169 lines
60 KiB
CSV
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,0,0,0,867091,867096,33554432,256,0,0,8,32,6464,0x0,0x7f1723204180,4009488,3796892,524288,501185,501185,4009480,3808756,481466,131072,524288,237812,762100,0,0,0,0,0,0,0,0,0,3145728,524288,0,12075245655947833,12075254841595086,12075254841918603,12075245900085460
|
||
|
|
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,867091,867096,32768,256,0,0,24,24,12480,0x0,0x7f1723235100,227376,78085,512,28421,28421,227368,89705,11822,128,512,116,628,0,0,0,0,0,0,0,0,0,2560,512,0,12075245914782663,12075254857383717,12075254857390437,12075245915123937
|
||
|
|
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,867091,867096,4194304,256,0,0,24,24,12928,0x7f1853411900,0x7f1723235140,1789856,1625054,65536,223731,223731,1789848,1636787,201193,16384,65536,146267,185422,36101,0,528910,530495,0,0,0,0,0,327680,65536,0,12075245915195861,12075254857456036,12075254857593475,12075245915562362
|
||
|
|
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,867091,867096,4194304,256,0,0,36,24,13632,0x7f1853411800,0x7f1723235180,3143504,2970097,65536,392937,392937,3143496,2981825,379496,16384,65536,433234,367580,171259,0,0,6371366,0,0,0,0,0,327680,65536,0,12075245915640387,12075254857655395,12075254857898913,12075245916123494
|
||
|
|
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,867091,867096,4194304,256,0,0,28,24,14080,0x7f1853411700,0x7f17232351c0,3544224,2912555,65536,443027,443027,3544216,2934031,385897,16384,65536,385430,431382,9832,0,0,277811,0,0,0,0,0,327680,65536,0,12075245916157297,12075254858038911,12075254858281149,12075245916686431
|
||
|
|
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,867091,867096,4194304,256,0,0,24,24,14528,0x7f1853411600,0x7f1723235200,1813264,1645068,65536,226657,226657,1813256,1656797,202820,16384,65536,183589,208921,31580,0,724293,726682,0,0,0,0,0,327680,65536,0,12075245916713862,12075254858415228,12075254858540987,12075245917049225
|
||
|
|
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,867091,867096,4194304,256,0,0,24,24,14976,0x7f1853411500,0x7f1723235240,1785120,1624695,65536,223139,223139,1785112,1636429,201577,16384,65536,213238,230105,31669,0,593277,595297,0,0,0,0,0,327680,65536,0,12075245917108114,12075254858580827,12075254858705306,12075245917435643
|
||
|
|
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,867091,867096,4194304,256,0,0,24,24,15424,0x7f1853411400,0x7f1723235280,1698192,1539134,65536,212273,212273,1698184,1550865,198377,16384,65536,170015,222243,24082,0,409237,410610,0,0,0,0,0,327680,65536,0,12075245917524939,12075254858775065,12075254858899064,12075245917833402
|
||
|
|
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,867091,867096,4194304,256,0,0,28,24,16128,0x7f1853411300,0x7f17232352c0,3191776,3019543,65536,398971,398971,3191768,3031273,377705,16384,65536,419351,462352,5878,0,0,398805,0,0,0,0,0,327680,65536,0,12075245917894846,12075254858940184,12075254859191702,12075245918348299
|
||
|
|
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,867091,867096,4194304,256,0,0,28,24,16832,0x7f1853411a00,0x7f1723235300,3211792,3040387,65536,401473,401473,3211784,3053887,379504,16384,65536,247766,311071,3823,0,0,166336,0,0,0,0,0,327680,65536,0,12075245918397611,12075254859322741,12075254859566579,12075245918879827
|
||
|
|
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,867091,867096,4194304,256,0,0,24,24,17536,0x7f1853411900,0x7f1723235340,1726944,1563325,65536,215867,215867,1726936,1575055,197609,16384,65536,167117,216827,15384,0,482107,483679,0,0,0,0,0,327680,65536,0,12075245918904442,12075254859696338,12075254859821137,12075245919250916
|
||
|
|
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,867091,867096,4194304,256,0,0,24,24,18240,0x7f1853411800,0x7f1723235380,1771984,1611895,65536,221497,221497,1771976,1623635,201576,16384,65536,173185,214425,23898,0,401099,402350,0,0,0,0,0,327680,65536,0,12075245919310237,12075254859861297,12075254859986416,12075245919629710
|
||
|
|
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,867091,867096,4194304,256,0,0,24,24,18944,0x7f1853411700,0x7f17232353c0,1695328,1535104,65536,211915,211915,1695320,1546837,195305,16384,65536,147584,195527,21191,0,518355,520312,0,0,0,0,0,327680,65536,0,12075245919700101,12075254860045935,12075254860170894,12075245920008304
|
||
|
|
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,867091,867096,4194304,256,0,0,28,24,19904,0x7f1853411600,0x7f1723235400,3180496,3012128,65536,397561,397561,3180488,3023853,374376,16384,65536,293074,348851,16739,0,0,156015,0,0,0,0,0,327680,65536,0,12075245920069027,12075254860212334,12075254860464812,12075245920554208
|
||
|
|
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,867091,867096,4194304,256,0,0,28,24,20608,0x7f1853411500,0x7f1723235440,3141856,2969577,65536,392731,392731,3141848,2981307,376041,16384,65536,290338,352406,2066,0,0,35970,0,0,0,0,0,327680,65536,0,12075245920582331,12075254860571851,12075254860816009,12075245921073493
|
||
|
|
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,867091,867096,4194304,256,0,0,24,24,21312,0x7f1853411400,0x7f1723235480,1684816,1528882,65536,210601,210601,1684808,1540615,197476,16384,65536,178961,222717,12123,0,260711,261555,0,0,0,0,0,327680,65536,0,12075245921097859,12075254860919368,12075254861043847,12075245921427050
|
||
|
|
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,867091,867096,4194304,256,0,0,24,24,22016,0x7f1853411300,0x7f17232354c0,1731040,1570465,65536,216379,216379,1731032,1582189,195570,16384,65536,142172,192905,8539,0,128297,128801,0,0,0,0,0,327680,65536,0,12075245921485369,12075254861084967,12075254861209766,12075245921806756
|
||
|
|
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,867091,867096,4194304,256,0,0,24,24,22720,0x7f1853411a00,0x7f1723235500,1679120,1512656,65536,209889,209889,1679112,1524387,195813,16384,65536,152042,198872,19455,0,240969,241774,0,0,0,0,0,327680,65536,0,12075245921877487,12075254861262725,12075254861387364,12075245922183686
|
||
|
|
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,867091,867096,4194304,256,0,0,28,24,23680,0x7f1853411900,0x7f1723235540,3217952,3044753,65536,402243,402243,3217944,3056487,375529,16384,65536,386247,426567,9898,0,0,366833,0,0,0,0,0,327680,65536,0,12075245922244730,12075254861430404,12075254861684162,12075245922722488
|
||
|
|
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,867091,867096,4194304,256,0,0,28,24,24384,0x7f1853411800,0x7f1723235580,3146384,2972163,65536,393297,393297,3146376,2983889,376680,16384,65536,251357,312915,1681,0,0,182908,0,0,0,0,0,327680,65536,0,12075245922751371,12075254861759841,12075254862040159,12075245923236683
|
||
|
|
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,867091,867096,4194304,256,0,0,24,24,25088,0x7f1853411700,0x7f17232355c0,1727392,1563118,65536,215923,215923,1727384,1574845,197097,16384,65536,150903,200037,18004,0,35399,35598,0,0,0,0,0,327680,65536,0,12075245923261610,12075254862145918,12075254862270397,12075245923596031
|
||
|
|
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,867091,867096,4194304,256,0,0,24,24,25792,0x7f1853411600,0x7f1723235600,1731472,1563861,65536,216433,216433,1731464,1575591,202737,16384,65536,148028,196441,2214,0,318,326,0,0,0,0,0,327680,65536,0,12075245923654360,12075254862311357,12075254862436956,12075245923969796
|
||
|
|
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,867091,867096,4194304,256,0,0,24,24,26496,0x7f1853411500,0x7f1723235640,1720096,1556088,65536,215011,215011,1720088,1567817,193601,16384,65536,164710,215899,10653,0,318536,319666,0,0,0,0,0,327680,65536,0,12075245924045496,12075254862489275,12075254862613754,12075245924356925
|
||
|
|
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,867091,867096,4194304,256,0,0,28,24,27712,0x7f1853411400,0x7f1723235680,3199632,3019375,65536,399953,399953,3199624,3031097,375785,16384,65536,401346,440922,7932,0,0,156993,0,0,0,0,0,327680,65536,0,12075245924417848,12075254862657914,12075254862905432,12075245924893252
|
||
|
|
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,867091,867096,4194304,256,0,0,28,24,28416,0x7f1853411300,0x7f17232356c0,3120928,2954133,65536,390115,390115,3120920,2965861,383465,16384,65536,295436,357185,3732,0,0,38063,0,0,0,0,0,327680,65536,0,12075245924917637,12075254862979991,12075254863224629,12075245925414090
|
||
|
|
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,867091,867096,4194304,256,0,0,24,24,29120,0x7f1853411a00,0x7f1723235700,1769424,1607677,65536,221177,221177,1769416,1619409,196196,16384,65536,165135,227506,13918,0,153426,154099,0,0,0,0,0,327680,65536,0,12075245925438215,12075254863326548,12075254863450547,12075245925771915
|
||
|
|
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,867091,867096,4194304,256,0,0,24,24,30080,0x7f1853411900,0x7f1723235740,1728352,1569758,65536,216043,216043,1728344,1583267,196713,16384,65536,148575,211647,1433,0,44352,44549,0,0,0,0,0,327680,65536,0,12075245925834120,12075254863491027,12075254863615826,12075245926141441
|
||
|
|
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,867091,867096,4194304,256,0,0,24,24,30784,0x7f1853411800,0x7f1723235780,1679888,1507639,65536,209985,209985,1679880,1519375,192873,16384,65536,161912,227312,5498,0,84815,85153,0,0,0,0,0,327680,65536,0,12075245926214096,12075254863666386,12075254863791025,12075245926521929
|
||
|
|
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,867091,867096,4194304,256,0,0,28,24,32000,0x7f1853411700,0x7f17232357c0,3211808,3044543,65536,401475,401475,3211800,3056279,384624,16384,65536,325157,364449,12261,0,0,247327,0,0,0,0,0,327680,65536,0,12075245926583613,12075254863832144,12075254864082542,12075245927060409
|
||
|
|
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,867091,867096,4194304,256,0,0,28,24,32960,0x7f1853411600,0x7f1723235800,3099984,2916897,65536,387497,387497,3099976,2928627,381545,16384,65536,308376,371002,1927,0,0,195816,0,0,0,0,0,327680,65536,0,12075245927084825,12075254864185102,12075254864428620,12075245927573433
|
||
|
|
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,867091,867096,4194304,256,0,0,24,24,33920,0x7f1853411500,0x7f1723235840,1729184,1566633,65536,216147,216147,1729176,1578361,189680,16384,65536,176815,239599,22149,0,7428,7483,0,0,0,0,0,327680,65536,0,12075245927599972,12075254864507819,12075254864632778,12075245927924735
|
||
|
|
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,867091,867096,4194304,256,0,0,24,24,34880,0x7f1853411400,0x7f1723235880,1757072,1597713,65536,219633,219633,1757064,1609445,202092,16384,65536,148056,213166,231,0,20895,20995,0,0,0,0,0,327680,65536,0,12075245927986120,12075254864672298,12075254864797577,12075245928319739
|
||
|
|
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,867091,867096,4194304,256,0,0,24,24,35840,0x7f1853411300,0x7f17232358c0,1693088,1532127,65536,211635,211635,1693080,1543857,193253,16384,65536,182507,241399,5422,0,298057,299234,0,0,0,0,0,327680,65536,0,12075245928388547,12075254864849736,12075254864974855,12075245928694005
|
||
|
|
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,867091,867096,4194304,256,0,0,28,24,37312,0x7f1853411a00,0x7f1723235900,3650512,2957300,65536,456313,456313,3650504,2975347,388201,16384,65536,269373,328871,24226,0,0,529151,0,0,0,0,0,327680,65536,0,12075245928755289,12075254865020935,12075254865304932,12075245929270386
|
||
|
|
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,867091,867096,4194304,256,0,0,28,24,38272,0x7f1853411900,0x7f1723235940,3094304,2917679,65536,386787,386787,3094296,2929409,374633,16384,65536,322580,384755,1669,0,0,160528,0,0,0,0,0,327680,65536,0,12075245929298819,12075254865384612,12075254865629890,12075245929783039
|
||
|
|
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,867091,867096,4194304,256,0,0,24,24,39232,0x7f1853411800,0x7f1723235980,1718032,1553042,65536,214753,214753,1718024,1564773,189295,16384,65536,122516,187886,1138,0,5293,5313,0,0,0,0,0,327680,65536,0,12075245929808406,12075254865711169,12075254865835808,12075245930133660
|
||
|
|
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,867091,867096,4194304,256,0,0,24,24,40192,0x7f1853411700,0x7f17232359c0,2271328,1625142,65536,283915,283915,2271320,1643197,195561,16384,65536,151123,213959,159,0,9440,9509,0,0,0,0,0,327680,65536,0,12075245930192470,12075254865877568,12075254866003647,12075245930550174
|
||
|
|
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,867091,867096,4194304,256,0,0,24,24,41152,0x7f1853411600,0x7f1723235a00,1707984,1534138,65536,213497,213497,1707976,1545869,195265,16384,65536,183161,241553,3346,0,6068,6125,0,0,0,0,0,327680,65536,0,12075245930619764,12075254866058846,12075254866183485,12075245930926895
|
||
|
|
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,867091,867096,4194304,256,0,0,28,24,42624,0x7f1853411500,0x7f1723235a40,3164192,2992166,65536,395523,395523,3164184,3003893,381296,16384,65536,390722,406412,31899,0,0,799764,0,0,0,0,0,327680,65536,0,12075245930985924,12075254866225565,12075254866477723,12075245931475434
|
||
|
|
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,867091,867096,4194304,256,0,0,28,24,43584,0x7f1853411400,0x7f1723235a80,3598928,2984357,65536,449865,449865,3598920,3002405,386408,16384,65536,411353,473460,3527,0,0,135556,0,0,0,0,0,327680,65536,0,12075245931498857,12075254866588602,12075254866838360,12075245932033501
|
||
|
|
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,867091,867096,4194304,256,0,0,24,24,44544,0x7f1853411300,0x7f1723235ac0,1732576,1562250,65536,216571,216571,1732568,1573987,197578,16384,65536,138789,202913,219,0,167910,168728,0,0,0,0,0,327680,65536,0,12075245932057536,12075254866957399,12075254867082678,12075245932388250
|
||
|
|
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,867091,867096,4194304,256,0,0,24,24,45760,0x7f1853411a00,0x7f1723235b00,1769360,1610826,65536,221169,221169,1769352,1622563,202090,16384,65536,142292,206628,3545,0,86838,87187,0,0,0,0,0,327680,65536,0,12075245932450576,12075254867124598,12075254867250197,12075245932760292
|
||
|
|
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,867091,867096,4194304,256,0,0,24,24,46720,0x7f1853411900,0x7f1723235b40,1698272,1535609,65536,212283,212283,1698264,1547337,193264,16384,65536,133942,197023,690,0,112512,113032,0,0,0,0,0,327680,65536,0,12075245932831233,12075254867306036,12075254867431315,12075245933135389
|
||
|
|
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,867091,867096,4194304,256,0,0,28,24,48448,0x7f1853411800,0x7f1723235b80,3187344,3023145,65536,398417,398417,3187336,3034881,394960,16384,65536,375478,364259,65047,0,0,1826178,0,0,0,0,0,327680,65536,0,12075245933194869,12075254867473875,12075254867737713,12075245933670864
|
||
|
|
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,867091,867096,4194304,256,0,0,28,24,49408,0x7f1853411700,0x7f1723235bc0,3140064,2957019,65536,392507,392507,3140056,2968745,381929,16384,65536,249644,313763,1807,0,0,109252,0,0,0,0,0,327680,65536,0,12075245933696291,12075254867794992,12075254868039310,12075245934184068
|
||
|
|
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,867091,867096,4194304,256,0,0,24,24,50368,0x7f1853411600,0x7f1723235c00,1712464,1553625,65536,214057,214057,1712456,1565357,197357,16384,65536,141668,201360,953,0,228795,229899,0,0,0,0,0,327680,65536,0,12075245934208192,12075254868098350,12075254868223149,12075245934537945
|
||
|
|
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,867091,867096,4194304,256,0,0,24,24,51584,0x7f1853411500,0x7f1723235c40,1769632,1600503,65536,221203,221203,1769624,1612227,198000,16384,65536,152144,209099,10787,0,291366,292354,0,0,0,0,0,327680,65536,0,12075245934597526,12075254868264748,12075254868391147,12075245934920386
|
||
|
|
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,867091,867096,4194304,256,0,0,24,24,52544,0x7f1853411400,0x7f1723235c80,1685264,1524283,65536,210657,210657,1685256,1536019,199605,16384,65536,138435,203333,693,0,0,0,0,0,0,0,0,327680,65536,0,12075245934990456,12075254868442347,12075254868567146,12075245935300081
|
||
|
|
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,867091,867096,4194304,256,0,0,28,24,54272,0x7f1853411300,0x7f1723235cc0,3300064,3120270,65536,412507,412507,3300056,3131999,389736,16384,65536,328941,326494,91112,0,0,3305548,0,0,0,0,0,327680,65536,0,12075245935360504,12075254868609066,12075254868866343,12075245935845094
|
||
|
|
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,867091,867096,4194304,256,0,0,28,24,55488,0x7f1853411a00,0x7f1723235d00,3179984,2997368,65536,397497,397497,3179976,3009099,386537,16384,65536,348014,407994,2433,0,0,109382,0,0,0,0,0,327680,65536,0,12075245935872936,12075254868924103,12075254869168581,12075245936371032
|
||
|
|
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,867091,867096,4194304,256,0,0,24,24,56704,0x7f1853411900,0x7f1723235d40,1720736,1549003,65536,215091,215091,1720728,1560737,202992,16384,65536,111932,177385,2149,0,79645,80000,0,0,0,0,0,327680,65536,0,12075245936398373,12075254869230341,12075254869355300,12075245936721443
|
||
|
|
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,867091,867096,4194304,256,0,0,24,24,58176,0x7f1853411800,0x7f1723235d80,1772816,1601628,65536,221601,221601,1772808,1613363,203762,16384,65536,155875,206852,26759,0,225957,226861,0,0,0,0,0,327680,65536,0,12075245936777968,12075254869397539,12075254869525698,12075245937093775
|
||
|
|
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,867091,867096,4194304,256,0,0,24,24,59392,0x7f1853411700,0x7f1723235dc0,1728800,1562383,65536,216099,216099,1728792,1574115,196324,16384,65536,154097,217389,2,0,117448,118039,0,0,0,0,0,327680,65536,0,12075245937166490,12075254869576738,12075254869702017,12075245937477638
|
||
|
|
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,867091,867096,4194304,256,0,0,28,24,61376,0x7f1853411600,0x7f1723235e00,3242512,3068265,65536,405313,405313,3242504,3079999,386384,16384,65536,357277,339302,93004,0,0,2783298,0,0,0,0,0,327680,65536,0,12075245937537249,12075254869744576,12075254870004574,12075245937987957
|
||
|
|
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,867091,867096,4194304,256,0,0,28,24,62592,0x7f1853411500,0x7f1723235e40,3605536,2988234,65536,450691,450691,3605528,3008061,380520,16384,65536,309347,371110,2352,0,0,122860,0,0,0,0,0,327680,65536,0,12075245938039713,12075254870066334,12075254870312092,12075245938561512
|
||
|
|
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,867091,867096,4194304,256,0,0,24,24,63808,0x7f1853411400,0x7f1723235e80,1696208,1527498,65536,212025,212025,1696200,1539235,191593,16384,65536,133352,198870,522,0,15,16,0,0,0,0,0,327680,65536,0,12075245938585277,12075254870369051,12075254870494010,12075245938915961
|
||
|
|
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,867091,867096,4194304,256,0,0,24,24,65280,0x7f1853411300,0x7f1723235ec0,1824800,1646152,65536,228099,228099,1824792,1657891,211953,16384,65536,245294,267408,28278,0,241593,242532,0,0,0,0,0,327680,65536,0,12075245938979579,12075254870533850,12075254870662809,12075245939303782
|
||
|
|
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,867091,867096,4194304,256,0,0,24,24,66496,0x7f1853411a00,0x7f1723235f00,1751568,1586185,65536,218945,218945,1751560,1597913,192869,16384,65536,148729,214169,0,0,43350,43554,0,0,0,0,0,327680,65536,0,12075245939375826,12075254870715768,12075254870840887,12075245939687585
|
||
|
|
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,867091,867096,4194304,256,0,0,28,24,68480,0x7f1853411900,0x7f1723235f40,3284256,3094133,65536,410531,410531,3284248,3105863,392168,16384,65536,562707,473748,75996,0,0,2317955,0,0,0,0,0,327680,65536,0,12075245939745693,12075254870881687,12075254871136565,12075245940232908
|
||
|
|
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,867091,867096,4194304,256,0,0,28,24,69696,0x7f1853411800,0x7f1723235f80,3150096,2977525,65536,393761,393761,3150088,2989257,378446,16384,65536,332721,392976,5508,0,0,83051,0,0,0,0,0,327680,65536,0,12075245940257013,12075254871199765,12075254871448243,12075245940750621
|
||
|
|
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,867091,867096,4194304,256,0,0,24,24,70912,0x7f1853411700,0x7f1723235fc0,1739104,1577659,65536,217387,217387,1739096,1589395,196719,16384,65536,127808,191544,460,0,21402,21420,0,0,0,0,0,327680,65536,0,12075245940776689,12075254871510002,12075254871635441,12075245941108175
|
||
|
|
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,867091,867096,4194304,256,0,0,24,24,72384,0x7f1853411600,0x7f1723236000,1793872,1629730,65536,224233,224233,1793864,1641459,209008,16384,65536,195473,259403,1815,0,125402,125943,0,0,0,0,0,327680,65536,0,12075245941167595,12075254871675601,12075254871811600,12075245941497218
|
||
|
|
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,867091,867096,4194304,256,0,0,24,24,73600,0x7f1853411500,0x7f1723236040,1683744,1516435,65536,210467,210467,1683736,1528167,199881,16384,65536,148483,211797,215,0,0,0,0,0,0,0,0,327680,65536,0,12075245941566978,12075254871861999,12075254871986638,12075245941869380
|
||
|
|
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,867091,867096,4194304,256,0,0,28,24,75840,0x7f1853411400,0x7f1723236080,3219408,3027952,65536,402425,402425,3219400,3039681,394729,16384,65536,320175,313714,77685,0,0,3554244,0,0,0,0,0,327680,65536,0,12075245941931395,12075254872032078,12075254872327755,12075245942409493
|
||
|
|
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,867091,867096,4194304,256,0,0,28,24,77056,0x7f1853411300,0x7f17232360c0,3136352,2967891,65536,392043,392043,3136344,2979619,379368,16384,65536,351813,413123,1114,0,0,61871,0,0,0,0,0,327680,65536,0,12075245942438397,12075254872390635,12075254872634153,12075245942923258
|
||
|
|
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,867091,867096,4194304,256,0,0,24,24,78272,0x7f1853411a00,0x7f1723236100,1789584,1624130,65536,223697,223697,1789576,1635859,197357,16384,65536,152598,217989,956,0,5426,5468,0,0,0,0,0,327680,65536,0,12075245942946491,12075254872689992,12075254872814311,12075245943285101
|
||
|
|
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,867091,867096,4194304,256,0,0,24,24,80000,0x7f1853411900,0x7f1723236140,1857888,1688352,65536,232235,232235,1857880,1700083,212722,16384,65536,221401,285411,2228,0,5187,5215,0,0,0,0,0,327680,65536,0,12075245943342678,12075254872856871,12075254872998630,12075245943671980
|
||
|
|
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,867091,867096,4194304,256,0,0,24,24,81216,0x7f1853411800,0x7f1723236180,1730192,1562964,65536,216273,216273,1730184,1574699,197949,16384,65536,165241,229850,28,0,7268,7329,0,0,0,0,0,327680,65536,0,12075245943742290,12075254873050150,12075254873175588,12075245944046225
|
||
|
|
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,867091,867096,4194304,256,0,0,28,24,83456,0x7f1853411700,0x7f17232361c0,3228000,3056536,65536,403499,403499,3227992,3068275,388457,16384,65536,518899,453746,68982,0,0,2227300,0,0,0,0,0,327680,65536,0,12075245944106818,12075254873217668,12075254873473186,12075245944590527
|
||
|
|
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,867091,867096,4194304,256,0,0,28,24,84928,0x7f1853411600,0x7f1723236200,3212432,3033149,65536,401553,401553,3212424,3044879,376553,16384,65536,283286,346931,1428,0,0,189558,0,0,0,0,0,327680,65536,0,12075245944613910,12075254873532546,12075254873779744,12075245945115643
|
||
|
|
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,867091,867096,4194304,256,0,0,24,24,86400,0x7f1853411500,0x7f1723236240,1669280,1502991,65536,208659,208659,1669272,1514721,195649,16384,65536,118240,183633,1241,0,6101,6151,0,0,0,0,0,327680,65536,0,12075245945138886,12075254873838463,12075254873963742,12075245945468488
|
||
|
|
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,867091,867096,4194304,256,0,0,24,24,88128,0x7f1853411400,0x7f1723236280,1943312,1773664,65536,242913,242913,1943304,1785389,223346,16384,65536,210044,275580,0,0,11549,11586,0,0,0,0,0,327680,65536,0,12075245945532036,12075254874005502,12075254874155901,12075245945859465
|
||
|
|
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,867091,867096,4194304,256,0,0,24,24,89600,0x7f1853411300,0x7f17232362c0,1748320,1576725,65536,218539,218539,1748312,1590229,197362,16384,65536,161671,227064,1,0,1731,1750,0,0,0,0,0,327680,65536,0,12075245945949793,12075254874223900,12075254874349499,12075245946267944
|
||
|
|
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,867091,867096,4194304,256,0,0,28,24,92096,0x7f1853411a00,0x7f1723236300,3333136,3155629,65536,416641,416641,3333128,3167365,396137,16384,65536,540553,464057,67539,0,0,3474198,0,0,0,0,0,327680,65536,0,12075245946328186,12075254874390619,12075254874644857,12075245946820912
|
||
|
|
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,867091,867096,4194304,256,0,0,28,24,93568,0x7f1853411900,0x7f1723236340,3089632,2902369,65536,386203,386203,3089624,2914091,366825,16384,65536,254817,318405,1707,0,0,76470,0,0,0,0,0,327680,65536,0,12075245946844415,12075254874702456,12075254874951254,12075245947338864
|
||
|
|
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,867091,867096,4194304,256,0,0,24,24,95040,0x7f1853411800,0x7f1723236380,1746960,1582803,65536,218369,218369,1746952,1594529,193362,16384,65536,120682,186214,9,0,36234,36405,0,0,0,0,0,327680,65536,0,12075245947361937,12075254875006614,12075254875132053,12075245947691289
|
||
|
|
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,867091,867096,4194304,256,0,0,24,24,96768,0x7f1853411700,0x7f17232363c0,2016672,1860328,65536,252083,252083,2016664,1872065,236132,16384,65536,209283,274819,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245947749437,12075254875172852,12075254875329971,12075245948091443
|
||
|
|
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,867091,867096,4194304,256,0,0,24,24,98240,0x7f1853411600,0x7f1723236400,1704528,1533392,65536,213065,213065,1704520,1545129,199017,16384,65536,147877,213014,103,0,22329,22422,0,0,0,0,0,327680,65536,0,12075245948162495,12075254875383571,12075254875508690,12075245948471048
|
||
|
|
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,867091,867096,4194304,256,0,0,28,24,100736,0x7f1853411500,0x7f1723236440,3299616,3119186,65536,412451,412451,3299608,3130919,391144,16384,65536,372924,351686,73711,0,0,3092386,0,0,0,0,0,327680,65536,0,12075245948530188,12075254875551409,12075254875807567,12075245949016742
|
||
|
|
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,867091,867096,4194304,256,0,0,28,24,102208,0x7f1853411400,0x7f1723236480,3134544,2971109,65536,391817,391817,3134536,2982837,371049,16384,65536,311974,372396,3996,0,0,192376,0,0,0,0,0,327680,65536,0,12075245949042841,12075254875860047,12075254876109485,12075245949533563
|
||
|
|
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,867091,867096,4194304,256,0,0,24,24,103680,0x7f1853411300,0x7f17232364c0,1757152,1591894,65536,219643,219643,1757144,1603625,206056,16384,65536,154014,218195,1316,0,3610,3631,0,0,0,0,0,327680,65536,0,12075245949558910,12075254876169324,12075254876294923,12075245949887040
|
||
|
|
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,867091,867096,4194304,256,0,0,24,24,105664,0x7f1853411a00,0x7f1723236500,2113232,1952915,65536,264153,264153,2113224,1964643,245746,16384,65536,264824,330360,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245949947071,12075254876338603,12075254876504201,12075245950296250
|
||
|
|
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,867091,867096,4194304,256,0,0,24,24,107136,0x7f1853411900,0x7f1723236540,1680224,1512978,65536,210027,210027,1680216,1524711,197609,16384,65536,174515,239747,1045,0,41916,42112,0,0,0,0,0,327680,65536,0,12075245950366350,12075254876555241,12075254876681480,12075245950670035
|
||
|
|
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,867091,867096,4194304,256,0,0,28,24,109888,0x7f1853411800,0x7f1723236580,3248528,3031445,65536,406065,406065,3248520,3043181,386157,16384,65536,472222,419511,82917,0,0,1744975,0,0,0,0,0,327680,65536,0,12075245950728183,12075254876722760,12075254876980198,12075245951211972
|
||
|
|
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,867091,867096,4194304,256,0,0,28,24,111360,0x7f1853411700,0x7f17232365c0,3143456,2975587,65536,392931,392931,3143448,2987319,382185,16384,65536,270022,329613,1456,0,0,1158738,0,0,0,0,0,327680,65536,0,12075245951235275,12075254877040837,12075254877288355,12075245951732980
|
||
|
|
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,867091,867096,4194304,256,0,0,24,24,112832,0x7f1853411600,0x7f1723236600,1758928,1597627,65536,219865,219865,1758920,1609353,201712,16384,65536,148834,208082,2315,0,18220,18323,0,0,0,0,0,327680,65536,0,12075245951755802,12075254877344195,12075254877470434,12075245952084944
|
||
|
|
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,867091,867096,4194304,256,0,0,24,24,114816,0x7f1853411500,0x7f1723236640,2197344,2037402,65536,274667,274667,2197336,2049125,258415,16384,65536,234816,300352,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245952146909,12075254877510913,12075254877682912,12075245952494455
|
||
|
|
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,867091,867096,4194304,256,0,0,24,24,116288,0x7f1853411400,0x7f1723236680,1685136,1518736,65536,210641,210641,1685128,1530475,204658,16384,65536,154073,213232,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245952566970,12075254877734431,12075254877859870,12075245952868871
|
||
|
|
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,867091,867096,4194304,256,0,0,28,24,119040,0x7f1853411300,0x7f17232366c0,3213216,3019129,65536,401651,401651,3213208,3030857,383208,16384,65536,296494,294324,101983,0,0,2526433,0,0,0,0,0,327680,65536,0,12075245952929714,12075254877902110,12075254878153788,12075245953419985
|
||
|
|
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,867091,867096,4194304,256,0,0,28,24,120768,0x7f1853411a00,0x7f1723236700,3635920,2974803,65536,454489,454489,3635912,2992853,379625,16384,65536,264329,300008,5400,0,0,1183927,0,0,0,0,0,327680,65536,0,12075245953443258,12075254878217788,12075254878464826,12075245953973504
|
||
|
|
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,867091,867096,4194304,256,0,0,24,24,122496,0x7f1853411900,0x7f1723236740,1792928,1612577,65536,224115,224115,1792920,1624303,207080,16384,65536,171662,237080,2182,0,23071,23153,0,0,0,0,0,327680,65536,0,12075245954005513,12075254878525145,12075254878650904,12075245954335937
|
||
|
|
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,867091,867096,4194304,256,0,0,24,24,124736,0x7f1853411800,0x7f1723236780,2306320,2150156,65536,288289,288289,2306312,2161885,271858,16384,65536,253746,319282,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245954395738,12075254878690424,12075254878871702,12075245954761628
|
||
|
|
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,867091,867096,4194304,256,0,0,24,24,126464,0x7f1853411700,0x7f17232367c0,1732576,1561640,65536,216571,216571,1732568,1573367,203463,16384,65536,161143,225424,140,0,40309,40514,0,0,0,0,0,327680,65536,0,12075245954831628,12075254878922422,12075254879047861,12075245955139571
|
||
|
|
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,867091,867096,4194304,256,0,0,20,24,127936,0x7f1853411600,0x7f1723236800,3281616,3114498,65536,410201,410201,3281608,3126225,392941,16384,65536,372854,438390,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245955200855,12075254879090420,12075254879353938,12075245955662753
|
||
|
|
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,867091,867096,4194304,256,0,0,28,24,129664,0x7f1853411500,0x7f1723236840,3117280,2930875,65536,389659,389659,3117272,2942599,375913,16384,65536,253021,316475,1376,0,0,1643204,0,0,0,0,0,327680,65536,0,12075245955716553,12075254879411858,12075254879656176,12075245956161660
|
||
|
|
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,867091,867096,4194304,256,0,0,24,24,131392,0x7f1853411400,0x7f1723236880,1762320,1594457,65536,220289,220289,1762312,1606183,197481,16384,65536,169989,234691,2461,0,9036,9094,0,0,0,0,0,327680,65536,0,12075245956211563,12075254879716015,12075254879841774,12075245956518774
|
||
|
|
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,867091,867096,4194304,256,0,0,24,24,133632,0x7f1853411300,0x7f17232368c0,2424544,2253727,65536,303067,303067,2424536,2267229,283503,16384,65536,193377,258913,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245956580158,12075254879886734,12075254880077932,12075245956957489
|
||
|
|
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,867091,867096,4194304,256,0,0,24,24,135360,0x7f1853411a00,0x7f1723236900,1773968,1615347,65536,221745,221745,1773960,1627075,205768,16384,65536,155592,218563,3220,0,86832,87226,0,0,0,0,0,327680,65536,0,12075245957034933,12075254880129772,12075254880257771,12075245957352323
|
||
|
|
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,867091,867096,4194304,256,0,0,20,24,136832,0x7f1853411900,0x7f1723236940,3493792,3325330,65536,436723,436723,3493784,3337065,418672,16384,65536,291381,356917,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245957414328,12075254880299851,12075254880582088,12075245957914948
|
||
|
|
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,867091,867096,4194304,256,0,0,28,24,138560,0x7f1853411800,0x7f1723236980,3176208,2998397,65536,397025,397025,3176200,3010131,384745,16384,65536,266280,328995,10530,0,0,1554798,0,0,0,0,0,327680,65536,0,12075245957944984,12075254880638248,12075254880890886,12075245958447538
|
||
|
|
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,867091,867096,4194304,256,0,0,24,24,140288,0x7f1853411700,0x7f17232369c0,1769120,1595744,65536,221139,221139,1769112,1607477,201020,16384,65536,152234,215235,5027,0,13792,13853,0,0,0,0,0,327680,65536,0,12075245958471683,12075254880943845,12075254881070244,12075245958802718
|
||
|
|
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,867091,867096,4194304,256,0,0,24,24,142784,0x7f1853411600,0x7f1723236a00,2638352,2479620,65536,329793,329793,2638344,2491351,312933,16384,65536,310200,375736,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245958864573,12075254881111524,12075254881320322,12075245959271770
|
||
|
|
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,867091,867096,4194304,256,0,0,24,24,144768,0x7f1853411500,0x7f1723236a40,1813088,1637683,65536,226635,226635,1813080,1649421,205540,16384,65536,150914,202335,10467,0,50649,50845,0,0,0,0,0,327680,65536,0,12075245959334316,12075254881389122,12075254881517601,12075245959648340
|
||
|
|
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,867091,867096,4194304,256,0,0,20,24,145728,0x7f1853411400,0x7f1723236a80,4139920,3617497,65536,517489,517489,4139912,3635547,452587,16384,65536,372326,437862,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245959708742,12075254881558880,12075254881895518,12075245960236773
|
||
|
|
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,867091,867096,4194304,256,0,0,28,24,147712,0x7f1853411300,0x7f1723236ac0,3127328,2937077,65536,390915,390915,3127320,2948805,382568,16384,65536,257013,301274,42635,0,0,2329819,0,0,0,0,0,327680,65536,0,12075245960288890,12075254881953757,12075254882202715,12075245960726633
|
||
|
|
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,867091,867096,4194304,256,0,0,24,24,149696,0x7f1853411a00,0x7f1723236b00,1756496,1594441,65536,219561,219561,1756488,1606169,208754,16384,65536,157977,209871,7400,0,130047,130613,0,0,0,0,0,327680,65536,0,12075245960778800,12075254882268635,12075254882395834,12075245961084328
|
||
|
|
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,867091,867096,4194304,256,0,0,24,24,152192,0x7f1853411900,0x7f1723236b40,2865696,2687618,65536,358211,358211,2865688,2699343,339648,16384,65536,257185,322721,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245961143238,12075254882437593,12075254882664791,12075245961600487
|
||
|
|
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,867091,867096,4194304,256,0,0,24,24,154176,0x7f1853411800,0x7f1723236b80,1794448,1626263,65536,224305,224305,1794440,1637991,201456,16384,65536,163955,213143,10526,0,392611,394066,0,0,0,0,0,327680,65536,0,12075245961640652,12075254882734231,12075254882861750,12075245961955908
|
||
|
|
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,867091,867096,4194304,256,0,0,20,24,155648,0x7f1853411700,0x7f1723236bc0,4052576,3879867,65536,506571,506571,4052568,3891591,490480,16384,65536,391970,457506,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245962023323,12075254882902389,12075254883230227,12075245962572203
|
||
|
|
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,867091,867096,4194304,256,0,0,28,24,157632,0x7f1853411600,0x7f1723236c00,3130192,2966089,65536,391273,391273,3130184,2977817,390721,16384,65536,263786,317772,10739,0,0,2307958,0,0,0,0,0,327680,65536,0,12075245962601828,12075254883296626,12075254883547984,12075245963094634
|
||
|
|
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,867091,867096,4194304,256,0,0,24,24,159616,0x7f1853411500,0x7f1723236c40,1809888,1635146,65536,226235,226235,1809880,1646875,205040,16384,65536,184764,230573,14244,0,347037,348306,0,0,0,0,0,327680,65536,0,12075245963119881,12075254883608464,12075254883736463,12075245963457919
|
||
|
|
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,867091,867096,4194304,256,0,0,24,24,162368,0x7f1853411400,0x7f1723236c80,3066832,2902080,65536,383353,383353,3066824,2913807,365128,16384,65536,323394,388930,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245963522159,12075254883778542,12075254884022860,12075245963982534
|
||
|
|
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,867091,867096,4194304,256,0,0,24,24,164608,0x7f1853411300,0x7f1723236cc0,1861280,1681880,65536,232659,232659,1861272,1693613,206064,16384,65536,200030,238881,18319,0,382734,384208,0,0,0,0,0,327680,65536,0,12075245964030744,12075254884096300,12075254884224779,12075245964356389
|
||
|
|
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,867091,867096,4194304,256,0,0,20,24,166336,0x7f1853411a00,0x7f1723236d00,4585872,4430183,65536,573233,573233,4585864,4443683,558704,16384,65536,481026,546562,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245964414477,12075254884263658,12075254884638375,12075245964993032
|
||
|
|
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,867091,867096,4194304,256,0,0,28,24,168576,0x7f1853411900,0x7f1723236d40,3208608,3007709,65536,401075,401075,3208600,3019443,388073,16384,65536,335970,334823,143900,0,0,1520068,0,0,0,0,0,327680,65536,0,12075245965055228,12075254884691015,12075254884944133,12075245965536121
|
||
|
|
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,867091,867096,4194304,256,0,0,24,24,170816,0x7f1853411800,0x7f1723236d80,1808400,1634390,65536,226049,226049,1808392,1646113,211173,16384,65536,205439,248987,23720,0,140281,140751,0,0,0,0,0,327680,65536,0,12075245965563753,12075254885003812,12075254885134211,12075245965893255
|
||
|
|
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,867091,867096,4194304,256,0,0,24,24,174080,0x7f1853411700,0x7f1723236dc0,3468960,3311395,65536,433619,433619,3468952,3323121,415724,16384,65536,297753,363289,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245965957184,12075254885174531,12075254885453089,12075245966464987
|
||
|
|
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,867091,867096,4194304,256,0,0,24,24,176576,0x7f1853411600,0x7f1723236e00,1831952,1660549,65536,228993,228993,1831944,1672279,211393,16384,65536,193347,257161,43,0,8740,8791,0,0,0,0,0,327680,65536,0,12075245966504922,12075254885522528,12075254885657407,12075245966821610
|
||
|
|
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,867091,867096,4194304,256,0,0,20,24,177792,0x7f1853411500,0x7f1723236e40,5158304,4992344,65536,644787,644787,5158296,5004079,628978,16384,65536,363851,429387,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245966880209,12075254885697727,12075254886120283,12075245967526821
|
||
|
|
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,867091,867096,4194304,256,0,0,28,24,180288,0x7f1853411400,0x7f1723236e80,3280464,3098885,65536,410057,410057,3280456,3110615,387177,16384,65536,494353,428476,67940,0,0,3178210,0,0,0,0,0,327680,65536,0,12075245967551496,12075254886185403,12075254886451801,12075245968054341
|
||
|
|
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,867091,867096,4194304,256,0,0,24,24,182784,0x7f1853411300,0x7f1723236ec0,1800096,1630603,65536,225011,225011,1800088,1642325,209597,16384,65536,134441,199960,1154,0,235,237,0,0,0,0,0,327680,65536,0,12075245968079227,12075254886510360,12075254886645719,12075245968415031
|
||
|
|
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,867091,867096,4194304,256,0,0,24,24,186304,0x7f1853411a00,0x7f1723236f00,3902416,3744339,65536,487801,487801,3902408,3756063,470130,16384,65536,312203,377739,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245968473169,12075254886686519,12075254886999636,12075245968988206
|
||
|
|
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,867091,867096,4194304,256,0,0,24,24,189312,0x7f1853411900,0x7f1723236f40,1951008,1780260,65536,243875,243875,1951000,1791993,224242,16384,65536,191385,256921,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245969055682,12075254887072276,12075254887223954,12075245969380946
|
||
|
|
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,867091,867096,4194304,256,0,0,20,24,190784,0x7f1853411800,0x7f1723236f80,6479824,6106909,65536,809977,809977,6479816,6124667,766317,16384,65536,340247,405783,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245969440046,12075254887265554,12075254887780110,12075245970194147
|
||
|
|
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,867091,867096,4194304,256,0,0,28,24,193792,0x7f1853411700,0x7f1723236fc0,3674528,3465724,65536,459315,459315,3674520,3477453,434156,16384,65536,510129,432819,171366,0,0,3845808,0,0,0,0,0,327680,65536,0,12075245970221548,12075254887839789,12075254888137387,12075245970761622
|
||
|
|
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,867091,867096,4194304,256,0,0,24,24,196800,0x7f1853411600,0x7f1723237000,1971984,1817779,65536,246497,246497,1971976,1829501,228466,16384,65536,198375,263911,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245970787079,12075254888205866,12075254888361065,12075245971139174
|
||
|
|
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,867091,867096,4194304,256,0,0,24,24,201088,0x7f1853411500,0x7f1723237040,5055136,4590445,65536,631891,631891,5055128,4608503,575340,16384,65536,292031,357567,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245971198895,12075254888402825,12075254888786982,12075245971834135
|
||
|
|
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,867091,867096,4194304,256,0,0,24,24,204608,0x7f1853411400,0x7f1723237080,2239120,2065957,65536,279889,279889,2239112,2077689,260040,16384,65536,240686,306222,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245971874661,12075254888856421,12075254889032260,12075245972229841
|
||
|
|
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,867091,867096,4194304,256,0,0,20,24,206080,0x7f1853411300,0x7f17232370c0,7397920,7234945,65536,924739,924739,7397912,7246671,907500,16384,65536,423206,488742,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245972287908,12075254889073379,12075254889681374,12075245973126467
|
||
|
|
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,867091,867096,4194304,256,0,0,28,24,209600,0x7f1853411a00,0x7f1723237100,4013456,3842400,65536,501681,501681,4013448,3855905,482025,16384,65536,556501,582605,83779,0,0,3297618,0,0,0,0,0,327680,65536,0,12075245973155641,12075254889740734,12075254890067131,12075245973723797
|
||
|
|
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,867091,867096,4194304,256,0,0,24,24,213120,0x7f1853411900,0x7f1723237140,2256096,2097674,65536,282011,282011,2256088,2109409,263652,16384,65536,161750,227286,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245973749605,12075254890128411,12075254890306169,12075245974124301
|
||
|
|
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,867091,867096,4194304,256,0,0,24,24,218176,0x7f1853411800,0x7f1723237180,5589200,5419611,65536,698649,698649,5589192,5431345,680171,16384,65536,365426,430962,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245974189192,12075254890347449,12075254890802965,12075245974864066
|
||
|
|
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,867091,867096,4194304,256,0,0,24,24,222208,0x7f1853411700,0x7f17232371c0,2497312,2336937,65536,312163,312163,2497304,2348665,295659,16384,65536,225713,291249,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245974904752,12075254890871445,12075254891071923,12075245975327227
|
||
|
|
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,867091,867096,4194304,256,0,0,20,24,223936,0x7f1853411600,0x7f1723237200,8520912,8356541,65536,1065113,1065113,8520904,8368271,1049164,16384,65536,238815,304351,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245975351812,12075254891142963,12075254891844237,12075245976288613
|
||
|
|
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,867091,867096,4194304,256,0,0,28,24,227968,0x7f1853411500,0x7f1723237240,4552992,4383589,65536,569123,569123,4552984,4395323,548335,16384,65536,549473,615008,288,0,0,23206,0,0,0,0,0,327680,65536,0,12075245976314000,12075254891907916,12075254892280713,12075245976922090
|
||
|
|
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,867091,867096,4194304,256,0,0,24,24,232000,0x7f1853411400,0x7f1723237280,2552656,2393789,65536,319081,319081,2552648,2405515,300397,16384,65536,318768,384304,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245976951555,12075254892347593,12075254892548071,12075245977392364
|
||
|
|
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,867091,867096,4194304,256,0,0,24,24,237824,0x7f1853411300,0x7f17232372c0,6420704,6253024,65536,802587,802587,6420696,6264753,785388,16384,65536,293388,358924,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245977415537,12075254892604071,12075254893129186,12075245978184266
|
||
|
|
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,867091,867096,4194304,256,0,0,24,24,242368,0x7f1853411a00,0x7f1723237300,2788560,2626483,65536,348569,348569,2788552,2638215,331373,16384,65536,231919,297455,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245978223068,12075254893199746,12075254893423104,12075245978666442
|
||
|
|
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,867091,867096,4194304,256,0,0,20,24,243584,0x7f1853411900,0x7f1723237340,9652384,9488727,65536,1206547,1206547,9652376,9500459,1189304,16384,65536,289288,354824,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245978691559,12075254893481344,12075254894278297,12075245979725570
|
||
|
|
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,867091,867096,4194304,256,0,0,28,24,248128,0x7f1853411800,0x7f1723237380,5094032,4924562,65536,636753,636753,5094024,4936289,618219,16384,65536,431039,496384,966,0,0,142,0,0,0,0,0,327680,65536,0,12075245979755666,12075254894340217,12075254894760053,12075245980411906
|
||
|
|
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,867091,867096,4194304,256,0,0,24,24,252672,0x7f1853411700,0x7f17232373c0,2841952,2674750,65536,355243,355243,2841944,2688261,334949,16384,65536,275775,341311,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245980435630,12075254894820213,12075254895045171,12075245980875998
|
||
|
|
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,867091,867096,4194304,256,0,0,24,24,259264,0x7f1853411600,0x7f1723237400,7426448,7114020,65536,928305,928305,7426440,7132065,890853,16384,65536,369319,434855,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245980928055,12075254895114130,12075254895709805,12075245981739914
|
||
|
|
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,867091,867096,4194304,256,0,0,24,24,264832,0x7f1853411500,0x7f1723237440,3346848,3174302,65536,418355,418355,3346840,3186035,399851,16384,65536,353922,419458,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245981802220,12075254895779885,12075254896047883,12075245982263958
|
||
|
|
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,867091,867096,4194304,256,0,0,20,24,266304,0x7f1853411400,0x7f1723237480,11892432,11735981,65536,1486553,1486553,11892424,11747711,1470188,16384,65536,353615,419151,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245982312488,12075254896107402,12075254897090754,12075245983523548
|
||
|
|
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,867091,867096,4194304,256,0,0,28,24,271872,0x7f1853411300,0x7f17232374c0,6255264,6067985,65536,781907,781907,6255256,6079713,761705,16384,65536,755655,821191,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245983551220,12075254897148994,12075254897680029,12075245984311954
|
||
|
|
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,867091,867096,4194304,256,0,0,24,24,277440,0x7f1853411a00,0x7f1723237500,3359184,3197695,65536,419897,419897,3359176,3209429,403786,16384,65536,349093,414629,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245984340547,12075254897739229,12075254898009947,12075245984848641
|
||
|
|
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,867091,867096,4194304,256,0,0,12,24,279936,0x7f1853411900,0x7f1723237540,9004512,8847627,65536,1125563,1125563,9004504,8859357,1109613,16384,65536,388058,453594,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245984875030,12075254898071226,12075254898807860,12075245985857055
|
||
|
|
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,867091,867096,4194304,256,0,0,24,24,286528,0x7f1853411800,0x7f1723237580,3897232,3739115,65536,487153,487153,3897224,3750847,472040,16384,65536,319638,385174,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245985897430,12075254898878260,12075254899193777,12075245986434097
|
||
|
|
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,867091,867096,4194304,256,0,0,20,24,288000,0x7f1853411700,0x7f17232375c0,14137760,13980084,65536,1767219,1767219,14137752,13991817,1749488,16384,65536,377965,443501,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245986458673,12075254899261457,12075254900430727,12075245987868212
|
||
|
|
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,867091,867096,4194304,256,0,0,32,24,294592,0x7f1853411600,0x7f1723237600,7331856,7172683,65536,916481,916481,7331848,7184419,899952,16384,65536,1621616,833221,733276,0,0,37560409,0,0,0,0,0,327680,65536,0,12075245987897276,12075254900492967,12075254901105282,12075245988754590
|
||
|
|
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,867091,867096,4194304,256,0,0,24,24,301184,0x7f1853411500,0x7f1723237640,3928544,3769740,65536,491067,491067,3928536,3781473,475365,16384,65536,277197,342733,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245988780678,12075254901166721,12075254901484639,12075245989340799
|
||
|
|
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,867091,867096,4194304,256,0,0,12,24,304960,0x7f1853411400,0x7f1723237680,10686544,10533385,65536,1335817,1335817,10686536,10545117,1318898,16384,65536,427994,493530,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245989365956,12075254901544798,12075254902421591,12075245990484705
|
||
|
|
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,867091,867096,4194304,256,0,0,24,24,313600,0x7f1853411300,0x7f17232376c0,5007776,4845607,65536,625971,625971,5007768,4857337,609520,16384,65536,386843,452379,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245990528196,12075254902494390,12075254902904467,12075245991157415
|
||
|
|
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,867091,867096,4194304,256,0,0,20,24,314816,0x7f1853411a00,0x7f1723237700,18658128,18495246,65536,2332265,2332265,18658120,18508747,2315222,16384,65536,305573,371109,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245991187631,12075254902966227,12075254904515014,12075245992976105
|
||
|
|
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,867091,867096,4194304,256,0,0,20,24,317568,0x7f1853411900,0x7f1723237740,9621280,9442305,65536,1202659,1202659,9621272,9454035,1181673,16384,65536,358471,424007,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245993014526,12075254904622073,12075254905415188,12075245994043659
|
||
|
|
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,867091,867096,4194304,256,0,0,12,24,320320,0x7f1853411800,0x7f1723237780,5393104,4961152,65536,674137,674137,5393096,4979209,622275,16384,65536,238759,304295,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245994069126,12075254905521906,12075254905935664,12075245994744671
|
||
|
|
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,867091,867096,4194304,256,0,0,12,24,324096,0x7f1853411700,0x7f17232377c0,14074656,13901218,65536,1759331,1759331,14074648,13912943,1739753,16384,65536,445270,510806,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245994768015,12075254906043983,12075254907202535,12075245996162917
|
||
|
|
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,867091,867096,4194304,256,0,0,12,24,328896,0x7f1853411600,0x7f1723237800,9579408,9427262,65536,1197425,1197425,9579400,9438995,1179373,16384,65536,345958,411494,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245996207470,12075254907315174,12075254908100289,12075245997217787
|
||
|
|
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,867091,867096,4194304,256,0,0,20,24,330112,0x7f1853411500,0x7f1723237840,36660448,36507407,65536,4582555,4582555,36660440,36519143,4565873,16384,65536,434298,499834,0,0,0,0,0,0,0,0,0,327680,65536,0,12075245997246791,12075254908202689,12075254911254028,12075246000539681
|
||
|
|
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,867091,867096,4194304,256,0,0,20,24,332864,0x7f1853411400,0x7f1723237880,18597200,18425984,65536,2324649,2324649,18597192,18439487,2305648,16384,65536,392983,458519,0,0,0,0,0,0,0,0,0,327680,65536,0,12075246000567643,12075254911356108,12075254912897857,12075246002354944
|
||
|
|
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,867091,867096,4194304,256,0,0,12,24,335616,0x7f1853411300,0x7f17232378c0,9620320,9456540,65536,1202539,1202539,9620312,9468265,1185137,16384,65536,323971,389507,0,0,0,0,0,0,0,0,0,327680,65536,0,12075246002388156,12075254913002977,12075254913791291,12075246003414253
|
||
|
|
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,867091,867096,4194304,256,0,0,12,24,339392,0x7f1853411a00,0x7f1723237900,27549968,27379779,65536,3443745,3443745,27549960,27391509,3424997,16384,65536,383188,448724,0,0,0,0,0,0,0,0,0,327680,65536,0,12075246003447034,12075254913898651,12075254916180396,12075246005967798
|
||
|
|
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,867091,867096,4194304,256,0,0,12,24,344192,0x7f1853411900,0x7f1723237940,18589728,18421135,65536,2323715,2323715,18589720,18432867,2304749,16384,65536,337517,403053,0,0,0,0,0,0,0,0,0,327680,65536,0,12075246006024784,12075254916295915,12075254917831585,12075246007784023
|
||
|
|
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,867091,867096,4194304,256,0,0,20,24,345408,0x7f1853411800,0x7f1723237980,72707088,72532555,65536,9088385,9088385,72707080,72544287,9069161,16384,65536,374147,439683,0,0,0,0,0,0,0,0,0,327680,65536,0,12075246007817636,12075254917936544,12075254923992184,12075246014109568
|
||
|
|
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,867091,867096,4194304,256,0,0,20,24,348160,0x7f1853411700,0x7f17232379c0,36579360,36413441,65536,4572419,4572419,36579352,36425171,4553328,16384,65536,584361,649897,0,0,0,0,0,0,0,0,0,327680,65536,0,12075246014145125,12075254924104663,12075254927146403,12075246017426703
|
||
|
|
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,867091,867096,4194304,256,0,0,12,24,350912,0x7f1853411600,0x7f1723237a00,18638992,18460897,65536,2329873,2329873,18638984,18472625,2310258,16384,65536,378900,444436,0,0,0,0,0,0,0,0,0,327680,65536,0,12075246017454675,12075254927251522,12075254928790552,12075246019235604
|
||
|
|
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,867091,867096,4194304,256,0,0,12,24,0,0x7f1853411500,0x7f1723237a40,54503200,54334484,65536,6812899,6812899,54503192,54346213,6793970,16384,65536,318550,384086,0,0,0,0,0,0,0,0,0,327680,65536,0,12075246019269167,12075254928895191,12075254933422201,12075246024038270
|