,1440,0,0,65536,12074964706742758,12074968664576091,12074968664821049,12074964707260550
|
|
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,855764,855769,4194304,256,0,0,24,24,103680,0x7fb681303300,0x7fb5756364c0,1815776,1638986,24259521,65536,147687210,1152,48,0,226971,226971,0,0,1200,0,2949120,2937898,49,17602,172324,0,0,131072,129584,48,1440,65536,65536,0,12074964707284886,12074968664877369,12074968665003128,12074964707631600
|
|
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,855764,855769,4194304,256,0,0,24,24,105664,0x7fb681303a00,0x7fb575636500,2102416,1946754,28963554,65536,235478047,1488,48,0,262801,262801,0,0,1536,0,3866624,3848712,101,22669,220310,0,0,131072,129584,48,1440,65536,65536,0,12074964707694347,12074968665046967,12074968665211766,12074964708051841
|
|
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,855764,855769,4194304,256,0,0,24,24,107136,0x7fb681303900,0x7fb575636540,1822368,1646552,24304500,65536,153511320,1152,48,0,227795,227795,0,0,1200,0,3014656,3008499,48,8903,192044,0,0,131072,129584,48,1440,65536,65536,0,12074964708128984,12074968665263925,12074968665389524,12074964708450171
|
|
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,855764,855769,4194304,256,0,0,28,24,109888,0x7fb681303800,0x7fb575636580,3337104,3158427,46746767,65536,336756191,2064,48,0,417137,417137,0,0,2112,0,5439488,5430197,99,12934,181083,0,0,131072,129584,48,1440,0,131072,0,12074964708513028,12074968665432404,12074968665688722,12074964709040588
|
|
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,855764,855769,4194304,256,0,0,28,24,111360,0x7fb681303700,0x7fb5756365c0,3169376,2991782,44620877,65536,350268389,1200,48,0,396171,396171,0,0,1248,0,3145728,3140710,48,6111,175944,0,0,65536,64048,48,1440,0,0,65536,12074964709064613,12074968665744882,12074968665992400,12074964709588416
|
|
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,855764,855769,4194304,256,0,0,24,24,112832,0x7fb681303600,0x7fb575636600,1801744,1634448,24158868,65536,146355198,1200,48,0,225217,225217,0,0,1248,0,3080192,3072131,48,10698,204820,0,0,131072,129584,48,1440,65536,65536,0,12074964709612732,12074968666053199,12074968666178158,12074964709951722
|
|
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,855764,855769,4194304,256,0,0,24,24,114816,0x7fb681303500,0x7fb575636640,2209504,2046797,30448707,65536,247563462,1536,48,0,276187,276187,0,0,1584,0,4063232,4048070,96,18932,215351,0,0,131072,129584,48,1440,65536,65536,0,12074964710020850,12074968666218798,12074968666390636,12074964710388193
|
|
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,855764,855769,4194304,256,0,0,24,24,116288,0x7fb681303400,0x7fb575636680,1723088,1556787,23015652,65536,152077224,1200,48,0,215385,215385,0,0,1248,0,3145728,3136377,49,13852,203037,0,0,131072,129584,48,1440,65536,65536,0,12074964710463212,12074968666442796,12074968666568875,12074964710777596
|
|
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,855764,855769,4194304,256,0,0,28,24,119040,0x7fb681303300,0x7fb5756366c0,3278048,3097407,46001779,65536,342460705,2160,48,0,409755,409755,0,0,2208,0,5701632,5686114,117,28530,194895,0,0,131072,129584,48,1440,0,131072,0,12074964710841084,12074968666611115,12074968666862953,12074964711368845
|
|
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,855764,855769,4194304,256,0,0,28,24,120768,0x7fb681303a00,0x7fb575636700,3146640,2971319,44267808,65536,329070311,1248,48,0,393329,393329,0,0,1296,0,3276800,3271427,50,6709,180130,0,0,65536,64048,48,1440,0,0,65536,12074964711393832,12074968666918312,12074968667168710,12074964711912906
|
|
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,855764,855769,4194304,256,0,0,24,24,122496,0x7fb681303900,0x7fb575636740,1799264,1641056,24253092,65536,141518113,1248,48,0,224907,224907,0,0,1296,0,3211264,3199578,102,17587,199211,0,0,131072,129584,48,1440,65536,65536,0,12074964711936831,12074968667233670,12074968667359589,12074964712279397
|
|
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,855764,855769,4194304,256,0,0,24,24,124736,0x7fb681303800,0x7fb575636780,2310224,2147979,31954698,65536,256638885,1632,48,0,288777,288777,0,0,1680,0,4259840,4246218,48,16641,212591,0,0,131072,129584,48,1440,65536,65536,0,12074964712342735,12074968667402788,12074968667585507,12074964712716119
|
|
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,855764,855769,4194304,256,0,0,24,24,126464,0x7fb681303700,0x7fb5756367c0,1758944,1589282,23456146,65536,145229397,1248,48,0,219867,219867,0,0,1296,0,3276800,3264849,108,20302,194145,0,0,131072,129584,48,1440,65536,65536,0,12074964712815504,12074968667638946,12074968667766145,12074964713131771
|
|
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,855764,855769,4194304,256,0,0,20,24,127936,0x7fb681303600,0x7fb575636800,3289872,3126557,46511693,65536,380606940,1200,48,0,411233,411233,0,0,1248,0,7733248,7730420,48,3195,197830,0,0,131072,129584,48,1440,0,131072,0,12074964713192985,12074968667808865,12074968668072223,12074964713719423
|
|
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,855764,855769,4194304,256,0,0,28,24,129664,0x7fb681303500,0x7fb575636840,3249056,3076406,45792267,65536,315334218,1296,48,0,406131,406131,0,0,1344,0,3407872,3400382,96,8633,177648,0,0,65536,64048,48,1440,0,0,65536,12074964713741464,12074968668134142,12074968668383260,12074964714269686
|
|
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,855764,855769,4194304,256,0,0,24,24,131392,0x7fb681303400,0x7fb575636880,1740496,1572532,23253565,65536,150470915,1296,48,0,217561,217561,0,0,1344,0,3342336,3331075,48,14450,189994,0,0,131072,129584,48,1440,65536,65536,0,12074964714292498,12074968668441500,12074968668567899,12074964714630707
|
|
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,855764,855769,4194304,256,0,0,24,24,133632,0x7fb681303300,0x7fb5756368c0,2424160,2259193,33562977,65536,273293979,1680,48,0,303019,303019,0,0,1728,0,4456448,4440795,96,18911,195359,0,0,131072,129584,48,1440,65536,65536,0,12074964714692933,12074968668612379,12074968668802617,12074964715125807
|
|
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,855764,855769,4194304,256,0,0,24,24,135360,0x7fb681303a00,0x7fb575636900,1709904,1518049,22397134,65536,152813831,1344,48,0,213737,213737,0,0,1392,0,3538944,3527201,57,17980,202438,0,0,131072,129584,48,1440,65536,65536,0,12074964715162185,12074968668855417,12074968668982616,12074964715483782
|
|
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,855764,855769,4194304,256,0,0,20,24,136832,0x7fb681303900,0x7fb575636940,3502624,3336775,49717276,65536,403200015,1104,48,0,437827,437827,0,0,1152,0,8978432,8976658,48,2119,196214,0,0,131072,129584,48,1440,0,131072,0,12074964715541810,12074968669031415,12074968669313653,12074964716090299
|
|
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,855764,855769,4194304,256,0,0,28,24,138560,0x7fb681303800,0x7fb575636980,3270480,3057239,45508426,65536,287260121,1392,48,0,408809,408809,0,0,1440,0,3670016,3665409,48,5770,174173,0,0,65536,64048,48,1440,0,0,65536,12074964716110126,12074968669371253,12074968669617811,12074964716649038
|
|
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,855764,855769,4194304,256,0,0,24,24,140288,0x7fb681303700,0x7fb5756369c0,1830752,1657624,24494884,65536,150973903,1392,48,0,228843,228843,0,0,1440,0,3604480,3596693,48,10690,195659,0,0,131072,129584,48,1440,65536,65536,0,12074964716673744,12074968669674610,12074968669801169,12074964717021259
|
|
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,855764,855769,4194304,256,0,0,24,24,142784,0x7fb681303600,0x7fb575636a00,2649808,2492679,37013768,65536,301771396,1824,48,0,331225,331225,0,0,1872,0,4849664,4828658,102,28689,213865,0,0,131072,129584,48,1440,65536,65536,0,12074964717085098,12074968669838929,12074968670048687,12074964717557796
|
|
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,855764,855769,4194304,256,0,0,24,24,144768,0x7fb681303500,0x7fb575636a40,1853216,1667187,24564350,65536,152744660,1440,48,0,231651,231651,0,0,1488,0,3801088,3789227,65,20219,196720,0,0,131072,129584,48,1440,65536,65536,0,12074964717592311,12074968670122767,12074968670250446,12074964717924999
|
|
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,855764,855769,4194304,256,0,0,20,24,145728,0x7fb681303400,0x7fb575636a80,3783120,3620644,53923451,65536,442188811,816,48,0,472889,472889,0,0,864,0,14548992,14547215,50,2160,189896,0,0,131072,129584,48,1440,0,131072,0,12074964717988807,12074968670287565,12074968670593003,12074964718557254
|
|
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,855764,855769,4194304,256,0,0,28,24,147712,0x7fb681303300,0x7fb575636ac0,3242464,3052692,45389184,65536,293050479,1488,48,0,405307,405307,0,0,1536,0,3932160,3927118,48,6357,181056,0,0,65536,64048,48,1440,0,0,65536,12074964718581108,12074968670652202,12074968670901480,12074964719112936
|
|
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,855764,855769,4194304,256,0,0,24,24,149696,0x7fb681303a00,0x7fb575636b00,1784400,1602678,23586927,65536,149791262,1488,48,0,223049,223049,0,0,1536,0,3866624,3854339,101,19367,194397,0,0,131072,129584,48,1440,65536,65536,0,12074964719137903,12074968670958280,12074968671087239,12074964719488154
|
|
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,855764,855769,4194304,256,0,0,24,24,152192,0x7fb681303900,0x7fb575636b40,2857824,2689997,39900709,65536,326028254,1968,48,0,357227,357227,0,0,2016,0,5242880,5219565,53,29633,194024,0,0,131072,129584,48,1440,65536,65536,0,12074964719552904,12074968671131398,12074968671359877,12074964720036032
|
|
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,855764,855769,4194304,256,0,0,24,24,154176,0x7fb681303800,0x7fb575636b80,1823568,1646989,24300455,65536,145953008,1536,48,0,227945,227945,0,0,1584,0,4063232,4047724,108,23716,197201,0,0,131072,129584,48,1440,65536,65536,0,12074964720070847,12074968671433636,12074968671562275,12074964720403545
|
|
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,855764,855769,4194304,256,0,0,20,24,155648,0x7fb681303700,0x7fb575636bc0,4041568,3874339,57748258,65536,471974692,1200,48,0,505195,505195,0,0,1248,0,10027008,10025170,48,2326,198689,0,0,131072,129584,48,1440,0,131072,0,12074964720468275,12074968671604675,12074968671932832,12074964721054324
|
|
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,855764,855769,4194304,256,0,0,28,24,157632,0x7fb681303600,0x7fb575636c00,3274128,3097494,46033319,65536,282984437,1584,48,0,409265,409265,0,0,1632,0,4194304,4186491,96,9049,180682,0,0,65536,64048,48,1440,0,0,65536,12074964721078108,12074968671989632,12074968672242270,12074964721609105
|
|
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,855764,855769,4194304,256,0,0,24,24,159616,0x7fb681303500,0x7fb575636c40,1821280,1623478,23920482,65536,157089458,1584,48,0,227659,227659,0,0,1632,0,4128768,4113513,79,27019,196572,0,0,131072,129584,48,1440,65536,65536,0,12074964721632108,12074968672304509,12074968672432828,12074964721975757
|
|
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,855764,855769,4194304,256,0,0,24,24,162368,0x7fb681303400,0x7fb575636c80,3059856,2894353,43040149,65536,348499292,2112,48,0,382481,382481,0,0,2160,0,5636096,5612845,96,28209,192988,0,0,131072,129584,48,1440,65536,65536,0,12074964722038834,12074968672474428,12074968672717306,12074964722544013
|
|
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,855764,855769,4194304,256,0,0,24,24,164608,0x7fb681303300,0x7fb575636cc0,1816032,1648916,24187147,65536,157309817,1728,48,0,227003,227003,0,0,1776,0,4587520,4569239,92,31221,195640,0,0,131072,129584,48,1440,65536,65536,0,12074964722580210,12074968672781625,12074968672911544,12074964722913920
|
|
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,855764,855769,4194304,256,0,0,20,24,166336,0x7fb681303a00,0x7fb575636d00,4588752,4429963,66012479,65536,541445792,1296,48,0,573593,573593,0,0,1344,0,11075584,11073369,48,2590,207658,0,0,131072,129584,48,1440,0,131072,0,12074964722969984,12074968672953784,12074968673328981,12074964723612679
|
|
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,855764,855769,4194304,256,0,0,28,24,168576,0x7fb681303900,0x7fb575636d40,3267616,3089409,45859617,65536,298733834,1728,48,0,408451,408451,0,0,1776,0,4718592,4701770,48,18065,176179,0,0,65536,64048,48,1440,0,0,65536,12074964723635902,12074968673388340,12074968673638738,12074964724166458
|
|
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,855764,855769,4194304,256,0,0,24,24,170816,0x7fb681303800,0x7fb575636d80,1785872,1610205,23684556,65536,164895078,1776,48,0,223233,223233,0,0,1824,0,4653056,4636124,51,22864,198646,0,0,131072,129584,48,1440,65536,65536,0,12074964724189901,12074968673699058,12074968673827537,12074964724530494
|
|
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,855764,855769,4194304,256,0,0,24,24,174080,0x7fb681303700,0x7fb575636dc0,3467936,3302296,49185494,65536,402381884,2400,48,0,433491,433491,0,0,2448,0,6422528,6397173,96,29330,195778,0,0,131072,129584,48,1440,65536,65536,0,12074964724594413,12074968673864337,12074968674141454,12074964725131100
|
|
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,855764,855769,4194304,256,0,0,24,24,176576,0x7fb681303600,0x7fb575636e00,1771152,1587415,23453479,65536,155696735,1920,48,0,221393,221393,0,0,1968,0,5111808,5095449,116,32043,195649,0,0,131072,129584,48,1440,65536,65536,0,12074964725166757,12074968674212974,12074968674348653,12074964725494566
|
|
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,855764,855769,4194304,256,0,0,20,24,177792,0x7fb681303500,0x7fb575636e40,5435680,4998813,74549611,65536,612865429,1008,48,0,679459,679459,0,0,1056,0,15007744,15005090,48,3003,197487,0,0,131072,129584,48,1440,0,131072,0,12074964725558595,12074968674385772,12074968674807849,12074964726266210
|
|
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,855764,855769,4194304,256,0,0,28,24,180288,0x7fb681303400,0x7fb575636e80,3299792,3082248,45697940,65536,284698095,1968,48,0,412473,412473,0,0,2016,0,5242880,5231364,48,12947,182018,0,0,65536,64048,48,1440,0,0,65536,12074964726290535,12074968674865769,12074968675123366,12074964726824768
|
|
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,855764,855769,4194304,256,0,0,24,24,182784,0x7fb681303300,0x7fb575636ec0,1801248,1628927,24121570,65536,173935067,1968,48,0,225155,225155,0,0,2016,0,5177344,5155106,175,44893,189324,0,0,131072,129584,48,1440,65536,65536,0,12074964726849414,12074968675188486,12074968675324645,12074964727202009
|
|
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,855764,855769,4194304,256,0,0,24,24,186304,0x7fb681303a00,0x7fb575636f00,3901072,3738301,55666872,65536,456250725,2688,48,0,487633,487633,0,0,2736,0,7208960,7176094,96,38961,130669,0,0,131072,129584,48,1440,65536,65536,0,12074964727258484,12074968675363525,12074968675677762,12074964727843872
|
|
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,855764,855769,4194304,256,0,0,24,24,189312,0x7fb681303900,0x7fb575636f40,1950432,1783413,26470909,65536,214432035,2304,48,0,243803,243803,0,0,2352,0,6160384,6139412,155,36582,198924,0,0,131072,129584,48,1440,65536,65536,0,12074964727880219,12074968675751041,12074968675902080,12074964728231442
|
|
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,855764,855769,4194304,256,0,0,20,24,190784,0x7fb681303800,0x7fb575636f80,6293584,6115122,91228080,65536,749004271,1104,48,0,786697,786697,0,0,1152,0,17104896,17103199,48,2084,190111,0,0,131072,129584,48,1440,0,131072,0,12074964728295982,12074968675944480,12074968676459996,12074964729046937
|
|
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,855764,855769,4194304,256,0,0,28,24,193792,0x7fb681303700,0x7fb575636fc0,3662304,3494800,51578484,65536,378615962,2352,48,0,457787,457787,0,0,2400,0,6291456,6264525,96,28535,171483,0,0,65536,64048,48,1440,0,0,65536,12074964729092472,12074968676522555,12074968676819353,12074964729637144
|
|
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,855764,855769,4194304,256,0,0,24,24,196800,0x7fb681303600,0x7fb575637000,1972944,1809995,26907555,65536,217480350,2352,48,0,246617,246617,0,0,2400,0,6225920,6203923,117,34083,188731,0,0,131072,129584,48,1440,65536,65536,0,12074964729661379,12074968676881112,12074968677035831,12074964730020206
|
|
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,855764,855769,4194304,256,0,0,24,24,201088,0x7fb681303500,0x7fb575637040,4740896,4585471,68416772,65536,561435912,3264,48,0,592611,592611,0,0,3312,0,8781824,8749318,105,53247,217003,0,0,131072,129584,48,1440,65536,65536,0,12074964730085668,12074968677073751,12074968677458228,12074964730730236
|
|
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,855764,855769,4194304,256,0,0,24,24,204608,0x7fb681303400,0x7fb575637080,2228240,2067684,30751855,65536,250188617,2688,48,0,278529,278529,0,0,2736,0,7208960,7176138,113,64225,193192,0,0,131072,129584,48,1440,65536,65536,0,12074964730769168,12074968677529107,12074968677704626,12074964731129728
|
|
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,855764,855769,4194304,256,0,0,20,24,206080,0x7fb681303300,0x7fb5756370c0,7400864,7239154,108027916,65536,888918223,1200,48,0,925107,925107,0,0,1248,0,19202048,19200417,48,1917,191713,0,0,131072,129584,48,1440,0,131072,0,12074964731222601,12074968677745745,12074968678355181,12074964732085394
|
|
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,855764,855769,4194304,256,0,0,28,24,209600,0x7fb681303a00,0x7fb575637100,4018896,3844711,57047773,65536,458257247,2736,48,0,502361,502361,0,0,2784,0,7340032,7315819,96,25625,180728,0,0,65536,64048,48,1440,0,0,65536,12074964732109990,12074968678423180,12074968678752937,12074964732711998
|
|
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,855764,855769,4194304,256,0,0,24,24,213120,0x7fb681303900,0x7fb575637140,2269088,2107134,31293951,65536,254640491,2736,48,0,283635,283635,0,0,2784,0,7274496,7246650,210,54789,193149,0,0,131072,129584,48,1440,65536,65536,0,12074964732735953,12074968678817257,12074968678995175,12074964733122992
|
|
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,855764,855769,4194304,256,0,0,24,24,218176,0x7fb681303800,0x7fb575637180,5595472,5430038,81036787,65536,666413883,3840,48,0,699433,699433,0,0,3888,0,10354688,10314772,97,60421,194521,0,0,131072,129584,48,1440,65536,65536,0,12074964733220614,12074968679042055,12074968679496931,12074964733922759
|
|
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,855764,855769,4194304,256,0,0,24,24,222208,0x7fb681303700,0x7fb5756371c0,2499936,2338192,34752870,65536,283999346,3072,48,0,312491,312491,0,0,3120,0,8257536,8229743,220,55251,196135,0,0,131072,129584,48,1440,65536,65536,0,12074964733958405,12074968679571811,12074968679770529,12074964734417308
|
|
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,855764,855769,4194304,256,0,0,20,24,223936,0x7fb681303600,0x7fb575637200,8525264,8355487,124742588,65536,1028324402,1296,48,0,1065657,1065657,0,0,1344,0,21299200,21297181,49,2392,195594,0,0,131072,129584,48,1440,0,131072,0,12074964734443827,12074968679830689,12074968680532603,12074964735414831
|
|
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,855764,855769,4194304,256,0,0,28,24,227968,0x7fb681303500,0x7fb575637240,4853792,4375501,65200946,65536,530016300,3120,48,0,606723,606723,0,0,3168,0,8388608,8353467,96,37650,172747,0,0,65536,64048,48,1440,0,0,65536,12074964735439347,12074968680602203,12074968680974360,12074964736111185
|
|
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,855764,855769,4194304,256,0,0,24,24,232000,0x7fb681303400,0x7fb575637280,2556368,2385354,35485131,65536,288820277,3120,48,0,319545,319545,0,0,3168,0,8323072,8293203,308,73726,195298,0,0,131072,129584,48,1440,65536,65536,0,12074964736141121,12074968681038999,12074968681241397,12074964736609812
|
|
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,855764,855769,4194304,256,0,0,24,24,237824,0x7fb681303300,0x7fb5756372c0,6442720,6271211,93589952,65536,767930504,4416,48,0,805339,805339,0,0,4464,0,11927552,11884981,144,60460,199514,0,0,131072,129584,48,1440,65536,65536,0,12074964736634187,12074968681305877,12074968681831313,12074964737428273
|
|
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,855764,855769,4194304,256,0,0,24,24,242368,0x7fb681303a00,0x7fb575637300,2786896,2625399,39114916,65536,319587327,3456,48,0,348361,348361,0,0,3504,0,9306112,9274092,341,77856,195353,0,0,131072,129584,48,1440,65536,65536,0,12074964737465031,12074968681904272,12074968682127310,12074964737939994
|
|
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,855764,855769,4194304,256,0,0,20,24,243584,0x7fb681303900,0x7fb575637340,9661024,9493485,141691490,65536,1167651458,1008,48,0,1207627,1207627,0,0,1056,0,29163520,29162136,49,2159,214963,0,0,131072,129584,48,1440,0,131072,0,12074964737963067,12074968682192430,12074968682989383,12074964739043234
|
|
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,855764,855769,4194304,256,0,0,28,24,248128,0x7fb681303800,0x7fb575637380,5108240,4940305,73625961,65536,603677998,3504,48,0,638529,638529,0,0,3552,0,9437184,9395304,96,43835,105536,0,0,65536,64048,48,1440,0,0,65536,12074964739070986,12074968683053063,12074968683495619,12074964739754907
|
|
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,855764,855769,4194304,256,0,0,24,24,252672,0x7fb681303700,0x7fb5756373c0,2837024,2673159,39792379,65536,325273336,3504,48,0,354627,354627,0,0,3552,0,9371648,9330873,178,75557,199684,0,0,131072,129584,48,1440,65536,65536,0,12074964739780444,12074968683555139,12074968683780577,12074964740273761
|
|
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,855764,855769,4194304,256,0,0,24,24,259264,0x7fb681303600,0x7fb575637400,7291344,7117219,106220890,65536,874554254,4992,48,0,911417,911417,0,0,5040,0,13500416,13447085,172,84742,200728,0,0,131072,129584,48,1440,65536,65536,0,12074964740299519,12074968683842817,12074968684438492,12074964741162483
|
|
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,855764,855769,4194304,256,0,0,24,24,264832,0x7fb681303500,0x7fb575637440,3325024,3160631,47011104,65536,385224575,4224,48,0,415627,415627,0,0,4272,0,11403264,11371818,488,94451,191757,0,0,131072,129584,48,1440,65536,65536,0,12074964741200283,12074968684517371,12074968684786009,12074964741722433
|
|
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,855764,855769,4194304,256,0,0,20,24,266304,0x7fb681303400,0x7fb575637480,11901200,11734599,175261528,65536,1446530860,1104,48,0,1487649,1487649,0,0,1152,0,33357824,33355836,97,2303,192817,0,0,131072,129584,48,1440,0,131072,0,12074964741752499,12074968684848249,12074968685832241,12074964743003163
|
|
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,855764,855769,4194304,256,0,0,28,24,271872,0x7fb681303300,0x7fb5756374c0,6217056,6050798,90258093,65536,741860573,4272,48,0,777131,777131,0,0,4320,0,11534336,11496558,96,55728,178467,0,0,65536,64048,48,1440,0,0,65536,12074964743028310,12074968685896560,12074968686410316,12074964743813950
|
|
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,855764,855769,4194304,256,0,0,24,24,277440,0x7fb681303a00,0x7fb575637500,3390352,3223579,47893223,65536,390858366,4272,48,0,423793,423793,0,0,4320,0,11534336,11499493,589,104368,151352,0,0,131072,129584,48,1440,65536,65536,0,12074964743838465,12074968686477516,12074968686748393,12074964744383078
|
|
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,855764,855769,4194304,256,0,0,12,24,279936,0x7fb681303900,0x7fb575637540,9019296,8852975,132105808,65536,1089397501,1968,48,0,1127411,1127411,0,0,2016,0,19267584,19260468,48,7131,227314,0,0,131072,129584,48,1440,65536,65536,0,12074964744405640,12074968686807273,12074968687544227,12074964745412020
|
|
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,855764,855769,4194304,256,0,0,24,24,286528,0x7fb681303800,0x7fb575637580,3922576,3751753,55809617,65536,456468063,4992,48,0,490321,490321,0,0,5040,0,13500416,13466280,821,121911,179636,0,0,131072,129584,48,1440,65536,65536,0,12074964745454148,12074968687615106,12074968687929504,12074964746019919
|
|
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,855764,855769,4194304,256,0,0,20,24,288000,0x7fb681303700,0x7fb5756375c0,14147104,13978418,208772321,65536,1724528471,1200,48,0,1768387,1768387,0,0,1248,0,37552128,37550111,49,2499,195442,0,0,131072,129584,48,1440,0,131072,0,12074964746050045,12074968687990463,12074968689161174,12074964747488659
|
|
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,855764,855769,4194304,256,0,0,32,24,294592,0x7fb681303600,0x7fb575637600,7368720,7195183,107273148,65536,806048373,5040,48,0,921089,921089,0,0,5088,0,13631488,13585009,146,65336,176873,0,0,65536,64048,48,1440,0,0,65536,12074964747519326,12074968689232053,12074968689842449,12074964748396145
|
|
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,855764,855769,4194304,256,0,0,24,24,301184,0x7fb681303500,0x7fb575637640,3936160,3773877,56146986,65536,460139099,5040,48,0,492019,492019,0,0,5088,0,13631488,13598215,832,120927,190840,0,0,131072,129584,48,1440,65536,65536,0,12074964748425610,12074968689904528,12074968690252205,12074964749018953
|
|
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,855764,855769,4194304,256,0,0,12,24,304960,0x7fb681303400,0x7fb575637680,10697360,10535650,157352435,65536,1299600324,2832,48,0,1337169,1337169,0,0,2880,0,21692416,21678678,97,14167,194568,0,0,131072,129584,48,1440,65536,65536,0,12074964749048688,12074968690322765,12074968691199398,12074964750201681
|
|
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,855764,855769,4194304,256,0,0,24,24,313600,0x7fb681303300,0x7fb5756376c0,5028128,4854396,72347475,65536,594294163,6528,48,0,628515,628515,0,0,6576,0,17694720,17646265,1077,158255,187193,0,0,131072,129584,48,1440,65536,65536,0,12074964750236966,12074968691278277,12074968691687074,12074964750908164
|
|
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,855764,855769,4194304,256,0,0,20,24,314816,0x7fb681303a00,0x7fb575637700,18687760,18500484,276307567,65536,2284739867,1008,48,0,2335969,2335969,0,0,1056,0,57475072,57473713,50,1907,195139,0,0,131072,129584,48,1440,0,131072,0,12074964750930866,12074968691751393,12074968693299381,12074964752762380
|
|
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,855764,855769,4194304,256,0,0,20,24,317568,0x7fb681303900,0x7fb575637740,9612512,9436427,140914089,65536,1162299428,2064,48,0,1201563,1201563,0,0,2112,0,19660800,19654572,49,6431,179574,0,0,65536,64048,48,1440,0,0,65536,12074964752790452,12074968693389441,12074968694183356,12074964753860731
|
|
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,855764,855769,4194304,256,0,0,12,24,320320,0x7fb681303800,0x7fb575637780,5120336,4959440,73956001,65536,607789639,2112,48,0,640041,640041,0,0,2160,0,20381696,20371250,48,11915,153365,0,0,131072,129584,48,1440,65536,65536,0,12074964753888051,12074968694270554,12074968694683352,12074964754575800
|
|
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,855764,855769,4194304,256,0,0,12,24,324096,0x7fb681303700,0x7fb5756377c0,14068000,13899431,207621996,65536,1715808483,2832,48,0,1758499,1758499,0,0,2880,0,28704768,28694032,96,11036,191302,0,0,131072,129584,48,1440,65536,65536,0,12074964754600606,12074968694773751,12074968695931343,12074964756025884
|
|
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,855764,855769,4194304,256,0,0,12,24,328896,0x7fb681303600,0x7fb575637800,9588944,9432242,140864312,65536,1163103267,3600,48,0,1198617,1198617,0,0,3648,0,36634624,36613647,97,22987,197311,0,0,131072,129584,48,1440,65536,65536,0,12074964756063083,12074968696038383,12074968696823017,12074964757110259
|
|
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,855764,855769,4194304,256,0,0,20,24,330112,0x7fb681303500,0x7fb575637840,36683680,36510100,545558481,65536,4515872609,1008,48,0,4585459,4585459,0,0,1056,0,105840640,105839261,96,1815,193369,0,0,131072,129584,48,1440,0,131072,0,12074964757133292,12074968696914057,12074968699965077,12074964760459704
|
|
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,855764,855769,4194304,256,0,0,20,24,332864,0x7fb681303400,0x7fb575637880,18591504,18430877,275298047,65536,2276249258,2064,48,0,2323937,2323937,0,0,2112,0,38535168,38528875,48,6609,172840,0,0,65536,64048,48,1440,0,0,65536,12074964760487916,12074968700062356,12074968701603466,12074964762300675
|
|
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,855764,855769,4194304,256,0,0,12,24,335616,0x7fb681303300,0x7fb5756378c0,9623520,9457612,141277913,65536,1166051201,2112,48,0,1202939,1202939,0,0,2160,0,39124992,39117269,97,8139,196466,0,0,131072,129584,48,1440,65536,65536,0,12074964762327275,12074968701695625,12074968702484100,12074964763389238
|
|
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,855764,855769,4194304,256,0,0,12,24,339392,0x7fb681303a00,0x7fb575637900,27559184,27384523,409105688,65536,3384544691,2832,48,0,3444897,3444897,0,0,2880,0,55771136,55761545,97,9890,194916,0,0,131072,129584,48,1440,65536,65536,0,12074964763419064,12074968702570340,12074968704851764,12074964765970375
|
|
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,855764,855769,4194304,256,0,0,12,24,344192,0x7fb681303900,0x7fb575637940,18595168,18424214,275204723,65536,2275863488,3600,48,0,2324395,2324395,0,0,3648,0,72548352,72532542,99,15969,196606,0,0,131072,129584,48,1440,65536,65536,0,12074964766019336,12074968704951444,12074968706486474,12074964767804423
|
|
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,855764,855769,4194304,256,0,0,20,24,345408,0x7fb681303800,0x7fb575637980,72691344,72530057,1084062746,65536,8977542078,1008,48,0,9086417,9086417,0,0,1056,0,210698240,210696903,50,1540,109722,0,0,131072,129584,48,1440,0,131072,0,12074964767831654,12074968706579913,12074968712634433,12074964774169141
|
|
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,855764,855769,4194304,256,0,0,20,24,348160,0x7fb681303700,0x7fb5756379c0,36586336,36411725,544127413,65536,4502747911,2064,48,0,4573291,4573291,0,0,2112,0,76283904,76278421,98,5613,183695,0,0,65536,64048,48,1440,0,0,65536,12074964774198095,12074968712727873,12074968715769932,12074964777515370
|
|
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,855764,855769,4194304,256,0,0,12,24,350912,0x7fb681303600,0x7fb575637a00,18621136,18461607,275818063,65536,2280925612,2112,48,0,2327641,2327641,0,0,2160,0,77398016,77392106,97,6209,193393,0,0,131072,129584,48,1440,65536,65536,0,12074964777546628,12074968715862892,12074968717400802,12074964779355339
|
|
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,855764,855769,4194304,256,0,0,12,24,0,0x7fb681303500,0x7fb575637a40,54504800,54337086,812014762,65536,6723191637,2832,48,0,6813099,6813099,0,0,2880,0,110821376,110809335,97,12258,194867,0,0,131072,129584,48,1440,65536,65536,0,12074964779385204,12074968717496801,12074968722023011,12074964784183962
|