Files
rocm-systems/tests/workloads/SQC/mi200/pmc_perf.csv
T

169 lines
61 KiB
CSV
Raw Normal View History

2022-11-04 14:49:36 -05:00
Index,KernelName,gpu-id,queue-id,queue-index,pid,tid,grd,wgr,lds,scr,vgpr,sgpr,fbar,sig,obj,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,DispatchNs,BeginNs,EndNs,CompleteNs
0,__amd_rocclr_fillBufferAligned.kd,0,0,0,142876,142876,33554432,256,0,0,4,32,4160,0x0,0x7f9c48e04280,3083768,2993273,38889450,524288,244059548,392,224,0,385470,385470,0,0,616,0,4718592,4714796,112,3684,1043234,0,524288,3670016,3663326,224,6466,1048576,1048576,1048576,15992426510816,15995326289103,15995326528944,15992575262378
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,142876,142876,32768,256,0,0,12,24,13888,0x0,0x7f9c48e23f80,261016,158043,1348509,512,1598971,504,56,0,32626,32626,0,0,560,0,8192,6249,56,1887,652,0,0,512,0,56,456,0,512,0,15992580439443,15995331324002,15995331337762,15992580578030
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,142876,142876,4194304,256,0,0,12,24,14336,0x7f9c4bd80380,0x7f9c48e23fc0,1318936,1211916,15668226,65536,81562850,392,56,0,164866,164866,0,0,448,0,917504,913474,0,4030,890705,0,0,65536,63800,56,1680,0,65536,0,15992580627039,15995331407843,15995331500803,15992580974291
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,142876,142876,4194304,256,0,0,16,24,15040,0x7f9c4bd80200,0x7f9c48e24000,2454888,2346081,30363053,65536,206220356,560,56,0,306860,306860,0,0,616,0,1114112,1109238,56,4818,480480,0,0,65536,63800,56,1680,0,65536,0,15992581025480,15995331534883,15995331713444,15992581402142
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,142876,142876,4194304,256,0,0,16,24,15488,0x7f9c4bd80080,0x7f9c48e24040,2477960,2370593,30698089,65536,222633048,448,56,0,309744,309744,0,0,504,0,917504,914338,56,3110,444404,0,0,65536,63800,56,1680,0,65536,0,15992581449511,15995331739524,15995331919525,15992581822582
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,142876,142876,4194304,256,0,0,12,24,15936,0x7f9c49721f00,0x7f9c48e24080,1330096,1216573,15739759,65536,78096656,504,56,0,166261,166261,0,0,560,0,1048576,1044479,56,4041,636848,0,0,65536,63800,56,1680,0,65536,0,15992581869141,15995331945125,15995332038885,15992582150605
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,142876,142876,4194304,256,0,0,12,24,16384,0x7f9c49721d80,0x7f9c48e240c0,1329520,1211913,15671866,65536,87442436,448,56,0,166189,166189,0,0,504,0,983040,978968,57,4015,882232,0,0,65536,63800,56,1680,0,65536,0,15992582198134,15995332064165,15995332156006,15992582499917
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,142876,142876,4194304,256,0,0,12,24,17088,0x7f9c49721c00,0x7f9c48e24100,1306248,1202658,15568455,65536,100918067,504,56,0,163280,163280,0,0,560,0,1114112,1111727,0,2385,889774,0,0,131072,129336,56,1680,65536,65536,0,15992582559306,15995332196806,15995332289446,15992582831510
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,142876,142876,4194304,256,0,0,16,24,17792,0x7f9c49721a80,0x7f9c48e24140,2475608,2368585,30722682,65536,218607995,616,56,0,309450,309450,0,0,672,0,1310720,1307266,56,3398,480392,0,0,131072,129336,56,1680,0,131072,0,15992582876529,15995332333447,15995332512167,15992583264220
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,142876,142876,4194304,256,0,0,16,24,18496,0x7f9c49721900,0x7f9c48e24180,2510568,2391175,30930597,65536,223791418,560,56,0,313820,313820,0,0,616,0,1179648,1175517,56,4075,475679,0,0,65536,63800,56,1680,0,0,65536,15992583308669,15995332540967,15995332720328,15992583685361
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,142876,142876,4194304,256,0,0,16,24,19200,0x7f9c49721780,0x7f9c48e241c0,1314376,1210200,15668160,65536,99673632,560,56,0,164296,164296,0,0,616,0,1245184,1240943,56,4185,435912,0,0,131072,129336,56,1680,65536,65536,0,15992583730050,15995332760328,15995332854409,15992584012464
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,142876,142876,4194304,256,0,0,16,24,19904,0x7f9c49721600,0x7f9c48e24200,1334304,1226038,15866470,65536,94840732,560,56,0,166787,166787,0,0,616,0,1245184,1241263,58,3863,555997,0,0,131072,129336,56,1680,65536,65536,0,15992584058803,15995332882889,15995332975689,15992584341887
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,142876,142876,4194304,256,0,0,12,24,20608,0x7f9c4bd80480,0x7f9c48e24240,1314088,1205199,15593182,65536,87517057,560,56,0,164260,164260,0,0,616,0,1245184,1241548,56,3580,432665,0,0,131072,129336,56,1680,65536,65536,0,15992584397335,15995333008009,15995333100650,15992584673759
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,142876,142876,4194304,256,0,0,16,24,21312,0x7f9c4bd80300,0x7f9c48e24280,2483224,2376110,30776511,65536,230943651,672,56,0,310402,310402,0,0,728,0,1441792,1437175,56,4561,448041,0,0,131072,129336,56,1680,0,131072,0,15992584719698,15995333138730,15995333318731,15992585090660
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,142876,142876,4194304,256,0,0,16,24,22016,0x7f9c4bd80180,0x7f9c48e242c0,2462224,2354616,30513272,65536,215235281,616,56,0,307777,307777,0,0,672,0,1310720,1306557,56,4107,438673,0,0,65536,63800,56,1680,0,0,65536,15992585137009,15995333350891,15995333532651,15992585516341
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,142876,142876,4194304,256,0,0,16,24,22720,0x7f9c4bd80000,0x7f9c48e24300,1331256,1222955,15809832,65536,90411391,616,56,0,166406,166406,0,0,672,0,1376256,1372283,56,3917,449940,0,0,131072,129336,56,1680,65536,65536,0,15992585562350,15995333560331,15995333654572,15992585849543
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,142876,142876,4194304,256,0,0,12,24,23424,0x7f9c49721e80,0x7f9c48e24340,1314568,1201372,15555731,65536,101662703,672,56,0,164320,164320,0,0,728,0,1441792,1437899,56,3837,435742,0,0,131072,129336,56,1680,65536,65536,0,15992585894742,15995333686412,15995333780492,15992586175186
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,142876,142876,4194304,256,0,0,12,24,24128,0x7f9c49721d00,0x7f9c48e24380,1310168,1202557,15561565,65536,97081552,616,56,0,163770,163770,0,0,672,0,1310720,1306585,112,4023,791446,0,0,131072,129336,56,1680,65536,65536,0,15992586229295,15995333814253,15995333906893,15992586510908
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,142876,142876,4194304,256,0,0,16,24,24832,0x7f9c49721b80,0x7f9c48e243c0,2473640,2364618,30641068,65536,220475283,728,56,0,309204,309204,0,0,784,0,1572864,1569195,56,3613,484780,0,0,131072,129336,56,1680,0,131072,0,15992586557167,15995333942893,15995334122414,15992586896860
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,142876,142876,4194304,256,0,0,16,24,25536,0x7f9c49721a00,0x7f9c48e24400,2464320,2355354,30499217,65536,219660677,616,56,0,308039,308039,0,0,672,0,1441792,1439508,0,2284,849337,0,0,65536,63800,56,1680,0,0,65536,15992586944459,15995334149454,15995334329615,15992587283971
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,142876,142876,4194304,256,0,0,12,24,26240,0x7f9c49721880,0x7f9c48e24440,1313800,1211593,15676369,65536,98985086,672,56,0,164224,164224,0,0,728,0,1507328,1503414,56,3858,439552,0,0,131072,129336,56,1680,65536,65536,0,15992587329500,15995334359855,15995334453775,15992587587764
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,142876,142876,4194304,256,0,0,12,24,26944,0x7f9c49721700,0x7f9c48e24480,1314568,1207457,15615813,65536,99086627,728,56,0,164320,164320,0,0,784,0,1638400,1634309,56,4035,458577,0,0,131072,129336,56,1680,65536,65536,0,15992587632913,15995334485775,15995334579056,15992587888518
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,142876,142876,4194304,256,0,0,12,24,27648,0x7f9c4bd80580,0x7f9c48e244c0,1313592,1205183,15603029,65536,97826079,616,56,0,164198,164198,0,0,672,0,1441792,1438176,56,3560,907627,0,0,131072,129336,56,1680,65536,65536,0,15992587941486,15995334612976,15995334704976,15992588187061
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,142876,142876,4194304,256,0,0,16,24,28608,0x7f9c4bd80400,0x7f9c48e24500,2477208,2373480,30733490,65536,225186273,784,56,0,309650,309650,0,0,840,0,1703936,1700469,56,3411,566329,0,0,131072,129336,56,1680,0,131072,0,15992588233010,15995334732496,15995334911857,15992588571532
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,142876,142876,4194304,256,0,0,16,24,29312,0x7f9c4bd80280,0x7f9c48e24540,2471272,2368888,30685855,65536,212209348,728,56,0,308908,308908,0,0,784,0,1572864,1568397,56,4411,529609,0,0,65536,63800,56,1680,0,0,65536,15992588618681,15995334939057,15995335118418,15992588956634
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,142876,142876,4194304,256,0,0,12,24,30016,0x7f9c4bd80100,0x7f9c48e24580,1298456,1193548,15443522,65536,95116765,672,56,0,162306,162306,0,0,728,0,1638400,1634783,0,3617,886302,0,0,131072,129336,56,1680,65536,65536,0,15992589003723,15995335161778,15995335253938,15992589255957
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,142876,142876,4194304,256,0,0,8,24,30976,0x7f9c49721f80,0x7f9c48e245c0,1302520,1196505,15463436,65536,84998574,784,56,0,162814,162814,0,0,840,0,1835008,1830841,0,4167,875994,0,0,131072,129336,56,1680,65536,65536,0,15992589303016,15995335283218,15995335375699,15992589556780
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,142876,142876,4194304,256,0,0,12,24,31680,0x7f9c49721e00,0x7f9c48e24600,1322104,1205336,15591760,65536,87038478,728,56,0,165262,165262,0,0,784,0,1507328,1502993,112,4223,583047,0,0,131072,129336,56,1680,65536,65536,0,15992589609649,15995335408979,15995335501779,15992589861054
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,142876,142876,4194304,256,0,0,16,24,32640,0x7f9c49721c80,0x7f9c48e24640,2458632,2349315,30453232,65536,223304018,784,56,0,307328,307328,0,0,840,0,1835008,1831644,0,3364,883694,0,0,131072,129336,56,1680,0,131072,0,15992589907103,15995335531539,15995335710900,15992590252745
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,142876,142876,4194304,256,0,0,12,24,33600,0x7f9c49721b00,0x7f9c48e24680,2463688,2355812,30482710,65536,219219828,784,56,0,307960,307960,0,0,840,0,1703936,1699649,56,4231,870096,0,0,65536,63800,56,1680,0,0,65536,15992590300404,15995335738740,15995335920661,15992590646226
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,142876,142876,4194304,256,0,0,12,24,34560,0x7f9c49721980,0x7f9c48e246c0,1306456,1200242,15529638,65536,100500555,784,56,0,163306,163306,0,0,840,0,1769472,1764869,56,4547,445417,0,0,131072,129336,56,1680,65536,65536,0,15992590692545,15995335948661,15995336042902,15992590947109
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,142876,142876,4194304,256,0,0,8,24,35520,0x7f9c49721800,0x7f9c48e24700,1322280,1216048,15699601,65536,91155932,896,56,0,165284,165284,0,0,952,0,2031616,2024265,112,7239,437016,0,0,131072,129336,56,1680,65536,65536,0,15992590993508,15995336075862,15995336170102,15992591253433
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,142876,142876,4194304,256,0,0,12,24,36224,0x7f9c49721680,0x7f9c48e24740,1305600,1200177,15522362,65536,92333383,728,56,0,163199,163199,0,0,784,0,1638400,1633009,56,5335,567533,0,0,131072,129336,56,1680,65536,65536,0,15992591307051,15995336203222,15995336296983,15992591551986
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,142876,142876,4194304,256,0,0,12,24,37184,0x7f9c4bd80500,0x7f9c48e24780,2459176,2354468,30484469,65536,226686442,840,56,0,307396,307396,0,0,896,0,1966080,1961917,0,4163,856011,0,0,131072,129336,56,1680,0,131072,0,15992591599105,15995336329303,15995336508983,15992591938847
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,142876,142876,4194304,256,0,0,12,24,38144,0x7f9c4bd80380,0x7f9c48e247c0,2435992,2331646,30219337,65536,209301702,840,56,0,304498,304498,0,0,896,0,1835008,1830395,56,4557,442112,0,0,65536,63800,56,1680,0,0,65536,15992591984796,15995336541144,15995336720824,15992592327929
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,142876,142876,4194304,256,0,0,12,24,39104,0x7f9c4bd80200,0x7f9c48e24800,1312352,1201202,15522543,65536,88869773,840,56,0,164043,164043,0,0,896,0,1900544,1895716,112,4716,549619,0,0,131072,129336,56,1680,65536,65536,0,15992592374248,15995336745144,15995336838745,15992592626592
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,142876,142876,4194304,256,0,0,8,24,40320,0x7f9c4bd80080,0x7f9c48e24840,1305984,1199644,15485047,65536,89094592,1008,56,0,163247,163247,0,0,1064,0,2228224,2222505,56,5663,511148,0,0,131072,129336,56,1680,65536,65536,0,15992592675071,15995336867225,15995336961305,15992592923776
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,142876,142876,4194304,256,0,0,12,24,41280,0x7f9c49721f00,0x7f9c48e24880,1300032,1194203,15450056,65536,94821093,784,56,0,162503,162503,0,0,840,0,1703936,1699241,56,4639,441648,0,0,131072,129336,56,1680,65536,65536,0,15992592977254,15995336996505,15995337089306,15992593227279
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,142876,142876,4194304,256,0,0,12,24,42240,0x7f9c49721d80,0x7f9c48e248c0,2443872,2334526,30236914,65536,225528359,952,56,0,305483,305483,0,0,1008,0,2097152,2091753,56,5343,440963,0,0,131072,129336,56,1680,0,131072,0,15992593273158,15995337119066,15995337297947,15992593614140
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,142876,142876,4194304,256,0,0,12,24,43200,0x7f9c49721c00,0x7f9c48e24900,2446512,2341034,30320906,65536,219903469,840,56,0,305813,305813,0,0,896,0,1966080,1963545,56,2479,886382,0,0,65536,63800,56,1680,0,0,65536,15992593660569,15995337329947,15995337509627,15992594001272
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,142876,142876,4194304,256,0,0,8,24,44160,0x7f9c49721a80,0x7f9c48e24940,1305672,1199922,15503193,65536,100387436,896,56,0,163208,163208,0,0,952,0,2031616,2026472,56,5088,519311,0,0,131072,129336,56,1680,65536,65536,0,15992594046641,15995337551868,15995337646588,15992594305955
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,142876,142876,4194304,256,0,0,12,24,45376,0x7f9c49721900,0x7f9c48e24980,1322808,1207725,15586845,65536,87114918,1064,56,0,165350,165350,0,0,1120,0,2424832,2418198,56,6578,442153,0,0,131072,129336,56,1680,65536,65536,0,15992594351634,15995337682268,15995337777469,15992594616628
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,142876,142876,4194304,256,0,0,12,24,46336,0x7f9c49721780,0x7f9c48e249c0,1303064,1195565,15459533,65536,88745935,840,56,0,162882,162882,0,0,896,0,1835008,1830439,56,4513,671631,0,0,131072,129336,56,1680,65536,65536,0,15992594669757,15995337811069,15995337904509,15992594925401
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,142876,142876,4194304,256,0,0,12,24,47552,0x7f9c49721600,0x7f9c48e24a00,2431176,2316471,29994205,65536,217755604,1008,56,0,303896,303896,0,0,1064,0,2228224,2222927,112,5185,514935,0,0,131072,129336,56,1680,0,131072,0,15992594971700,15995337937149,15995338115710,15992595314523
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,142876,142876,4194304,256,0,0,12,24,48512,0x7f9c4bd80480,0x7f9c48e24a40,2432232,2325450,30109448,65536,209863212,952,56,0,304028,304028,0,0,1008,0,2097152,2092051,56,5045,443798,0,0,65536,63800,56,1680,0,0,65536,15992595361532,15995338145790,15995338325631,15992595703094
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,142876,142876,4194304,256,0,0,8,24,49472,0x7f9c4bd80300,0x7f9c48e24a80,1297256,1191430,15385955,65536,93885053,896,56,0,162156,162156,0,0,952,0,2162688,2157907,0,4781,894628,0,0,131072,129336,56,1680,65536,65536,0,15992595749163,15995338356511,15995338449471,15992595999087
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,142876,142876,4194304,256,0,0,12,24,50688,0x7f9c4bd80180,0x7f9c48e24ac0,1293280,1187164,15314340,65536,96472386,1120,56,0,161659,161659,0,0,1176,0,2621440,2612945,56,8439,896359,0,0,131072,129336,56,1680,65536,65536,0,15992596045486,15995338476671,15995338570112,15992596298681
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,142876,142876,4194304,256,0,0,12,24,51648,0x7f9c4bd80000,0x7f9c48e24b00,1295472,1186229,15344769,65536,93700228,840,56,0,161933,161933,0,0,896,0,1966080,1960191,0,5889,898336,0,0,131072,129336,56,1680,65536,65536,0,15992596352160,15995338604032,15995338696192,15992596606594
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,142876,142876,4194304,256,0,0,12,24,52864,0x7f9c49721e80,0x7f9c48e24b40,2428968,2324936,30107223,65536,218092990,1064,56,0,303620,303620,0,0,1120,0,2359296,2351655,56,7585,439753,0,0,131072,129336,56,1680,0,131072,0,15992596651713,15995338728352,15995338906753,15992597002835
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,142876,142876,4194304,256,0,0,12,24,54080,0x7f9c49721d00,0x7f9c48e24b80,2436544,2320543,30047671,65536,218027300,1008,56,0,304567,304567,0,0,1064,0,2228224,2223167,56,5001,441268,0,0,65536,63800,56,1680,0,0,65536,15992597049104,15995338958273,15995339136674,15992597392817
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,142876,142876,4194304,256,0,0,8,24,55296,0x7f9c49721b80,0x7f9c48e24bc0,1318688,1208044,15603092,65536,93369680,1008,56,0,164835,164835,0,0,1064,0,2293760,2288310,112,5338,474960,0,0,131072,129336,56,1680,65536,65536,0,15992597437786,15995339175394,15995339270115,15992597694580
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,142876,142876,4194304,256,0,0,12,24,56768,0x7f9c49721a00,0x7f9c48e24c00,1311096,1198574,15456846,65536,102005487,1232,56,0,163886,163886,0,0,1288,0,2752512,2741006,57,11449,442921,0,0,131072,129336,56,1680,65536,65536,0,15992597739939,15995339309155,15995339404515,15992597995353
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,142876,142876,4194304,256,0,0,12,24,57728,0x7f9c49721880,0x7f9c48e24c40,1301480,1193304,15424114,65536,95064782,952,56,0,162684,162684,0,0,1008,0,2031616,2025705,56,5855,470517,0,0,131072,129336,56,1680,65536,65536,0,15992598048092,15995339437795,15995339531076,15992598316096
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,142876,142876,4194304,256,0,0,12,24,58944,0x7f9c49721700,0x7f9c48e24c80,2438952,2326534,30101950,65536,216475736,1064,56,0,304868,304868,0,0,1120,0,2490368,2484712,56,5600,875638,0,0,131072,129336,56,1680,0,131072,0,15992598361205,15995339556516,15995339736196,15992598705767
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,142876,142876,4194304,256,0,0,12,24,60160,0x7f9c4bd80580,0x7f9c48e24cc0,2424536,2315175,30000514,65536,213992078,1064,56,0,303066,303066,0,0,1120,0,2359296,2353305,56,5935,446324,0,0,65536,63800,56,1680,0,0,65536,15992598750996,15995339760837,15995339941317,15992599096749
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,142876,142876,4194304,256,0,0,8,24,61376,0x7f9c4bd80400,0x7f9c48e24d00,1306512,1201444,15502995,65536,94104523,1064,56,0,163313,163313,0,0,1120,0,2424832,2414501,56,10275,468710,0,0,131072,129336,56,1680,65536,65536,0,15992599142778,15995339965317,15995340059558,15992599397092
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,142876,142876,4194304,256,0,0,12,24,62848,0x7f9c4bd80280,0x7f9c48e24d40,1350400,1241534,16004849,65536,102438364,1344,56,0,168799,168799,0,0,1400,0,2949120,2940529,112,8479,456291,0,0,131072,129336,56,1680,65536,65536,0,15992599443291,15995340087238,15995340187558,15992599699735
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,142876,142876,4194304,256,0,0,12,24,63808,0x7f9c4bd80100,0x7f9c48e24d80,1297088,1192652,15420062,65536,92339006,952,56,0,162135,162135,0,0,1008,0,2162688,2157624,56,5008,437298,0,0,131072,129336,56,1680,65536,65536,0,15992599753684,15995340221638,15995340316039,15992600000078
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,142876,142876,4194304,256,0,0,12,24,65024,0x7f9c49721f80,0x7f9c48e24dc0,2411248,2300350,29785662,65536,214917935,1120,56,0,301405,301405,0,0,1176,0,2621440,2616787,0,4653,873376,0,0,131072,129336,56,1680,0,131072,0,15992600046107,15995340344839,15995340524200,15992600385470
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,142876,142876,4194304,256,0,0,12,24,66240,0x7f9c49721e00,0x7f9c48e24e00,2413032,2302816,29836311,65536,212949223,1064,56,0,301628,301628,0,0,1120,0,2490368,2486407,56,3905,900451,0,0,65536,63800,56,1680,0,0,65536,15992600431219,15995340548840,15995340728040,15992600769821
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,142876,142876,4194304,256,0,0,8,24,67456,0x7f9c49721c80,0x7f9c48e24e40,1317384,1208043,15576277,65536,93871458,1120,56,0,164672,164672,0,0,1176,0,2555904,2546006,56,9842,434912,0,0,131072,129336,56,1680,65536,65536,0,15992600815950,15995340753001,15995340848041,15992601070884
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,142876,142876,4194304,256,0,0,12,24,68928,0x7f9c49721b00,0x7f9c48e24e80,1416576,1308369,16862716,65536,110878421,1400,56,0,177071,177071,0,0,1456,0,3145728,3130257,85,15386,447760,0,0,131072,129336,56,1680,65536,65536,0,15992601115713,15995340873481,15995340977481,15992601386167
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,142876,142876,4194304,256,0,0,12,24,70144,0x7f9c49721980,0x7f9c48e24ec0,1287400,1181834,15272478,65536,92922495,952,56,0,160924,160924,0,0,1008,0,2228224,2223024,56,5144,877482,0,0,131072,129336,56,1680,65536,65536,0,15992601439126,15995341010122,15995341102922,15992601689101
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,142876,142876,4194304,256,0,0,12,24,71616,0x7f9c49721800,0x7f9c48e24f00,2425160,2316196,29975209,65536,216080010,1232,56,0,303144,303144,0,0,1288,0,2752512,2746015,56,6441,437378,0,0,131072,129336,56,1680,0,131072,0,15992601734440,15995341128842,15995341309003,15992602080632
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,142876,142876,4194304,256,0,0,12,24,72832,0x7f9c49721680,0x7f9c48e24f40,2430904,2314958,29948613,65536,215703750,1176,56,0,303862,303862,0,0,1232,0,2621440,2613711,56,7673,437558,0,0,65536,63800,56,1680,0,0,65536,15992602124381,15995341336683,15995341517484,15992602471943
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,142876,142876,4194304,256,0,0,8,24,74048,0x7f9c4bd80500,0x7f9c48e24f80,1305752,1191013,15352966,65536,89585211,1120,56,0,163218,163218,0,0,1176,0,2686976,2678406,56,8514,888198,0,0,131072,129336,56,1680,65536,65536,0,15992602517102,15995341541804,15995341635884,15992602772627
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,142876,142876,4194304,256,0,0,12,24,75776,0x7f9c4bd80380,0x7f9c48e24fc0,1459016,1349828,17414259,65536,109488032,1456,56,0,182376,182376,0,0,1512,0,3342336,3329439,2,12895,893755,0,0,131072,129336,56,1680,65536,65536,0,15992602818676,15995341661004,15995341768045,15992603085340
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,142876,142876,4194304,256,0,0,12,24,76992,0x7f9c4bd80200,0x7f9c48e25000,1289160,1184235,15299629,65536,90255124,1064,56,0,161144,161144,0,0,1120,0,2359296,2350088,56,9152,439430,0,0,131072,129336,56,1680,65536,65536,0,15992603149678,15995341801485,15995341894765,15992603384613
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,142876,142876,4194304,256,0,0,12,24,78464,0x7f9c4bd80080,0x7f9c48e25040,2419368,2310544,29952701,65536,218802150,1288,56,0,302420,302420,0,0,1344,0,2883584,2876314,112,7158,439568,0,0,131072,129336,56,1680,0,131072,0,15992603429872,15995341919565,15995342100206,15992603779244
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,142876,142876,4194304,256,0,0,12,24,79936,0x7f9c49721f00,0x7f9c48e25080,2403944,2295871,29752930,65536,208882331,1232,56,0,300492,300492,0,0,1288,0,2686976,2680510,56,6410,438173,0,0,65536,63800,56,1680,0,0,65536,15992603825463,15995342125966,15995342306287,15992604163186
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,142876,142876,4194304,256,0,0,8,24,81408,0x7f9c49721d80,0x7f9c48e250c0,1305160,1197885,15445767,65536,93873488,1232,56,0,163144,163144,0,0,1288,0,2818048,2808461,56,9531,440931,0,0,131072,129336,56,1680,65536,65536,0,15992604208465,15995342331087,15995342426447,15992604464279
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,142876,142876,4194304,256,0,0,12,24,83136,0x7f9c49721c00,0x7f9c48e25100,1538880,1425907,18381978,65536,110686497,1568,56,0,192359,192359,0,0,1624,0,3538944,3516005,112,22827,438435,0,0,131072,129336,56,1680,65536,65536,0,15992604509518,15995342450767,15995342566928,15992604781772
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,142876,142876,4194304,256,0,0,12,24,84352,0x7f9c49721a80,0x7f9c48e25140,1296056,1186968,15330984,65536,91405243,1120,56,0,162006,162006,0,0,1176,0,2424832,2416435,56,8341,618368,0,0,131072,129336,56,1680,65536,65536,0,15992604834591,15995342612368,15995342705968,15992605083995
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,142876,142876,4194304,256,0,0,12,24,85824,0x7f9c49721900,0x7f9c48e25180,2418496,2311450,29914700,65536,218917871,1344,56,0,302311,302311,0,0,1400,0,3014656,3006548,112,7996,437974,0,0,131072,129336,56,1680,0,131072,0,15992605129264,15995342731249,15995342911569,15992605473207
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,142876,142876,4194304,256,0,0,12,24,87296,0x7f9c49721780,0x7f9c48e251c0,2426624,2312509,29936244,65536,209043780,1288,56,0,303327,303327,0,0,1344,0,2818048,2812035,56,5957,434397,0,0,65536,63800,56,1680,0,0,65536,15992605518036,15995342935409,15995343117010,15992605866238
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,142876,142876,4194304,256,0,0,12,24,88768,0x7f9c49721600,0x7f9c48e25200,1306520,1195373,15401322,65536,94960632,1288,56,0,163314,163314,0,0,1344,0,2949120,2937895,56,11169,441419,0,0,131072,129336,56,1680,65536,65536,0,15992605911037,15995343141330,15995343237011,15992606171031
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,142876,142876,4194304,256,0,0,12,24,90752,0x7f9c4bd80480,0x7f9c48e25240,1620976,1505657,19404215,65536,115188079,1680,56,0,202621,202621,0,0,1736,0,3735552,3718431,131,16990,642109,0,0,131072,129336,56,1680,65536,65536,0,15992606218200,15995343261331,15995343383091,15992606503084
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,142876,142876,4194304,256,0,0,12,24,91968,0x7f9c4bd80300,0x7f9c48e25280,1307832,1200165,15476182,65536,91092158,1120,56,0,163478,163478,0,0,1176,0,2555904,2543708,56,12140,464153,0,0,131072,129336,56,1680,65536,65536,0,15992606556523,15995343416371,15995343511892,15992606805617
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,142876,142876,4194304,256,0,0,12,24,93440,0x7f9c4bd80180,0x7f9c48e252c0,2442568,2328728,30141633,65536,218611406,1344,56,0,305320,305320,0,0,1400,0,3145728,3135271,56,10401,634472,0,0,131072,129336,56,1680,0,131072,0,15992606851806,15995343536532,15995343715733,15992607200328
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,142876,142876,4194304,256,0,0,12,24,94912,0x7f9c4bd80000,0x7f9c48e25300,2400104,2293342,29688508,65536,213719363,1344,56,0,300012,300012,0,0,1400,0,2949120,2942248,56,6816,571427,0,0,65536,63800,56,1680,0,0,65536,15992607247667,15995343741493,15995343920533,15992607586160
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,142876,142876,4194304,256,0,0,12,24,96384,0x7f9c49721e80,0x7f9c48e25340,1307256,1197092,15429234,65536,96978603,1344,56,0,163406,163406,0,0,1400,0,3080192,3069457,64,10671,453799,0,0,131072,129336,56,1680,65536,65536,0,15992607631409,15995343946453,15995344041174,15992607887153
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,142876,142876,4194304,256,0,0,12,24,98368,0x7f9c49721d00,0x7f9c48e25380,1696456,1576772,20343540,65536,117354999,1736,56,0,212056,212056,0,0,1792,0,3932160,3913730,134,18296,636004,0,0,131072,129336,56,1680,65536,65536,0,15992607932042,15995344067894,15995344193814,15992608224656
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,142876,142876,4194304,256,0,0,12,24,99584,0x7f9c49721b80,0x7f9c48e253c0,1302920,1194558,15397289,65536,95063193,1176,56,0,162864,162864,0,0,1232,0,2621440,2609272,56,12112,589647,0,0,131072,129336,56,1680,65536,65536,0,15992608277785,15995344226775,15995344320855,15992608524979
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,142876,142876,4194304,256,0,0,12,24,101312,0x7f9c49721a00,0x7f9c48e25400,2414664,2304059,29812655,65536,215660744,1400,56,0,301832,301832,0,0,1456,0,3276800,3267044,0,9756,892558,0,0,131072,129336,56,1680,0,131072,0,15992608570928,15995344347255,15995344525976,15992608909021
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,142876,142876,4194304,256,0,0,12,24,102784,0x7f9c49721880,0x7f9c48e25440,2394424,2284535,29585412,65536,210576410,1400,56,0,299302,299302,0,0,1456,0,3080192,3074076,56,6060,560680,0,0,65536,63800,56,1680,0,0,65536,15992608954879,15995344550616,15995344730297,15992609295662
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,142876,142876,4194304,256,0,0,12,24,104256,0x7f9c49721700,0x7f9c48e25480,1296680,1185503,15291605,65536,96571639,1344,56,0,162084,162084,0,0,1400,0,3211264,3203031,0,8233,883309,0,0,131072,129336,56,1680,65536,65536,0,15992609341261,15995344754937,15995344849337,15992609596275
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,142876,142876,4194304,256,0,0,12,24,106240,0x7f9c4bd80580,0x7f9c48e254c0,1761704,1642482,21185626,65536,130964517,1792,56,0,220212,220212,0,0,1848,0,4128768,4107209,58,21501,870000,0,0,131072,129336,56,1680,65536,65536,0,15992609641944,15995344873177,15995345003258,15992609932328
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,142876,142876,4194304,256,0,0,12,24,107712,0x7f9c4bd80400,0x7f9c48e25500,1291752,1186808,15306476,65536,90837788,1176,56,0,161468,161468,0,0,1232,0,2752512,2740597,0,11915,866106,0,0,131072,129336,56,1680,65536,65536,0,15992609986237,15995345037978,15995345130938,15992610244891
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,142876,142876,4194304,256,0,0,16,24,109440,0x7f9c4bd80280,0x7f9c48e25540,2392344,2288567,29631296,65536,216208959,1512,56,0,299042,299042,0,0,1568,0,3407872,3394263,112,13497,481075,0,0,131072,129336,56,1680,0,131072,0,15992610290810,15995345157978,15995345337659,15992610636972
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,142876,142876,4194304,256,0,0,16,24,111168,0x7f9c4bd80100,0x7f9c48e25580,2411064,2299871,29764771,65536,214901339,1456,56,0,301382,301382,0,0,1512,0,3211264,3204936,56,6272,570139,0,0,65536,63800,56,1680,0,0,65536,15992610684941,15995345361979,15995345542780,15992611026623
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,142876,142876,4194304,256,0,0,8,24,112896,0x7f9c49721f80,0x7f9c48e255c0,1317672,1206614,15556929,65536,101439725,1456,56,0,164708,164708,0,0,1512,0,3276800,3263218,56,13526,440716,0,0,131072,129336,56,1680,65536,65536,0,15992611075512,15995345567420,15995345664060,15992611335616
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,142876,142876,4194304,256,0,0,12,24,115136,0x7f9c49721e00,0x7f9c48e25600,1843304,1724927,22285875,65536,146544553,1904,56,0,230412,230412,0,0,1960,0,4325376,4299754,142,25480,747984,0,0,131072,129336,56,1680,65536,65536,0,15992611381685,15995345689661,15995345828541,15992611684409
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,142876,142876,4194304,256,0,0,12,24,116608,0x7f9c49721c80,0x7f9c48e25640,1302664,1188816,15339425,65536,95648636,1232,56,0,162832,162832,0,0,1288,0,2818048,2802694,56,15298,462499,0,0,131072,129336,56,1680,65536,65536,0,15992611737838,15995345861981,15995345957022,15992611990152
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,142876,142876,4194304,256,0,0,16,24,118336,0x7f9c49721b00,0x7f9c48e25680,2386888,2273915,29454464,65536,210678686,1568,56,0,298360,298360,0,0,1624,0,3538944,3523174,112,15658,485417,0,0,131072,129336,56,1680,0,131072,0,15992612035781,15995345981822,15995346162462,15992612374513
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,142876,142876,4194304,256,0,0,16,24,120064,0x7f9c49721980,0x7f9c48e256c0,2397696,2291446,29666946,65536,216012208,1512,56,0,299711,299711,0,0,1568,0,3407872,3398735,56,9081,484442,0,0,65536,63800,56,1680,0,0,65536,15992612420012,15995346187903,15995346367583,15992612766665
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,142876,142876,4194304,256,0,0,12,24,121792,0x7f9c49721800,0x7f9c48e25700,1316600,1205874,15556272,65536,103618503,1512,56,0,164574,164574,0,0,1568,0,3407872,3387840,112,19920,447515,0,0,131072,129336,56,1680,65536,65536,0,15992612812024,15995346392543,15995346490144,15992613070788
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,142876,142876,4194304,256,0,0,12,24,124032,0x7f9c49721680,0x7f9c48e25740,1907768,1801768,23262342,65536,162229023,2016,56,0,238470,238470,0,0,2072,0,4521984,4493034,90,28860,561728,0,0,131072,129336,56,1680,65536,65536,0,15992613115717,15995346515584,15995346660064,15992613422430
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,142876,142876,4194304,256,0,0,12,24,125504,0x7f9c4bd80500,0x7f9c48e25780,1288232,1183415,15234349,65536,94544859,1344,56,0,161028,161028,0,0,1400,0,3014656,3003577,112,10967,433698,0,0,131072,129336,56,1680,65536,65536,0,15992613475539,15995346692545,15995346789185,15992613726333
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,142876,142876,4194304,256,0,0,12,24,127488,0x7f9c4bd80380,0x7f9c48e257c0,2395096,2285395,29581869,65536,208538752,1680,56,0,299386,299386,0,0,1736,0,3801088,3790204,56,10828,734937,0,0,131072,129336,56,1680,0,131072,0,15992613773132,15995346814785,15995346994466,15992614111434
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,142876,142876,4194304,256,0,0,12,24,129216,0x7f9c4bd80200,0x7f9c48e25800,2401352,2287337,29603594,65536,202854921,1624,56,0,300168,300168,0,0,1680,0,3670016,3656109,112,13795,439654,0,0,65536,63800,56,1680,0,0,65536,15992614158843,15995347018466,15995347198307,15992614509256
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,142876,142876,4194304,256,0,0,12,24,130944,0x7f9c4bd80080,0x7f9c48e25840,1363032,1255338,16189791,65536,103454257,1568,56,0,170378,170378,0,0,1624,0,3670016,3649604,0,20412,880367,0,0,131072,129336,56,1680,65536,65536,0,15992614555095,15995347222467,15995347322467,15992614816999
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,142876,142876,4194304,256,0,0,12,24,133440,0x7f9c49721f00,0x7f9c48e25880,2086648,1968320,25387383,65536,166494237,2128,56,0,260830,260830,0,0,2184,0,4915200,4886889,103,28208,885939,0,0,131072,129336,56,1680,65536,65536,0,15992614863818,15995347348547,15995347504228,15992615184481
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,142876,142876,4194304,256,0,0,12,24,134912,0x7f9c49721d80,0x7f9c48e258c0,1297824,1190131,15347464,65536,97211459,1400,56,0,162227,162227,0,0,1456,0,3145728,3135650,56,10022,1001628,0,0,131072,129336,56,1680,65536,65536,0,15992615237790,15995347537508,15995347633668,15992615493494
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,142876,142876,4194304,256,0,0,12,24,136896,0x7f9c49721c00,0x7f9c48e25900,2387992,2276152,29457760,65536,201532900,1736,56,0,298498,298498,0,0,1792,0,4063232,4053339,0,9893,859903,0,0,131072,129336,56,1680,0,131072,0,15992615538593,15995347659108,15995347837989,15992615879815
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,142876,142876,4194304,256,0,0,12,24,138880,0x7f9c49721a80,0x7f9c48e25940,2370296,2261713,29295935,65536,205914179,1736,56,0,296286,296286,0,0,1792,0,3932160,3914782,56,17322,438253,0,0,65536,63800,56,1680,0,0,65536,15992615926804,15995347863269,15995348043590,15992616266147
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,142876,142876,4194304,256,0,0,12,24,140864,0x7f9c49721900,0x7f9c48e25980,1436280,1325628,17092553,65536,116415556,1736,56,0,179534,179534,0,0,1792,0,3932160,3903178,56,28926,443213,0,0,131072,129336,56,1680,65536,65536,0,15992616311236,15995348069030,15995348176871,15992616580650
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,142876,142876,4194304,256,0,0,12,24,143616,0x7f9c49721780,0x7f9c48e259c0,2249528,2130852,27497450,65536,185675554,2352,56,0,281190,281190,0,0,2408,0,5308416,5282914,71,25431,440011,0,0,131072,129336,56,1680,65536,65536,0,15992616626159,15995348201511,15995348372711,15992616954921
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,142876,142876,4194304,256,0,0,12,24,145344,0x7f9c49721600,0x7f9c48e25a00,1293448,1187920,15325190,65536,97771970,1512,56,0,161680,161680,0,0,1568,0,3342336,3331867,112,10357,1010621,0,0,131072,129336,56,1680,65536,65536,0,15992617008490,15995348405191,15995348501032,15992617265675
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,142876,142876,4194304,256,0,0,12,24,147584,0x7f9c4bd80480,0x7f9c48e25a40,2362808,2247266,29076298,65536,201004017,1904,56,0,295350,295350,0,0,1960,0,4325376,4301226,56,24094,432035,0,0,131072,129336,56,1680,0,131072,0,15992617311224,15995348525672,15995348706313,15992617654106
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,142876,142876,4194304,256,0,0,12,24,149568,0x7f9c4bd80300,0x7f9c48e25a80,2379112,2263220,29301648,65536,209881908,1848,56,0,297388,297388,0,0,1904,0,4194304,4175465,112,18727,560715,0,0,65536,63800,56,1680,0,0,65536,15992617700535,15995348730793,15995348912554,15992618045927
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,142876,142876,4194304,256,0,0,12,24,151552,0x7f9c4bd80180,0x7f9c48e25ac0,1503336,1381830,17810322,65536,109261781,1792,56,0,187916,187916,0,0,1848,0,4194304,4177847,0,16457,889937,0,0,131072,129336,56,1680,65536,65536,0,15992618093016,15995348937674,15995349048554,15992618372250
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,142876,142876,4194304,256,0,0,12,24,154304,0x7f9c4bd80000,0x7f9c48e25b00,2400712,2283039,29517257,65536,208305265,2464,56,0,300088,300088,0,0,2520,0,5701632,5660829,121,40682,901407,0,0,131072,129336,56,1680,65536,65536,0,15992618418289,15995349074634,15995349256235,15992618757951
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,142876,142876,4194304,256,0,0,12,24,156288,0x7f9c49721e80,0x7f9c48e25b40,1375080,1266365,16343792,65536,103988621,1624,56,0,171884,171884,0,0,1680,0,3735552,3717345,29,18178,1003910,0,0,131072,129336,56,1680,65536,65536,0,15992618811700,15995349290635,15995349392715,15992619065245
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,142876,142876,4194304,256,0,0,12,24,158784,0x7f9c49721d00,0x7f9c48e25b80,2392792,2271962,29342718,65536,178673423,2128,56,0,299098,299098,0,0,2184,0,4849664,4823499,113,26052,495299,0,0,131072,129336,56,1680,0,131072,0,15992619111054,15995349418476,15995349604716,15992619453286
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,142876,142876,4194304,256,0,0,12,24,161024,0x7f9c49721b80,0x7f9c48e25bc0,2393032,2261496,29225331,65536,170973336,2072,56,0,299128,299128,0,0,2128,0,4718592,4693730,112,24750,444375,0,0,65536,63800,56,1680,0,0,65536,15992619497695,15995349630316,15995349815117,15992619846847
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,142876,142876,4194304,256,0,0,12,24,163264,0x7f9c49721a00,0x7f9c48e25c00,1654312,1536113,19811013,65536,113967461,2016,56,0,206788,206788,0,0,2072,0,4718592,4684978,3,33611,891809,0,0,131072,129336,56,1680,65536,65536,0,15992619892216,15995349840397,15995349962638,15992620173370
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,142876,142876,4194304,256,0,0,12,24,166528,0x7f9c49721880,0x7f9c48e25c40,2731448,2614669,33740030,65536,222935065,2800,56,0,341430,341430,0,0,2856,0,6488064,6440250,120,47694,886409,0,0,131072,129336,56,1680,65536,65536,0,15992620218409,15995349987598,15995350193999,15992620632240
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,142876,142876,4194304,256,0,0,12,24,168512,0x7f9c49721700,0x7f9c48e25c80,1474952,1365883,17619819,65536,115204126,1848,56,0,184368,184368,0,0,1904,0,4128768,4105819,85,22864,1003661,0,0,131072,129336,56,1680,65536,65536,0,15992620652009,15995350271439,15995350382479,15992620924673
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,142876,142876,4194304,256,0,0,12,24,171264,0x7f9c4bd80580,0x7f9c48e25cc0,2362952,2251364,29020420,65536,196431179,2296,56,0,295368,295368,0,0,2352,0,5373952,5346533,56,27363,861218,0,0,131072,129336,56,1680,0,131072,0,15992620970262,15995350409200,15995350592080,15992621312665
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,142876,142876,4194304,256,0,0,12,24,173760,0x7f9c4bd80400,0x7f9c48e25d00,2374008,2259641,29158469,65536,185343162,2296,56,0,296750,296750,0,0,2352,0,5242880,5219143,112,23625,432082,0,0,65536,63800,56,1680,0,0,65536,15992621359104,15995350615280,15995350803921,15992621701796
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,142876,142876,4194304,256,0,0,12,24,176256,0x7f9c4bd80280,0x7f9c48e25d40,1805336,1690163,21804284,65536,148595513,2240,56,0,225666,225666,0,0,2296,0,5242880,5210091,1,32788,888890,0,0,131072,129336,56,1680,65536,65536,0,15992621747275,15995350828881,15995350963762,15992622040689
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,142876,142876,4194304,256,0,0,12,24,179776,0x7f9c4bd80100,0x7f9c48e25d80,3052928,2928599,37866152,65536,266494453,3136,56,0,381615,381615,0,0,3192,0,7274496,7221883,127,52486,886912,0,0,131072,129336,56,1680,65536,65536,0,15992622092938,15995350987922,15995351219923,15992622544167
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,142876,142876,4194304,256,0,0,12,24,182272,0x7f9c49721f80,0x7f9c48e25dc0,1692376,1579128,20365612,65536,128719887,2128,56,0,211546,211546,0,0,2184,0,4915200,4885181,96,29923,1014821,0,0,131072,129336,56,1680,65536,65536,0,15992622562707,15995351291283,15995351418164,15992622853211
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,142876,142876,4194304,256,0,0,12,24,185536,0x7f9c49721e00,0x7f9c48e25e00,2473752,2345561,30163620,65536,186481718,2800,56,0,309218,309218,0,0,2856,0,6422528,6392988,119,29421,480584,0,0,131072,129336,56,1680,0,131072,0,15992622899249,15995351444884,15995351635765,15992623293701
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,142876,142876,4194304,256,0,0,12,24,188544,0x7f9c49721c80,0x7f9c48e25e40,2493208,2352070,30306654,65536,178201468,2744,56,0,311650,311650,0,0,2800,0,6291456,6254404,56,36996,434997,0,0,65536,63800,56,1680,0,0,65536,15992623304100,15995351660085,15995351853205,15992623710481
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,142876,142876,4194304,256,0,0,12,24,191552,0x7f9c49721b00,0x7f9c48e25e80,2131224,2013352,26029846,65536,182802271,2688,56,0,266402,266402,0,0,2744,0,6291456,6237970,59,53427,901176,0,0,131072,129336,56,1680,65536,65536,0,15992623720871,15995351878006,15995352038006,15992624050834
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,142876,142876,4194304,256,0,0,12,24,195840,0x7f9c49721980,0x7f9c48e25ec0,3701256,3576778,46285578,65536,339708008,3752,56,0,462656,462656,0,0,3808,0,8847360,8794158,69,53133,907796,0,0,131072,129336,56,1680,65536,65536,0,15992624096733,15995352062486,15995352346007,15992624585522
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,142876,142876,4194304,256,0,0,12,24,198592,0x7f9c49721800,0x7f9c48e25f00,1949992,1838840,23762015,65536,169324470,2520,56,0,243748,243748,0,0,2576,0,5701632,5665152,148,36332,1018754,0,0,131072,129336,56,1680,65536,65536,0,15992624604081,15995352417528,15995352566648,15992624919394
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,142876,142876,4194304,256,0,0,12,24,202368,0x7f9c49721680,0x7f9c48e25f40,2692440,2561733,33020336,65536,207253957,3192,56,0,336554,336554,0,0,3248,0,7471104,7433145,94,37865,1017914,0,0,131072,129336,56,1680,0,131072,0,15992624965693,15995352591768,15995352799289,15992625377374
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,142876,142876,4194304,256,0,0,12,24,205888,0x7f9c4bd80500,0x7f9c48e25f80,2676680,2534733,32705176,65536,193064216,3192,56,0,334584,334584,0,0,3248,0,7340032,7298347,112,41573,492562,0,0,65536,63800,56,1680,0,0,65536,15992625387994,15995352860409,15995353066330,15992625784575
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,142876,142876,4194304,256,0,0,12,24,209408,0x7f9c4bd80380,0x7f9c48e25fc0,2447072,2341866,30233648,65536,212630234,3136,56,0,305883,305883,0,0,3192,0,7340032,7287665,58,52309,453225,0,0,131072,129336,56,1680,65536,65536,0,15992625813284,15995353104250,15995353290331,15992626162207
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,142876,142876,4194304,256,0,0,12,24,214464,0x7f9c4bd80200,0x7f9c48e26000,4342880,4222180,54664837,65536,401047861,4424,56,0,542859,542859,0,0,4480,0,10420224,10347333,110,72781,856964,0,0,131072,129336,56,1680,65536,65536,0,15992626209146,15995353314971,15995353649213,15992626724874
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,142876,142876,4194304,256,0,0,12,24,217728,0x7f9c4bd80080,0x7f9c48e26040,2181120,2070141,26750796,65536,188716798,2856,56,0,272639,272639,0,0,2912,0,6488064,6449702,162,38200,1003252,0,0,131072,129336,56,1680,65536,65536,0,15992626760273,15995353692573,15995353859774,15992627093616
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,142876,142876,4194304,256,0,0,12,24,222016,0x7f9c49721f00,0x7f9c48e26080,2938584,2820997,36288985,65536,245351076,3696,56,0,367322,367322,0,0,3752,0,8519680,8475890,183,43607,1014845,0,0,131072,129336,56,1680,0,131072,0,15992627140485,15995353884734,15995354113695,15992627545866
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,142876,142876,4194304,256,0,0,12,24,226048,0x7f9c49721d80,0x7f9c48e260c0,2929512,2809603,36161101,65536,254536340,3640,56,0,366188,366188,0,0,3696,0,8388608,8351591,112,36905,454459,0,0,65536,63800,56,1680,0,0,65536,15992627575335,15995354157215,15995354386656,15992627989466
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,142876,142876,4194304,256,0,0,12,24,230080,0x7f9c49721c00,0x7f9c48e26100,2786840,2668075,34467634,65536,240927346,3584,56,0,348354,348354,0,0,3640,0,8388608,8314995,58,73555,916621,0,0,131072,129336,56,1680,65536,65536,0,15992628018795,15995354450496,15995354662177,15992628409807
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,142876,142876,4194304,256,0,0,12,24,235904,0x7f9c49721a80,0x7f9c48e26140,4997480,4877521,63108608,65536,470890363,5096,56,0,624684,624684,0,0,5152,0,11993088,11914891,100,78097,879101,0,0,131072,129336,56,1680,65536,65536,0,15992628439286,15995354722017,15995355107459,15992629005024
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,142876,142876,4194304,256,0,0,12,24,239424,0x7f9c49721900,0x7f9c48e26180,2440824,2324059,29947336,65536,198372934,3192,56,0,305102,305102,0,0,3248,0,7274496,7212127,263,62106,1034777,0,0,131072,129336,56,1680,65536,65536,0,15992629043033,15995355174659,15995355362020,15992629395805
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,142876,142876,4194304,256,0,0,12,24,244224,0x7f9c49721780,0x7f9c48e261c0,3202056,3087725,39839080,65536,277119947,4088,56,0,400256,400256,0,0,4144,0,9568256,9511523,181,56552,1017349,0,0,131072,129336,56,1680,0,131072,0,15992629441764,15995355387140,15995355636421,15992629870264
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,142876,142876,4194304,256,0,0,12,24,248768,0x7f9c49721600,0x7f9c48e26200,3137944,3024896,39158160,65536,286863595,4088,56,0,392242,392242,0,0,4144,0,9437184,9371968,112,65104,618633,0,0,65536,63800,56,1680,0,0,65536,15992629901554,15995355695141,15995355943302,15992630328654
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,142876,142876,4194304,256,0,0,12,24,253312,0x7f9c4bd80480,0x7f9c48e26240,3112688,2992666,38685542,65536,273872954,3976,56,0,389085,389085,0,0,4032,0,9437184,9360128,58,76998,857479,0,0,131072,129336,56,1680,65536,65536,0,15992630357304,15995356007142,15995356244423,15992630815183
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,142876,142876,4194304,256,0,0,8,24,255552,0x7f9c4bd80300,0x7f9c48e26280,5759200,5631063,72885894,65536,536153814,1960,56,0,719899,719899,0,0,2016,0,16056320,16051609,56,4655,1015865,0,0,131072,129336,56,1680,65536,65536,0,15992630825973,15995356288103,15995356741865,15992631490148
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,142876,142876,4194304,256,0,0,12,24,259840,0x7f9c4bd80180,0x7f9c48e262c0,2914376,2799545,36180045,65536,258057223,3864,56,0,364296,364296,0,0,3920,0,8847360,8777434,202,69724,1009023,0,0,131072,129336,56,1680,65536,65536,0,15992631509418,15995356813545,15995357039306,15992631936519
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,142876,142876,4194304,256,0,0,12,24,265664,0x7f9c4bd80000,0x7f9c48e26300,3766440,3650870,47229949,65536,342296559,4984,56,0,470804,470804,0,0,5040,0,11665408,11565982,113,99313,1023136,0,0,131072,129336,56,1680,0,131072,0,15992631947228,15995357077867,15995357375628,15992632458757
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,142876,142876,4194304,256,0,0,12,24,271232,0x7f9c49721e80,0x7f9c48e26340,3786304,3669489,47439471,65536,350681114,4984,56,0,473287,473287,0,0,5040,0,11468800,11375088,380,93332,442302,0,0,65536,63800,56,1680,0,0,65536,15992632471017,15995357411468,15995357710989,15992632982475
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,142876,142876,4194304,256,0,0,8,24,273216,0x7f9c49721d00,0x7f9c48e26380,3860704,3747412,48497627,65536,347964416,1736,56,0,482587,482587,0,0,1792,0,14090240,14085692,3,4545,1024442,0,0,131072,129336,56,1680,65536,65536,0,15992632993625,15995357748589,15995358045230,15992633501834
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,142876,142876,4194304,256,0,0,8,24,275712,0x7f9c49721b80,0x7f9c48e263c0,7044088,6928506,89661550,65536,680844459,2296,56,0,880510,880510,0,0,2352,0,19202048,19194120,112,7816,1013996,0,0,131072,129336,56,1680,65536,65536,0,15992633512584,15995358097071,15995358653553,15992634286366
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,142876,142876,4194304,256,0,0,12,24,280768,0x7f9c49721a00,0x7f9c48e26400,3421888,3301183,42706893,65536,311919870,4424,56,0,427735,427735,0,0,4480,0,10420224,10331298,56,88870,1006239,0,0,131072,129336,56,1680,65536,65536,0,15992634305796,15995358725073,15995358989394,15992634782415
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,142876,142876,4194304,256,0,0,12,24,287616,0x7f9c49721880,0x7f9c48e26440,4421456,4306524,55704680,65536,408880232,5936,56,0,552681,552681,0,0,5992,0,13762560,13650743,619,111198,1019610,0,0,131072,129336,56,1680,0,131072,0,15992634793125,15995359053555,15995359403636,15992635359332
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,142876,142876,4194304,256,0,0,12,24,294208,0x7f9c49721700,0x7f9c48e26480,4414088,4300654,55592816,65536,408616838,5880,56,0,551760,551760,0,0,5936,0,13565952,13459934,571,105447,442053,0,0,65536,63800,56,1680,0,0,65536,15992635370152,15995359473876,15995359824598,15992635932460
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,142876,142876,4194304,256,0,0,8,24,296960,0x7f9c4bd80580,0x7f9c48e264c0,4519000,4391110,56818299,65536,415039516,2408,56,0,564874,564874,0,0,2464,0,15466496,15457885,0,8611,995878,0,0,131072,129336,56,1680,65536,65536,0,15992635942739,15995359893878,15995360241399,15992636502157
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,142876,142876,4194304,256,0,0,8,24,299968,0x7f9c4bd80400,0x7f9c48e26500,8341880,8224084,106434948,65536,809140216,2632,56,0,1042734,1042734,0,0,2688,0,22347776,22338298,112,9366,1008898,0,0,131072,129336,56,1680,65536,65536,0,15992636512857,15995360303000,15995360963482,15992637383937
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,142876,142876,4194304,256,0,0,8,24,302720,0x7f9c4bd80280,0x7f9c48e26540,5776328,5653980,73234242,65536,543383608,2408,56,0,722040,722040,0,0,2464,0,20250624,20240468,112,10044,1013453,0,0,131072,129336,56,1680,65536,65536,0,15992637403537,15995361033723,15995361481564,15992638034253
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,142876,142876,4194304,256,0,0,12,24,305472,0x7f9c4bd80100,0x7f9c48e26580,5783032,5676062,73493530,65536,559301857,2464,56,0,722878,722878,0,0,2520,0,20447232,20436509,58,10665,1014335,0,0,131072,129336,56,1680,0,131072,0,15992638060082,15995361545085,15995362009726,15992638737587
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,142876,142876,4194304,256,0,0,12,24,308224,0x7f9c49721f80,0x7f9c48e265c0,5780504,5660864,73265483,65536,547847712,2408,56,0,722562,722562,0,0,2464,0,19595264,19586166,112,8986,434897,0,0,65536,63800,56,1680,0,0,65536,15992638748237,15995362047007,15995362508769,15992639428362
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,142876,142876,4194304,256,0,0,8,24,310976,0x7f9c49721e00,0x7f9c48e26600,5822488,5699507,73725815,65536,542345938,2464,56,0,727810,727810,0,0,2520,0,20381696,20372886,112,8698,1023747,0,0,131072,129336,56,1680,65536,65536,0,15992639439612,15995362575489,15995363027331,15992640114427
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,142876,142876,4194304,256,0,0,8,24,313216,0x7f9c49721c80,0x7f9c48e26640,10946408,10814867,140070201,65536,1072167281,1960,56,0,1368300,1368300,0,0,2016,0,31522816,31518239,57,4520,1000200,0,0,131072,129336,56,1680,65536,65536,0,15992640125546,15995363090851,15995363960774,15992641222162
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,142876,142876,4194304,256,0,0,8,24,315968,0x7f9c49721b00,0x7f9c48e26680,10972008,10849447,140592700,65536,1083648054,2408,56,0,1371500,1371500,0,0,2464,0,38993920,38986575,114,7231,1012105,0,0,131072,129336,56,1680,65536,65536,0,15992641241752,15995364038215,15995364891178,15992642336947
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,142876,142876,4194304,256,0,0,12,24,318720,0x7f9c49721980,0x7f9c48e266c0,10994936,10863229,140736877,65536,1074338021,2464,56,0,1374366,1374366,0,0,2520,0,39124992,39115629,114,9249,1008783,0,0,131072,129336,56,1680,0,131072,0,15992642348727,15995364958698,15995365844462,15992643489162
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,142876,142876,4194304,256,0,0,12,24,321472,0x7f9c49721800,0x7f9c48e26700,10973144,10846599,140516226,65536,1073084839,2408,56,0,1371642,1371642,0,0,2464,0,38469632,38461922,56,7654,515033,0,0,65536,63800,56,1680,0,0,65536,15992643500251,15995365913422,15995366792626,15992644631826
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,142876,142876,4194304,256,0,0,8,24,324224,0x7f9c49721680,0x7f9c48e26740,11009280,10879780,140968088,65536,1089761554,2464,56,0,1376159,1376159,0,0,2520,0,39059456,39051302,113,8041,1000432,0,0,131072,129336,56,1680,65536,65536,0,15992644643096,15995366870386,15995367731030,15992645758081
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,142876,142876,4194304,256,0,0,8,24,326464,0x7f9c4bd80500,0x7f9c48e26780,21296872,21177916,274521477,65536,2126518197,1960,56,0,2662108,2662108,0,0,2016,0,60489728,60484768,112,4848,1003467,0,0,131072,129336,56,1680,65536,65536,0,15992645769411,15995367798070,15995369496317,15992647725808
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,142876,142876,4194304,256,0,0,8,24,329216,0x7f9c4bd80380,0x7f9c48e267c0,21367752,21224857,275039006,65536,2128297688,2408,56,0,2670968,2670968,0,0,2464,0,77266944,77256988,56,9900,999806,0,0,131072,129336,56,1680,65536,65536,0,15992647744637,15995369590237,15995371255684,15992649662134
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,142876,142876,4194304,256,0,0,12,24,331968,0x7f9c4bd80200,0x7f9c48e26800,21354672,21233424,275210899,65536,2131485842,2464,56,0,2669333,2669333,0,0,2520,0,77398016,77389972,113,7931,1008615,0,0,131072,129336,56,1680,0,131072,0,15992649673214,15995371354724,15995373081131,15992651652210
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,142876,142876,4194304,256,0,0,12,24,334720,0x7f9c4bd80080,0x7f9c48e26840,21354104,21226510,275041256,65536,2124013206,2408,56,0,2669262,2669262,0,0,2464,0,76218368,76209423,112,8833,435770,0,0,65536,63800,56,1680,0,0,65536,15992651663970,15995373218252,15995374934259,15992653636876
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,142876,142876,4194304,256,0,0,8,24,337472,0x7f9c49721f00,0x7f9c48e26880,21372920,21257975,275461987,65536,2135121626,2464,56,0,2671614,2671614,0,0,2520,0,77332480,77323622,56,8802,1016523,0,0,131072,129336,56,1680,65536,65536,0,15992653648706,15995375025939,15995376700026,15992655579913
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,142876,142876,4194304,256,0,0,8,24,0,0x7f9c49721d80,0x7f9c48e268c0,42056296,41922880,543368872,65536,4224358552,1960,56,0,5257036,5257036,0,0,2016,0,120258560,120253321,112,5127,1004246,0,0,131072,129336,56,1680,65536,65536,0,15992655590882,15995376793466,15995380151560,15992659215852