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,0,0,0,157596,157596,33554432,256,0,0,4,32,4160,0x0,0x7f3dcc204280,3029720,2939484,524288,378714,378714,3028009,2945891,370029,131072,524288,208770,534570,194898,0,9353793,0,0,0,0,0,0,1572864,524288,0,16379423217189,16385586870073,16385587107675,16379569394275
|
|
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,157596,157596,32768,256,0,0,12,24,13888,0x0,0x7f3dcc223f80,201600,101231,512,25199,25199,201592,109278,14871,128,512,6,518,0,0,0,0,0,0,0,0,0,1024,512,0,16379574609650,16385591946586,16385591956026,16379574748737
|
|
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,157596,157596,4194304,256,0,0,12,24,14336,0x7f3dea9f1380,0x7f3dcc223fc0,1315896,1206067,65536,164486,164486,1315888,1214126,153755,16384,65536,221429,216568,70636,0,1718682,0,0,0,0,0,0,131072,65536,0,16379574791106,16385592030587,16385592123387,16379575140868
|
|
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,157596,157596,4194304,256,0,0,16,24,15040,0x7f3dea9f1200,0x7f3dcc224000,2478592,2368147,65536,309823,309823,2478584,2376214,297449,16384,65536,496529,376181,197601,0,6890987,0,0,0,0,0,0,131072,65536,0,16379575185647,16385592157307,16385592336509,16379575570979
|
|
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,157596,157596,4194304,256,0,0,16,24,15488,0x7f3dea9f1080,0x7f3dcc224040,2487080,2376122,65536,310884,310884,2487072,2384184,299574,16384,65536,497579,369761,187043,0,6723620,0,0,0,0,0,0,131072,65536,0,16379575609908,16385592361309,16385592541310,16379575993149
|
|
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,157596,157596,4194304,256,0,0,12,24,15936,0x7f3de834df00,0x7f3dcc224080,1327296,1217159,65536,165911,165911,1327288,1225232,152857,16384,65536,221335,213573,74232,0,1426120,0,0,0,0,0,0,131072,65536,0,16379576033108,16385592565790,16385592658591,16379576326582
|
|
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,157596,157596,4194304,256,0,0,12,24,16384,0x7f3de834dd80,0x7f3dcc2240c0,1313960,1205122,65536,164244,164244,1313952,1213196,152638,16384,65536,217056,210853,67897,0,1762992,0,0,0,0,0,0,131072,65536,0,16379576366091,16385592683871,16385592775392,16379576655325
|
|
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,157596,157596,4194304,256,0,0,12,24,17088,0x7f3de834dc00,0x7f3dcc224100,1319240,1205546,65536,164904,164904,1319232,1213610,151841,16384,65536,212410,202058,74444,0,2765592,0,0,0,0,0,0,131072,65536,0,16379576709154,16385592817632,16385592909632,16379576984308
|
|
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,157596,157596,4194304,256,0,0,16,24,17792,0x7f3de834da80,0x7f3dcc224140,2499384,2384647,65536,312422,312422,2499376,2392718,297225,16384,65536,495206,375773,198623,0,8129434,0,0,0,0,0,0,131072,65536,0,16379577023217,16385592947873,16385593127874,16379577402008
|
|
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,157596,157596,4194304,256,0,0,16,24,18496,0x7f3de834d900,0x7f3dcc224180,2487832,2368293,65536,310978,310978,2487824,2376372,295774,16384,65536,496190,394060,167531,0,6055127,0,0,0,0,0,0,131072,65536,0,16379577441047,16385593154434,16385593333955,16379577830609
|
|
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,157596,157596,4194304,256,0,0,16,24,19200,0x7f3de834d780,0x7f3dcc2241c0,1315496,1208927,65536,164436,164436,1315488,1216994,153859,16384,65536,223300,217074,65245,0,1901639,0,0,0,0,0,0,131072,65536,0,16379577869538,16385593367556,16385593460676,16379578158202
|
|
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,157596,157596,4194304,256,0,0,16,24,19904,0x7f3de834d600,0x7f3dcc224200,1317704,1208172,65536,164712,164712,1317696,1216248,152633,16384,65536,217901,213827,66710,0,1679930,0,0,0,0,0,0,131072,65536,0,16379578198671,16385593500036,16385593592197,16379578491444
|
|
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,157596,157596,4194304,256,0,0,12,24,20608,0x7f3dea9f1480,0x7f3dcc224240,1314760,1202146,65536,164344,164344,1314752,1210218,151846,16384,65536,173305,176785,58571,0,2592403,0,0,0,0,0,0,131072,65536,0,16379578539123,16385593629637,16385593721958,16379578834437
|
|
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,157596,157596,4194304,256,0,0,16,24,21312,0x7f3dea9f1300,0x7f3dcc224280,2463680,2356149,65536,307959,307959,2463672,2364220,298227,16384,65536,493694,376488,196227,0,8074511,0,0,0,0,0,0,131072,65536,0,16379578876186,16385593758278,16385593938279,16379579215098
|
|
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,157596,157596,4194304,256,0,0,16,24,22016,0x7f3dea9f1180,0x7f3dcc2242c0,2471464,2361635,65536,308932,308932,2471456,2369712,296209,16384,65536,496129,379442,184922,0,6039943,0,0,0,0,0,0,131072,65536,0,16379579253647,16385593973800,16385594154441,16379579598160
|
|
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,157596,157596,4194304,256,0,0,16,24,22720,0x7f3dea9f1000,0x7f3dcc224300,1305136,1199525,65536,163141,163141,1305128,1207594,152410,16384,65536,212758,207729,71735,0,2224259,0,0,0,0,0,0,131072,65536,0,16379579637919,16385594180521,16385594272842,16379579892213
|
|
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,157596,157596,4194304,256,0,0,12,24,23424,0x7f3de834de80,0x7f3dcc224340,1305040,1196013,65536,163129,163129,1305032,1204080,153185,16384,65536,200617,198730,65670,0,2005584,0,0,0,0,0,0,131072,65536,0,16379579930982,16385594303082,16385594394762,16379580192977
|
|
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,157596,157596,4194304,256,0,0,12,24,24128,0x7f3de834dd00,0x7f3dcc224380,1302920,1195572,65536,162864,162864,1302912,1203642,150726,16384,65536,193080,187563,57998,0,1805504,0,0,0,0,0,0,131072,65536,0,16379580239666,16385594428363,16385594519883,16379580489500
|
|
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,157596,157596,4194304,256,0,0,16,24,24832,0x7f3de834db80,0x7f3dcc2243c0,2468976,2362186,65536,308621,308621,2468968,2370256,297894,16384,65536,495001,378531,181640,0,8057723,0,0,0,0,0,0,131072,65536,0,16379580528799,16385594546763,16385594726925,16379580875261
|
|
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,157596,157596,4194304,256,0,0,16,24,25536,0x7f3de834da00,0x7f3dcc224400,2460200,2342057,65536,307524,307524,2460192,2350112,296441,16384,65536,496742,384686,171250,0,6254855,0,0,0,0,0,0,131072,65536,0,16379580914501,16385594754605,16385594934446,16379581259163
|
|
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,157596,157596,4194304,256,0,0,12,24,26240,0x7f3de834d880,0x7f3dcc224440,1314952,1205410,65536,164368,164368,1314944,1213474,152297,16384,65536,201671,196741,70756,0,2588653,0,0,0,0,0,0,131072,65536,0,16379581298272,16385594959566,16385595052367,16379581555466
|
|
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,157596,157596,4194304,256,0,0,12,24,26944,0x7f3de834d700,0x7f3dcc224480,1324776,1209248,65536,165596,165596,1324768,1217320,152185,16384,65536,185005,187871,71400,0,2215593,0,0,0,0,0,0,131072,65536,0,16379581595075,16385595095567,16385595187728,16379581855350
|
|
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,157596,157596,4194304,256,0,0,12,24,27648,0x7f3dea9f1580,0x7f3dcc2244c0,1297720,1193067,65536,162214,162214,1297712,1201132,151062,16384,65536,221333,208361,75932,0,2539487,0,0,0,0,0,0,131072,65536,0,16379581902839,16385595221808,16385595313489,16379582158963
|
|
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,157596,157596,4194304,256,0,0,16,24,28608,0x7f3dea9f1400,0x7f3dcc224500,2467032,2355444,65536,308378,308378,2467024,2363518,298905,16384,65536,494382,377217,202861,0,8665991,0,0,0,0,0,0,131072,65536,0,16379582202072,16385595342289,16385595521650,16379582549724
|
|
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,157596,157596,4194304,256,0,0,16,24,29312,0x7f3dea9f1280,0x7f3dcc224540,2445976,2340300,65536,305746,305746,2445968,2348374,298011,16384,65536,492998,387907,178061,0,5439418,0,0,0,0,0,0,131072,65536,0,16379582588874,16385595547250,16385595727731,16379582949466
|
|
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,157596,157596,4194304,256,0,0,12,24,30016,0x7f3dea9f1100,0x7f3dcc224580,1309256,1200447,65536,163656,163656,1309248,1208516,151291,16384,65536,214999,201101,79855,0,2503233,0,0,0,0,0,0,131072,65536,0,16379582989925,16385595754771,16385595847092,16379583245049
|
|
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,157596,157596,4194304,256,0,0,8,24,30976,0x7f3de834df80,0x7f3dcc2245c0,1293880,1184402,65536,161734,161734,1293872,1192466,150622,16384,65536,219533,215505,75035,0,2158198,0,0,0,0,0,0,131072,65536,0,16379583284578,16385595874292,16385595966293,16379583540273
|
|
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,157596,157596,4194304,256,0,0,12,24,31680,0x7f3de834de00,0x7f3dcc224600,1298328,1191955,65536,162290,162290,1298320,1200024,151399,16384,65536,208592,201316,60592,0,2056722,0,0,0,0,0,0,131072,65536,0,16379583585792,16385596000533,16385596092214,16379583838586
|
|
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,157596,157596,4194304,256,0,0,16,24,32640,0x7f3de834dc80,0x7f3dcc224640,2457520,2348568,65536,307189,307189,2457512,2356636,296105,16384,65536,488425,382844,179114,0,7552287,0,0,0,0,0,0,131072,65536,0,16379583878895,16385596121174,16385596300855,16379584236747
|
|
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,157596,157596,4194304,256,0,0,12,24,33600,0x7f3de834db00,0x7f3dcc224680,2442160,2335632,65536,305269,305269,2442152,2343698,296110,16384,65536,490563,364097,182624,0,6203191,0,0,0,0,0,0,131072,65536,0,16379584276806,16385596325655,16385596504856,16379584618029
|
|
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,157596,157596,4194304,256,0,0,12,24,34560,0x7f3de834d980,0x7f3dcc2246c0,1312584,1202548,65536,164072,164072,1312576,1210616,153073,16384,65536,140129,156875,73385,0,2712225,0,0,0,0,0,0,131072,65536,0,16379584660328,16385596531257,16385596623577,16379584918662
|
|
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,157596,157596,4194304,256,0,0,8,24,35520,0x7f3de834d800,0x7f3dcc224700,1309000,1195502,65536,163624,163624,1308992,1203574,152065,16384,65536,220588,213736,71920,0,2103336,0,0,0,0,0,0,131072,65536,0,16379584958441,16385596653017,16385596745818,16379585214686
|
|
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,157596,157596,4194304,256,0,0,12,24,36224,0x7f3de834d680,0x7f3dcc224740,1300264,1194710,65536,162532,162532,1300256,1202770,150619,16384,65536,207661,203689,78600,0,1909810,0,0,0,0,0,0,131072,65536,0,16379585260285,16385596778618,16385596870459,16379585515509
|
|
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,157596,157596,4194304,256,0,0,12,24,37184,0x7f3dea9f1500,0x7f3dcc224780,2453536,2343536,65536,306691,306691,2453528,2351606,294874,16384,65536,487823,359843,189432,0,8021365,0,0,0,0,0,0,131072,65536,0,16379585556028,16385596905659,16385597084860,16379585899451
|
|
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,157596,157596,4194304,256,0,0,12,24,38144,0x7f3dea9f1380,0x7f3dcc2247c0,2447200,2341809,65536,305899,305899,2447192,2349882,296778,16384,65536,488101,363940,184236,0,6089868,0,0,0,0,0,0,131072,65536,0,16379585938980,16385597113501,16385597293182,16379586293432
|
|
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,157596,157596,4194304,256,0,0,12,24,39104,0x7f3dea9f1200,0x7f3dcc224800,1305672,1195767,65536,163208,163208,1305664,1203834,152073,16384,65536,174098,177747,70860,0,1872309,0,0,0,0,0,0,131072,65536,0,16379586334721,16385597318302,16385597410943,16379586592635
|
|
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,157596,157596,4194304,256,0,0,8,24,40320,0x7f3dea9f1080,0x7f3dcc224840,1297680,1190581,65536,162209,162209,1297672,1198640,150278,16384,65536,168342,178828,60086,0,1728310,0,0,0,0,0,0,131072,65536,0,16379586632245,16385597436543,16385597528863,16379586891999
|
|
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,157596,157596,4194304,256,0,0,12,24,41280,0x7f3de834df00,0x7f3dcc224880,1296192,1187059,65536,162023,162023,1296184,1195118,151513,16384,65536,169362,176787,71853,0,1947105,0,0,0,0,0,0,131072,65536,0,16379586938828,16385597562144,16385597654784,16379587188942
|
|
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,157596,157596,4194304,256,0,0,12,24,42240,0x7f3de834dd80,0x7f3dcc2248c0,2446568,2337961,65536,305820,305820,2446560,2346032,294203,16384,65536,487466,393151,184887,0,7768177,0,0,0,0,0,0,131072,65536,0,16379587228761,16385597680064,16385597859586,16379587573604
|
|
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,157596,157596,4194304,256,0,0,12,24,43200,0x7f3de834dc00,0x7f3dcc224900,2453192,2347351,65536,306648,306648,2453184,2355420,295995,16384,65536,490333,386410,161763,0,6315375,0,0,0,0,0,0,131072,65536,0,16379587611953,16385597889826,16385598069187,16379587964155
|
|
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,157596,157596,4194304,256,0,0,8,24,44160,0x7f3de834da80,0x7f3dcc224940,1307000,1197745,65536,163374,163374,1306992,1205816,151290,16384,65536,167419,170070,75452,0,1823690,0,0,0,0,0,0,131072,65536,0,16379588003664,16385598117347,16385598209988,16379588262109
|
|
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,157596,157596,4194304,256,0,0,12,24,45376,0x7f3de834d900,0x7f3dcc224980,1298904,1190785,65536,162362,162362,1298896,1198850,150953,16384,65536,198674,192443,77176,0,2160543,0,0,0,0,0,0,131072,65536,0,16379588301038,16385598237188,16385598330469,16379588556712
|
|
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,157596,157596,4194304,256,0,0,12,24,46336,0x7f3de834d780,0x7f3dcc2249c0,1304288,1196001,65536,163035,163035,1304280,1204052,150502,16384,65536,161121,171144,71663,0,2104592,0,0,0,0,0,0,131072,65536,0,16379588602921,16385598364069,16385598456069,16379588861875
|
|
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,157596,157596,4194304,256,0,0,12,24,47552,0x7f3de834d600,0x7f3dcc224a00,2438184,2324736,65536,304772,304772,2438176,2332804,293422,16384,65536,485052,379149,177410,0,7694503,0,0,0,0,0,0,131072,65536,0,16379588902855,16385598488230,16385598669031,16379589245187
|
|
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,157596,157596,4194304,256,0,0,12,24,48512,0x7f3dea9f1480,0x7f3dcc224a40,2437272,2326659,65536,304658,304658,2437264,2334730,291290,16384,65536,483810,383202,178688,0,5553009,0,0,0,0,0,0,131072,65536,0,16379589284116,16385598692391,16385598871912,16379589627699
|
|
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,157596,157596,4194304,256,0,0,8,24,49472,0x7f3dea9f1300,0x7f3dcc224a80,1298296,1189135,65536,162286,162286,1298288,1197196,149726,16384,65536,217673,213763,73198,0,1698309,0,0,0,0,0,0,131072,65536,0,16379589666978,16385598895432,16385598988233,16379589924362
|
|
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,157596,157596,4194304,256,0,0,12,24,50688,0x7f3dea9f1180,0x7f3dcc224ac0,1291800,1183457,65536,161474,161474,1291792,1191520,149494,16384,65536,217133,203062,74615,0,2089957,0,0,0,0,0,0,131072,65536,0,16379589965051,16385599011753,16385599103754,16379590232715
|
|
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,157596,157596,4194304,256,0,0,12,24,51648,0x7f3dea9f1000,0x7f3dcc224b00,1289264,1180475,65536,161157,161157,1289256,1188542,149275,16384,65536,197469,196685,70136,0,2115563,0,0,0,0,0,0,131072,65536,0,16379590279534,16385599135754,16385599227595,16379590536259
|
|
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,157596,157596,4194304,256,0,0,12,24,52864,0x7f3de834de80,0x7f3dcc224b40,2424312,2317831,65536,303038,303038,2424304,2325896,291953,16384,65536,483567,374668,176851,0,7427926,0,0,0,0,0,0,131072,65536,0,16379590575008,16385599253515,16385599431596,16379590922300
|
|
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,157596,157596,4194304,256,0,0,12,24,54080,0x7f3de834dd00,0x7f3dcc224b80,2404344,2297016,65536,300542,300542,2404336,2305082,290729,16384,65536,481950,371166,168079,0,5611247,0,0,0,0,0,0,131072,65536,0,16379590960819,16385599456876,16385599634797,16379591303482
|
|
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,157596,157596,4194304,256,0,0,8,24,55296,0x7f3de834db80,0x7f3dcc224bc0,1298040,1186227,65536,162254,162254,1298032,1194288,151177,16384,65536,174658,177614,72460,0,2201961,0,0,0,0,0,0,131072,65536,0,16379591342111,16385599657997,16385599750158,16379591599445
|
|
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,157596,157596,4194304,256,0,0,12,24,56768,0x7f3de834da00,0x7f3dcc224c00,1290224,1183477,65536,161277,161277,1290216,1191550,150499,16384,65536,210396,198916,75451,0,2037006,0,0,0,0,0,0,131072,65536,0,16379591638484,16385599773998,16385599867279,16379591896978
|
|
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,157596,157596,4194304,256,0,0,12,24,57728,0x7f3de834d880,0x7f3dcc224c40,1294744,1184779,65536,161842,161842,1294736,1192838,150841,16384,65536,212677,206209,63480,0,1999870,0,0,0,0,0,0,131072,65536,0,16379591943827,16385599899439,16385599991280,16379592198642
|
|
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,157596,157596,4194304,256,0,0,12,24,58944,0x7f3de834d700,0x7f3dcc224c80,2425120,2315637,65536,303139,303139,2425112,2323712,289383,16384,65536,483831,371077,167893,0,6909018,0,0,0,0,0,0,131072,65536,0,16379592237081,16385600014640,16385600194161,16379592580783
|
|
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,157596,157596,4194304,256,0,0,12,24,60160,0x7f3dea9f1580,0x7f3dcc224cc0,2416776,2306047,65536,302096,302096,2416768,2314124,292519,16384,65536,485732,374137,166176,0,5748730,0,0,0,0,0,0,131072,65536,0,16379592619492,16385600217361,16385600398482,16379592961815
|
|
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,157596,157596,4194304,256,0,0,8,24,61376,0x7f3dea9f1400,0x7f3dcc224d00,1299216,1191081,65536,162401,162401,1299208,1199150,151174,16384,65536,217346,206768,77540,0,2341716,0,0,0,0,0,0,131072,65536,0,16379593001164,16385600422163,16385600515603,16379593264728
|
|
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,157596,157596,4194304,256,0,0,12,24,62848,0x7f3dea9f1280,0x7f3dcc224d40,1346328,1231969,65536,168290,168290,1346320,1240040,156214,16384,65536,226623,208328,87217,0,2572926,0,0,0,0,0,0,131072,65536,0,16379593305157,16385600541523,16385600639284,16379593566331
|
|
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,157596,157596,4194304,256,0,0,12,24,63808,0x7f3dea9f1100,0x7f3dcc224d80,1303216,1194192,65536,162901,162901,1303208,1202264,150841,16384,65536,157641,169743,55144,0,1655311,0,0,0,0,0,0,131072,65536,0,16379593613850,16385600671444,16385600764085,16379593859775
|
|
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,157596,157596,4194304,256,0,0,12,24,65024,0x7f3de834df80,0x7f3dcc224dc0,2405208,2298224,65536,300650,300650,2405200,2306280,291959,16384,65536,483407,370114,165571,0,6947586,0,0,0,0,0,0,131072,65536,0,16379593898384,16385600791285,16385600970166,16379594239426
|
|
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,157596,157596,4194304,256,0,0,12,24,66240,0x7f3de834de00,0x7f3dcc224e00,2411328,2301803,65536,301415,301415,2411320,2309866,288369,16384,65536,462204,369797,169267,0,5471523,0,0,0,0,0,0,131072,65536,0,16379594279616,16385600994326,16385601172888,16379594625468
|
|
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,157596,157596,4194304,256,0,0,8,24,67456,0x7f3de834dc80,0x7f3dcc224e40,1305696,1196160,65536,163211,163211,1305688,1204226,150502,16384,65536,199580,197267,74129,0,1887809,0,0,0,0,0,0,131072,65536,0,16379594665227,16385601197688,16385601290328,16379594923561
|
|
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,157596,157596,4194304,256,0,0,12,24,68928,0x7f3de834db00,0x7f3dcc224e80,1411480,1296526,65536,176434,176434,1411472,1304590,163610,16384,65536,241271,218652,90426,0,2795082,0,0,0,0,0,0,131072,65536,0,16379594962351,16385601313689,16385601415609,16379595230995
|
|
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,157596,157596,4194304,256,0,0,12,24,70144,0x7f3de834d980,0x7f3dcc224ec0,1283048,1176376,65536,160380,160380,1283040,1184456,149166,16384,65536,198760,193471,65774,0,1937504,0,0,0,0,0,0,131072,65536,0,16379595277004,16385601448249,16385601540410,16379595532018
|
|
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,157596,157596,4194304,256,0,0,12,24,71616,0x7f3de834d800,0x7f3dcc224f00,2426656,2322186,65536,303331,303331,2426648,2330252,290619,16384,65536,484162,375552,171290,0,7043997,0,0,0,0,0,0,131072,65536,0,16379595570417,16385601564570,16385601744251,16379595913900
|
|
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,157596,157596,4194304,256,0,0,12,24,72832,0x7f3de834d680,0x7f3dcc224f40,2430984,2321833,65536,303872,303872,2430976,2329888,291515,16384,65536,483873,378245,177409,0,6810875,0,0,0,0,0,0,131072,65536,0,16379595952229,16385601768252,16385601946653,16379596298411
|
|
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,157596,157596,4194304,256,0,0,8,24,74048,0x7f3dea9f1500,0x7f3dcc224f80,1283536,1177772,65536,160441,160441,1283528,1185854,148378,16384,65536,212766,197239,68130,0,1890822,0,0,0,0,0,0,131072,65536,0,16379596336420,16385601970013,16385602061854,16379596593055
|
|
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,157596,157596,4194304,256,0,0,12,24,75776,0x7f3dea9f1380,0x7f3dcc224fc0,1450968,1338829,65536,181370,181370,1450960,1346898,170110,16384,65536,250213,219640,98233,0,2973253,0,0,0,0,0,0,131072,65536,0,16379596632774,16385602101854,16385602207454,16379596909128
|
|
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,157596,157596,4194304,256,0,0,12,24,76992,0x7f3dea9f1200,0x7f3dcc225000,1299600,1186012,65536,162449,162449,1299592,1194074,150506,16384,65536,194648,191708,78271,0,2189202,0,0,0,0,0,0,131072,65536,0,16379596970006,16385602239935,16385602332735,16379597209811
|
|
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,157596,157596,4194304,256,0,0,12,24,78464,0x7f3dea9f1080,0x7f3dcc225040,2405496,2299362,65536,300686,300686,2405488,2307430,290947,16384,65536,480174,380023,182373,0,6898849,0,0,0,0,0,0,131072,65536,0,16379597248780,16385602356575,16385602537057,16379597604942
|
|
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,157596,157596,4194304,256,0,0,12,24,79936,0x7f3de834df00,0x7f3dcc225080,2432728,2313743,65536,304090,304090,2432720,2321804,290617,16384,65536,482939,372946,176453,0,7079992,0,0,0,0,0,0,131072,65536,0,16379597644922,16385602560257,16385602740738,16379597992274
|
|
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,157596,157596,4194304,256,0,0,8,24,81408,0x7f3de834dd80,0x7f3dcc2250c0,1290904,1180991,65536,161362,161362,1290896,1189056,151401,16384,65536,198006,192853,71997,0,2247819,0,0,0,0,0,0,131072,65536,0,16379598030503,16385602765218,16385602858979,16379598312307
|
|
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,157596,157596,4194304,256,0,0,12,24,83136,0x7f3de834dc00,0x7f3dcc225100,1518944,1410870,65536,189867,189867,1518936,1418940,179395,16384,65536,268230,241681,108622,0,3263810,0,0,0,0,0,0,131072,65536,0,16379598351076,16385602881539,16385602993380,16379598629160
|
|
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,157596,157596,4194304,256,0,0,12,24,84352,0x7f3de834da80,0x7f3dcc225140,1287440,1179956,65536,160929,160929,1287432,1188014,149611,16384,65536,201148,195246,74228,0,2107903,0,0,0,0,0,0,131072,65536,0,16379598676539,16385603040740,16385603133381,16379598934173
|
|
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,157596,157596,4194304,256,0,0,12,24,85824,0x7f3de834d900,0x7f3dcc225180,2400984,2295338,65536,300122,300122,2400976,2303392,289489,16384,65536,486047,376242,193303,0,7606641,0,0,0,0,0,0,131072,65536,0,16379598972472,16385603158021,16385603336422,16379599315425
|
|
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,157596,157596,4194304,256,0,0,12,24,87296,0x7f3de834d780,0x7f3dcc2251c0,2399664,2293217,65536,299957,299957,2399656,2301286,290286,16384,65536,480805,368507,173584,0,6789866,0,0,0,0,0,0,131072,65536,0,16379599355244,16385603360262,16385603538823,16379599697726
|
|
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,157596,157596,4194304,256,0,0,12,24,88768,0x7f3de834d600,0x7f3dcc225200,1294936,1188831,65536,161866,161866,1294928,1196902,149268,16384,65536,192348,186924,71065,0,2291344,0,0,0,0,0,0,131072,65536,0,16379599736096,16385603562024,16385603656104,16379599992240
|
|
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,157596,157596,4194304,256,0,0,12,24,90752,0x7f3dea9f1480,0x7f3dcc225240,1601840,1491590,65536,200229,200229,1601832,1499672,188025,16384,65536,288711,256866,96066,0,3169674,0,0,0,0,0,0,131072,65536,0,16379600032789,16385603679464,16385603798345,16379600313363
|
|
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,157596,157596,4194304,256,0,0,12,24,91968,0x7f3dea9f1300,0x7f3dcc225280,1286856,1177881,65536,160856,160856,1286848,1185956,149489,16384,65536,200612,186180,71145,0,2161508,0,0,0,0,0,0,131072,65536,0,16379600359362,16385603830505,16385603922986,16379600607966
|
|
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,157596,157596,4194304,256,0,0,12,24,93440,0x7f3dea9f1180,0x7f3dcc2252c0,2404880,2298405,65536,300609,300609,2404872,2306474,289827,16384,65536,486620,381939,172515,0,7334944,0,0,0,0,0,0,131072,65536,0,16379600648785,16385603946506,16385604125387,16379600994858
|
|
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,157596,157596,4194304,256,0,0,12,24,94912,0x7f3dea9f1000,0x7f3dcc225300,2391880,2285267,65536,298984,298984,2391872,2293324,290391,16384,65536,478763,362817,164676,0,5327998,0,0,0,0,0,0,131072,65536,0,16379601034507,16385604148587,16385604327789,16379601375999
|
|
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,157596,157596,4194304,256,0,0,12,24,96384,0x7f3de834de80,0x7f3dcc225340,1297544,1188587,65536,162192,162192,1297536,1196668,150057,16384,65536,213119,201422,77212,0,2176680,0,0,0,0,0,0,131072,65536,0,16379601415369,16385604350989,16385604445389,16379601673063
|
|
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,157596,157596,4194304,256,0,0,12,24,98368,0x7f3de834dd00,0x7f3dcc225380,1681952,1574696,65536,210243,210243,1681944,1582768,198218,16384,65536,302828,259556,103541,0,3627947,0,0,0,0,0,0,131072,65536,0,16379601711412,16385604468590,16385604592270,16379601998876
|
|
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,157596,157596,4194304,256,0,0,12,24,99584,0x7f3de834db80,0x7f3dcc2253c0,1289792,1182395,65536,161223,161223,1289784,1190454,149502,16384,65536,212748,199143,78633,0,1907162,0,0,0,0,0,0,131072,65536,0,16379602044405,16385604621071,16385604713391,16379602305749
|
|
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,157596,157596,4194304,256,0,0,12,24,101312,0x7f3de834da00,0x7f3dcc225400,2378400,2272472,65536,297299,297299,2378392,2280546,287150,16384,65536,478442,359998,179471,0,6899685,0,0,0,0,0,0,131072,65536,0,16379602344458,16385604737391,16385604915473,16379602689901
|
|
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,157596,157596,4194304,256,0,0,12,24,102784,0x7f3de834d880,0x7f3dcc225440,2392160,2284317,65536,299019,299019,2392152,2292378,287587,16384,65536,477936,364715,168210,0,5775901,0,0,0,0,0,0,131072,65536,0,16379602729530,16385604939313,16385605120114,16379603074912
|
|
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,157596,157596,4194304,256,0,0,12,24,104256,0x7f3de834d700,0x7f3dcc225480,1290976,1183221,65536,161371,161371,1290968,1191288,148379,16384,65536,213615,199496,74253,0,2293766,0,0,0,0,0,0,131072,65536,0,16379603113861,16385605143474,16385605236915,16379603377015
|
|
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,157596,157596,4194304,256,0,0,12,24,106240,0x7f3dea9f1580,0x7f3dcc2254c0,1750336,1639898,65536,218791,218791,1750328,1647980,205726,16384,65536,323371,274417,116387,0,3624211,0,0,0,0,0,0,131072,65536,0,16379603416405,16385605261555,16385605390836,16379603709218
|
|
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,157596,157596,4194304,256,0,0,12,24,107712,0x7f3dea9f1400,0x7f3dcc225500,1280784,1171863,65536,160097,160097,1280776,1179928,148379,16384,65536,196898,187077,84008,0,2149253,0,0,0,0,0,0,131072,65536,0,16379603756757,16385605422996,16385605515317,16379604009201
|
|
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,157596,157596,4194304,256,0,0,16,24,109440,0x7f3dea9f1280,0x7f3dcc225540,2398336,2290031,65536,299791,299791,2398328,2298080,286030,16384,65536,474834,365746,178029,0,6636015,0,0,0,0,0,0,131072,65536,0,16379604048101,16385605541237,16385605720438,16379604389813
|
|
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,157596,157596,4194304,256,0,0,16,24,111168,0x7f3dea9f1100,0x7f3dcc225580,2393544,2282079,65536,299192,299192,2393536,2290148,287923,16384,65536,473196,362650,171796,0,6405672,0,0,0,0,0,0,131072,65536,0,16379604429222,16385605743638,16385605923159,16379604772775
|
|
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,157596,157596,4194304,256,0,0,8,24,112896,0x7f3de834df80,0x7f3dcc2255c0,1304592,1194427,65536,163073,163073,1304584,1202494,149275,16384,65536,214460,197132,79758,0,2618819,0,0,0,0,0,0,131072,65536,0,16379604812154,16385605947959,16385606042680,16379605070708
|
|
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,157596,157596,4194304,256,0,0,12,24,115136,0x7f3de834de00,0x7f3dcc225600,1831480,1720900,65536,228934,228934,1831472,1728970,216810,16384,65536,344903,279756,94376,0,3019622,0,0,0,0,0,0,131072,65536,0,16379605109467,16385606066680,16385606202521,16379605425790
|
|
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,157596,157596,4194304,256,0,0,12,24,116608,0x7f3de834dc80,0x7f3dcc225640,1284488,1175677,65536,160560,160560,1284480,1183750,149271,16384,65536,210451,196325,81960,0,2598835,0,0,0,0,0,0,131072,65536,0,16379605471649,16385606235641,16385606328922,16379605727804
|
|
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,157596,157596,4194304,256,0,0,16,24,118336,0x7f3de834db00,0x7f3dcc225680,2392784,2282810,65536,299097,299097,2392776,2290886,286363,16384,65536,475063,368912,180791,0,6612142,0,0,0,0,0,0,131072,65536,0,16379605767163,16385606352442,16385606531963,16379606115745
|
|
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,157596,157596,4194304,256,0,0,16,24,120064,0x7f3de834d980,0x7f3dcc2256c0,2386376,2269809,65536,298296,298296,2386368,2277890,286139,16384,65536,478103,363512,178482,0,6051441,0,0,0,0,0,0,131072,65536,0,16379606155464,16385606555163,16385606736445,16379606503717
|
|
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,157596,157596,4194304,256,0,0,12,24,121792,0x7f3de834d800,0x7f3dcc225700,1311032,1199293,65536,163878,163878,1311024,1207370,150951,16384,65536,214181,201802,86038,0,2737743,0,0,0,0,0,0,131072,65536,0,16379606542186,16385606760925,16385606855965,16379606805780
|
|
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,157596,157596,4194304,256,0,0,12,24,124032,0x7f3de834d680,0x7f3dcc225740,1899856,1791113,65536,237481,237481,1899848,1799182,226106,16384,65536,359156,306594,143274,0,4048236,0,0,0,0,0,0,131072,65536,0,16379606845589,16385606879486,16385607021247,16379607150342
|
|
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,157596,157596,4194304,256,0,0,12,24,125504,0x7f3dea9f1500,0x7f3dcc225780,1283712,1174406,65536,160463,160463,1283704,1182468,148259,16384,65536,209404,197523,75900,0,2180962,0,0,0,0,0,0,131072,65536,0,16379607197101,16385607053407,16385607146687,16379607444956
|
|
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,157596,157596,4194304,256,0,0,12,24,127488,0x7f3dea9f1380,0x7f3dcc2257c0,2372016,2266947,65536,296501,296501,2372008,2275008,285351,16384,65536,475456,369400,169693,0,5386591,0,0,0,0,0,0,131072,65536,0,16379607484035,16385607170048,16385607348609,16379607825967
|
|
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,157596,157596,4194304,256,0,0,12,24,129216,0x7f3dea9f1200,0x7f3dcc225800,2375952,2266861,65536,296993,296993,2375944,2274934,285577,16384,65536,477417,356996,175317,0,5204489,0,0,0,0,0,0,131072,65536,0,16379607865856,16385607371969,16385607551330,16379608209779
|
|
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,157596,157596,4194304,256,0,0,12,24,130944,0x7f3dea9f1080,0x7f3dcc225840,1353648,1245777,65536,169205,169205,1353640,1253848,157562,16384,65536,232629,210088,86430,0,2665226,0,0,0,0,0,0,131072,65536,0,16379608249018,16385607575010,16385607673571,16379608511952
|
|
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,157596,157596,4194304,256,0,0,12,24,133440,0x7f3de834df00,0x7f3dcc225880,2062936,1954975,65536,257866,257866,2062928,1963048,247161,16384,65536,400574,315530,152777,0,5235139,0,0,0,0,0,0,131072,65536,0,16379608550411,16385607696771,16385607849732,16379608872744
|
|
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,157596,157596,4194304,256,0,0,12,24,134912,0x7f3de834dd80,0x7f3dcc2258c0,1281440,1175959,65536,160179,160179,1281432,1184024,148823,16384,65536,194749,182831,79287,0,2169558,0,0,0,0,0,0,131072,65536,0,16379608920463,16385607881892,16385607975013,16379609177717
|
|
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,157596,157596,4194304,256,0,0,12,24,136896,0x7f3de834dc00,0x7f3dcc225900,2367168,2259910,65536,295895,295895,2367160,2267972,285239,16384,65536,473707,363676,183915,0,5099670,0,0,0,0,0,0,131072,65536,0,16379609217206,16385607998533,16385608177254,16379609560549
|
|
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,157596,157596,4194304,256,0,0,12,24,138880,0x7f3de834da80,0x7f3dcc225940,2358928,2252255,65536,294865,294865,2358920,2260330,284011,16384,65536,473156,362920,181326,0,6314406,0,0,0,0,0,0,131072,65536,0,16379609601188,16385608201734,16385608381096,16379609941920
|
|
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,157596,157596,4194304,256,0,0,12,24,140864,0x7f3de834d900,0x7f3dcc225980,1425368,1314048,65536,178170,178170,1425360,1322122,167299,16384,65536,247857,208300,104583,0,3269764,0,0,0,0,0,0,131072,65536,0,16379609980809,16385608404136,16385608507817,16379610262873
|
|
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,157596,157596,4194304,256,0,0,12,24,143616,0x7f3de834d780,0x7f3dcc2259c0,2226104,2107071,65536,278262,278262,2226096,2115136,265747,16384,65536,435777,338614,159166,0,6756875,0,0,0,0,0,0,131072,65536,0,16379610301832,16385608531177,16385608699178,16379610637735
|
|
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,157596,157596,4194304,256,0,0,12,24,145344,0x7f3de834d600,0x7f3dcc225a00,1281096,1172557,65536,160136,160136,1281088,1180620,148826,16384,65536,215513,196534,78860,0,2384624,0,0,0,0,0,0,131072,65536,0,16379610684504,16385608731818,16385608826219,16379610936358
|
|
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,157596,157596,4194304,256,0,0,12,24,147584,0x7f3dea9f1480,0x7f3dcc225a40,2364584,2257138,65536,295572,295572,2364576,2265206,283897,16384,65536,459417,365859,162623,0,5688963,0,0,0,0,0,0,131072,65536,0,16379610974938,16385608849579,16385609028620,16379611330180
|
|
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,157596,157596,4194304,256,0,0,12,24,149568,0x7f3dea9f1300,0x7f3dcc225a80,2363288,2256665,65536,295410,295410,2363280,2264742,284574,16384,65536,473627,358030,190920,0,6042041,0,0,0,0,0,0,131072,65536,0,16379611369779,16385609051500,16385609231661,16379611718691
|
|
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,157596,157596,4194304,256,0,0,12,24,151552,0x7f3dea9f1180,0x7f3dcc225ac0,1483888,1372950,65536,185485,185485,1483880,1381020,173806,16384,65536,260228,217785,95942,0,2575369,0,0,0,0,0,0,131072,65536,0,16379611758360,16385609254541,16385609363182,16379612034584
|
|
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,157596,157596,4194304,256,0,0,12,24,154304,0x7f3dea9f1000,0x7f3dcc225b00,2370648,2263835,65536,296330,296330,2370640,2271898,285582,16384,65536,473174,368716,206243,0,7495782,0,0,0,0,0,0,131072,65536,0,16379612074013,16385609386062,16385609565104,16379612419176
|
|
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,157596,157596,4194304,256,0,0,12,24,156288,0x7f3de834de80,0x7f3dcc225b40,1371784,1260303,65536,171472,171472,1371776,1268364,160471,16384,65536,226766,205611,93896,0,2547581,0,0,0,0,0,0,131072,65536,0,16379612464885,16385609597264,16385609697264,16379612723559
|
|
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,157596,157596,4194304,256,0,0,12,24,158784,0x7f3de834dd00,0x7f3dcc225b80,2376992,2266589,65536,297123,297123,2376984,2274666,286474,16384,65536,476990,366154,165615,0,4104042,0,0,0,0,0,0,131072,65536,0,16379612762598,16385609721425,16385609903666,16379613109491
|
|
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,157596,157596,4194304,256,0,0,12,24,161024,0x7f3de834db80,0x7f3dcc225bc0,2368872,2256275,65536,296108,296108,2368864,2264342,285689,16384,65536,468633,366455,165539,0,4748244,0,0,0,0,0,0,131072,65536,0,16379613149150,16385609927346,16385610109907,16379613492412
|
|
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,157596,157596,4194304,256,0,0,12,24,163264,0x7f3de834da00,0x7f3dcc225c00,1644944,1530233,65536,205617,205617,1644936,1538292,193289,16384,65536,298631,256610,124890,0,4551404,0,0,0,0,0,0,131072,65536,0,16379613530781,16385610134387,16385610255508,16379613820105
|
|
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,157596,157596,4194304,256,0,0,12,24,166528,0x7f3de834d880,0x7f3dcc225c40,2704192,2594708,65536,338023,338023,2704184,2602770,327242,16384,65536,550421,363537,206090,0,7494873,0,0,0,0,0,0,131072,65536,0,16379613859064,16385610278708,16385610483350,16379614260375
|
|
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,157596,157596,4194304,256,0,0,12,24,168512,0x7f3de834d700,0x7f3dcc225c80,1478872,1362954,65536,184858,184858,1478864,1371016,170547,16384,65536,255950,222362,98098,0,3133597,0,0,0,0,0,0,131072,65536,0,16379614284165,16385610526390,16385610635191,16379614562249
|
|
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,157596,157596,4194304,256,0,0,12,24,171264,0x7f3dea9f1580,0x7f3dcc225cc0,2375072,2238561,65536,296883,296883,2375064,2246630,286359,16384,65536,416000,325903,154173,0,4865551,0,0,0,0,0,0,131072,65536,0,16379614601278,16385610661751,16385610844472,16379614951250
|
|
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,157596,157596,4194304,256,0,0,12,24,173760,0x7f3dea9f1400,0x7f3dcc225d00,2394736,2263194,65536,299341,299341,2394728,2271262,288822,16384,65536,477768,366338,174380,0,4880134,0,0,0,0,0,0,131072,65536,0,16379614990689,16385610867672,16385611050553,16379615337962
|
|
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,157596,157596,4194304,256,0,0,12,24,176256,0x7f3dea9f1280,0x7f3dcc225d40,1794904,1684142,65536,224362,224362,1794896,1692228,210985,16384,65536,334601,266531,127758,0,5027938,0,0,0,0,0,0,131072,65536,0,16379615376661,16385611073914,16385611206555,16379615677454
|
|
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,157596,157596,4194304,256,0,0,12,24,179776,0x7f3dea9f1100,0x7f3dcc225d80,3024704,2912578,65536,378087,378087,3024696,2920660,366779,16384,65536,629390,444348,244899,0,10218817,0,0,0,0,0,0,131072,65536,0,16379615717353,16385611230235,16385611460316,16379616128424
|
|
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,157596,157596,4194304,256,0,0,12,24,182272,0x7f3de834df80,0x7f3dcc225dc0,1684088,1575694,65536,210510,210510,1684080,1583766,198782,16384,65536,309685,258937,106683,0,3676562,0,0,0,0,0,0,131072,65536,0,16379616159203,16385611502556,16385611627837,16379616445587
|
|
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,157596,157596,4194304,256,0,0,12,24,185536,0x7f3de834de00,0x7f3dcc225e00,2455912,2328413,65536,306988,306988,2455904,2336478,296442,16384,65536,482767,377503,177707,0,4504355,0,0,0,0,0,0,131072,65536,0,16379616485766,16385611651997,16385611843039,16379616853338
|
|
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,157596,157596,4194304,256,0,0,12,24,188544,0x7f3de834dc80,0x7f3dcc225e40,2492912,2352511,65536,311613,311613,2492904,2360570,301811,16384,65536,493141,388705,152405,0,5006123,0,0,0,0,0,0,131072,65536,0,16379616879948,16385611866719,16385612061120,16379617254009
|
|
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,157596,157596,4194304,256,0,0,12,24,191552,0x7f3de834db00,0x7f3dcc225e80,2101472,1993856,65536,262683,262683,2101464,2001920,252874,16384,65536,409581,304603,164096,0,6027846,0,0,0,0,0,0,131072,65536,0,16379617281779,16385612086880,16385612245601,16379617607102
|
|
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,157596,157596,4194304,256,0,0,12,24,195840,0x7f3de834d980,0x7f3dcc225ec0,3668344,3558143,65536,458542,458542,3668336,3566210,447754,16384,65536,779833,536099,398411,0,13741707,0,0,0,0,0,0,131072,65536,0,16379617644971,16385612268642,16385612549923,16379618112140
|
|
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,157596,157596,4194304,256,0,0,12,24,198592,0x7f3de834d800,0x7f3dcc225f00,1941920,1830929,65536,242739,242739,1941912,1839000,230814,16384,65536,358977,293050,168042,0,6376357,0,0,0,0,0,0,131072,65536,0,16379618140260,16385612596004,16385612742405,16379618448773
|
|
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,157596,157596,4194304,256,0,0,12,24,202368,0x7f3de834d680,0x7f3dcc225f40,2677648,2558136,65536,334705,334705,2677640,2566208,325337,16384,65536,444112,349317,174871,0,5231785,0,0,0,0,0,0,131072,65536,0,16379618487692,16385612766885,16385612978406,16379618876554
|
|
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,157596,157596,4194304,256,0,0,12,24,205888,0x7f3dea9f1500,0x7f3dcc225f80,2652192,2529926,65536,331523,331523,2652184,2538000,320518,16384,65536,535629,411809,179547,0,5698510,0,0,0,0,0,0,131072,65536,0,16379618902043,16385613015207,16385613225448,16379619287375
|
|
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,157596,157596,4194304,256,0,0,12,24,209408,0x7f3dea9f1380,0x7f3dcc225fc0,2438776,2331207,65536,304846,304846,2438768,2339264,293422,16384,65536,486468,373901,184576,0,7565166,0,0,0,0,0,0,131072,65536,0,16379619314444,16385613263688,16385613447529,16379619666246
|
|
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,157596,157596,4194304,256,0,0,12,24,214464,0x7f3dea9f1200,0x7f3dcc226000,4322688,4210372,65536,540335,540335,4322680,4218434,527834,16384,65536,932507,636597,406076,0,14859224,0,0,0,0,0,0,131072,65536,0,16379619704995,16385613472170,16385613804812,16379620221704
|
|
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,157596,157596,4194304,256,0,0,12,24,217728,0x7f3dea9f1080,0x7f3dcc226040,2171800,2060291,65536,271474,271474,2171792,2068350,258366,16384,65536,423854,326862,148374,0,6300615,0,0,0,0,0,0,131072,65536,0,16379620256873,16385613844812,16385614009133,16379620587296
|
|
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,157596,157596,4194304,256,0,0,12,24,222016,0x7f3de834df00,0x7f3dcc226080,2933112,2810434,65536,366638,366638,2933104,2818494,355798,16384,65536,594492,455512,222408,0,6212397,0,0,0,0,0,0,131072,65536,0,16379620625395,16385614033293,16385614261775,16379621033096
|
|
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,157596,157596,4194304,256,0,0,12,24,226048,0x7f3de834dd80,0x7f3dcc2260c0,2943312,2828623,65536,367913,367913,2943304,2836686,354910,16384,65536,600993,422346,222980,0,7081670,0,0,0,0,0,0,131072,65536,0,16379621060136,16385614299535,16385614529137,16379621467777
|
|
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,157596,157596,4194304,256,0,0,12,24,230080,0x7f3de834dc00,0x7f3dcc226100,2762456,2653065,65536,345306,345306,2762448,2661128,334969,16384,65536,568994,392487,242438,0,9169676,0,0,0,0,0,0,131072,65536,0,16379621495416,16385614565297,16385614774738,16379621885997
|
|
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,157596,157596,4194304,256,0,0,12,24,235904,0x7f3de834da80,0x7f3dcc226140,4968968,4850237,65536,621120,621120,4968960,4858312,610046,16384,65536,1086852,754127,531000,0,18779310,0,0,0,0,0,0,131072,65536,0,16379621911897,16385614810899,16385615194261,16379622476834
|
|
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,157596,157596,4194304,256,0,0,12,24,239424,0x7f3de834d900,0x7f3dcc226180,2415352,2305718,65536,301918,301918,2415344,2313790,289945,16384,65536,483257,360393,190237,0,8531357,0,0,0,0,0,0,131072,65536,0,16379622510914,16385615236181,16385615420663,16379622870206
|
|
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,157596,157596,4194304,256,0,0,12,24,244224,0x7f3de834d780,0x7f3dcc2261c0,3191144,3076795,65536,398892,398892,3191136,3084852,387950,16384,65536,670407,484786,235834,0,7135168,0,0,0,0,0,0,131072,65536,0,16379622909015,16385615444503,16385615697144,16379623342475
|
|
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,157596,157596,4194304,256,0,0,12,24,248768,0x7f3de834d600,0x7f3dcc226200,3118176,3012692,65536,389771,389771,3118168,3020752,381443,16384,65536,649716,416936,236815,0,11572499,0,0,0,0,0,0,131072,65536,0,16379623365525,16385615730745,16385615977146,16379623792675
|
|
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,157596,157596,4194304,256,0,0,12,24,253312,0x7f3dea9f1480,0x7f3dcc226240,3098264,2988493,65536,387282,387282,3098256,2996546,375070,16384,65536,643968,347709,311518,0,11888351,0,0,0,0,0,0,131072,65536,0,16379623819785,16385616012347,16385616248028,16379624236175
|
|
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,157596,157596,4194304,256,0,0,8,24,255552,0x7f3dea9f1300,0x7f3dcc226280,5713984,5599091,65536,714247,714247,5713976,5607162,702433,16384,65536,1262535,811954,497968,0,20713400,0,0,0,0,0,0,131072,65536,0,16379624262035,16385616284348,16385616734911,16379624888211
|
|
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,157596,157596,4194304,256,0,0,12,24,259840,0x7f3dea9f1180,0x7f3dcc2262c0,2905704,2792961,65536,363212,363212,2905696,2801016,349866,16384,65536,596309,373082,270215,0,11753893,0,0,0,0,0,0,131072,65536,0,16379624923490,16385616779072,16385617001633,16379625326061
|
|
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,157596,157596,4194304,256,0,0,12,24,265664,0x7f3dea9f1000,0x7f3dcc226300,3763968,3652730,65536,470495,470495,3763960,3660788,458062,16384,65536,800176,529470,445113,0,15779454,0,0,0,0,0,0,131072,65536,0,16379625353671,16385617037633,16385617336515,16379625833110
|
|
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,157596,157596,4194304,256,0,0,12,24,271232,0x7f3de834de80,0x7f3dcc226340,3810664,3703268,65536,476332,476332,3810656,3711324,460074,16384,65536,806927,558065,379780,0,10902933,0,0,0,0,0,0,131072,65536,0,16379625859859,16385617375396,16385617674758,16379626341119
|
|
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,157596,157596,4194304,256,0,0,8,24,273216,0x7f3de834dd00,0x7f3dcc226380,3838816,3722725,65536,479851,479851,3838808,3730796,467242,16384,65536,817135,540759,387797,0,11363183,0,0,0,0,0,0,131072,65536,0,16379626365998,16385617707078,16385618001960,16379626849888
|
|
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,157596,157596,4194304,256,0,0,8,24,275712,0x7f3de834db80,0x7f3dcc2263c0,7003080,6895109,65536,875384,875384,7003072,6903170,865059,16384,65536,1567233,744403,842191,0,32174689,0,0,0,0,0,0,131072,65536,0,16379626871827,16385618032200,16385618586764,16379627610651
|
|
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,157596,157596,4194304,256,0,0,12,24,280768,0x7f3de834da00,0x7f3dcc226400,3394400,3285695,65536,424299,424299,3394392,3293768,413146,16384,65536,716524,512997,343823,0,10888936,0,0,0,0,0,0,131072,65536,0,16379627641730,16385618633004,16385618895406,16379628082130
|
|
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,157596,157596,4194304,256,0,0,12,24,287616,0x7f3de834d880,0x7f3dcc226440,4409384,4294199,65536,551172,551172,4409376,4302250,542054,16384,65536,953151,642005,471907,0,13972294,0,0,0,0,0,0,131072,65536,0,16379628108360,16385618932206,16385619283728,16379628636858
|
|
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,157596,157596,4194304,256,0,0,12,24,294208,0x7f3de834d700,0x7f3dcc226480,4436864,4322131,65536,554607,554607,4436856,4330202,540939,16384,65536,955198,589400,499174,0,17408481,0,0,0,0,0,0,131072,65536,0,16379628666908,16385619320209,16385619670611,16379629196716
|
|
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,157596,157596,4194304,256,0,0,8,24,296960,0x7f3dea9f1580,0x7f3dcc2264c0,4469920,4358908,65536,558739,558739,4469912,4366966,547546,16384,65536,970958,716436,380944,0,14995515,0,0,0,0,0,0,131072,65536,0,16379629223985,16385619707091,16385620052053,16379629751834
|
|
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,157596,157596,4194304,256,0,0,8,24,299968,0x7f3dea9f1400,0x7f3dcc226500,8298088,8189894,65536,1037260,1037260,8298080,8197960,1027123,16384,65536,1873178,897417,990586,0,26832766,0,0,0,0,0,0,131072,65536,0,16379629777833,16385620088374,16385620746458,16379630624384
|
|
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,157596,157596,4194304,256,0,0,8,24,302720,0x7f3dea9f1280,0x7f3dcc226540,5742984,5625588,65536,717872,717872,5742976,5633668,706355,16384,65536,1265747,832960,610633,0,23685827,0,0,0,0,0,0,131072,65536,0,16379630648994,16385620791418,16385621236061,16379631271660
|
|
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,157596,157596,4194304,256,0,0,12,24,305472,0x7f3dea9f1100,0x7f3dcc226580,5748872,5637443,65536,718608,718608,5748864,5645508,708042,16384,65536,1269354,551626,518301,0,22028568,0,0,0,0,0,0,131072,65536,0,16379631298590,16385621272542,16385621733985,16379631944875
|
|
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,157596,157596,4194304,256,0,0,12,24,308224,0x7f3de834df80,0x7f3dcc2265c0,5745120,5631933,65536,718139,718139,5745112,5640004,706249,16384,65536,1269032,796634,576319,0,28474687,0,0,0,0,0,0,131072,65536,0,16379631964865,16385621767585,16385622226148,16379632620731
|
|
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,157596,157596,4194304,256,0,0,8,24,310976,0x7f3de834de00,0x7f3dcc226600,5768848,5659642,65536,721105,721105,5768840,5667710,710947,16384,65536,1274484,793089,695567,0,25992756,0,0,0,0,0,0,131072,65536,0,16379632648850,16385622268068,16385622716391,16379633275476
|
|
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,157596,157596,4194304,256,0,0,8,24,313216,0x7f3de834dc80,0x7f3dcc226640,10904744,10783447,65536,1363092,1363092,10904736,10791496,1350579,16384,65536,2492079,997949,1138246,0,48180186,0,0,0,0,0,0,131072,65536,0,16379633301386,16385622757512,16385623623277,16379634348712
|
|
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,157596,157596,4194304,256,0,0,8,24,315968,0x7f3de834db00,0x7f3dcc226680,10931424,10816078,65536,1366427,1366427,10931416,10824156,1355395,16384,65536,2498207,765223,1551371,0,67810314,0,0,0,0,0,0,131072,65536,0,16379634381752,16385623670958,16385624522163,16379635435068
|
|
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,157596,157596,4194304,256,0,0,12,24,318720,0x7f3de834d980,0x7f3dcc2266c0,10940880,10827085,65536,1367609,1367609,10940872,10835148,1355290,16384,65536,2504694,1025120,1420859,0,62876117,0,0,0,0,0,0,131072,65536,0,16379635446938,16385624558484,16385625440729,16379636541494
|
|
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,157596,157596,4194304,256,0,0,12,24,321472,0x7f3de834d800,0x7f3dcc226700,10938032,10818342,65536,1367253,1367253,10938024,10826410,1355283,16384,65536,2499629,777213,1762155,0,69676660,0,0,0,0,0,0,131072,65536,0,16379636552254,16385625479770,16385626356256,16379637640039
|
|
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,157596,157596,4194304,256,0,0,8,24,324224,0x7f3de834d680,0x7f3dcc226740,10981232,10856001,65536,1372653,1372653,10981224,10864070,1359091,16384,65536,2510385,958910,1773575,0,66615489,0,0,0,0,0,0,131072,65536,0,16379637651929,16385626403776,16385627260902,16379638724616
|
|
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,157596,157596,4194304,256,0,0,8,24,326464,0x7f3dea9f1500,0x7f3dcc226780,21269872,21156444,65536,2658733,2658733,21269864,21164498,2646983,16384,65536,4951836,883837,4053427,0,198805907,0,0,0,0,0,0,131072,65536,0,16379638737385,16385627298342,16385628993713,16379640653643
|
|
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,157596,157596,4194304,256,0,0,8,24,329216,0x7f3dea9f1380,0x7f3dcc2267c0,21316248,21197428,65536,2664530,2664530,21316240,21205502,2651687,16384,65536,4963635,1167214,3936294,0,171034355,0,0,0,0,0,0,131072,65536,0,16379640672733,16385629083474,16385630746205,16379642584091
|
|
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,157596,157596,4194304,256,0,0,12,24,331968,0x7f3dea9f1200,0x7f3dcc226800,21322848,21213077,65536,2665355,2665355,21322840,21221148,2653258,16384,65536,4965554,942318,4207700,0,186980909,0,0,0,0,0,0,131072,65536,0,16379642597350,16385630828125,16385632550377,16379644555287
|
|
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,157596,157596,4194304,256,0,0,12,24,334720,0x7f3dea9f1080,0x7f3dcc226840,21317592,21198304,65536,2664698,2664698,21317584,21206368,2652131,16384,65536,4964807,988425,4056294,0,174833632,0,0,0,0,0,0,131072,65536,0,16379644567937,16385632634857,16385634347989,16379646522034
|
|
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,157596,157596,4194304,256,0,0,8,24,337472,0x7f3de834df00,0x7f3dcc226880,21365192,21236614,65536,2670648,2670648,21365184,21244680,2656842,16384,65536,4970973,636247,4052104,0,177431644,0,0,0,0,0,0,131072,65536,0,16379646534674,16385634433909,16385636105921,16379648450711
|
|
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,157596,157596,4194304,256,0,0,8,24,0,0x7f3de834dd80,0x7f3dcc2268c0,42014552,41899223,65536,5251818,5251818,42014544,41907290,5239895,16384,65536,9878595,1233614,8884810,0,408383757,0,0,0,0,0,0,131072,65536,0,16379648462461,16385636187361,16385639542103,16379652056242
|