Files
rocm-systems/tests/workloads/SPI/mi100/pmc_perf.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

169 lines
60 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_fillBuffer.kd,0,0,0,866123,866128,33554432,256,0,0,8,32,6464,0x0,0x7f8756c04180,4039312,3829273,524288,504913,504913,4039304,3841146,480691,131072,524288,243029,767317,0,0,0,0,0,0,0,0,0,3145728,524288,0,12075222642432714,12075231812466956,12075231812792233,12075222885713539
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,866123,866128,32768,256,0,0,24,24,12480,0x0,0x7f8756c35100,223584,76405,512,27947,27947,223576,88027,12078,128,512,116,628,0,0,0,0,0,0,0,0,0,2560,512,0,12075222900007172,12075231827875508,12075231827882068,12075222900344198
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,866123,866128,4194304,256,0,0,24,24,12928,0x7f8886c24900,0x7f8756c35140,1737952,1566380,65536,217243,217243,1737944,1578107,198642,16384,65536,231405,241240,27397,0,772162,774953,0,0,0,0,0,327680,65536,0,12075222900410802,12075231827930868,12075231828062387,12075222900772574
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,866123,866128,4194304,256,0,0,36,24,13632,0x7f8886c24800,0x7f8756c35180,3146704,2981171,65536,393337,393337,3146696,2992895,375271,16384,65536,528762,430769,135214,0,0,5867132,0,0,0,0,0,327680,65536,0,12075222900848806,12075231828111826,12075231828353744,12075222901361729
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,866123,866128,4194304,256,0,0,28,24,14080,0x7f8886c24700,0x7f8756c351c0,3199712,3022728,65536,399963,399963,3199704,3034457,366698,16384,65536,399625,444809,5877,0,0,304808,0,0,0,0,0,327680,65536,0,12075222901401243,12075231828488623,12075231828737101,12075222901908525
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,866123,866128,4194304,256,0,0,24,24,14528,0x7f8886c24600,0x7f8756c35200,1733392,1566405,65536,216673,216673,1733384,1578139,203119,16384,65536,162097,195287,39431,0,628827,630825,0,0,0,0,0,327680,65536,0,12075222901946756,12075231828870700,12075231828995499,12075222902268484
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,866123,866128,4194304,256,0,0,24,24,14976,0x7f8886c24500,0x7f8756c35240,1729376,1557822,65536,216171,216171,1729368,1569553,200297,16384,65536,161350,194785,32467,0,618892,620950,0,0,0,0,0,327680,65536,0,12075222902327955,12075231829024459,12075231829149738,12075222902645435
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,866123,866128,4194304,256,0,0,24,24,15424,0x7f8886c24400,0x7f8756c35280,1728848,1560722,65536,216105,216105,1728840,1572457,196453,16384,65536,184008,219813,18907,0,286967,287984,0,0,0,0,0,327680,65536,0,12075222902731855,12075231829208297,12075231829332136,12075222903046670
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,866123,866128,4194304,256,0,0,28,24,16128,0x7f8886c24300,0x7f8756c352c0,3185632,3000889,65536,398203,398203,3185624,3012615,378217,16384,65536,326153,381886,13778,0,0,247613,0,0,0,0,0,327680,65536,0,12075222903106161,12075231829361896,12075231829612774,12075222903577667
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,866123,866128,4194304,256,0,0,28,24,16832,0x7f8886c24a00,0x7f8756c35300,3284432,3088756,65536,410553,410553,3284424,3100481,371177,16384,65536,250855,313858,2167,0,0,57653,0,0,0,0,0,327680,65536,0,12075222903615838,12075231829742053,12075231829990211,12075222904129433
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,866123,866128,4194304,256,0,0,24,24,17536,0x7f8886c24900,0x7f8756c35340,1736736,1555166,65536,217091,217091,1736728,1568671,196965,16384,65536,181630,220902,36103,0,396292,397624,0,0,0,0,0,327680,65536,0,12075222904154850,12075231830120930,12075231830245409,12075222904497787
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,866123,866128,4194304,256,0,0,24,24,18240,0x7f8886c24800,0x7f8756c35380,1751248,1570387,65536,218905,218905,1751240,1583891,204791,16384,65536,191124,221430,25250,0,428302,429812,0,0,0,0,0,327680,65536,0,12075222904554563,12075231830274208,12075231830399327,12075222904870269
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,866123,866128,4194304,256,0,0,24,24,18944,0x7f8886c24700,0x7f8756c353c0,1729696,1553530,65536,216211,216211,1729688,1565269,196984,16384,65536,185224,227646,15372,0,327775,328931,0,0,0,0,0,327680,65536,0,12075222904940540,12075231830442047,12075231830566526,12075222905259633
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,866123,866128,4194304,256,0,0,28,24,19904,0x7f8886c24600,0x7f8756c35400,3172816,2992550,65536,396601,396601,3172808,3004281,377704,16384,65536,340464,392975,20238,0,0,316056,0,0,0,0,0,327680,65536,0,12075222905322460,12075231830598206,12075231830845884,12075222905817249
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,866123,866128,4194304,256,0,0,28,24,20608,0x7f8886c24500,0x7f8756c35440,3195680,3020860,65536,399459,399459,3195672,3032585,380137,16384,65536,285408,346062,1456,0,0,74917,0,0,0,0,0,327680,65536,0,12075222905847075,12075231830979002,12075231831227640,12075222906367852
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,866123,866128,4194304,256,0,0,24,24,21312,0x7f8886c24400,0x7f8756c35480,1711440,1547359,65536,213929,213929,1711432,1560867,196478,16384,65536,137747,201009,18702,0,295614,296594,0,0,0,0,0,327680,65536,0,12075222906396526,12075231831319480,12075231831444119,12075222906719957
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,866123,866128,4194304,256,0,0,24,24,22016,0x7f8886c24300,0x7f8756c354c0,1733280,1558640,65536,216659,216659,1733272,1570371,195183,16384,65536,137204,195156,12010,0,429251,430599,0,0,0,0,0,327680,65536,0,12075222906777113,12075231831477558,12075231831603157,12075222907095274
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,866123,866128,4194304,256,0,0,24,24,22720,0x7f8886c24a00,0x7f8756c35500,1759312,1585601,65536,219913,219913,1759304,1597331,193635,16384,65536,161813,211109,12520,0,285906,286814,0,0,0,0,0,327680,65536,0,12075222907167398,12075231831644757,12075231831769716,12075222907480210
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,866123,866128,4194304,256,0,0,28,24,23680,0x7f8886c24900,0x7f8756c35540,3224480,3047169,65536,403059,403059,3224472,3058901,375281,16384,65536,279720,333466,24274,0,0,1033588,0,0,0,0,0,327680,65536,0,12075222907537306,12075231831801556,12075231832045714,12075222908037395
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,866123,866128,4194304,256,0,0,28,24,24384,0x7f8886c24800,0x7f8756c35580,3191952,3027937,65536,398993,398993,3191944,3039667,379623,16384,65536,253662,316475,1379,0,0,87256,0,0,0,0,0,327680,65536,0,12075222908063954,12075231832131473,12075231832375471,12075222908585554
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,866123,866128,4194304,256,0,0,24,24,25088,0x7f8886c24700,0x7f8756c355c0,1764192,1590680,65536,220523,220523,1764184,1602411,194794,16384,65536,162221,215046,5789,0,376138,377391,0,0,0,0,0,327680,65536,0,12075222908614828,12075231832460430,12075231832585069,12075222908939952
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,866123,866128,4194304,256,0,0,24,24,25792,0x7f8886c24600,0x7f8756c35600,1676496,1503584,65536,209561,209561,1676488,1515309,194020,16384,65536,127985,192945,359,0,27739,27903,0,0,0,0,0,327680,65536,0,12075222908995896,12075231832616909,12075231832742668,12075222909316953
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,866123,866128,4194304,256,0,0,24,24,26496,0x7f8886c24500,0x7f8756c35640,1787168,1613780,65536,223395,223395,1787160,1625517,194921,16384,65536,155670,219945,16949,0,14033,14093,0,0,0,0,0,327680,65536,0,12075222909387203,12075231832784268,12075231832908747,12075222909701407
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,866123,866128,4194304,256,0,0,28,24,27712,0x7f8886c24400,0x7f8756c35680,3283920,3107787,65536,410489,410489,3283912,3119517,392866,16384,65536,281644,335637,20435,0,0,575815,0,0,0,0,0,327680,65536,0,12075222909757241,12075231832940426,12075231833192424,12075222910270765
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,866123,866128,4194304,256,0,0,28,24,28416,0x7f8886c24300,0x7f8756c356c0,3704800,3053285,65536,463099,463099,3704792,3074961,384588,16384,65536,263782,326766,3452,0,0,127327,0,0,0,0,0,327680,65536,0,12075222910295892,12075231833279784,12075231833525541,12075222910855332
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,866123,866128,4194304,256,0,0,24,24,29120,0x7f8886c24a00,0x7f8756c35700,1716816,1542657,65536,214601,214601,1716808,1554387,195172,16384,65536,146309,200916,1838,0,63283,63564,0,0,0,0,0,327680,65536,0,12075222910881290,12075231833659140,12075231833783779,12075222911222985
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,866123,866128,4194304,256,0,0,24,24,30080,0x7f8886c24900,0x7f8756c35740,1726560,1546020,65536,215819,215819,1726552,1557747,194918,16384,65536,128114,192987,0,0,1966,1983,0,0,0,0,0,327680,65536,0,12075222911282165,12075231833815139,12075231833940098,12075222911597120
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,866123,866128,4194304,256,0,0,24,24,30784,0x7f8886c24800,0x7f8756c35780,1750608,1584859,65536,218825,218825,1750600,1596589,198767,16384,65536,186376,234962,16375,0,156635,157316,0,0,0,0,0,327680,65536,0,12075222911666469,12075231833981058,12075231834105857,12075222911975574
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,866123,866128,4194304,256,0,0,28,24,32000,0x7f8886c24700,0x7f8756c357c0,3242976,3064401,65536,405371,405371,3242968,3076131,374505,16384,65536,328150,373992,18958,0,0,317702,0,0,0,0,0,327680,65536,0,12075222912033551,12075231834137216,12075231834385534,12075222912544010
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,866123,866128,4194304,256,0,0,28,24,32960,0x7f8886c24600,0x7f8756c35800,3231120,3047395,65536,403889,403889,3231112,3059123,372205,16384,65536,269670,330307,2043,0,0,33916,0,0,0,0,0,327680,65536,0,12075222912569918,12075231834519293,12075231834762971,12075222913082190
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,866123,866128,4194304,256,0,0,24,24,33920,0x7f8886c24500,0x7f8756c35840,1754080,1583095,65536,219259,219259,1754072,1594821,195561,16384,65536,145867,207260,1615,0,117486,117991,0,0,0,0,0,327680,65536,0,12075222913108269,12075231834893850,12075231835018169,12075222913442650
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,866123,866128,4194304,256,0,0,24,24,34880,0x7f8886c24400,0x7f8756c35880,1756752,1583188,65536,219593,219593,1756744,1594917,200040,16384,65536,135782,201106,4634,0,481,495,0,0,0,0,0,327680,65536,0,12075222913501139,12075231835049849,12075231835174968,12075222913817406
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,866123,866128,4194304,256,0,0,24,24,35840,0x7f8886c24300,0x7f8756c358c0,1747808,1570552,65536,218475,218475,1747800,1582281,193868,16384,65536,146542,208992,116,0,239627,240599,0,0,0,0,0,327680,65536,0,12075222913886625,12075231835216888,12075231835341527,12075222914207942
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,866123,866128,4194304,256,0,0,28,24,37312,0x7f8886c24a00,0x7f8756c35900,3104016,2934205,65536,388001,388001,3104008,2945937,378733,16384,65536,266298,317784,10368,0,0,465412,0,0,0,0,0,327680,65536,0,12075222914268124,12075231835372886,12075231835622484,12075222914753286
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,866123,866128,4194304,256,0,0,28,24,38272,0x7f8886c24900,0x7f8756c35940,3733408,3054180,65536,466675,466675,3733400,3072229,371306,16384,65536,322039,385374,5553,0,0,134182,0,0,0,0,0,327680,65536,0,12075222914781408,12075231835717523,12075231835963921,12075222915335187
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,866123,866128,4194304,256,0,0,24,24,39232,0x7f8886c24800,0x7f8756c35980,1765840,1581332,65536,220729,220729,1765832,1593057,194287,16384,65536,142329,207754,259,0,65394,65708,0,0,0,0,0,327680,65536,0,12075222915360494,12075231836053361,12075231836178480,12075222915690698
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,866123,866128,4194304,256,0,0,24,24,40192,0x7f8886c24700,0x7f8756c359c0,1745312,1556083,65536,218163,218163,1745304,1567807,196074,16384,65536,132546,195378,57,0,6504,6536,0,0,0,0,0,327680,65536,0,12075222915750869,12075231836210159,12075231836335758,12075222916057309
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,866123,866128,4194304,256,0,0,24,24,41152,0x7f8886c24600,0x7f8756c35a00,1747664,1576424,65536,218457,218457,1747656,1588151,198250,16384,65536,167754,233124,2873,0,246555,247586,0,0,0,0,0,327680,65536,0,12075222916127319,12075231836376238,12075231836500557,12075222916437195
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,866123,866128,4194304,256,0,0,28,24,42624,0x7f8886c24500,0x7f8756c35a40,3203040,3023844,65536,400379,400379,3203032,3035579,384205,16384,65536,268952,317242,50333,0,0,309609,0,0,0,0,0,327680,65536,0,12075222916493630,12075231836530637,12075231836815754,12075222916993869
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,866123,866128,4194304,256,0,0,28,24,43584,0x7f8886c24400,0x7f8756c35a80,3612496,2988580,65536,451561,451561,3612488,3006625,374251,16384,65536,318656,380562,3957,0,0,72400,0,0,0,0,0,327680,65536,0,12075222917025558,12075231836858794,12075231837105512,12075222917578917
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,866123,866128,4194304,256,0,0,24,24,44544,0x7f8886c24300,0x7f8756c35ac0,1705504,1524205,65536,213187,213187,1705496,1535931,197613,16384,65536,160673,220199,2196,0,98361,98757,0,0,0,0,0,327680,65536,0,12075222917607089,12075231837155112,12075231837279911,12075222917925691
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,866123,866128,4194304,256,0,0,24,24,45760,0x7f8886c24a00,0x7f8756c35b00,1782096,1604098,65536,222761,222761,1782088,1615837,200296,16384,65536,148888,214004,1974,0,31741,31894,0,0,0,0,0,327680,65536,0,12075222917981976,12075231837311750,12075231837438149,12075222918307190
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,866123,866128,4194304,256,0,0,24,24,46720,0x7f8886c24900,0x7f8756c35b40,1680352,1501450,65536,210043,210043,1680344,1513177,195946,16384,65536,156454,210660,634,0,22322,22449,0,0,0,0,0,327680,65536,0,12075222918376529,12075231837479429,12075231837603588,12075222918678861
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,866123,866128,4194304,256,0,0,28,24,48448,0x7f8886c24800,0x7f8756c35b80,3290448,3121852,65536,411305,411305,3290440,3133585,386152,16384,65536,395271,368378,90290,0,0,2648170,0,0,0,0,0,327680,65536,0,12075222918735426,12075231837635908,12075231837889346,12075222919241556
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,866123,866128,4194304,256,0,0,28,24,49408,0x7f8886c24700,0x7f8756c35bc0,3233056,3061863,65536,404131,404131,3233048,3073587,381290,16384,65536,254115,317458,1852,0,0,23337,0,0,0,0,0,327680,65536,0,12075222919268096,12075231837932065,12075231838177503,12075222919781039
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,866123,866128,4194304,256,0,0,24,24,50368,0x7f8886c24600,0x7f8756c35c00,1679056,1507505,65536,209881,209881,1679048,1519239,196720,16384,65536,142324,204142,10292,0,65261,65614,0,0,0,0,0,327680,65536,0,12075222919806727,12075231838225823,12075231838349982,12075222920124076
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,866123,866128,4194304,256,0,0,24,24,51584,0x7f8886c24500,0x7f8756c35c40,1808416,1630550,65536,226051,226051,1808408,1642279,199021,16384,65536,144706,206519,8557,0,281380,282432,0,0,0,0,0,327680,65536,0,12075222920185841,12075231838379901,12075231838506460,12075222920509052
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,866123,866128,4194304,256,0,0,24,24,52544,0x7f8886c24400,0x7f8756c35c80,1709392,1543712,65536,213673,213673,1709384,1555443,194670,16384,65536,143662,204508,10912,0,23568,23713,0,0,0,0,0,327680,65536,0,12075222920577629,12075231838547100,12075231838672699,12075222920881875
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,866123,866128,4194304,256,0,0,28,24,54272,0x7f8886c24300,0x7f8756c35cc0,3345952,3173510,65536,418243,418243,3345944,3185245,393075,16384,65536,331492,325065,137973,0,0,1832694,0,0,0,0,0,327680,65536,0,12075222920936967,12075231838703899,12075231838956377,12075222921461963
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,866123,866128,4194304,256,0,0,28,24,55488,0x7f8886c24a00,0x7f8756c35d00,3143632,2977463,65536,392953,392953,3143624,2989199,382302,16384,65536,274331,335261,2605,0,0,82912,0,0,0,0,0,327680,65536,0,12075222921488081,12075231838998776,12075231839243254,12075222921995274
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,866123,866128,4194304,256,0,0,24,24,56704,0x7f8886c24900,0x7f8756c35d40,1703200,1536088,65536,212899,212899,1703192,1547821,194410,16384,65536,152800,207595,1089,0,4158,4175,0,0,0,0,0,327680,65536,0,12075222922020250,12075231839289174,12075231839414773,12075222922350243
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,866123,866128,4194304,256,0,0,24,24,58176,0x7f8886c24800,0x7f8756c35d80,1852496,1643300,65536,231561,231561,1852488,1656803,209201,16384,65536,173601,224608,17987,0,562064,564308,0,0,0,0,0,327680,65536,0,12075222922406638,12075231839447413,12075231839575732,12075222922727995
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,866123,866128,4194304,256,0,0,24,24,59392,0x7f8886c24700,0x7f8756c35dc0,1792160,1619815,65536,224019,224019,1792152,1631545,196334,16384,65536,136949,197331,2518,0,0,0,0,0,0,0,0,327680,65536,0,12075222922798346,12075231839616531,12075231839741490,12075222923108753
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,866123,866128,4194304,256,0,0,28,24,61376,0x7f8886c24600,0x7f8756c35e00,3351184,3176443,65536,418897,418897,3351176,3188173,396007,16384,65536,549105,480475,94442,0,0,2257515,0,0,0,0,0,327680,65536,0,12075222923165519,12075231839769650,12075231840022608,12075222923679914
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,866123,866128,4194304,256,0,0,28,24,62592,0x7f8886c24500,0x7f8756c35e40,3178464,3003543,65536,397307,397307,3178456,3015275,378474,16384,65536,422485,480127,4931,0,0,119039,0,0,0,0,0,327680,65536,0,12075222923706784,12075231840068688,12075231840317486,12075222924222082
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,866123,866128,4194304,256,0,0,24,24,63808,0x7f8886c24400,0x7f8756c35e80,1727568,1552733,65536,215945,215945,1727560,1564461,192625,16384,65536,160288,218527,23,0,10265,10327,0,0,0,0,0,327680,65536,0,12075222924247439,12075231840363245,12075231840488524,12075222924573846
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,866123,866128,4194304,256,0,0,24,24,65280,0x7f8886c24300,0x7f8756c35ec0,1813792,1626206,65536,226723,226723,1813784,1637935,204785,16384,65536,196144,237163,16396,0,586307,588566,0,0,0,0,0,327680,65536,0,12075222924630301,12075231840522444,12075231840651403,12075222924949404
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,866123,866128,4194304,256,0,0,24,24,66496,0x7f8886c24a00,0x7f8756c35f00,1683216,1512105,65536,210401,210401,1683208,1523841,199269,16384,65536,134364,199817,187,0,2872,2905,0,0,0,0,0,327680,65536,0,12075222925025295,12075231840693962,12075231840818761,12075222925328668
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,866123,866128,4194304,256,0,0,28,24,68480,0x7f8886c24900,0x7f8756c35f40,3331616,3135409,65536,416451,416451,3331608,3147137,381289,16384,65536,352325,338843,74234,0,0,4479833,0,0,0,0,0,327680,65536,0,12075222925385224,12075231840848041,12075231841109319,12075222925896774
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,866123,866128,4194304,256,0,0,28,24,69696,0x7f8886c24800,0x7f8756c35f80,3186384,3024522,65536,398297,398297,3186376,3036255,379760,16384,65536,245126,307308,2984,0,0,134839,0,0,0,0,0,327680,65536,0,12075222925921049,12075231841159559,12075231841404037,12075222926435806
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,866123,866128,4194304,256,0,0,24,24,70912,0x7f8886c24700,0x7f8756c35fc0,1684256,1509307,65536,210531,210531,1684248,1521035,197867,16384,65536,150020,215461,594,0,26906,27075,0,0,0,0,0,327680,65536,0,12075222926465681,12075231841450596,12075231841575235,12075222926788020
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,866123,866128,4194304,256,0,0,24,24,72384,0x7f8886c24600,0x7f8756c36000,1782992,1600077,65536,222873,222873,1782984,1611807,205037,16384,65536,179632,236710,665,0,60886,61214,0,0,0,0,0,327680,65536,0,12075222926846720,12075231841607875,12075231841744034,12075222927171243
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,866123,866128,4194304,256,0,0,24,24,73600,0x7f8886c24500,0x7f8756c36040,1757408,1578801,65536,219675,219675,1757400,1590537,195821,16384,65536,129875,194832,315,0,23337,23467,0,0,0,0,0,327680,65536,0,12075222927242104,12075231841785633,12075231841910112,12075222927547512
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,866123,866128,4194304,256,0,0,28,24,75840,0x7f8886c24400,0x7f8756c36080,3354768,3146321,65536,419345,419345,3354760,3158049,390887,16384,65536,324053,316851,145041,0,0,3607118,0,0,0,0,0,327680,65536,0,12075222927604438,12075231841937952,12075231842188670,12075222928111790
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,866123,866128,4194304,256,0,0,28,24,77056,0x7f8886c24300,0x7f8756c360c0,3159968,2985599,65536,394995,394995,3159960,2997327,371178,16384,65536,265412,328661,3138,0,0,122210,0,0,0,0,0,327680,65536,0,12075222928137468,12075231842231710,12075231842514587,12075222928646965
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,866123,866128,4194304,256,0,0,24,24,78272,0x7f8886c24a00,0x7f8756c36100,1721808,1555409,65536,215225,215225,1721800,1567131,195941,16384,65536,137040,201468,1925,0,8788,8841,0,0,0,0,0,327680,65536,0,12075222928674156,12075231842555547,12075231842679866,12075222928999470
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,866123,866128,4194304,256,0,0,24,24,80000,0x7f8886c24900,0x7f8756c36140,1870560,1680383,65536,233819,233819,1870552,1692109,215274,16384,65536,211742,276537,633,0,17275,17358,0,0,0,0,0,327680,65536,0,12075222929058400,12075231842711386,12075231842853785,12075222929379807
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,866123,866128,4194304,256,0,0,24,24,81216,0x7f8886c24800,0x7f8756c36180,1734416,1566260,65536,216801,216801,1734408,1577987,192873,16384,65536,130839,196270,18,0,19360,19443,0,0,0,0,0,327680,65536,0,12075222929449256,12075231842894584,12075231843019223,12075222929752800
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,866123,866128,4194304,256,0,0,28,24,83456,0x7f8886c24700,0x7f8756c361c0,3265888,3093752,65536,408235,408235,3265880,3105477,388594,16384,65536,337512,331362,134296,0,0,1969979,0,0,0,0,0,327680,65536,0,12075222929809776,12075231843053783,12075231843309781,12075222930316418
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,866123,866128,4194304,256,0,0,28,24,84928,0x7f8886c24600,0x7f8756c36200,3233424,3062524,65536,404177,404177,3233416,3074249,370383,16384,65536,244994,308544,7854,0,0,138202,0,0,0,0,0,327680,65536,0,12075222930344800,12075231843361140,12075231843605938,12075222930861811
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,866123,866128,4194304,256,0,0,24,24,86400,0x7f8886c24500,0x7f8756c36240,1769888,1586491,65536,221235,221235,1769880,1598225,203756,16384,65536,118337,183847,1,0,4966,5023,0,0,0,0,0,327680,65536,0,12075222930887579,12075231843655538,12075231843780817,12075222931223383
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,866123,866128,4194304,256,0,0,24,24,88128,0x7f8886c24400,0x7f8756c36280,1916496,1752885,65536,239561,239561,1916488,1764613,222446,16384,65536,226399,291935,213,0,0,0,0,0,0,0,0,327680,65536,0,12075222931279157,12075231843812977,12075231843961456,12075222931609891
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,866123,866128,4194304,256,0,0,24,24,89600,0x7f8886c24300,0x7f8756c362c0,1825952,1643803,65536,228243,228243,1825944,1655539,199909,16384,65536,151399,214309,444,0,70381,70751,0,0,0,0,0,327680,65536,0,12075222931693757,12075231844022575,12075231844148014,12075222932006769
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,866123,866128,4194304,256,0,0,28,24,92096,0x7f8886c24a00,0x7f8756c36300,3378128,3156711,65536,422265,422265,3378120,3168445,389861,16384,65536,435522,398838,105233,0,0,2134170,0,0,0,0,0,327680,65536,0,12075222932063244,12075231844177774,12075231844433292,12075222932583080
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,866123,866128,4194304,256,0,0,28,24,93568,0x7f8886c24900,0x7f8756c36340,3170656,2991890,65536,396331,396331,3170648,3003619,374505,16384,65536,262603,325365,12781,0,0,61368,0,0,0,0,0,327680,65536,0,12075222932607525,12075231844479051,12075231844725769,12075222933119056
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,866123,866128,4194304,256,0,0,24,24,95040,0x7f8886c24800,0x7f8756c36380,1769424,1596586,65536,221177,221177,1769416,1608317,198770,16384,65536,136219,201585,946,0,120294,120681,0,0,0,0,0,327680,65536,0,12075222933147188,12075231844775529,12075231844900808,12075222933475569
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,866123,866128,4194304,256,0,0,24,24,96768,0x7f8886c24700,0x7f8756c363c0,2018016,1848809,65536,252251,252251,2018008,1860541,234097,16384,65536,198847,264383,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222933533697,12075231844928808,12075231845086566,12075222933873077
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,866123,866128,4194304,256,0,0,24,24,98240,0x7f8886c24600,0x7f8756c36400,1741200,1560616,65536,217649,217649,1741192,1572345,199273,16384,65536,149419,213393,0,0,817,825,0,0,0,0,0,327680,65536,0,12075222933941474,12075231845130886,12075231845256165,12075222934252783
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,866123,866128,4194304,256,0,0,28,24,100736,0x7f8886c24500,0x7f8756c36440,3264608,3085996,65536,408075,408075,3264600,3097727,386024,16384,65536,340973,327257,137494,0,0,2873721,0,0,0,0,0,327680,65536,0,12075222934311873,12075231845288005,12075231845551522,12075222934819246
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,866123,866128,4194304,256,0,0,28,24,102208,0x7f8886c24400,0x7f8756c36480,3221328,3036103,65536,402665,402665,3221320,3047837,369392,16384,65536,243347,306630,3403,0,0,231376,0,0,0,0,0,327680,65536,0,12075222934843972,12075231845593442,12075231845839040,12075222935338761
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,866123,866128,4194304,256,0,0,24,24,103680,0x7f8886c24300,0x7f8756c364c0,1800288,1628857,65536,225035,225035,1800280,1640579,208745,16384,65536,139957,203912,1252,0,11166,11242,0,0,0,0,0,327680,65536,0,12075222935378505,12075231845884480,12075231846010559,12075222935690925
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,866123,866128,4194304,256,0,0,24,24,105664,0x7f8886c24a00,0x7f8756c36500,2116688,1946192,65536,264585,264585,2116680,1957921,245615,16384,65536,141236,206772,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222935747030,12075231846038878,12075231846203997,12075222936093413
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,866123,866128,4194304,256,0,0,24,24,107136,0x7f8886c24900,0x7f8756c36540,1726304,1553907,65536,215787,215787,1726296,1565639,190961,16384,65536,157599,222870,5837,0,4457,4503,0,0,0,0,0,327680,65536,0,12075222936162592,12075231846245277,12075231846370716,12075222936470855
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,866123,866128,4194304,256,0,0,28,24,109888,0x7f8886c24800,0x7f8756c36580,3225744,3028317,65536,403217,403217,3225736,3040041,383594,16384,65536,396590,366167,87654,0,0,2208821,0,0,0,0,0,327680,65536,0,12075222936527009,12075231846402235,12075231846656793,12075222937015196
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,866123,866128,4194304,256,0,0,28,24,111360,0x7f8886c24700,0x7f8756c365c0,3183456,2980203,65536,397931,397931,3183448,2991941,369767,16384,65536,316848,362990,3326,0,0,165087,0,0,0,0,0,327680,65536,0,12075222937042617,12075231846700793,12075231846946711,12075222937541765
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,866123,866128,4194304,256,0,0,24,24,112832,0x7f8886c24600,0x7f8756c36600,1819920,1655288,65536,227489,227489,1819912,1667031,201193,16384,65536,137592,201622,88,0,21659,21794,0,0,0,0,0,327680,65536,0,12075222937566190,12075231846992471,12075231847118229,12075222937896063
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,866123,866128,4194304,256,0,0,24,24,114816,0x7f8886c24500,0x7f8756c36640,2206688,2045732,65536,275835,275835,2206680,2057461,259054,16384,65536,238988,304524,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222937952699,12075231847150069,12075231847322548,12075222938312127
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,866123,866128,4194304,256,0,0,24,24,116288,0x7f8886c24400,0x7f8756c36680,1816592,1633102,65536,227073,227073,1816584,1644833,193385,16384,65536,143661,209190,1121,0,0,0,0,0,0,0,0,327680,65536,0,12075222938381455,12075231847363507,12075231847488946,12075222938694978
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,866123,866128,4194304,256,0,0,28,24,119040,0x7f8886c24300,0x7f8756c366c0,3251872,3052392,65536,406483,406483,3251864,3064117,382576,16384,65536,294792,294270,76962,0,0,2339677,0,0,0,0,0,327680,65536,0,12075222938751343,12075231847519346,12075231847773104,12075222939215315
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,866123,866128,4194304,256,0,0,28,24,120768,0x7f8886c24a00,0x7f8756c36700,3236496,3053428,65536,404561,404561,3236488,3065163,370922,16384,65536,263366,303633,18332,0,0,60546,0,0,0,0,0,327680,65536,0,12075222939267502,12075231847820144,12075231848064142,12075222939747153
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,866123,866128,4194304,256,0,0,24,24,122496,0x7f8886c24900,0x7f8756c36740,1836000,1659833,65536,229499,229499,1835992,1673341,198000,16384,65536,142462,207711,117,0,71626,71977,0,0,0,0,0,327680,65536,0,12075222939774294,12075231848110861,12075231848236460,12075222940103155
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,866123,866128,4194304,256,0,0,24,24,124736,0x7f8886c24800,0x7f8756c36780,2313040,2149605,65536,289129,289129,2313032,2161333,271210,16384,65536,258600,324136,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222940161564,12075231848268620,12075231848450859,12075222940528225
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,866123,866128,4194304,256,0,0,24,24,126464,0x7f8886c24700,0x7f8756c367c0,1791264,1619163,65536,223907,223907,1791256,1630897,208495,16384,65536,145325,209015,2661,0,29391,29538,0,0,0,0,0,327680,65536,0,12075222940597574,12075231848492138,12075231848617897,12075222940907610
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,866123,866128,4194304,256,0,0,20,24,127936,0x7f8886c24600,0x7f8756c36800,3328208,3132623,65536,416025,416025,3328200,3144353,391142,16384,65536,377285,442821,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222940963734,12075231848645897,12075231848909255,12075222941463353
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,866123,866128,4194304,256,0,0,28,24,129664,0x7f8886c24500,0x7f8756c36840,3247840,3077256,65536,405979,405979,3247832,3088973,370151,16384,65536,293724,352802,58360,0,0,109665,0,0,0,0,0,327680,65536,0,12075222941488620,12075231848954054,12075231849203172,12075222941984862
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,866123,866128,4194304,256,0,0,24,24,131392,0x7f8886c24400,0x7f8756c36880,1823120,1654161,65536,227889,227889,1823112,1665899,199146,16384,65536,145304,204811,1404,0,26021,26143,0,0,0,0,0,327680,65536,0,12075222942015198,12075231849255652,12075231849381251,12075222942348898
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,866123,866128,4194304,256,0,0,24,24,133632,0x7f8886c24300,0x7f8756c368c0,2416224,2255921,65536,302027,302027,2416216,2267647,284592,16384,65536,253679,319215,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222942405484,12075231849412931,12075231849603649,12075222942821617
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,866123,866128,4194304,256,0,0,24,24,135360,0x7f8886c24a00,0x7f8756c36900,1828944,1645084,65536,228617,228617,1828936,1656811,208243,16384,65536,167593,230339,2194,0,29603,29758,0,0,0,0,0,327680,65536,0,12075222942857574,12075231849644449,12075231849771488,12075222943180454
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,866123,866128,4194304,256,0,0,20,24,136832,0x7f8886c24900,0x7f8756c36940,3495136,3325176,65536,436891,436891,3495128,3336907,421353,16384,65536,498420,563956,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222943235977,12075231849799487,12075231850080765,12075222943749201
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,866123,866128,4194304,256,0,0,28,24,138560,0x7f8886c24800,0x7f8756c36980,3188304,3006909,65536,398537,398537,3188296,3018641,369257,16384,65536,312021,319335,46204,0,0,1381107,0,0,0,0,0,327680,65536,0,12075222943775820,12075231850123805,12075231850371803,12075222944270209
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,866123,866128,4194304,256,0,0,24,24,140288,0x7f8886c24700,0x7f8756c369c0,1823264,1637059,65536,227907,227907,1823256,1648787,202473,16384,65536,155683,220537,18317,0,170545,171302,0,0,0,0,0,327680,65536,0,12075222944296327,12075231850414362,12075231850539961,12075222944629196
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,866123,866128,4194304,256,0,0,24,24,142784,0x7f8886c24600,0x7f8756c36a00,2638800,2477856,65536,329849,329849,2638792,2489595,312623,16384,65536,285753,351289,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222944685681,12075231850572761,12075231850782839,12075222945119958
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,866123,866128,4194304,256,0,0,24,24,144768,0x7f8886c24500,0x7f8756c36a40,1795680,1614098,65536,224459,224459,1795672,1625827,204569,16384,65536,150891,214321,8511,0,103012,103465,0,0,0,0,0,327680,65536,0,12075222945156526,12075231850837399,12075231850964918,12075222945472253
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,866123,866128,4194304,256,0,0,20,24,145728,0x7f8886c24400,0x7f8756c36a80,3776784,3609242,65536,472097,472097,3776776,3620975,452205,16384,65536,359864,425400,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222945527375,12075231850992918,12075231851299475,12075222946063131
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,866123,866128,4194304,256,0,0,28,24,147712,0x7f8886c24300,0x7f8756c36ac0,3224416,3041686,65536,403051,403051,3224408,3053417,378985,16384,65536,409641,464220,79404,0,0,98968,0,0,0,0,0,327680,65536,0,12075222946088518,12075231851344595,12075231851594353,12075222946587125
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,866123,866128,4194304,256,0,0,24,24,149696,0x7f8886c24a00,0x7f8756c36b00,1810064,1638898,65536,226257,226257,1810056,1650623,197224,16384,65536,135806,195195,10173,0,229194,230011,0,0,0,0,0,327680,65536,0,12075222946613754,12075231851634992,12075231851762671,12075222946946893
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,866123,866128,4194304,256,0,0,24,24,152192,0x7f8886c24900,0x7f8756c36b40,2856224,2687711,65536,357027,357027,2856216,2701207,338540,16384,65536,298131,363667,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222947011062,12075231851790671,12075231852018669,12075222947476067
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,866123,866128,4194304,256,0,0,24,24,154176,0x7f8886c24800,0x7f8756c36b80,1835024,1657864,65536,229377,229377,1835016,1669599,205554,16384,65536,146696,201094,19683,0,262324,263366,0,0,0,0,0,327680,65536,0,12075222947512745,12075231852079469,12075231852207628,12075222947830826
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,866123,866128,4194304,256,0,0,20,24,155648,0x7f8886c24700,0x7f8756c36bc0,4036064,3863806,65536,504507,504507,4036056,3875535,485354,16384,65536,300250,365786,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222947886028,12075231852235627,12075231852563785,12075222948448123
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,866123,866128,4194304,256,0,0,28,24,157632,0x7f8886c24600,0x7f8756c36c00,3253136,3044108,65536,406641,406641,3253128,3055843,381928,16384,65536,310402,304848,60080,0,0,2744120,0,0,0,0,0,327680,65536,0,12075222948473119,12075231852608744,12075231852857702,12075222948976044
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,866123,866128,4194304,256,0,0,24,24,159616,0x7f8886c24500,0x7f8756c36c40,1823776,1632886,65536,227971,227971,1823768,1644625,207209,16384,65536,157858,202457,15847,0,331605,333052,0,0,0,0,0,327680,65536,0,12075222949005539,12075231852902982,12075231853030501,12075222949339259
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,866123,866128,4194304,256,0,0,24,24,162368,0x7f8886c24400,0x7f8756c36c80,3063120,2901121,65536,382889,382889,3063112,2912853,365168,16384,65536,252981,318517,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222949401394,12075231853062181,12075231853307298,12075222949866178
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,866123,866128,4194304,256,0,0,24,24,164608,0x7f8886c24300,0x7f8756c36cc0,1847008,1662836,65536,230875,230875,1847000,1674571,206692,16384,65536,152469,199255,6044,0,213618,214650,0,0,0,0,0,327680,65536,0,12075222949901844,12075231853369698,12075231853498977,12075222950228381
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,866123,866128,4194304,256,0,0,20,24,166336,0x7f8886c24a00,0x7f8756c36d00,4595664,4429370,65536,574457,574457,4595656,4442873,556140,16384,65536,345230,410766,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222950289094,12075231853527137,12075231853902014,12075222950910128
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,866123,866128,4194304,256,0,0,28,24,168576,0x7f8886c24900,0x7f8756c36d40,3294048,3111696,65536,411755,411755,3294040,3123429,381162,16384,65536,307452,302228,67370,0,0,4375444,0,0,0,0,0,327680,65536,0,12075222950935485,12075231853944573,12075231854204091,12075222951447998
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,866123,866128,4194304,256,0,0,24,24,170816,0x7f8886c24800,0x7f8756c36d80,1835344,1660375,65536,229417,229417,1835336,1672101,212070,16384,65536,179403,227918,34233,0,518466,520766,0,0,0,0,0,327680,65536,0,12075222951475449,12075231854254171,12075231854383770,12075222951806123
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,866123,866128,4194304,256,0,0,24,24,174080,0x7f8886c24700,0x7f8756c36dc0,3472032,3301486,65536,434003,434003,3472024,3313217,416739,16384,65536,327104,392640,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222951860224,12075231854412729,12075231854690327,12075222952376042
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,866123,866128,4194304,256,0,0,24,24,176576,0x7f8886c24600,0x7f8756c36e00,1759888,1582875,65536,219985,219985,1759880,1594613,210229,16384,65536,193376,257146,5836,0,38450,38685,0,0,0,0,0,327680,65536,0,12075222952414474,12075231854749207,12075231854884245,12075222952726113
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,866123,866128,4194304,256,0,0,20,24,177792,0x7f8886c24500,0x7f8756c36e40,5167776,4997911,65536,645971,645971,5167768,5009643,625517,16384,65536,523147,588683,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222952781596,12075231854912565,12075231855334642,12075222953433648
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,866123,866128,4194304,256,0,0,28,24,180288,0x7f8886c24400,0x7f8756c36e80,3213648,3040285,65536,401705,401705,3213640,3052017,384233,16384,65536,578195,492042,80700,0,0,4105730,0,0,0,0,0,327680,65536,0,12075222953459376,12075231855380081,12075231855637199,12075222953955578
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,866123,866128,4194304,256,0,0,24,24,182784,0x7f8886c24300,0x7f8756c36ec0,1827296,1647708,65536,228411,228411,1827288,1659433,205426,16384,65536,151825,217139,304,0,984,999,0,0,0,0,0,327680,65536,0,12075222953982879,12075231855678319,12075231855814158,12075222954319234
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,866123,866128,4194304,256,0,0,24,24,186304,0x7f8886c24a00,0x7f8756c36f00,4241680,3727829,65536,530209,530209,4241672,3747473,469361,16384,65536,322654,388190,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222954381569,12075231855844878,12075231856159115,12075222954958732
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,866123,866128,4194304,256,0,0,24,24,189312,0x7f8886c24900,0x7f8756c36f40,1981216,1801832,65536,247651,247651,1981208,1813561,225386,16384,65536,179118,244654,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222954994258,12075231856216235,12075231856367753,12075222955338608
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,866123,866128,4194304,256,0,0,20,24,190784,0x7f8886c24800,0x7f8756c36f80,6277328,6112073,65536,784665,784665,6277320,6123801,765933,16384,65536,364576,430112,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222955396496,12075231856399273,12075231856914629,12075222956141069
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,866123,866128,4194304,256,0,0,28,24,193792,0x7f8886c24700,0x7f8756c36fc0,3667168,3487457,65536,458395,458395,3667160,3499193,438442,16384,65536,628012,512404,162526,0,0,3944100,0,0,0,0,0,327680,65536,0,12075222956174511,12075231856959428,12075231857255586,12075222956711980
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,866123,866128,4194304,256,0,0,24,24,196800,0x7f8886c24600,0x7f8756c37000,1973648,1808770,65536,246705,246705,1973640,1820503,227955,16384,65536,214238,279774,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222956745392,12075231857307426,12075231857461344,12075222957085344
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,866123,866128,4194304,256,0,0,24,24,201088,0x7f8886c24500,0x7f8756c37040,4756256,4582735,65536,594531,594531,4756248,4594473,575548,16384,65536,308056,373592,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222957137421,12075231857489344,12075231857873661,12075222957769596
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,866123,866128,4194304,256,0,0,24,24,204608,0x7f8886c24400,0x7f8756c37080,2225360,2061299,65536,278169,278169,2225352,2073029,261104,16384,65536,164892,230428,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222957809009,12075231857933180,12075231858109019,12075222958160672
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,866123,866128,4194304,256,0,0,20,24,206080,0x7f8886c24300,0x7f8756c370c0,7407200,7241710,65536,925899,925899,7407192,7253441,908773,16384,65536,372491,438027,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222958218790,12075231858138619,12075231858760214,12075222959061226
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,866123,866128,4194304,256,0,0,28,24,209600,0x7f8886c24a00,0x7f8756c37100,4010704,3838047,65536,501337,501337,4010696,3849779,481260,16384,65536,526086,545520,41239,0,0,876997,0,0,0,0,0,327680,65536,0,12075222959091402,12075231858806613,12075231859132050,12075222959654248
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,866123,866128,4194304,256,0,0,24,24,213120,0x7f8886c24900,0x7f8756c37140,2262304,2087096,65536,282787,282787,2262296,2098829,266084,16384,65536,187294,252830,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222959679725,12075231859184210,12075231859361169,12075222960048951
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,866123,866128,4194304,256,0,0,24,24,218176,0x7f8886c24800,0x7f8756c37180,5574288,5410201,65536,696785,696785,5574280,5421931,681197,16384,65536,264235,329771,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222960107951,12075231859389168,12075231859844365,12075222960784478
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,866123,866128,4194304,256,0,0,24,24,222208,0x7f8886c24700,0x7f8756c371c0,2521696,2350125,65536,315211,315211,2521688,2361853,295017,16384,65536,259803,325339,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222960824853,12075231859900364,12075231860099883,12075222961243381
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,866123,866128,4194304,256,0,0,20,24,223936,0x7f8886c24600,0x7f8756c37200,8518352,8350851,65536,1064793,1064793,8518344,8362579,1047277,16384,65536,397048,462584,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222961268658,12075231860145322,12075231860853956,12075222962230706
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,866123,866128,4194304,256,0,0,28,24,227968,0x7f8886c24500,0x7f8756c37240,4560992,4392419,65536,570123,570123,4560984,4404143,548850,16384,65536,466752,532283,2064,0,0,114605,0,0,0,0,0,327680,65536,0,12075222962256504,12075231860898756,12075231861272353,12075222962886535
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,866123,866128,4194304,256,0,0,24,24,232000,0x7f8886c24400,0x7f8756c37280,2582416,2393559,65536,322801,322801,2582408,2405291,299753,16384,65536,214134,279670,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222962914627,12075231861323072,12075231861525311,12075222963383168
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,866123,866128,4194304,256,0,0,24,24,237824,0x7f8886c24300,0x7f8756c372c0,6433184,6265123,65536,804147,804147,6433176,6276851,785711,16384,65536,393368,458904,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222963409336,12075231861568830,12075231862094586,12075222964194375
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,866123,866128,4194304,256,0,0,24,24,242368,0x7f8886c24a00,0x7f8756c37300,2788304,2627891,65536,348537,348537,2788296,2639613,330733,16384,65536,281463,346999,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222964234039,12075231862156346,12075231862379224,12075222964696078
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,866123,866128,4194304,256,0,0,20,24,243584,0x7f8886c24900,0x7f8756c37340,9657376,9492207,65536,1207171,1207171,9657368,9503939,1189232,16384,65536,438248,503784,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222964723829,12075231862428343,12075231863225457,12075222965788027
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,866123,866128,4194304,256,0,0,28,24,248128,0x7f8886c24800,0x7f8756c37380,5109712,4940722,65536,638713,638713,5109704,4952451,618085,16384,65536,601612,666467,95,0,0,0,0,0,0,0,0,327680,65536,0,12075222965823352,12075231863273136,12075231863693133,12075222966499028
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,866123,866128,4194304,256,0,0,24,24,252672,0x7f8886c24700,0x7f8756c373c0,2830752,2660947,65536,353843,353843,2830744,2672679,337640,16384,65536,245260,310796,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222966526870,12075231863738573,12075231863963211,12075222966979130
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,866123,866128,4194304,256,0,0,24,24,259264,0x7f8886c24600,0x7f8756c37400,7271056,7106109,65536,908881,908881,7271048,7117843,892147,16384,65536,439489,505025,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222967012993,12075231864015690,12075231864611045,12075222967862492
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,866123,866128,4194304,256,0,0,24,24,264832,0x7f8886c24500,0x7f8756c37440,3339168,3169446,65536,417395,417395,3339160,3181169,401137,16384,65536,314231,379767,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222967897777,12075231864674405,12075231864942883,12075222968410600
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,866123,866128,4194304,256,0,0,20,24,266304,0x7f8886c24400,0x7f8756c37480,11897296,11731497,65536,1487161,1487161,11897288,11743223,1470188,16384,65536,242958,308494,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222968434815,12075231864989122,12075231865972634,12075222969681763
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,866123,866128,4194304,256,0,0,28,24,271872,0x7f8886c24300,0x7f8756c374c0,6233184,6059778,65536,779147,779147,6233176,6071505,759803,16384,65536,859275,924811,52,0,0,0,0,0,0,0,0,327680,65536,0,12075222969714904,12075231866023834,12075231866555829,12075222970489494
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,866123,866128,4194304,256,0,0,24,24,277440,0x7f8886c24a00,0x7f8756c37500,3387536,3223468,65536,423441,423441,3387528,3235203,404710,16384,65536,236746,302282,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222970515472,12075231866602549,12075231866873427,12075222971051628
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,866123,866128,4194304,256,0,0,12,24,279936,0x7f8886c24900,0x7f8756c37540,9027680,8854188,65536,1128459,1128459,9027672,8865915,1107438,16384,65536,316892,382428,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222971077507,12075231866921266,12075231867658060,12075222972071774
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,866123,866128,4194304,256,0,0,24,24,286528,0x7f8886c24800,0x7f8756c37580,4259024,3745930,65536,532377,532377,4259016,3763981,470758,16384,65536,368773,434309,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222972110566,12075231867721420,12075231868036937,12075222972697257
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,866123,866128,4194304,256,0,0,20,24,288000,0x7f8886c24700,0x7f8756c375c0,14153760,13977726,65536,1769219,1769219,14153752,13989457,1750708,16384,65536,348211,413747,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222972728715,12075231868086217,12075231869255167,12075222974157069
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,866123,866128,4194304,256,0,0,32,24,294592,0x7f8886c24600,0x7f8756c37600,7381904,7208857,65536,922737,922737,7381896,7220583,904947,16384,65536,1628127,1015602,692932,0,0,36746998,0,0,0,0,0,327680,65536,0,12075222974188558,12075231869301407,12075231869912442,12075222975059246
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,866123,866128,4194304,256,0,0,24,24,301184,0x7f8886c24500,0x7f8756c37640,3944160,3762722,65536,493019,493019,3944152,3774439,475632,16384,65536,314385,379921,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222975085365,12075231869960441,12075231870278359,12075222975661125
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,866123,866128,4194304,256,0,0,12,24,304960,0x7f8886c24400,0x7f8756c37680,10694672,10526837,65536,1336833,1336833,10694664,10538563,1318867,16384,65536,362429,427965,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222975686241,12075231870334358,12075231871211471,12075222976827452
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,866123,866128,4194304,256,0,0,24,24,313600,0x7f8886c24300,0x7f8756c376c0,5038240,4860357,65536,629779,629779,5038232,4872089,612715,16384,65536,412075,477611,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222976862427,12075231871273870,12075231871684107,12075222977523656
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,866123,866128,4194304,256,0,0,20,24,314816,0x7f8886c24a00,0x7f8756c37700,18652624,18488461,65536,2331577,2331577,18652616,18500201,2314477,16384,65536,285956,351492,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222977552459,12075231871732107,12075231873279454,12075222979351543
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,866123,866128,4194304,256,0,0,20,24,317568,0x7f8886c24900,0x7f8756c37740,9628512,9448099,65536,1203563,1203563,9628504,9459825,1182565,16384,65536,299614,365150,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222979383763,12075231873347773,12075231874140247,12075222980438643
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,866123,866128,4194304,256,0,0,12,24,320320,0x7f8886c24800,0x7f8756c37780,5123280,4960568,65536,640409,640409,5123272,4974077,620913,16384,65536,311459,376995,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222980471164,12075231874229686,12075231874643283,12075222981142070
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,866123,866128,4194304,256,0,0,12,24,324096,0x7f8886c24700,0x7f8756c377c0,14077728,13901011,65536,1759715,1759715,14077720,13912745,1739887,16384,65536,346943,412479,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222981175422,12075231874733218,12075231875891610,12075222982591263
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,866123,866128,4194304,256,0,0,12,24,328896,0x7f8886c24600,0x7f8756c37800,9599952,9427286,65536,1199993,1199993,9599944,9439017,1180657,16384,65536,365118,430654,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222982637059,12075231875999768,12075231876784563,12075222983667594
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,866123,866128,4194304,256,0,0,20,24,330112,0x7f8886c24500,0x7f8756c37840,36683936,36509927,65536,4585491,4585491,36683928,36521657,4566250,16384,65536,393677,459213,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222983701777,12075231876877042,12075231879927581,12075222987019643
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,866123,866128,4194304,256,0,0,20,24,332864,0x7f8886c24400,0x7f8756c37880,18608848,18429047,65536,2326105,2326105,18608840,18442559,2305516,16384,65536,357945,423481,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222987055580,12075231880029180,12075231881569809,12075222988845997
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,866123,866128,4194304,256,0,0,12,24,335616,0x7f8886c24300,0x7f8756c378c0,9631200,9462867,65536,1203899,1203899,9631192,9474601,1185395,16384,65536,260152,325688,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222988877906,12075231881668208,12075231882456843,12075222989922467
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,866123,866128,4194304,256,0,0,12,24,339392,0x7f8886c24a00,0x7f8756c37900,27563408,27388043,65536,3445425,3445425,27563400,27399771,3424878,16384,65536,315590,381126,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222989955268,12075231882551242,12075231884832346,12075222992500358
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,866123,866128,4194304,256,0,0,12,24,344192,0x7f8886c24900,0x7f8756c37940,18590752,18418067,65536,2323843,2323843,18590744,18431577,2304364,16384,65536,391926,457462,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222992547025,12075231884936345,12075231886472015,12075222994324348
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,866123,866128,4194304,256,0,0,20,24,345408,0x7f8886c24800,0x7f8756c37980,72702736,72530002,65536,9087841,9087841,72702728,72541735,9069541,16384,65536,372030,437566,0,0,0,0,0,0,0,0,0,327680,65536,0,12075222994356748,12075231886567214,12075231892621411,12075223000673867
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,866123,866128,4194304,256,0,0,20,24,348160,0x7f8886c24700,0x7f8756c379c0,36582496,36411788,65536,4572811,4572811,36582488,36425293,4555628,16384,65536,484687,550223,0,0,0,0,0,0,0,0,0,327680,65536,0,12075223000702811,12075231892711651,12075231895753709,12075223004006340
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,866123,866128,4194304,256,0,0,12,24,350912,0x7f8886c24600,0x7f8756c37a00,18647248,18464200,65536,2330905,2330905,18647240,18475929,2311270,16384,65536,496876,562412,0,0,0,0,0,0,0,0,0,327680,65536,0,12075223004034122,12075231895843309,12075231897382178,12075223005842923
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,866123,866128,4194304,256,0,0,12,24,0,0x7f8886c24500,0x7f8756c37a40,54520480,54337510,65536,6815059,6815059,54520472,54349241,6793840,16384,65536,401940,467476,0,0,0,0,0,0,0,0,0,327680,65536,0,12075223005875093,12075231897477697,12075231902005345,12075223010674613