169 lines
58 KiB
CSV
169 lines
58 KiB
CSV
|
|
Index,KernelName,gpu-id,queue-id,queue-index,pid,tid,grd,wgr,lds,scr,vgpr,sgpr,fbar,sig,obj,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,GRBM_COUNT,GRBM_GUI_ACTIVE,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,GRBM_SPI_BUSY,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,DispatchNs,BeginNs,EndNs,CompleteNs
|
||
|
|
0,__amd_rocclr_fillBufferAligned.kd,0,0,0,158654,158654,33554432,256,0,0,4,32,4160,0x0,0x7fa6dc604280,3092728,3006178,524288,386590,386590,3091017,3012577,369581,131072,524288,206210,533836,200024,0,9758208,0,0,0,0,0,0,1572864,524288,0,16413065555999,16419337860341,16419338099862,16413209395409
|
||
|
|
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,158654,158654,32768,256,0,0,12,24,13888,0x0,0x7fa6dc623f80,265064,158730,512,33132,33132,265056,166792,24057,128,512,6,518,0,0,0,0,0,0,0,0,0,1024,512,0,16413214566424,16419342871250,16419342884850,16413214708661
|
||
|
|
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,158654,158654,4194304,256,0,0,12,24,14336,0x7fa6fb036380,0x7fa6dc623fc0,1321432,1217149,65536,165178,165178,1321424,1225218,153082,16384,65536,123905,146734,54346,0,1784508,0,0,0,0,0,0,131072,65536,0,16413214749460,16419342956210,16419343048851,16413215092723
|
||
|
|
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,158654,158654,4194304,256,0,0,16,24,15040,0x7fa6fb036200,0x7fa6dc624000,2475336,2367634,65536,309416,309416,2475328,2375710,296665,16384,65536,325264,276065,175349,0,6309684,0,0,0,0,0,0,131072,65536,0,16413215133782,16419343082611,16419343262772,16413215515963
|
||
|
|
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,158654,158654,4194304,256,0,0,16,24,15488,0x7fa6fb036080,0x7fa6dc624040,2487256,2371260,65536,310906,310906,2487248,2379340,297898,16384,65536,489167,401740,206967,0,3817566,0,0,0,0,0,0,131072,65536,0,16413215554102,16419343287252,16419343466293,16413215932584
|
||
|
|
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,158654,158654,4194304,256,0,0,12,24,15936,0x7fa6f8a09f00,0x7fa6dc624080,1320968,1215790,65536,165120,165120,1320960,1223866,153299,16384,65536,181306,188011,58568,0,1764113,0,0,0,0,0,0,131072,65536,0,16413215970613,16419343490933,16419343583734,16413216255297
|
||
|
|
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,158654,158654,4194304,256,0,0,12,24,16384,0x7fa6f8a09d80,0x7fa6dc6240c0,1332376,1212522,65536,166546,166546,1332368,1220586,152635,16384,65536,124689,147976,62392,0,1416286,0,0,0,0,0,0,131072,65536,0,16413216293246,16419343609334,16419343701335,16413216578010
|
||
|
|
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,158654,158654,4194304,256,0,0,12,24,17088,0x7fa6f8a09c00,0x7fa6dc624100,1314392,1209855,65536,164298,164298,1314384,1217922,152297,16384,65536,124488,145611,70037,0,1869679,0,0,0,0,0,0,131072,65536,0,16413216629059,16419343740375,16419343832535,16413216894013
|
||
|
|
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,158654,158654,4194304,256,0,0,16,24,17792,0x7fa6f8a09a80,0x7fa6dc624140,2472792,2370023,65536,309098,309098,2472784,2378086,296779,16384,65536,467498,369483,197232,0,6381571,0,0,0,0,0,0,131072,65536,0,16413216931372,16419343864376,16419344043257,16413217301804
|
||
|
|
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,158654,158654,4194304,256,0,0,16,24,18496,0x7fa6f8a09900,0x7fa6dc624180,2469648,2364884,65536,308705,308705,2469640,2372954,295767,16384,65536,500709,388234,199638,0,3336362,0,0,0,0,0,0,131072,65536,0,16413217339243,16419344087897,16419344267098,16413217722685
|
||
|
|
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,158654,158654,4194304,256,0,0,16,24,19200,0x7fa6f8a09780,0x7fa6dc6241c0,1324496,1217951,65536,165561,165561,1324488,1226014,152521,16384,65536,125165,144862,65546,0,1729928,0,0,0,0,0,0,131072,65536,0,16413217760174,16419344301338,16419344395419,16413218043628
|
||
|
|
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,158654,158654,4194304,256,0,0,16,24,19904,0x7fa6f8a09600,0x7fa6dc624200,1315144,1212856,65536,164392,164392,1315136,1220918,153082,16384,65536,221080,217579,69105,0,1514700,0,0,0,0,0,0,131072,65536,0,16413218089267,16419344422299,16419344515899,16413218398490
|
||
|
|
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,158654,158654,4194304,256,0,0,12,24,20608,0x7fa6fb036480,0x7fa6dc624240,1312832,1207759,65536,164103,164103,1312824,1215820,152634,16384,65536,123450,143404,64351,0,2248659,0,0,0,0,0,0,131072,65536,0,16413218445339,16419344548060,16419344641340,16413218697683
|
||
|
|
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,158654,158654,4194304,256,0,0,16,24,21312,0x7fa6fb036300,0x7fa6dc624280,2477184,2372852,65536,309647,309647,2477176,2380926,294871,16384,65536,499552,383811,208153,0,8047559,0,0,0,0,0,0,131072,65536,0,16413218737122,16419344668060,16419344847421,16413219074895
|
||
|
|
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,158654,158654,4194304,256,0,0,16,24,22016,0x7fa6fb036180,0x7fa6dc6242c0,2461672,2352931,65536,307708,307708,2461664,2361006,295209,16384,65536,412368,330056,171296,0,5630738,0,0,0,0,0,0,131072,65536,0,16413219113054,16419344886782,16419345066303,16413219454507
|
||
|
|
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,158654,158654,4194304,256,0,0,16,24,22720,0x7fa6fb036000,0x7fa6dc624300,1317384,1213179,65536,164672,164672,1317376,1221248,153187,16384,65536,124932,146943,73157,0,1602205,0,0,0,0,0,0,131072,65536,0,16413219493836,16419345091583,16419345185023,16413219751810
|
||
|
|
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,158654,158654,4194304,256,0,0,12,24,23424,0x7fa6f8a09e80,0x7fa6dc624340,1316032,1210654,65536,164503,164503,1316024,1218730,151738,16384,65536,128196,146842,68648,0,2662321,0,0,0,0,0,0,131072,65536,0,16413219789999,16419345222624,16419345315424,16413220049613
|
||
|
|
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,158654,158654,4194304,256,0,0,12,24,24128,0x7fa6f8a09d00,0x7fa6dc624380,1316824,1207014,65536,164602,164602,1316816,1215074,151738,16384,65536,124617,145399,74375,0,1655382,0,0,0,0,0,0,131072,65536,0,16413220095142,16419345348384,16419345440865,16413220344917
|
||
|
|
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,158654,158654,4194304,256,0,0,16,24,24832,0x7fa6f8a09b80,0x7fa6dc6243c0,2459984,2354476,65536,307497,307497,2459976,2362538,297003,16384,65536,391184,323280,171172,0,7898523,0,0,0,0,0,0,131072,65536,0,16413220383796,16419345469505,16419345649026,16413220725049
|
||
|
|
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,158654,158654,4194304,256,0,0,16,24,25536,0x7fa6f8a09a00,0x7fa6dc624400,2463880,2355814,65536,307984,307984,2463872,2363882,296666,16384,65536,478318,399462,173170,0,5906274,0,0,0,0,0,0,131072,65536,0,16413220763818,16419345684546,16419345865188,16413221103960
|
||
|
|
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,158654,158654,4194304,256,0,0,12,24,26240,0x7fa6f8a09880,0x7fa6dc624440,1316440,1212330,65536,164554,164554,1316432,1220404,153297,16384,65536,123222,144926,68892,0,2263680,0,0,0,0,0,0,131072,65536,0,16413221140899,16419345890948,16419345984708,16413221398084
|
||
|
|
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,158654,158654,4194304,256,0,0,12,24,26944,0x7fa6f8a09700,0x7fa6dc624480,1320280,1217226,65536,165034,165034,1320272,1225302,152746,16384,65536,220695,218304,74542,0,1960117,0,0,0,0,0,0,131072,65536,0,16413221436693,16419346017348,16419346110309,16413221693237
|
||
|
|
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,158654,158654,4194304,256,0,0,12,24,27648,0x7fa6fb036580,0x7fa6dc6244c0,1303464,1199546,65536,162932,162932,1303456,1207626,150618,16384,65536,124505,145373,69854,0,2016773,0,0,0,0,0,0,131072,65536,0,16413221738846,16419346144549,16419346236390,16413221989971
|
||
|
|
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,158654,158654,4194304,256,0,0,16,24,28608,0x7fa6fb036400,0x7fa6dc624500,2451712,2349221,65536,306463,306463,2451704,2357300,293971,16384,65536,488233,360160,204955,0,3998786,0,0,0,0,0,0,131072,65536,0,16413222029240,16419346269830,16419346448551,16413222375632
|
||
|
|
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,158654,158654,4194304,256,0,0,16,24,29312,0x7fa6fb036280,0x7fa6dc624540,2463464,2360495,65536,307932,307932,2463456,2368562,294867,16384,65536,494961,391758,188262,0,4388195,0,0,0,0,0,0,131072,65536,0,16413222414041,16419346479591,16419346659112,16413222760294
|
||
|
|
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,158654,158654,4194304,256,0,0,12,24,30016,0x7fa6fb036100,0x7fa6dc624580,1298480,1193338,65536,162309,162309,1298472,1201396,151177,16384,65536,124570,143986,68193,0,2143383,0,0,0,0,0,0,131072,65536,0,16413222799613,16419346683272,16419346775113,16413223051177
|
||
|
|
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,158654,158654,4194304,256,0,0,8,24,30976,0x7fa6f8a09f80,0x7fa6dc6245c0,1303736,1201160,65536,162966,162966,1303728,1209238,150618,16384,65536,120488,143067,68802,0,1426479,0,0,0,0,0,0,131072,65536,0,16413223090137,16419346802313,16419346894634,16413223350971
|
||
|
|
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,158654,158654,4194304,256,0,0,12,24,31680,0x7fa6f8a09e00,0x7fa6dc624600,1298976,1194168,65536,162371,162371,1298968,1202226,150951,16384,65536,192312,195048,78212,0,1708600,0,0,0,0,0,0,131072,65536,0,16413223396160,16419346927434,16419347020394,16413223642504
|
||
|
|
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,158654,158654,4194304,256,0,0,16,24,32640,0x7fa6f8a09c80,0x7fa6dc624640,2456768,2350319,65536,307095,307095,2456760,2358384,293978,16384,65536,307666,268112,179540,0,6537573,0,0,0,0,0,0,131072,65536,0,16413223681584,16419347048555,16419347228236,16413224019906
|
||
|
|
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,158654,158654,4194304,256,0,0,12,24,33600,0x7fa6f8a09b00,0x7fa6dc624680,2466312,2353424,65536,308288,308288,2466304,2361496,296446,16384,65536,259986,239269,184475,0,5776729,0,0,0,0,0,0,131072,65536,0,16413224057745,16419347260716,16419347441517,16413224400428
|
||
|
|
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,158654,158654,4194304,256,0,0,12,24,34560,0x7fa6f8a09980,0x7fa6dc6246c0,1299528,1196306,65536,162440,162440,1299520,1204382,151729,16384,65536,124240,143431,68309,0,1728715,0,0,0,0,0,0,131072,65536,0,16413224439267,16419347464717,16419347558318,16413224692261
|
||
|
|
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,158654,158654,4194304,256,0,0,8,24,35520,0x7fa6f8a09800,0x7fa6dc624700,1310296,1205742,65536,163786,163786,1310288,1213808,151617,16384,65536,151709,163858,66051,0,1568020,0,0,0,0,0,0,131072,65536,0,16413224729940,16419347581998,16419347676398,16413224983655
|
||
|
|
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,158654,158654,4194304,256,0,0,12,24,36224,0x7fa6f8a09680,0x7fa6dc624740,1298480,1195978,65536,162309,162309,1298472,1204042,151065,16384,65536,123986,140745,74204,0,2504789,0,0,0,0,0,0,131072,65536,0,16413225028274,16419347708559,16419347802639,16413225277718
|
||
|
|
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,158654,158654,4194304,256,0,0,12,24,37184,0x7fa6fb036500,0x7fa6dc624780,2450904,2345818,65536,306362,306362,2450896,2353876,293198,16384,65536,345709,295639,193848,0,6932824,0,0,0,0,0,0,131072,65536,0,16413225317418,16419347827279,16419348007600,16413225652940
|
||
|
|
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,158654,158654,4194304,256,0,0,12,24,38144,0x7fa6fb036380,0x7fa6dc6247c0,2443448,2341751,65536,305430,305430,2443440,2349822,294654,16384,65536,484648,370917,196110,0,3331807,0,0,0,0,0,0,131072,65536,0,16413225692019,16419348031601,16419348211922,16413226032432
|
||
|
|
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,158654,158654,4194304,256,0,0,12,24,39104,0x7fa6fb036200,0x7fa6dc624800,1306744,1201489,65536,163342,163342,1306736,1209570,152073,16384,65536,180278,187226,67169,0,1614539,0,0,0,0,0,0,131072,65536,0,16413226072041,16419348235762,16419348329362,16413226331315
|
||
|
|
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,158654,158654,4194304,256,0,0,8,24,40320,0x7fa6fb036080,0x7fa6dc624840,1312976,1200860,65536,164121,164121,1312968,1208934,151177,16384,65536,176336,179235,69250,0,1672938,0,0,0,0,0,0,131072,65536,0,16413226369334,16419348352882,16419348447763,16413226625899
|
||
|
|
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,158654,158654,4194304,256,0,0,12,24,41280,0x7fa6f8a09f00,0x7fa6dc624880,1299176,1197610,65536,162396,162396,1299168,1205684,151841,16384,65536,133928,148395,70081,0,1818864,0,0,0,0,0,0,131072,65536,0,16413226671178,16419348480243,16419348574004,16413226921842
|
||
|
|
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,158654,158654,4194304,256,0,0,12,24,42240,0x7fa6f8a09d80,0x7fa6dc6248c0,2459312,2348858,65536,307413,307413,2459304,2356924,293753,16384,65536,256220,228878,171954,0,7421221,0,0,0,0,0,0,131072,65536,0,16413226961161,16419348598804,16419348776885,16413227299904
|
||
|
|
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,158654,158654,4194304,256,0,0,12,24,43200,0x7fa6f8a09c00,0x7fa6dc624900,2448368,2338657,65536,306045,306045,2448360,2346724,293982,16384,65536,346136,299413,157830,0,4955904,0,0,0,0,0,0,131072,65536,0,16413227338683,16419348800245,16419348981686,16413227682036
|
||
|
|
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,158654,158654,4194304,256,0,0,8,24,44160,0x7fa6f8a09a80,0x7fa6dc624940,1309744,1205709,65536,163717,163717,1309736,1213792,151622,16384,65536,122637,142361,70630,0,2067233,0,0,0,0,0,0,131072,65536,0,16413227720185,16419349006646,16419349101047,16413227971679
|
||
|
|
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,158654,158654,4194304,256,0,0,12,24,45376,0x7fa6f8a09900,0x7fa6dc624980,1300624,1193271,65536,162577,162577,1300616,1201350,151175,16384,65536,181623,179268,66177,0,1963894,0,0,0,0,0,0,131072,65536,0,16413228009598,16419349124567,16419349220248,16413228261753
|
||
|
|
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,158654,158654,4194304,256,0,0,12,24,46336,0x7fa6f8a09780,0x7fa6dc6249c0,1300992,1198648,65536,162623,162623,1300984,1206710,151065,16384,65536,141027,158597,71998,0,1683084,0,0,0,0,0,0,131072,65536,0,16413228307222,16419349252408,16419349345048,16413228558166
|
||
|
|
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,158654,158654,4194304,256,0,0,12,24,47552,0x7fa6f8a09600,0x7fa6dc624a00,2431712,2326555,65536,303963,303963,2431704,2334628,292746,16384,65536,482789,388264,176147,0,6282101,0,0,0,0,0,0,131072,65536,0,16413228597695,16419349369529,16419349548250,16413228933318
|
||
|
|
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,158654,158654,4194304,256,0,0,12,24,48512,0x7fa6fb036480,0x7fa6dc624a40,2411696,2306633,65536,301461,301461,2411688,2314696,289834,16384,65536,481617,393660,165646,0,3054123,0,0,0,0,0,0,131072,65536,0,16413228972007,16419349572570,16419349751771,16413229309320
|
||
|
|
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,158654,158654,4194304,256,0,0,8,24,49472,0x7fa6fb036300,0x7fa6dc624a80,1309648,1203176,65536,163705,163705,1309640,1211252,151507,16384,65536,122777,145335,68875,0,1683834,0,0,0,0,0,0,131072,65536,0,16413229348459,16419349774971,16419349867932,16413229600293
|
||
|
|
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,158654,158654,4194304,256,0,0,12,24,50688,0x7fa6fb036180,0x7fa6dc624ac0,1293344,1190212,65536,161667,161667,1293336,1198286,150843,16384,65536,185508,183907,71415,0,1784146,0,0,0,0,0,0,131072,65536,0,16413229638822,16419349893212,16419349986652,16413229893547
|
||
|
|
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,158654,158654,4194304,256,0,0,12,24,51648,0x7fa6fb036000,0x7fa6dc624b00,1298856,1194191,65536,162356,162356,1298848,1202262,148713,16384,65536,145177,160866,64427,0,1674310,0,0,0,0,0,0,131072,65536,0,16413229939326,16419350014492,16419350106333,16413230203780
|
||
|
|
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,158654,158654,4194304,256,0,0,12,24,52864,0x7fa6f8a09e80,0x7fa6dc624b40,2411664,2305025,65536,301457,301457,2411656,2313078,291175,16384,65536,259629,230446,154833,0,7312869,0,0,0,0,0,0,131072,65536,0,16413230245099,16419350132253,16419350312894,16413230590601
|
||
|
|
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,158654,158654,4194304,256,0,0,12,24,54080,0x7fa6f8a09d00,0x7fa6dc624b80,2433992,2330622,65536,304248,304248,2433984,2338692,290846,16384,65536,487487,379707,178306,0,3076567,0,0,0,0,0,0,131072,65536,0,16413230628691,16419350335774,16419350516575,16413230974743
|
||
|
|
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,158654,158654,4194304,256,0,0,8,24,55296,0x7fa6f8a09b80,0x7fa6dc624bc0,1309712,1207093,65536,163713,163713,1309704,1215162,152071,16384,65536,168543,172556,75069,0,2001454,0,0,0,0,0,0,131072,65536,0,16413231012702,16419350539456,16419350634336,16413231268856
|
||
|
|
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,158654,158654,4194304,256,0,0,12,24,56768,0x7fa6f8a09a00,0x7fa6dc624c00,1302232,1198014,65536,162778,162778,1302224,1206080,151177,16384,65536,218286,208976,69172,0,1830715,0,0,0,0,0,0,131072,65536,0,16413231306726,16419350657856,16419350752737,16413231563700
|
||
|
|
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,158654,158654,4194304,256,0,0,12,24,57728,0x7fa6f8a09880,0x7fa6dc624c40,1299536,1195906,65536,162441,162441,1299528,1203978,150499,16384,65536,188442,188719,63599,0,1875725,0,0,0,0,0,0,131072,65536,0,16413231609059,16419350784897,16419350878178,16413231861483
|
||
|
|
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,158654,158654,4194304,256,0,0,12,24,58944,0x7fa6f8a09700,0x7fa6dc624c80,2412312,2304746,65536,301538,301538,2412304,2312812,291182,16384,65536,393990,327505,141884,0,5325259,0,0,0,0,0,0,131072,65536,0,16413231900812,16419350902018,16419351082019,16413232237585
|
||
|
|
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,158654,158654,4194304,256,0,0,12,24,60160,0x7fa6fb036580,0x7fa6dc624cc0,2440112,2334450,65536,305013,305013,2440104,2342510,289718,16384,65536,441405,362704,172719,0,5692478,0,0,0,0,0,0,131072,65536,0,16413232275664,16419351105859,16419351286020,16413232618236
|
||
|
|
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,158654,158654,4194304,256,0,0,8,24,61376,0x7fa6fb036400,0x7fa6dc624d00,1303264,1200563,65536,162907,162907,1303256,1208638,151849,16384,65536,192773,194200,72878,0,1705231,0,0,0,0,0,0,131072,65536,0,16413232655856,16419351308740,16419351402501,16413232912870
|
||
|
|
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,158654,158654,4194304,256,0,0,12,24,62848,0x7fa6fb036280,0x7fa6dc624d40,1352752,1248878,65536,169093,169093,1352744,1256950,157785,16384,65536,149872,156553,72617,0,1584028,0,0,0,0,0,0,131072,65536,0,16413232951229,16419351426341,16419351525221,16413233205473
|
||
|
|
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,158654,158654,4194304,256,0,0,12,24,63808,0x7fa6fb036100,0x7fa6dc624d80,1296472,1193805,65536,162058,162058,1296464,1201870,151401,16384,65536,128717,144089,65771,0,1849689,0,0,0,0,0,0,131072,65536,0,16413233250522,16419351560742,16419351654502,16413233504367
|
||
|
|
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,158654,158654,4194304,256,0,0,12,24,65024,0x7fa6f8a09f80,0x7fa6dc624dc0,2404432,2300425,65536,300553,300553,2404424,2308488,288259,16384,65536,312886,281978,163298,0,6343615,0,0,0,0,0,0,131072,65536,0,16413233544566,16419351681542,16419351860263,16413233884108
|
||
|
|
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,158654,158654,4194304,256,0,0,12,24,66240,0x7fa6f8a09e00,0x7fa6dc624e00,2405312,2297229,65536,300663,300663,2405304,2305298,286590,16384,65536,371163,311881,160963,0,5070021,0,0,0,0,0,0,131072,65536,0,16413233922398,16419351884584,16419352063945,16413234262340
|
||
|
|
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,158654,158654,4194304,256,0,0,8,24,67456,0x7fa6f8a09c80,0x7fa6dc624e40,1317328,1203490,65536,164665,164665,1317320,1211552,151402,16384,65536,127103,140692,67611,0,1985290,0,0,0,0,0,0,131072,65536,0,16413234300849,16419352087785,16419352182025,16413234565353
|
||
|
|
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,158654,158654,4194304,256,0,0,12,24,68928,0x7fa6f8a09b00,0x7fa6dc624e80,1422720,1314785,65536,177839,177839,1422712,1322840,165066,16384,65536,242722,231021,83438,0,1886244,0,0,0,0,0,0,131072,65536,0,16413234603063,16419352206666,16419352311626,16413234867197
|
||
|
|
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,158654,158654,4194304,256,0,0,12,24,70144,0x7fa6f8a09980,0x7fa6dc624ec0,1285240,1182772,65536,160654,160654,1285232,1190842,148491,16384,65536,125930,144758,63527,0,1623070,0,0,0,0,0,0,131072,65536,0,16413234913406,16419352344106,16419352436587,16413235167970
|
||
|
|
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,158654,158654,4194304,256,0,0,12,24,71616,0x7fa6f8a09800,0x7fa6dc624f00,2423888,2309158,65536,302985,302985,2423880,2317222,291729,16384,65536,257008,231742,168446,0,6909418,0,0,0,0,0,0,131072,65536,0,16413235207399,16419352460587,16419352642188,16413235547652
|
||
|
|
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,158654,158654,4194304,256,0,0,12,24,72832,0x7fa6f8a09680,0x7fa6dc624f40,2416744,2303657,65536,302092,302092,2416736,2311724,289950,16384,65536,265584,240464,180271,0,7337236,0,0,0,0,0,0,131072,65536,0,16413235586351,16419352666508,16419352847309,16413235932773
|
||
|
|
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,158654,158654,4194304,256,0,0,8,24,74048,0x7fa6fb036500,0x7fa6dc624f80,1287584,1187509,65536,160947,160947,1287576,1195576,149387,16384,65536,183897,187744,61142,0,1619798,0,0,0,0,0,0,131072,65536,0,16413235971022,16419352872270,16419352965870,16413236221507
|
||
|
|
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,158654,158654,4194304,256,0,0,12,24,75776,0x7fa6fb036380,0x7fa6dc624fc0,1460632,1354611,65536,182578,182578,1460624,1362686,170665,16384,65536,140502,154643,55448,0,2425372,0,0,0,0,0,0,131072,65536,0,16413236260656,16419352988590,16419353095311,16413236526200
|
||
|
|
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,158654,158654,4194304,256,0,0,12,24,76992,0x7fa6fb036200,0x7fa6dc625000,1313072,1198391,65536,164133,164133,1313064,1206460,150174,16384,65536,173516,177212,71502,0,1802776,0,0,0,0,0,0,131072,65536,0,16413236583389,16419353127151,16419353220432,16413236823864
|
||
|
|
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,158654,158654,4194304,256,0,0,12,24,78464,0x7fa6fb036080,0x7fa6dc625040,2422248,2314780,65536,302780,302780,2422240,2322852,288038,16384,65536,254933,228057,154239,0,6540178,0,0,0,0,0,0,131072,65536,0,16413236862613,16419353244112,16419353423473,16413237219105
|
||
|
|
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,158654,158654,4194304,256,0,0,12,24,79936,0x7fa6f8a09f00,0x7fa6dc625080,2387744,2281629,65536,298467,298467,2387736,2289700,289166,16384,65536,466084,369962,150058,0,6665922,0,0,0,0,0,0,131072,65536,0,16413237258254,16419353447313,16419353626834,16413237597537
|
||
|
|
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,158654,158654,4194304,256,0,0,8,24,81408,0x7fa6f8a09d80,0x7fa6dc6250c0,1301976,1196755,65536,162746,162746,1301968,1204812,152297,16384,65536,166236,171605,72422,0,1962695,0,0,0,0,0,0,131072,65536,0,16413237635516,16419353650034,16419353744915,16413237895760
|
||
|
|
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,158654,158654,4194304,256,0,0,12,24,83136,0x7fa6f8a09c00,0x7fa6dc625100,1537184,1428802,65536,192147,192147,1537176,1436870,179742,16384,65536,153508,155171,61101,0,3025807,0,0,0,0,0,0,131072,65536,0,16413237933879,16419353768115,16419353883796,16413238212933
|
||
|
|
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,158654,158654,4194304,256,0,0,12,24,84352,0x7fa6f8a09a80,0x7fa6dc625140,1293304,1191126,65536,161662,161662,1293296,1199190,149719,16384,65536,211140,204927,75416,0,1967408,0,0,0,0,0,0,131072,65536,0,16413238258642,16419353927956,16419354021876,16413238512357
|
||
|
|
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,158654,158654,4194304,256,0,0,12,24,85824,0x7fa6f8a09900,0x7fa6dc625180,2415504,2311265,65536,301937,301937,2415496,2319330,289497,16384,65536,317769,271034,174527,0,6436124,0,0,0,0,0,0,131072,65536,0,16413238550916,16419354045077,16419354225878,16413238891658
|
||
|
|
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,158654,158654,4194304,256,0,0,12,24,87296,0x7fa6f8a09780,0x7fa6dc6251c0,2395416,2280706,65536,299426,299426,2395408,2288780,287481,16384,65536,427147,352530,153019,0,4329036,0,0,0,0,0,0,131072,65536,0,16413238930707,16419354250358,16419354431959,16413239267430
|
||
|
|
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,158654,158654,4194304,256,0,0,12,24,88768,0x7fa6f8a09600,0x7fa6dc625200,1297584,1190647,65536,162197,162197,1297576,1198722,150734,16384,65536,192963,193108,72479,0,2039054,0,0,0,0,0,0,131072,65536,0,16413239306179,16419354454839,16419354550040,16413239560243
|
||
|
|
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,158654,158654,4194304,256,0,0,12,24,90752,0x7fa6fb036480,0x7fa6dc625240,1631080,1517142,65536,203884,203884,1631072,1525198,189930,16384,65536,162576,163634,64941,0,2227484,0,0,0,0,0,0,131072,65536,0,16413239598573,16419354575160,16419354697240,16413239885536
|
||
|
|
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,158654,158654,4194304,256,0,0,12,24,91968,0x7fa6fb036300,0x7fa6dc625280,1296048,1187900,65536,162005,162005,1296040,1195968,150393,16384,65536,152669,164502,65436,0,2068444,0,0,0,0,0,0,131072,65536,0,16413239931215,16419354730201,16419354824761,16413240184200
|
||
|
|
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,158654,158654,4194304,256,0,0,12,24,93440,0x7fa6fb036180,0x7fa6dc6252c0,2406504,2298585,65536,300812,300812,2406496,2306644,287818,16384,65536,484589,379027,182810,0,3968820,0,0,0,0,0,0,131072,65536,0,16413240222369,16419354849561,16419355029242,16413240571071
|
||
|
|
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,158654,158654,4194304,256,0,0,12,24,94912,0x7fa6fb036000,0x7fa6dc625300,2378384,2276568,65536,297297,297297,2378376,2284632,286698,16384,65536,480009,391701,173555,0,3001824,0,0,0,0,0,0,131072,65536,0,16413240610780,16419355053243,16419355234204,16413240948413
|
||
|
|
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,158654,158654,4194304,256,0,0,12,24,96384,0x7fa6f8a09e80,0x7fa6dc625340,1292600,1188774,65536,161574,161574,1292592,1196852,151737,16384,65536,215354,206214,75867,0,1866545,0,0,0,0,0,0,131072,65536,0,16413240986072,16419355259164,16419355354844,16413241237197
|
||
|
|
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,158654,158654,4194304,256,0,0,12,24,98368,0x7fa6f8a09d00,0x7fa6dc625380,1680464,1574977,65536,210057,210057,1680456,1583044,200451,16384,65536,172458,173378,59404,0,3685193,0,0,0,0,0,0,131072,65536,0,16413241275296,16419355379965,16419355506845,16413241560139
|
||
|
|
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,158654,158654,4194304,256,0,0,12,24,99584,0x7fa6f8a09b80,0x7fa6dc6253c0,1298696,1187025,65536,162336,162336,1298688,1195096,149489,16384,65536,144400,157017,68549,0,1812115,0,0,0,0,0,0,131072,65536,0,16413241605508,16419355539646,16419355633246,16413241856883
|
||
|
|
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,158654,158654,4194304,256,0,0,12,24,101312,0x7fa6f8a09a00,0x7fa6dc625400,2384048,2276313,65536,298005,298005,2384040,2284382,285802,16384,65536,287359,259877,158009,0,5555015,0,0,0,0,0,0,131072,65536,0,16413241894972,16419355659166,16419355837087,16413242233465
|
||
|
|
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,158654,158654,4194304,256,0,0,12,24,102784,0x7fa6f8a09880,0x7fa6dc625440,2390312,2283367,65536,298788,298788,2390304,2291438,286250,16384,65536,483551,390595,188651,0,3164404,0,0,0,0,0,0,131072,65536,0,16413242272864,16419355863007,16419356042209,16413242618186
|
||
|
|
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,158654,158654,4194304,256,0,0,12,24,104256,0x7fa6f8a09700,0x7fa6dc625480,1296416,1192742,65536,162051,162051,1296408,1200800,149830,16384,65536,181370,181381,69783,0,1961815,0,0,0,0,0,0,131072,65536,0,16413242655865,16419356065729,16419356159169,16413242913920
|
||
|
|
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,158654,158654,4194304,256,0,0,12,24,106240,0x7fa6fb036580,0x7fa6dc6254c0,1756560,1643381,65536,219569,219569,1756552,1651450,207178,16384,65536,175880,179927,60315,0,2540299,0,0,0,0,0,0,131072,65536,0,16413242953059,16419356182369,16419356313250,16413243242342
|
||
|
|
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,158654,158654,4194304,256,0,0,12,24,107712,0x7fa6fb036400,0x7fa6dc625500,1288752,1186677,65536,161093,161093,1288744,1194742,149603,16384,65536,167605,173828,64147,0,1795371,0,0,0,0,0,0,131072,65536,0,16413243289171,16419356345730,16419356439331,16413243537306
|
||
|
|
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,158654,158654,4194304,256,0,0,16,24,109440,0x7fa6fb036280,0x7fa6dc625540,2389328,2288491,65536,298665,298665,2389320,2296560,286250,16384,65536,471811,367832,165255,0,3588731,0,0,0,0,0,0,131072,65536,0,16413243575495,16419356464291,16419356642372,16413243915428
|
||
|
|
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,158654,158654,4194304,256,0,0,16,24,111168,0x7fa6fb036100,0x7fa6dc625580,2383632,2279158,65536,297953,297953,2383624,2287222,290503,16384,65536,482482,377406,187847,0,3319801,0,0,0,0,0,0,131072,65536,0,16413243954187,16419356665412,16419356843493,16413244298299
|
||
|
|
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,158654,158654,4194304,256,0,0,8,24,112896,0x7fa6f8a09f80,0x7fa6dc6255c0,1302464,1201702,65536,162807,162807,1302456,1209768,150846,16384,65536,180817,172408,75132,0,2253108,0,0,0,0,0,0,131072,65536,0,16413244336618,16419356867013,16419356962534,16413244591043
|
||
|
|
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,158654,158654,4194304,256,0,0,12,24,115136,0x7fa6f8a09e00,0x7fa6dc625600,1831856,1725200,65536,228981,228981,1831848,1733264,217930,16384,65536,264436,238061,118706,0,3003511,0,0,0,0,0,0,131072,65536,0,16413244628702,16419356985254,16419357123975,16413244924825
|
||
|
|
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,158654,158654,4194304,256,0,0,12,24,116608,0x7fa6f8a09c80,0x7fa6dc625640,1286944,1185776,65536,160867,160867,1286936,1193840,149721,16384,65536,178204,178917,74651,0,2080198,0,0,0,0,0,0,131072,65536,0,16413244970724,16419357156455,16419357251496,16413245216729
|
||
|
|
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,158654,158654,4194304,256,0,0,16,24,118336,0x7fa6f8a09b00,0x7fa6dc625680,2382336,2274948,65536,297791,297791,2382328,2283014,285242,16384,65536,276420,236683,162906,0,6076524,0,0,0,0,0,0,131072,65536,0,16413245254618,16419357276136,16419357456137,16413245601590
|
||
|
|
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,158654,158654,4194304,256,0,0,16,24,120064,0x7fa6f8a09980,0x7fa6dc6256c0,2388344,2285766,65536,298542,298542,2388336,2293822,285354,16384,65536,460797,372627,182965,0,3904673,0,0,0,0,0,0,131072,65536,0,16413245639840,16419357480137,16419357659658,16413245979622
|
||
|
|
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,158654,158654,4194304,256,0,0,12,24,121792,0x7fa6f8a09800,0x7fa6dc625700,1312880,1204104,65536,164109,164109,1312872,1212166,152862,16384,65536,131015,146527,73395,0,2366194,0,0,0,0,0,0,131072,65536,0,16413246018301,16419357683018,16419357781099,16413246282785
|
||
|
|
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,158654,158654,4194304,256,0,0,12,24,124032,0x7fa6f8a09680,0x7fa6dc625740,1918456,1807621,65536,239806,239806,1918448,1815684,231587,16384,65536,364368,303207,109789,0,5816030,0,0,0,0,0,0,131072,65536,0,16413246320485,16419357806219,16419357950700,16413246625178
|
||
|
|
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,158654,158654,4194304,256,0,0,12,24,125504,0x7fa6fb036500,0x7fa6dc625780,1293280,1192486,65536,161659,161659,1293272,1200554,150721,16384,65536,142410,153835,69124,0,1921353,0,0,0,0,0,0,131072,65536,0,16413246670857,16419357982700,16419358077741,16413246927781
|
||
|
|
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,158654,158654,4194304,256,0,0,12,24,127488,0x7fa6fb036380,0x7fa6dc6257c0,2388888,2279471,65536,298610,298610,2388880,2287542,285683,16384,65536,256496,227275,150114,0,4215888,0,0,0,0,0,0,131072,65536,0,16413246967010,16419358104301,16419358284462,16413247307323
|
||
|
|
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,158654,158654,4194304,256,0,0,12,24,129216,0x7fa6fb036200,0x7fa6dc625800,2382624,2273630,65536,297827,297827,2382616,2281702,285911,16384,65536,257726,233482,160139,0,5440891,0,0,0,0,0,0,131072,65536,0,16413247346242,16419358308622,16419358488943,16413247687114
|
||
|
|
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,158654,158654,4194304,256,0,0,12,24,130944,0x7fa6fb036080,0x7fa6dc625840,1359512,1258550,65536,169938,169938,1359504,1266614,158238,16384,65536,180408,172433,73543,0,2178050,0,0,0,0,0,0,131072,65536,0,16413247725783,16419358512463,16419358613264,16413247986108
|
||
|
|
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,158654,158654,4194304,256,0,0,12,24,133440,0x7fa6f8a09f00,0x7fa6dc625880,2079080,1964015,65536,259884,259884,2079072,1972072,248170,16384,65536,218059,206851,74655,0,4374677,0,0,0,0,0,0,131072,65536,0,16413248024037,16419358636464,16419358791985,16413248343350
|
||
|
|
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,158654,158654,4194304,256,0,0,12,24,134912,0x7fa6f8a09d80,0x7fa6dc6258c0,1296928,1192423,65536,162115,162115,1296920,1200492,149834,16384,65536,182629,179864,78263,0,2096466,0,0,0,0,0,0,131072,65536,0,16413248388909,16419358823985,16419358919026,16413248643873
|
||
|
|
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,158654,158654,4194304,256,0,0,12,24,136896,0x7fa6f8a09c00,0x7fa6dc625900,2376248,2270949,65536,297030,297030,2376240,2279020,284458,16384,65536,259814,240069,155717,0,5106876,0,0,0,0,0,0,131072,65536,0,16413248681222,16419358942866,16419359121587,16413249021745
|
||
|
|
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,158654,158654,4194304,256,0,0,12,24,138880,0x7fa6f8a09a80,0x7fa6dc625940,2379400,2268635,65536,297424,297424,2379392,2276700,285467,16384,65536,254218,231436,162845,0,5610367,0,0,0,0,0,0,131072,65536,0,16413249060054,16419359145907,16419359325908,16413249401116
|
||
|
|
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,158654,158654,4194304,256,0,0,12,24,140864,0x7fa6f8a09900,0x7fa6dc625980,1431288,1321617,65536,178910,178910,1431280,1329676,167297,16384,65536,138314,148373,59918,0,2707695,0,0,0,0,0,0,131072,65536,0,16413249438655,16419359348788,16419359455189,16413249704150
|
||
|
|
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,158654,158654,4194304,256,0,0,12,24,143616,0x7fa6f8a09780,0x7fa6dc6259c0,2240240,2129574,65536,280029,280029,2240232,2137644,268211,16384,65536,238399,207382,91575,0,6354111,0,0,0,0,0,0,131072,65536,0,16413249741929,16419359479189,16419359649270,16413250069262
|
||
|
|
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,158654,158654,4194304,256,0,0,12,24,145344,0x7fa6f8a09600,0x7fa6dc625a00,1297144,1193609,65536,162142,162142,1297136,1201668,150398,16384,65536,191275,190016,80683,0,1951146,0,0,0,0,0,0,131072,65536,0,16413250115190,16419359681270,16419359777111,16413250372175
|
||
|
|
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,158654,158654,4194304,256,0,0,12,24,147584,0x7fa6fb036480,0x7fa6dc625a40,2379520,2269672,65536,297439,297439,2379512,2277746,283329,16384,65536,317768,275447,154679,0,4839177,0,0,0,0,0,0,131072,65536,0,16413250409744,16419359800791,16419359984312,16413250755336
|
||
|
|
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,158654,158654,4194304,256,0,0,12,24,149568,0x7fa6fb036300,0x7fa6dc625a80,2363952,2258145,65536,295493,295493,2363944,2266208,285127,16384,65536,439351,361827,176632,0,3395819,0,0,0,0,0,0,131072,65536,0,16413250793696,16419360007192,16419360188313,16413251133048
|
||
|
|
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,158654,158654,4194304,256,0,0,12,24,151552,0x7fa6fb036180,0x7fa6dc625ac0,1506392,1388405,65536,188298,188298,1506384,1396484,175930,16384,65536,174344,173849,63904,0,2015650,0,0,0,0,0,0,131072,65536,0,16413251171447,16419360211834,16419360323674,16413251445291
|
||
|
|
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,158654,158654,4194304,256,0,0,12,24,154304,0x7fa6fb036000,0x7fa6dc625b00,2400912,2290199,65536,300113,300113,2400904,2298268,288046,16384,65536,255724,234888,101068,0,5351189,0,0,0,0,0,0,131072,65536,0,16413251484420,16419360347194,16419360527995,16413251828363
|
||
|
|
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,158654,158654,4194304,256,0,0,12,24,156288,0x7fa6f8a09e80,0x7fa6dc625b40,1363016,1262627,65536,170376,170376,1363008,1270684,160590,16384,65536,148506,161477,64276,0,1883945,0,0,0,0,0,0,131072,65536,0,16413251873942,16419360560156,16419360661276,16413252132286
|
||
|
|
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,158654,158654,4194304,256,0,0,12,24,158784,0x7fa6f8a09d00,0x7fa6dc625b80,2379880,2268716,65536,297484,297484,2379872,2276786,287025,16384,65536,349414,296552,157222,0,3101760,0,0,0,0,0,0,131072,65536,0,16413252170525,16419360684636,16419360871517,16413252513078
|
||
|
|
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,158654,158654,4194304,256,0,0,12,24,161024,0x7fa6f8a09b80,0x7fa6dc625bc0,2386160,2260049,65536,298269,298269,2386152,2268112,290163,16384,65536,301996,255278,162195,0,4619401,0,0,0,0,0,0,131072,65536,0,16413252552057,16419360894558,16419361079679,16413252894109
|
||
|
|
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,158654,158654,4194304,256,0,0,12,24,163264,0x7fa6f8a09a00,0x7fa6dc625c00,1648904,1535921,65536,206112,206112,1648896,1543992,194186,16384,65536,165838,169316,63845,0,2639190,0,0,0,0,0,0,131072,65536,0,16413252931769,16419361103679,16419361226400,16413253217382
|
||
|
|
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,158654,158654,4194304,256,0,0,12,24,166528,0x7fa6f8a09880,0x7fa6dc625c40,2725592,2613801,65536,340698,340698,2725584,2621864,328362,16384,65536,432831,358725,114457,0,7458516,0,0,0,0,0,0,131072,65536,0,16413253254851,16419361249600,16419361456001,16413253646193
|
||
|
|
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,158654,158654,4194304,256,0,0,12,24,168512,0x7fa6f8a09700,0x7fa6dc625c80,1467648,1362024,65536,183455,183455,1467640,1370082,173795,16384,65536,260125,241844,57347,0,2190192,0,0,0,0,0,0,131072,65536,0,16413253674282,16419361502561,16419361614402,16413253939556
|
||
|
|
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,158654,158654,4194304,256,0,0,12,24,171264,0x7fa6fb036580,0x7fa6dc625cc0,2385192,2248964,65536,298148,298148,2385184,2257028,285354,16384,65536,295031,253836,165128,0,4675437,0,0,0,0,0,0,131072,65536,0,16413253978035,16419361639842,16419361823043,16413254333168
|
||
|
|
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,158654,158654,4194304,256,0,0,12,24,173760,0x7fa6fb036400,0x7fa6dc625d00,2374672,2255898,65536,296833,296833,2374664,2263958,286579,16384,65536,382578,319089,162386,0,3683144,0,0,0,0,0,0,131072,65536,0,16413254372117,16419361845763,16419362034884,16413254715909
|
||
|
|
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,158654,158654,4194304,256,0,0,12,24,176256,0x7fa6fb036280,0x7fa6dc625d40,1805816,1696858,65536,225726,225726,1805808,1704914,214346,16384,65536,186001,182523,67967,0,3127184,0,0,0,0,0,0,131072,65536,0,16413254754178,16419362059365,16419362193925,16413255047642
|
||
|
|
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,158654,158654,4194304,256,0,0,12,24,179776,0x7fa6fb036100,0x7fa6dc625d80,3057104,2936714,65536,382137,382137,3057096,2944788,369470,16384,65536,597742,462317,138131,0,6608304,0,0,0,0,0,0,131072,65536,0,16413255086301,16419362217286,16419362449447,16413255520762
|
||
|
|
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,158654,158654,4194304,256,0,0,12,24,182272,0x7fa6f8a09f80,0x7fa6dc625dc0,1693672,1582793,65536,211708,211708,1693664,1590856,199566,16384,65536,170825,173866,62110,0,4113512,0,0,0,0,0,0,131072,65536,0,16413255540431,16419362520647,16419362647528,16413255829815
|
||
|
|
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,158654,158654,4194304,256,0,0,12,24,185536,0x7fa6f8a09e00,0x7fa6dc625e00,2450128,2334814,65536,306265,306265,2450120,2342878,292401,16384,65536,495575,384374,172775,0,3943032,0,0,0,0,0,0,131072,65536,0,16413255867554,16419362671208,16419362860649,16413256262655
|
||
|
|
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,158654,158654,4194304,256,0,0,12,24,188544,0x7fa6f8a09c80,0x7fa6dc625e40,2469552,2331286,65536,308693,308693,2469544,2339348,300353,16384,65536,401329,317198,136166,0,4601590,0,0,0,0,0,0,131072,65536,0,16413256273735,16419362884010,16419363078731,16413256686606
|
||
|
|
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,158654,158654,4194304,256,0,0,12,24,191552,0x7fa6f8a09b00,0x7fa6dc625e80,2128584,2018206,65536,266072,266072,2128576,2026274,254554,16384,65536,225016,210345,78351,0,6381383,0,0,0,0,0,0,131072,65536,0,16413256698196,16419363102411,16419363263052,16413257026658
|
||
|
|
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,158654,158654,4194304,256,0,0,12,24,195840,0x7fa6f8a09980,0x7fa6dc625ec0,3704672,3584102,65536,463083,463083,3704664,3592172,451114,16384,65536,428242,348282,162751,0,10369365,0,0,0,0,0,0,131072,65536,0,16413257065168,16419363286572,16419363570414,16413257526367
|
||
|
|
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,158654,158654,4194304,256,0,0,12,24,198592,0x7fa6f8a09800,0x7fa6dc625f00,1947432,1840412,65536,243428,243428,1947424,1848486,233043,16384,65536,203551,194164,129385,0,3512221,0,0,0,0,0,0,131072,65536,0,16413257554117,16419363643214,16419363792975,16413257855520
|
||
|
|
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,158654,158654,4194304,256,0,0,12,24,202368,0x7fa6f8a09680,0x7fa6dc625f40,2673664,2558874,65536,334207,334207,2673656,2566942,324441,16384,65536,486333,385678,177843,0,5544180,0,0,0,0,0,0,131072,65536,0,16413257892759,16419363817615,16419364025936,16413258281051
|
||
|
|
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,158654,158654,4194304,256,0,0,12,24,205888,0x7fa6fb036500,0x7fa6dc625f80,2636336,2518300,65536,329541,329541,2636328,2526372,318275,16384,65536,465410,362150,160867,0,4541438,0,0,0,0,0,0,131072,65536,0,16413258302210,16419364090097,16419364299538,16413258717671
|
||
|
|
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,158654,158654,4194304,256,0,0,12,24,209408,0x7fa6fb036380,0x7fa6dc625fc0,2454656,2345626,65536,306831,306831,2454648,2353700,294538,16384,65536,266583,237680,92074,0,6610229,0,0,0,0,0,0,131072,65536,0,16413258728561,16419364363058,16419364548980,16413259087503
|
||
|
|
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,158654,158654,4194304,256,0,0,12,24,214464,0x7fa6fb036200,0x7fa6dc626000,4345096,4228207,65536,543136,543136,4345088,4236272,530634,16384,65536,870582,676083,201183,0,14474108,0,0,0,0,0,0,131072,65536,0,16413259126042,16419364574100,16419364908822,16413259668210
|
||
|
|
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,158654,158654,4194304,256,0,0,12,24,217728,0x7fa6fb036080,0x7fa6dc626040,2185464,2070329,65536,273182,273182,2185456,2078390,262275,16384,65536,426927,346174,147158,0,3823654,0,0,0,0,0,0,131072,65536,0,16413259688560,16419364974582,16419365141303,16413260021362
|
||
|
|
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,158654,158654,4194304,256,0,0,12,24,222016,0x7fa6f8a09f00,0x7fa6dc626080,2928360,2819793,65536,366044,366044,2928352,2827868,354675,16384,65536,601138,453769,208704,0,5696020,0,0,0,0,0,0,131072,65536,0,16413260060492,16419365164983,16419365394105,16413260489022
|
||
|
|
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,158654,158654,4194304,256,0,0,12,24,226048,0x7fa6f8a09d80,0x7fa6dc6260c0,2941352,2835193,65536,367668,367668,2941344,2843268,355129,16384,65536,605734,467281,228651,0,7147824,0,0,0,0,0,0,131072,65536,0,16413260503802,16419365454265,16419365684346,16413260942692
|
||
|
|
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,158654,158654,4194304,256,0,0,12,24,230080,0x7fa6f8a09c00,0x7fa6dc626100,2793272,2675531,65536,349158,349158,2793264,2683598,335310,16384,65536,305799,265729,169012,0,7008200,0,0,0,0,0,0,131072,65536,0,16413260954822,16419365721627,16419365933148,16413261377373
|
||
|
|
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,158654,158654,4194304,256,0,0,12,24,235904,0x7fa6f8a09a80,0x7fa6dc626140,5001352,4876976,65536,625168,625168,5001344,4885028,612730,16384,65536,1078083,709737,399957,0,18411358,0,0,0,0,0,0,131072,65536,0,16413261389362,16419365967868,16419366353310,16413261963470
|
||
|
|
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,158654,158654,4194304,256,0,0,12,24,239424,0x7fa6f8a09900,0x7fa6dc626180,2436104,2324441,65536,304512,304512,2436096,2332516,291617,16384,65536,264660,206235,97936,0,7794144,0,0,0,0,0,0,131072,65536,0,16413261993069,16419366423711,16419366611392,16413262345771
|
||
|
|
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,158654,158654,4194304,256,0,0,12,24,244224,0x7fa6f8a09780,0x7fa6dc6261c0,3194536,3087108,65536,399316,399316,3194528,3095172,386039,16384,65536,604434,468469,232635,0,6862966,0,0,0,0,0,0,131072,65536,0,16413262384080,16419366635552,16419366886274,16413262850080
|
||
|
|
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,158654,158654,4194304,256,0,0,12,24,248768,0x7fa6f8a09600,0x7fa6dc626200,3130904,3020732,65536,391362,391362,3130896,3028794,378307,16384,65536,651293,513668,227398,0,9828600,0,0,0,0,0,0,131072,65536,0,16413262861910,16419366948034,16419367196035,16413263322830
|
||
|
|
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,158654,158654,4194304,256,0,0,12,24,253312,0x7fa6fb036480,0x7fa6dc626240,3111656,2997337,65536,388956,388956,3111648,3005404,377194,16384,65536,348505,292573,137185,0,9292515,0,0,0,0,0,0,131072,65536,0,16413263334320,16419367260036,16419367497157,16413263783420
|
||
|
|
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,158654,158654,4194304,256,0,0,8,24,255552,0x7fa6fb036300,0x7fa6dc626280,5756512,5637280,65536,719563,719563,5756504,5645348,706807,16384,65536,661341,525001,252572,0,18196497,0,0,0,0,0,0,131072,65536,0,16413263795029,16419367558118,16419368012040,16413264459595
|
||
|
|
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,158654,158654,4194304,256,0,0,12,24,259840,0x7fa6fb036180,0x7fa6dc6262c0,2904448,2800432,65536,363055,363055,2904440,2808500,353891,16384,65536,599430,441049,111344,0,5472377,0,0,0,0,0,0,131072,65536,0,16413264479864,16419368081161,16419368306922,16413264907445
|
||
|
|
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,158654,158654,4194304,256,0,0,12,24,265664,0x7fa6fb036000,0x7fa6dc626300,3757656,3646447,65536,469706,469706,3757648,3654516,458618,16384,65536,797953,605884,254177,0,11628285,0,0,0,0,0,0,131072,65536,0,16413264918975,16419368353002,16419368651084,16413265426714
|
||
|
|
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,158654,158654,4194304,256,0,0,12,24,271232,0x7fa6f8a09e80,0x7fa6dc626340,3770136,3664258,65536,471266,471266,3770128,3672322,461187,16384,65536,806522,568212,310913,0,12152159,0,0,0,0,0,0,131072,65536,0,16413265437933,16419368694284,16419368992526,16413265924853
|
||
|
|
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,158654,158654,4194304,256,0,0,8,24,273216,0x7fa6f8a09d00,0x7fa6dc626380,3870232,3752074,65536,483778,483778,3870224,3760146,471050,16384,65536,455175,374611,190845,0,11758248,0,0,0,0,0,0,131072,65536,0,16413265946862,16419369032686,16419369329488,16413266458161
|
||
|
|
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,158654,158654,4194304,256,0,0,8,24,275712,0x7fa6f8a09b80,0x7fa6dc6263c0,7036824,6928644,65536,879602,879602,7036816,6936712,870435,16384,65536,1577206,1108697,684371,0,15890154,0,0,0,0,0,0,131072,65536,0,16413266470071,16419369364848,16419369922932,16413267246123
|
||
|
|
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,158654,158654,4194304,256,0,0,12,24,280768,0x7fa6f8a09a00,0x7fa6dc626400,3418328,3303357,65536,427290,427290,3418320,3311426,415834,16384,65536,430091,339289,189090,0,10125383,0,0,0,0,0,0,131072,65536,0,16413267266573,16419369965652,16419370229654,16413267739222
|
||
|
|
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,158654,158654,4194304,256,0,0,12,24,287616,0x7fa6f8a09880,0x7fa6dc626440,4405872,4296051,65536,550733,550733,4405864,4304102,537127,16384,65536,958128,618197,331006,0,16123045,0,0,0,0,0,0,131072,65536,0,16413267750772,16419370273654,16419370623736,16413268313790
|
||
|
|
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,158654,158654,4194304,256,0,0,12,24,294208,0x7fa6f8a09700,0x7fa6dc626480,4415232,4299616,65536,551903,551903,4415224,4307686,540379,16384,65536,959465,684002,398464,0,13674331,0,0,0,0,0,0,131072,65536,0,16413268325369,16419370664376,16419371015258,16413268888227
|
||
|
|
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,158654,158654,4194304,256,0,0,8,24,296960,0x7fa6fb036580,0x7fa6dc6264c0,4510576,4394763,65536,563821,563821,4510568,4402834,551690,16384,65536,613855,480552,268794,0,13560679,0,0,0,0,0,0,131072,65536,0,16413268900497,16419371056699,16419371403581,16413269460064
|
||
|
|
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,158654,158654,4194304,256,0,0,8,24,299968,0x7fa6fb036400,0x7fa6dc626500,8338544,8223455,65536,1042317,1042317,8338536,8231514,1032611,16384,65536,1890417,1326507,738535,0,28395703,0,0,0,0,0,0,131072,65536,0,16413269471814,16419371444701,16419372106145,16413270351654
|
||
|
|
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,158654,158654,4194304,256,0,0,8,24,302720,0x7fa6fb036280,0x7fa6dc626540,5784704,5662519,65536,723087,723087,5784696,5670590,710387,16384,65536,1280574,906948,485043,0,22041648,0,0,0,0,0,0,131072,65536,0,16413270372234,16419372151265,16419372598468,16413271030230
|
||
|
|
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,158654,158654,4194304,256,0,0,12,24,305472,0x7fa6fb036100,0x7fa6dc626580,5783792,5675060,65536,722973,722973,5783784,5683126,713971,16384,65536,1279562,834044,491713,0,19217136,0,0,0,0,0,0,131072,65536,0,16413271042689,16419372640708,16419373105191,16413271715934
|
||
|
|
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,158654,158654,4194304,256,0,0,12,24,308224,0x7fa6f8a09f80,0x7fa6dc6265c0,5784064,5663466,65536,723007,723007,5784056,5671540,710611,16384,65536,919668,651482,337140,0,19076850,0,0,0,0,0,0,131072,65536,0,16413271727864,16419373142151,16419373604554,16413272413259
|
||
|
|
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,158654,158654,4194304,256,0,0,8,24,310976,0x7fa6f8a09e00,0x7fa6dc626600,5800424,5690552,65536,725052,725052,5800416,5698612,717219,16384,65536,1287703,933194,446624,0,18352306,0,0,0,0,0,0,131072,65536,0,16413272425309,16419373652394,16419374104077,16413273102934
|
||
|
|
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,158654,158654,4194304,256,0,0,8,24,313216,0x7fa6f8a09c80,0x7fa6dc626640,10951688,10815797,65536,1368960,1368960,10951680,10823864,1356961,16384,65536,2476782,1614117,1046563,0,39092040,0,0,0,0,0,0,131072,65536,0,16413273114564,16419374149517,16419375019762,16413274212920
|
||
|
|
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,158654,158654,4194304,256,0,0,8,24,315968,0x7fa6f8a09b00,0x7fa6dc626680,10972712,10846449,65536,1371588,1371588,10972704,10854522,1360894,16384,65536,2504237,1340291,1195421,0,44753789,0,0,0,0,0,0,131072,65536,0,16413274234169,16419375094643,16419375948088,16413275335785
|
||
|
|
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,158654,158654,4194304,256,0,0,12,24,318720,0x7fa6f8a09980,0x7fa6dc6266c0,11000936,10867947,65536,1375116,1375116,11000928,10876020,1362003,16384,65536,2502604,1501316,966666,0,47385563,0,0,0,0,0,0,131072,65536,0,16413275348675,16419376019448,16419376905534,16413276485060
|
||
|
|
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,158654,158654,4194304,256,0,0,12,24,321472,0x7fa6f8a09800,0x7fa6dc626700,10973592,10849407,65536,1371698,1371698,10973584,10857474,1360551,16384,65536,2510939,1668039,1114168,0,47682935,0,0,0,0,0,0,131072,65536,0,16413276497509,16419376977374,16419377857699,16413277624994
|
||
|
|
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,158654,158654,4194304,256,0,0,8,24,324224,0x7fa6f8a09680,0x7fa6dc626740,11008472,10886347,65536,1376058,1376058,11008464,10894424,1365145,16384,65536,2514687,1564658,1051989,0,47595359,0,0,0,0,0,0,131072,65536,0,16413277636674,16419377929700,16419378790345,16413278754250
|
||
|
|
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,158654,158654,4194304,256,0,0,8,24,326464,0x7fa6fb036500,0x7fa6dc626780,21307800,21183080,65536,2663474,2663474,21307792,21191154,2652922,16384,65536,4964559,2717652,2147736,0,138569124,0,0,0,0,0,0,131072,65536,0,16413278766529,16419378858185,16419380558356,16413280727836
|
||
|
|
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,158654,158654,4194304,256,0,0,8,24,329216,0x7fa6fb036380,0x7fa6dc6267c0,21371224,21228284,65536,2671402,2671402,21371216,21236354,2656839,16384,65536,4968917,2083972,3013087,0,123281657,0,0,0,0,0,0,131072,65536,0,16413280747336,16419380659156,16419382325246,16413282672063
|
||
|
|
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,158654,158654,4194304,256,0,0,12,24,331968,0x7fa6fb036200,0x7fa6dc626800,21360104,21240546,65536,2670012,2670012,21360096,21248616,2659747,16384,65536,4972753,2175743,2644432,0,132346593,0,0,0,0,0,0,131072,65536,0,16413282684193,16419382415487,16419384142217,16413284660279
|
||
|
|
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,158654,158654,4194304,256,0,0,12,24,334720,0x7fa6fb036080,0x7fa6dc626840,21362728,21226457,65536,2670340,2670340,21362720,21234536,2657737,16384,65536,4968279,2075146,2969483,0,111512101,0,0,0,0,0,0,131072,65536,0,16413284672059,16419384228778,16419385946708,16413286642755
|
||
|
|
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,158654,158654,4194304,256,0,0,8,24,337472,0x7fa6f8a09f00,0x7fa6dc626880,21396080,21264410,65536,2674509,2674509,21396072,21272484,2663219,16384,65536,4981538,2146339,2861102,0,129476623,0,0,0,0,0,0,131072,65536,0,16413286655475,16419386032628,16419387707678,16413288593992
|
||
|
|
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,158654,158654,4194304,256,0,0,8,24,0,0x7fa6f8a09d80,0x7fa6dc6268c0,42070456,41931948,65536,5258806,5258806,42070448,41940016,5245379,16384,65536,9871811,2009266,8292233,0,374174125,0,0,0,0,0,0,131072,65536,0,16413288606222,16419387797119,16419391155699,16413292248902
|