Files
rocm-systems/tests/workloads/TD/mi200/pmc_perf.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

169 lines
55 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_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,GRBM_COUNT,GRBM_GUI_ACTIVE,TD_TD_BUSY_sum,TD_TC_STALL_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,TD_COALESCABLE_WAVEFRONT_sum,DispatchNs,BeginNs,EndNs,CompleteNs
0,__amd_rocclr_fillBufferAligned.kd,0,0,0,148935,148935,33554432,256,0,0,4,32,4160,0x0,0x7fe74a404280,3060592,2972533,38620036,524288,240875275,382573,382573,37840900.0,37281003.0,7661.0,524288.0,0.0,524288.0,0.0,16149794842349,16152833487509,16152833727350,16149943687783
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,148935,148935,32768,256,0,0,12,24,13888,0x0,0x7fe74a423f80,263752,161641,1390824,512,1728708,32968,32968,178468.0,159696.0,0.0,4096.0,0.0,0.0,4096.0,16149949158912,16152838526258,16152838539378,16149949350468
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,148935,148935,4194304,256,0,0,12,24,14336,0x7fe74d4cf380,0x7fe74a423fc0,1567456,1438041,18621854,65536,104017641,195931,195931,13732372.0,11593614.0,2600.0,524288.0,0.0,0.0,524288.0,16149949640741,16152838607859,16152838700339,16149949912285
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,148935,148935,4194304,256,0,0,16,24,15040,0x7fe74d4cf200,0x7fe74a424000,2506760,2379848,30798118,65536,215467337,313344,313344,29244072.0,20851862.0,1968.0,524288.0,0.0,0.0,0.0,16149950207079,16152838733299,16152838912180,16149950572251
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,148935,148935,4194304,256,0,0,16,24,15488,0x7fe74d4cf080,0x7fe74a424040,2530224,2400602,31098348,65536,216398876,316277,316277,29335678.0,20943408.0,2280.0,524288.0,0.0,0.0,0.0,16149950860334,16152838937461,16152839117622,16149951223766
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,148935,148935,4194304,256,0,0,12,24,15936,0x7fe74ae2ff00,0x7fe74a424080,1397224,1271352,16390759,65536,84347518,174652,174652,13895714.0,11753415.0,2144.0,524288.0,0.0,0.0,524288.0,16149951511880,16152839142422,16152839236182,16149951788164
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,148935,148935,4194304,256,0,0,12,24,16384,0x7fe74ae2fd80,0x7fe74a4240c0,1390168,1260920,16265011,65536,88797724,173770,173770,13901602.0,11763121.0,2287.0,524288.0,0.0,0.0,524288.0,16149952075857,16152839261943,16152839354423,16149952350181
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,148935,148935,4194304,256,0,0,12,24,17088,0x7fe74ae2fc00,0x7fe74a424100,1301320,1198951,15520248,65536,103928920,162664,162664,14415034.0,12277640.0,2111.0,524288.0,0.0,0.0,524288.0,16149952649125,16152839393463,16152839485144,16149952951928
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,148935,148935,4194304,256,0,0,16,24,17792,0x7fe74ae2fa80,0x7fe74a424140,2471472,2369393,30701420,65536,227881913,308933,308933,29508532.0,21117378.0,1995.0,524288.0,0.0,0.0,0.0,16149953239152,16152839521144,16152839701145,16149953638763
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,148935,148935,4194304,256,0,0,16,24,18496,0x7fe74ae2f900,0x7fe74a424180,2465408,2358579,30553344,65536,218401891,308175,308175,29293340.0,20902185.0,2352.0,524288.0,0.0,0.0,0.0,16149953924446,16152839734745,16152839914427,16149954331937
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,148935,148935,4194304,256,0,0,16,24,19200,0x7fe74ae2f780,0x7fe74a4241c0,1314328,1211316,15685269,65536,100533145,164290,164290,14483040.0,12345958.0,2142.0,524288.0,0.0,0.0,524288.0,16149954618181,16152839952187,16152840045307,16149954918984
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,148935,148935,4194304,256,0,0,16,24,19904,0x7fe74ae2f600,0x7fe74a424200,1317864,1212744,15686029,65536,92508528,164732,164732,14485940.0,12347892.0,2089.0,524288.0,0.0,0.0,524288.0,16149955205358,16152840070907,16152840164348,16149955505411
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,148935,148935,4194304,256,0,0,12,24,20608,0x7fe74d4cf480,0x7fe74a424240,1315816,1203371,15578196,65536,100673826,164476,164476,14376612.0,12240156.0,2161.0,524288.0,0.0,0.0,524288.0,16149955800765,16152840196188,16152840289149,16149956140567
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,148935,148935,4194304,256,0,0,16,24,21312,0x7fe74d4cf300,0x7fe74a424280,2470208,2360626,30592051,65536,225105776,308775,308775,29372832.0,20981676.0,1971.0,524288.0,0.0,0.0,0.0,16149956426341,16152840318269,16152840497950,16149956859021
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,148935,148935,4194304,256,0,0,16,24,22016,0x7fe74d4cf180,0x7fe74a4242c0,2482608,2378875,30779555,65536,223634749,310325,310325,29579132.0,21187979.0,2222.0,524288.0,0.0,0.0,0.0,16149957144905,16152840529150,16152840708831,16149957595425
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,148935,148935,4194304,256,0,0,16,24,22720,0x7fe74d4cf000,0x7fe74a424300,1312520,1210486,15662791,65536,94005776,164064,164064,14452510.0,12314778.0,2254.0,524288.0,0.0,0.0,524288.0,16149957881779,16152840734431,16152840827872,16149958225081
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,148935,148935,4194304,256,0,0,12,24,23424,0x7fe74ae2fe80,0x7fe74a424340,1308304,1201466,15551372,65536,101361863,163537,163537,14358296.0,12223277.0,2167.0,524288.0,0.0,0.0,524288.0,16149958511875,16152840859232,16152840952833,16149958856797
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,148935,148935,4194304,256,0,0,12,24,24128,0x7fe74ae2fd00,0x7fe74a424380,1297952,1192296,15443427,65536,104290672,162243,162243,14271456.0,12131631.0,2249.0,524288.0,0.0,0.0,524288.0,16149959149021,16152840985473,16152841078434,16149959477563
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,148935,148935,4194304,256,0,0,16,24,24832,0x7fe74ae2fb80,0x7fe74a4243c0,2464496,2359357,30559101,65536,229112628,308061,308061,29332584.0,20941448.0,1973.0,524288.0,0.0,0.0,0.0,16149959764887,16152841104354,16152841284035,16149960188258
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,148935,148935,4194304,256,0,0,16,24,25536,0x7fe74ae2fa00,0x7fe74a424400,2453216,2345901,30380077,65536,213152662,306651,306651,29287176.0,20896022.0,2310.0,524288.0,0.0,0.0,0.0,16149960476121,16152841309635,16152841490756,16149960905262
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,148935,148935,4194304,256,0,0,12,24,26240,0x7fe74ae2f880,0x7fe74a424440,1311520,1203677,15583576,65536,98521283,163939,163939,14324720.0,12187759.0,2162.0,524288.0,0.0,0.0,524288.0,16149961190995,16152841524676,16152841618437,16149961527028
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,148935,148935,4194304,256,0,0,12,24,26944,0x7fe74ae2f700,0x7fe74a424480,1313888,1201403,15542966,65536,104807274,164235,164235,14350392.0,12212542.0,2113.0,524288.0,0.0,0.0,524288.0,16149961815031,16152841652677,16152841746438,16149962114825
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,148935,148935,4194304,256,0,0,12,24,27648,0x7fe74d4cf580,0x7fe74a4244c0,1301968,1199623,15523389,65536,106172191,162745,162745,14367028.0,12228824.0,2133.0,524288.0,0.0,0.0,524288.0,16149962410268,16152841780518,16152841872678,16149962709302
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,148935,148935,4194304,256,0,0,16,24,28608,0x7fe74d4cf400,0x7fe74a424500,2477064,2368538,30661155,65536,231107473,309632,309632,29457556.0,21066391.0,1969.0,524288.0,0.0,0.0,0.0,16149962996275,16152841899559,16152842079720,16149963386637
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,148935,148935,4194304,256,0,0,16,24,29312,0x7fe74d4cf280,0x7fe74a424540,2467744,2353647,30479671,65536,217377496,308467,308467,29296240.0,20905077.0,2189.0,524288.0,0.0,0.0,0.0,16149963673531,16152842139400,16152842318761,16149964056842
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,148935,148935,4194304,256,0,0,12,24,30016,0x7fe74d4cf100,0x7fe74a424580,1296432,1192079,15426186,65536,102117310,162053,162053,14306780.0,12170192.0,2139.0,524288.0,0.0,0.0,524288.0,16149964343936,16152842346921,16152842438922,16149964646349
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,148935,148935,4194304,256,0,0,8,24,30976,0x7fe74ae2ff80,0x7fe74a4245c0,1300912,1192877,15421676,65536,91558785,162613,162613,14282492.0,12145308.0,2159.0,524288.0,0.0,0.0,524288.0,16149964933413,16152842464202,16152842556363,16149965229316
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,148935,148935,4194304,256,0,0,12,24,31680,0x7fe74ae2fe00,0x7fe74a424600,1296296,1191362,15422246,65536,102887801,162036,162036,14236664.0,12098132.0,2207.0,524288.0,0.0,0.0,524288.0,16149965523300,16152842589163,16152842682443,16149965835993
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,148935,148935,4194304,256,0,0,16,24,32640,0x7fe74ae2fc80,0x7fe74a424640,2447176,2338542,30306873,65536,222108803,305896,305896,29220260.0,20829116.0,2003.0,524288.0,0.0,0.0,0.0,16149966123157,16152842709323,16152842889805,16149966518788
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,148935,148935,4194304,256,0,0,12,24,33600,0x7fe74ae2fb00,0x7fe74a424680,2478096,2372092,30704192,65536,225095106,309761,309761,29557704.0,21166536.0,2210.0,524288.0,0.0,0.0,0.0,16149966805521,16152842913165,16152843093646,16149967195213
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,148935,148935,4194304,256,0,0,12,24,34560,0x7fe74ae2f980,0x7fe74a4246c0,1300848,1197088,15488540,65536,108394074,162605,162605,14294520.0,12156323.0,2059.0,524288.0,0.0,0.0,524288.0,16149967481996,16152843117486,16152843210767,16149967780520
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,148935,148935,4194304,256,0,0,8,24,35520,0x7fe74ae2f800,0x7fe74a424700,1311728,1203481,15542346,65536,87807705,163965,163965,14337330.0,12201678.0,2168.0,524288.0,0.0,0.0,524288.0,16149968067193,16152843235087,16152843329167,16149968364537
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,148935,148935,4194304,256,0,0,12,24,36224,0x7fe74ae2f680,0x7fe74a424740,1304400,1198426,15512163,65536,87206526,163049,163049,14326448.0,12192341.0,2198.0,524288.0,0.0,0.0,524288.0,16149968658390,16152843361327,16152843453968,16149968958394
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,148935,148935,4194304,256,0,0,12,24,37184,0x7fe74d4cf500,0x7fe74a424780,2442200,2333408,30203349,65536,225184057,305274,305274,29095716.0,20704560.0,2027.0,524288.0,0.0,0.0,0.0,16149969245317,16152843477168,16152843657169,16149969667478
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,148935,148935,4194304,256,0,0,12,24,38144,0x7fe74d4cf380,0x7fe74a4247c0,2441840,2330773,30187493,65536,203616711,305229,305229,29006452.0,20615277.0,2228.0,524288.0,0.0,0.0,0.0,16149969953842,16152843682129,16152843863730,16149970350023
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,148935,148935,4194304,256,0,0,12,24,39104,0x7fe74d4cf200,0x7fe74a424800,1304352,1200041,15522705,65536,98382332,163043,163043,14301130.0,12165032.0,2097.0,524288.0,0.0,0.0,524288.0,16149970638356,16152843887891,16152843982131,16149970944160
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,148935,148935,4194304,256,0,0,8,24,40320,0x7fe74d4cf080,0x7fe74a424840,1318040,1208516,15581549,65536,89903294,164754,164754,14143944.0,12004004.0,2239.0,524288.0,0.0,0.0,524288.0,16149971230633,16152844005811,16152844100372,16149971571836
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,148935,148935,4194304,256,0,0,12,24,41280,0x7fe74ae2ff00,0x7fe74a424880,1311336,1207447,15623514,65536,104150745,163916,163916,14286500.0,12148741.0,2162.0,524288.0,0.0,0.0,524288.0,16149971864419,16152844133172,16152844226293,16149972195652
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,148935,148935,4194304,256,0,0,12,24,42240,0x7fe74ae2fd80,0x7fe74a4248c0,2446720,2339964,30290088,65536,224783477,305839,305839,29104556.0,20713394.0,2176.0,524288.0,0.0,0.0,0.0,16149972481286,16152844252373,16152844431574,16149972913106
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,148935,148935,4194304,256,0,0,12,24,43200,0x7fe74ae2fc00,0x7fe74a424900,2444256,2334954,30235199,65536,220859283,305531,305531,29148832.0,20757664.0,2108.0,524288.0,0.0,0.0,0.0,16149973198960,16152844457174,16152844637815,16149973624250
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,148935,148935,4194304,256,0,0,8,24,44160,0x7fe74ae2fa80,0x7fe74a424940,1304680,1198952,15498517,65536,98105788,163084,163084,14294624.0,12158928.0,2134.0,524288.0,0.0,0.0,524288.0,16149973910364,16152844662775,16152844756536,16149974260176
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,148935,148935,4194304,256,0,0,12,24,45376,0x7fe74ae2f900,0x7fe74a424980,1319144,1204026,15502591,65536,92713885,164892,164892,14281512.0,12144572.0,2144.0,524288.0,0.0,0.0,524288.0,16149974546590,16152844781016,16152844875417,16149974862013
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,148935,148935,4194304,256,0,0,12,24,46336,0x7fe74ae2f780,0x7fe74a4249c0,1306152,1197459,15483887,65536,90135789,163268,163268,14211052.0,12073771.0,2122.0,524288.0,0.0,0.0,524288.0,16149975154166,16152844907577,16152845001977,16149975491489
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,148935,148935,4194304,256,0,0,12,24,47552,0x7fe74ae2f600,0x7fe74a424a00,2455960,2341234,30313426,65536,218469938,306994,306994,29014604.0,20623431.0,1906.0,524288.0,0.0,0.0,0.0,16149975777723,16152845026778,16152845205179,16149976208183
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,148935,148935,4194304,256,0,0,12,24,48512,0x7fe74d4cf480,0x7fe74a424a40,2415376,2299322,29793586,65536,216896403,301921,301921,28629972.0,20238819.0,2205.0,524288.0,0.0,0.0,0.0,16149976494947,16152845229659,16152845409500,16149976923357
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,148935,148935,4194304,256,0,0,8,24,49472,0x7fe74d4cf300,0x7fe74a424a80,1300688,1195231,15427742,65536,94612257,162585,162585,14297660.0,12160709.0,2108.0,524288.0,0.0,0.0,524288.0,16149977209561,16152845434300,16152845527101,16149977544173
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,148935,148935,4194304,256,0,0,12,24,50688,0x7fe74d4cf180,0x7fe74a424ac0,1300336,1188209,15325350,65536,96875824,162541,162541,14171826.0,12032707.0,2300.0,524288.0,0.0,0.0,524288.0,16149977830967,16152845551901,16152845645341,16149978169439
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,148935,148935,4194304,256,0,0,12,24,51648,0x7fe74d4cf000,0x7fe74a424b00,1289768,1186126,15340806,65536,99482377,161220,161220,14252608.0,12114977.0,2198.0,524288.0,0.0,0.0,524288.0,16149978462513,16152845678302,16152845769822,16149978797016
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,148935,148935,4194304,256,0,0,12,24,52864,0x7fe74ae2fe80,0x7fe74a424b40,2441312,2335378,30213479,65536,224334460,305163,305163,29010552.0,20619399.0,2025.0,524288.0,0.0,0.0,0.0,16149979083509,16152845796862,16152845975583,16149979514500
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,148935,148935,4194304,256,0,0,12,24,54080,0x7fe74ae2fd00,0x7fe74a424b80,2414576,2308143,29917902,65536,219085457,301821,301821,28754388.0,20363262.0,2149.0,524288.0,0.0,0.0,0.0,16149979800453,16152845999903,16152846179265,16149980230374
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,148935,148935,4194304,256,0,0,8,24,55296,0x7fe74ae2fb80,0x7fe74a424bc0,1300232,1191798,15375441,65536,96753564,162528,162528,14158630.0,12019447.0,2007.0,524288.0,0.0,0.0,524288.0,16149980515877,16152846202785,16152846296385,16149980818221
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,148935,148935,4194304,256,0,0,12,24,56768,0x7fe74ae2fa00,0x7fe74a424c00,1307776,1202978,15516593,65536,97994624,163471,163471,14141650.0,11993802.0,2301.0,524288.0,0.0,0.0,524288.0,16149981104484,16152846320225,16152846415906,16149981412778
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,148935,148935,4194304,256,0,0,12,24,57728,0x7fe74ae2f880,0x7fe74a424c40,1294968,1189137,15369842,65536,93261475,161870,161870,14178352.0,12041195.0,2098.0,524288.0,0.0,0.0,524288.0,16149981706101,16152846448386,16152846541667,16149982039024
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,148935,148935,4194304,256,0,0,12,24,58944,0x7fe74ae2f700,0x7fe74a424c80,2427264,2321638,30076667,65536,223199937,303407,303407,28964244.0,20573079.0,1934.0,524288.0,0.0,0.0,0.0,16149982325697,16152846564867,16152846742948,16149982725138
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,148935,148935,4194304,256,0,0,12,24,60160,0x7fe74d4cf580,0x7fe74a424cc0,2413552,2306209,29886541,65536,214468368,301693,301693,28604960.0,20213816.0,1948.0,524288.0,0.0,0.0,0.0,16149983011482,16152846767428,16152846947269,16149983409993
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,148935,148935,4194304,256,0,0,8,24,61376,0x7fe74d4cf400,0x7fe74a424d00,1302696,1198554,15456278,65536,92842864,162836,162836,14203124.0,12065181.0,2161.0,524288.0,0.0,0.0,524288.0,16149983696227,16152846971109,16152847065990,16149984041149
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,148935,148935,4194304,256,0,0,12,24,62848,0x7fe74d4cf280,0x7fe74a424d40,1340584,1238129,15955552,65536,104202383,167572,167572,14303048.0,12132438.0,2432.0,524288.0,0.0,0.0,524288.0,16149984327743,16152847091590,16152847190791,16149984676975
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,148935,148935,4194304,256,0,0,12,24,63808,0x7fe74d4cf100,0x7fe74a424d80,1297768,1195392,15453422,65536,100008013,162220,162220,14189128.0,12051490.0,2190.0,524288.0,0.0,0.0,524288.0,16149984970479,16152847224231,16152847317511,16149985306781
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,148935,148935,4194304,256,0,0,12,24,65024,0x7fe74ae2ff80,0x7fe74a424dc0,2408208,2298255,29758294,65536,219778786,301025,301025,28619052.0,20227872.0,2134.0,524288.0,0.0,0.0,0.0,16149985591845,16152847343272,16152847522793,16149986020175
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,148935,148935,4194304,256,0,0,12,24,66240,0x7fe74ae2fe00,0x7fe74a424e00,2403752,2293431,29709926,65536,214848879,300468,300468,28620616.0,20229450.0,2156.0,524288.0,0.0,0.0,0.0,16149986307649,16152847547753,16152847728874,16149986744599
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,148935,148935,4194304,256,0,0,8,24,67456,0x7fe74ae2fc80,0x7fe74a424e40,1311120,1205386,15549589,65536,92010656,163889,163889,14196998.0,12059330.0,2168.0,524288.0,0.0,0.0,524288.0,16149987030973,16152847752234,16152847847275,16149987377666
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,148935,148935,4194304,256,0,0,12,24,68928,0x7fe74ae2fb00,0x7fe74a424e80,1408960,1299501,16782144,65536,106930229,176119,176119,14657990.0,12460408.0,2369.0,524288.0,0.0,0.0,524288.0,16149987664229,16152847871755,16152847976555,16149988021691
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,148935,148935,4194304,256,0,0,12,24,70144,0x7fe74ae2f980,0x7fe74a424ec0,1288232,1183651,15276702,65536,97658584,161028,161028,14177502.0,12041442.0,2124.0,524288.0,0.0,0.0,524288.0,16149988314495,16152848009516,16152848102476,16149988647708
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,148935,148935,4194304,256,0,0,12,24,71616,0x7fe74ae2f800,0x7fe74a424f00,2435872,2329344,30157297,65536,221518793,304483,304483,28881620.0,20490458.0,2222.0,524288.0,0.0,0.0,0.0,16149988933901,16152848127436,16152848307437,16149989372712
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,148935,148935,4194304,256,0,0,12,24,72832,0x7fe74ae2f680,0x7fe74a424f40,2435816,2329967,30182705,65536,223722997,304476,304476,28879228.0,20488081.0,2174.0,524288.0,0.0,0.0,0.0,16149989658445,16152848333838,16152848513039,16149990086116
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,148935,148935,4194304,256,0,0,8,24,74048,0x7fe74d4cf500,0x7fe74a424f80,1294912,1188746,15325586,65536,93110356,161863,161863,14207266.0,12067861.0,2253.0,524288.0,0.0,0.0,524288.0,16149990374610,16152848537039,16152848630639,16149990683353
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,148935,148935,4194304,256,0,0,12,24,75776,0x7fe74d4cf380,0x7fe74a424fc0,1459144,1349814,17417885,65536,109161010,182392,182392,15021010.0,12800740.0,2246.0,524288.0,0.0,0.0,524288.0,16149990970346,16152848654960,16152848762000,16149991338088
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,148935,148935,4194304,256,0,0,12,24,76992,0x7fe74d4cf200,0x7fe74a425000,1294920,1188927,15346684,65536,88512306,161864,161864,14142256.0,12004697.0,2076.0,524288.0,0.0,0.0,524288.0,16149991640231,16152848794800,16152848888881,16149991982274
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,148935,148935,4194304,256,0,0,12,24,78464,0x7fe74d4cf080,0x7fe74a425040,2416400,2305940,29822372,65536,215757421,302049,302049,28579636.0,20188474.0,2145.0,524288.0,0.0,0.0,0.0,16149992268688,16152848914321,16152849094962,16149992668689
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,148935,148935,4194304,256,0,0,12,24,79936,0x7fe74ae2ff00,0x7fe74a425080,2428352,2321723,30061867,65536,222896304,303543,303543,28863280.0,20472120.0,2119.0,524288.0,0.0,0.0,0.0,16149992954792,16152849120722,16152849300563,16149993392313
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,148935,148935,4194304,256,0,0,8,24,81408,0x7fe74ae2fd80,0x7fe74a4250c0,1299808,1189143,15321108,65536,88888404,162475,162475,14096502.0,11957897.0,2191.0,524288.0,0.0,0.0,524288.0,16149993677586,16152849324724,16152849419444,16149994022399
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,148935,148935,4194304,256,0,0,12,24,83136,0x7fe74ae2fc00,0x7fe74a425100,1529912,1421451,18311355,65536,123393492,191238,191238,14869336.0,12605325.0,2158.0,524288.0,0.0,0.0,524288.0,16149994308982,16152849443124,16152849558325,16149994629435
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,148935,148935,4194304,256,0,0,12,24,84352,0x7fe74ae2fa80,0x7fe74a425140,1297584,1189787,15360232,65536,87780043,162197,162197,14094340.0,11957551.0,2145.0,524288.0,0.0,0.0,524288.0,16149994922099,16152849604405,16152849697846,16149995262641
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,148935,148935,4194304,256,0,0,12,24,85824,0x7fe74ae2f900,0x7fe74a425180,2427408,2317292,30005693,65536,223845452,303425,303425,28755044.0,20363881.0,2299.0,524288.0,0.0,0.0,0.0,16149995548695,16152849722006,16152849902007,16149995936376
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,148935,148935,4194304,256,0,0,12,24,87296,0x7fe74ae2f780,0x7fe74a4251c0,2412088,2301272,29796627,65536,220140652,301510,301510,28608048.0,20216904.0,2187.0,524288.0,0.0,0.0,0.0,16149996222270,16152849927127,16152850108248,16149996664790
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,148935,148935,4194304,256,0,0,12,24,88768,0x7fe74ae2f600,0x7fe74a425200,1300680,1190130,15338642,65536,93462388,162584,162584,14096998.0,11956551.0,2257.0,524288.0,0.0,0.0,524288.0,16149996951384,16152850133529,16152850229049,16149997310486
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,148935,148935,4194304,256,0,0,12,24,90752,0x7fe74d4cf480,0x7fe74a425240,1619704,1498189,19311483,65536,134706000,202462,202462,15223144.0,12942101.0,1983.0,524288.0,0.0,0.0,524288.0,16149997597119,16152850254649,16152850374970,16149997966871
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,148935,148935,4194304,256,0,0,12,24,91968,0x7fe74d4cf300,0x7fe74a425280,1299224,1187735,15317554,65536,88069570,162402,162402,14091700.0,11954173.0,2246.0,524288.0,0.0,0.0,524288.0,16149998259775,16152850412250,16152850506011,16149998604077
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,148935,148935,4194304,256,0,0,12,24,93440,0x7fe74d4cf180,0x7fe74a4252c0,2418568,2310885,29918967,65536,220194692,302320,302320,28672792.0,20281634.0,2136.0,524288.0,0.0,0.0,0.0,16149998890591,16152850530971,16152850710652,16149999274932
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,148935,148935,4194304,256,0,0,12,24,94912,0x7fe74d4cf000,0x7fe74a425300,2381856,2276419,29502863,65536,204655483,297731,297731,28290128.0,19898960.0,2008.0,524288.0,0.0,0.0,0.0,16149999563926,16152850734332,16152850915773,16149999998636
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,148935,148935,4194304,256,0,0,12,24,96384,0x7fe74ae2fe80,0x7fe74a425340,1298824,1194609,15412328,65536,96473838,162352,162352,14145432.0,12005146.0,2218.0,524288.0,0.0,0.0,524288.0,16150000284440,16152850939133,16152851034654,16150000633332
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,148935,148935,4194304,256,0,0,12,24,98368,0x7fe74ae2fd00,0x7fe74a425380,1681952,1568465,20244341,65536,129255076,210243,210243,15483946.0,13162642.0,1911.0,524288.0,0.0,0.0,524288.0,16150000918716,16152851059454,16152851185695,16150001305117
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,148935,148935,4194304,256,0,0,12,24,99584,0x7fe74ae2fb80,0x7fe74a4253c0,1291704,1187531,15312831,65536,86421458,161462,161462,14081070.0,11941621.0,2226.0,524288.0,0.0,0.0,524288.0,16150001597121,16152851219135,16152851313536,16150001931683
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,148935,148935,4194304,256,0,0,12,24,101312,0x7fe74ae2fa00,0x7fe74a425400,2410432,2297874,29740893,65536,220326378,301303,301303,28593244.0,20202073.0,2198.0,524288.0,0.0,0.0,0.0,16150002221197,16152851338016,16152851517057,16150002610978
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,148935,148935,4194304,256,0,0,12,24,102784,0x7fe74ae2f880,0x7fe74a425440,2403520,2290916,29658530,65536,206919935,300439,300439,28407136.0,20015973.0,2081.0,524288.0,0.0,0.0,0.0,16150002896852,16152851539617,16152851718338,16150003331362
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,148935,148935,4194304,256,0,0,12,24,104256,0x7fe74ae2f700,0x7fe74a425480,1293552,1188596,15328944,65536,96294250,161693,161693,14142184.0,12004506.0,2343.0,524288.0,0.0,0.0,524288.0,16150003617576,16152851743778,16152851837699,16150003965508
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,148935,148935,4194304,256,0,0,12,24,106240,0x7fe74d4cf580,0x7fe74a4254c0,1754752,1642139,21169537,65536,141071638,219343,219343,15817144.0,13482755.0,1752.0,524288.0,0.0,0.0,524288.0,16150004251882,16152851862499,16152851992900,16150004635933
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,148935,148935,4194304,256,0,0,12,24,107712,0x7fe74d4cf400,0x7fe74a425500,1297728,1187576,15315546,65536,89807209,162215,162215,14154588.0,12018279.0,2241.0,524288.0,0.0,0.0,524288.0,16150004928857,16152852026180,16152852119141,16150005262739
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,148935,148935,4194304,256,0,0,16,24,109440,0x7fe74d4cf280,0x7fe74a425540,2368912,2264081,29334057,65536,210480267,296113,296113,28099496.0,19708327.0,2179.0,524288.0,0.0,0.0,0.0,16150005549513,16152852143941,16152852323622,16150005982963
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,148935,148935,4194304,256,0,0,16,24,111168,0x7fe74d4cf100,0x7fe74a425580,2382456,2276345,29499946,65536,211184834,297806,297806,28294268.0,19903107.0,2094.0,524288.0,0.0,0.0,0.0,16150006271367,16152852348742,16152852528423,16150006660049
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,148935,148935,4194304,256,0,0,8,24,112896,0x7fe74ae2ff80,0x7fe74a4255c0,1320552,1210417,15617219,65536,104600368,165068,165068,14283998.0,12144162.0,2356.0,524288.0,0.0,0.0,524288.0,16150006946492,16152852553063,16152852648424,16150007296315
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,148935,148935,4194304,256,0,0,12,24,115136,0x7fe74ae2fe00,0x7fe74a425600,1850128,1730979,22355012,65536,129879799,231265,231265,15520574.0,13147027.0,1569.0,524288.0,0.0,0.0,524288.0,16150007582508,16152852673544,16152852812905,16150007976360
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,148935,148935,4194304,256,0,0,12,24,116608,0x7fe74ae2fc80,0x7fe74a425640,1291208,1184420,15265666,65536,100244665,161400,161400,13996398.0,11858099.0,2286.0,524288.0,0.0,0.0,524288.0,16150008268953,16152852844745,16152852939146,16150008606076
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,148935,148935,4194304,256,0,0,16,24,118336,0x7fe74ae2fb00,0x7fe74a425680,2376024,2268897,29389474,65536,210462537,297002,297002,28166872.0,19775722.0,2274.0,524288.0,0.0,0.0,0.0,16150008892019,16152852963146,16152853142027,16150009322580
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,148935,148935,4194304,256,0,0,16,24,120064,0x7fe74ae2f980,0x7fe74a4256c0,2407184,2293489,29690944,65536,213506567,300897,300897,28483800.0,20092652.0,2066.0,524288.0,0.0,0.0,0.0,16150009608064,16152853166507,16152853346348,16150010036694
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,148935,148935,4194304,256,0,0,12,24,121792,0x7fe74ae2f800,0x7fe74a425700,1312808,1203291,15522791,65536,104325955,164100,164100,14222694.0,12076760.0,2314.0,524288.0,0.0,0.0,524288.0,16150010324308,16152853370028,16152853468269,16150010627691
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,148935,148935,4194304,256,0,0,12,24,124032,0x7fe74ae2f680,0x7fe74a425740,1925632,1807124,23332426,65536,144905205,240703,240703,15792110.0,13395720.0,1571.0,524288.0,0.0,0.0,524288.0,16150010914175,16152853492909,16152853638510,16150011262617
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,148935,148935,4194304,256,0,0,12,24,125504,0x7fe74d4cf500,0x7fe74a425780,1288624,1184232,15254647,65536,95272002,161077,161077,13995762.0,11855064.0,2223.0,524288.0,0.0,0.0,524288.0,16150011555621,16152853671310,16152853765711,16150011896783
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,148935,148935,4194304,256,0,0,12,24,127488,0x7fe74d4cf380,0x7fe74a4257c0,2377592,2268679,29354718,65536,209053550,297198,297198,28111656.0,19720305.0,2073.0,524288.0,0.0,0.0,0.0,16150012183887,16152853790991,16152853971952,16150012624207
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,148935,148935,4194304,256,0,0,12,24,129216,0x7fe74d4cf200,0x7fe74a425800,2374928,2269659,29375800,65536,200701740,296865,296865,28154516.0,19763283.0,2054.0,524288.0,0.0,0.0,0.0,16150012910640,16152853996432,16152854176593,16150013340421
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,148935,148935,4194304,256,0,0,12,24,130944,0x7fe74d4cf080,0x7fe74a425840,1355920,1248950,16126166,65536,104509645,169489,169489,14752126.0,12591892.0,2441.0,524288.0,0.0,0.0,524288.0,16150013626405,16152854200913,16152854300914,16150013975257
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,148935,148935,4194304,256,0,0,12,24,133440,0x7fe74ae2ff00,0x7fe74a425880,2077520,1963144,25346998,65536,176815089,259689,259689,15153350.0,12736110.0,1622.0,524288.0,0.0,0.0,524288.0,16150014261591,16152854326354,16152854481715,16150014675841
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,148935,148935,4194304,256,0,0,12,24,134912,0x7fe74ae2fd80,0x7fe74a4258c0,1291936,1187170,15302074,65536,99285790,161491,161491,14037418.0,11896047.0,2298.0,524288.0,0.0,0.0,524288.0,16150014968865,16152854515155,16152854610036,16150015306107
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,148935,148935,4194304,256,0,0,12,24,136896,0x7fe74ae2fc00,0x7fe74a425900,2373688,2267684,29341221,65536,207840763,296710,296710,28179144.0,19787471.0,2240.0,524288.0,0.0,0.0,0.0,16150015592071,16152854634996,16152854813557,16150016025031
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,148935,148935,4194304,256,0,0,12,24,138880,0x7fe74ae2fa80,0x7fe74a425940,2364416,2259616,29244828,65536,208086535,295551,295551,28011088.0,19619934.0,2249.0,524288.0,0.0,0.0,0.0,16150016311355,16152854838197,16152855018358,16150016744575
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,148935,148935,4194304,256,0,0,12,24,140864,0x7fe74ae2f900,0x7fe74a425980,1430880,1322125,17057622,65536,109796937,178859,178859,15460446.0,13290897.0,2413.0,524288.0,0.0,0.0,524288.0,16150017030969,16152855040598,16152855147959,16150017383501
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,148935,148935,4194304,256,0,0,12,24,143616,0x7fe74ae2f780,0x7fe74a4259c0,2229424,2124144,27448471,65536,196965938,278677,278677,15117178.0,12685442.0,1249.0,524288.0,0.0,0.0,524288.0,16150017668455,16152855170519,16152855341400,16150018082076
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,148935,148935,4194304,256,0,0,12,24,145344,0x7fe74ae2f600,0x7fe74a425a00,1290224,1183715,15264882,65536,97492518,161277,161277,13988306.0,11840752.0,2408.0,524288.0,0.0,0.0,524288.0,16150018375009,16152855374520,16152855469881,16150018717742
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,148935,148935,4194304,256,0,0,12,24,147584,0x7fe74d4cf480,0x7fe74a425a40,2357752,2252617,29130652,65536,203475871,294718,294718,27842938.0,19451328.0,2353.0,524288.0,0.0,0.0,0.0,16150019004185,16152855495161,16152855675322,16150019441616
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,148935,148935,4194304,256,0,0,12,24,149568,0x7fe74d4cf300,0x7fe74a425a80,2371744,2258841,29238271,65536,204194512,296467,296467,27988206.0,19596980.0,2184.0,524288.0,0.0,0.0,0.0,16150019727539,16152855699162,16152855882523,16150020153630
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,148935,148935,4194304,256,0,0,12,24,151552,0x7fe74d4cf180,0x7fe74a425ac0,1489296,1381859,17825222,65536,117727227,186161,186161,16371758.0,14196866.0,2359.0,524288.0,0.0,0.0,524288.0,16150020441464,16152855906204,16152856017084,16150020762966
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,148935,148935,4194304,256,0,0,12,24,154304,0x7fe74d4cf000,0x7fe74a425b00,2395088,2279677,29457715,65536,210032889,299385,299385,15155304.0,12719562.0,1330.0,524288.0,0.0,0.0,524288.0,16150021049600,16152856040444,16152856221085,16150021483740
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,148935,148935,4194304,256,0,0,12,24,156288,0x7fe74ae2fe80,0x7fe74a425b40,1368624,1258214,16215144,65536,102655384,171077,171077,14644064.0,12468060.0,2433.0,524288.0,0.0,0.0,524288.0,16150021777784,16152856254046,16152856354526,16150022118996
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,148935,148935,4194304,256,0,0,12,24,158784,0x7fe74ae2fd00,0x7fe74a425b80,2390528,2273437,29332261,65536,184519857,298815,298815,27992934.0,19599282.0,2434.0,524288.0,0.0,0.0,0.0,16150022407780,16152856380126,16152856565088,16150022811221
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,148935,148935,4194304,256,0,0,12,24,161024,0x7fe74ae2fb80,0x7fe74a425bc0,2383960,2270552,29313611,65536,186445817,297994,297994,28009436.0,19616430.0,2236.0,524288.0,0.0,0.0,0.0,16150023097295,16152856589568,16152856773729,16150023532055
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,148935,148935,4194304,256,0,0,12,24,163264,0x7fe74ae2fa00,0x7fe74a425c00,1643872,1531854,19784449,65536,131555965,205483,205483,17872642.0,15673658.0,2122.0,524288.0,0.0,0.0,524288.0,16150023817889,16152856797089,16152856919330,16150024195640
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,148935,148935,4194304,256,0,0,12,24,166528,0x7fe74ae2f880,0x7fe74a425c40,2720544,2607346,33686793,65536,246736812,340067,340067,15461790.0,13030896.0,1052.0,524288.0,0.0,0.0,524288.0,16150024482184,16152856943010,16152857149571,16150024957413
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,148935,148935,4194304,256,0,0,12,24,168512,0x7fe74ae2f700,0x7fe74a425c80,1478368,1360346,17559367,65536,104684337,184795,184795,15726686.0,13517468.0,2205.0,524288.0,0.0,0.0,524288.0,16150025231247,16152857196931,16152857308772,16150025593659
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,148935,148935,4194304,256,0,0,12,24,171264,0x7fe74d4cf580,0x7fe74a425cc0,2366824,2253938,29057299,65536,195237421,295852,295852,27700026.0,19305078.0,2385.0,524288.0,0.0,0.0,0.0,16150025879693,16152857335012,16152857518053,16150026316403
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,148935,148935,4194304,256,0,0,12,24,173760,0x7fe74d4cf400,0x7fe74a425d00,2386384,2266963,29211052,65536,187922298,298297,298297,27864632.0,19471087.0,2260.0,524288.0,0.0,0.0,0.0,16150026602807,16152857542694,16152857728615,16150026999048
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,148935,148935,4194304,256,0,0,12,24,176256,0x7fe74d4cf280,0x7fe74a425d40,1795904,1684103,21763245,65536,150304438,224487,224487,19344110.0,17019062.0,2109.0,524288.0,0.0,0.0,524288.0,16150027285862,16152857753095,16152857887816,16150027665893
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,148935,148935,4194304,256,0,0,12,24,179776,0x7fe74d4cf100,0x7fe74a425d80,3038784,2927436,37860774,65536,281275938,379847,379847,15359248.0,12922712.0,1437.0,524288.0,0.0,0.0,524288.0,16150027952407,16152857911016,16152858143177,16150028463136
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,148935,148935,4194304,256,0,0,12,24,182272,0x7fe74ae2ff80,0x7fe74a425dc0,1686808,1572953,20305083,65536,133536953,210850,210850,17197372.0,14856365.0,1973.0,524288.0,0.0,0.0,524288.0,16150028738450,16152858215338,16152858342058,16150029103731
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,148935,148935,4194304,256,0,0,12,24,185536,0x7fe74ae2fe00,0x7fe74a425e00,2474872,2346751,30167687,65536,186850997,309358,309358,28111256.0,19676662.0,2276.0,524288.0,0.0,0.0,0.0,16150029389665,16152858366219,16152858557420,16150029800096
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,148935,148935,4194304,256,0,0,12,24,188544,0x7fe74ae2fc80,0x7fe74a425e40,2476080,2344653,30239056,65536,177856499,309509,309509,28515264.0,20099527.0,2240.0,524288.0,0.0,0.0,0.0,16150030069830,16152858583020,16152858778701,16150030537880
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,148935,148935,4194304,256,0,0,12,24,191552,0x7fe74ae2fb00,0x7fe74a425e80,2122096,2010881,26012607,65536,182317267,265261,265261,20018314.0,17543422.0,1322.0,524288.0,0.0,0.0,524288.0,16150030803564,16152858802701,16152858962862,16150031165726
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,148935,148935,4194304,256,0,0,12,24,195840,0x7fe74ae2f980,0x7fe74a425ec0,3689144,3576642,46265655,65536,339406850,461142,461142,16178464.0,13723077.0,947.0,524288.0,0.0,0.0,524288.0,16150031451510,16152858987182,16152859271184,16150031999578
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,148935,148935,4194304,256,0,0,12,24,198592,0x7fe74ae2f800,0x7fe74a425f00,1968632,1848907,23776328,65536,142979244,246078,246078,21741820.0,19517441.0,2016.0,524288.0,0.0,0.0,524288.0,16150032273832,16152859317264,16152859466385,16150032676483
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,148935,148935,4194304,256,0,0,12,24,202368,0x7fe74ae2f680,0x7fe74a425f40,2682056,2557821,32992836,65536,206860390,335256,335256,28818302.0,20308851.0,1940.0,524288.0,0.0,0.0,0.0,16150032963106,16152859494545,16152859704627,16150033442816
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,148935,148935,4194304,256,0,0,12,24,205888,0x7fe74d4cf500,0x7fe74a425f80,2660704,2528885,32569699,65536,218474274,332587,332587,30298172.0,21850608.0,1995.0,524288.0,0.0,0.0,0.0,16150033709710,16152859742707,16152859952148,16150034184559
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,148935,148935,4194304,256,0,0,12,24,209408,0x7fe74d4cf380,0x7fe74a425fc0,2451632,2338690,30227778,65536,214566203,306453,306453,20647646.0,18150670.0,1414.0,524288.0,0.0,0.0,524288.0,16150034450974,16152859990388,16152860175990,16150034897154
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,148935,148935,4194304,256,0,0,12,24,214464,0x7fe74d4cf200,0x7fe74a426000,4336400,4219603,54666103,65536,409556317,542049,542049,16285628.0,13833322.0,1208.0,524288.0,0.0,0.0,524288.0,16150035183587,16152860202070,16152860536792,16150035790164
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,148935,148935,4194304,256,0,0,12,24,217728,0x7fe74d4cf080,0x7fe74a426040,2189568,2075373,26751956,65536,171176415,273695,273695,18616194.0,16127931.0,1505.0,524288.0,0.0,0.0,524288.0,16150036065148,16152860578872,16152860746553,16150036470259
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,148935,148935,4194304,256,0,0,12,24,222016,0x7fe74ae2ff00,0x7fe74a426080,2931528,2806919,36176024,65536,240115787,366440,366440,29307762.0,20722632.0,1706.0,524288.0,0.0,0.0,0.0,16150036756752,16152860772313,16152861001115,16150037253791
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,148935,148935,4194304,256,0,0,12,24,226048,0x7fe74ae2fd80,0x7fe74a4260c0,2915584,2806122,36057564,65536,255068840,364447,364447,33051446.0,24530377.0,1719.0,524288.0,0.0,0.0,0.0,16150037521325,16152861034715,16152861263836,16150038020544
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,148935,148935,4194304,256,0,0,12,24,230080,0x7fe74ae2fc00,0x7fe74a426100,2771472,2662537,34411481,65536,249016532,346433,346433,21028328.0,18495815.0,1003.0,524288.0,0.0,0.0,524288.0,16150038294058,16152861299676,16152861510398,16150038778738
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,148935,148935,4194304,256,0,0,12,24,235904,0x7fe74ae2fa80,0x7fe74a426140,4987808,4871693,63046869,65536,470141136,623475,623475,16416688.0,13963755.0,888.0,524288.0,0.0,0.0,524288.0,16150039044952,16152861544478,16152861929760,16150039657048
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,148935,148935,4194304,256,0,0,12,24,239424,0x7fe74ae2f900,0x7fe74a426180,2424768,2315521,29886423,65536,208135171,303095,303095,19156682.0,16652186.0,1454.0,524288.0,0.0,0.0,524288.0,16150039931892,16152861971680,16152862158722,16150040356073
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,148935,148935,4194304,256,0,0,12,24,244224,0x7fe74ae2f780,0x7fe74a4261c0,3182648,3072565,39641401,65536,275275537,397830,397830,30359486.0,21691475.0,1513.0,524288.0,0.0,0.0,0.0,16150040642736,16152862184802,16152862434243,16150041172175
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,148935,148935,4194304,256,0,0,12,24,248768,0x7fe74ae2f600,0x7fe74a426200,3113136,3011498,38976367,65536,294946377,389141,389141,33408332.0,24657308.0,1466.0,524288.0,0.0,0.0,0.0,16150041440059,16152862493604,16152862740325,16150041947497
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,148935,148935,4194304,256,0,0,12,24,253312,0x7fe74d4cf480,0x7fe74a426240,3102744,2989117,38639818,65536,284024657,387842,387842,21164414.0,18643914.0,817.0,524288.0,0.0,0.0,524288.0,16150042222541,16152862803685,16152863040487,16150042740870
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,148935,148935,4194304,256,0,0,8,24,255552,0x7fe74d4cf300,0x7fe74a426280,5740368,5629687,72853887,65536,547653358,717545,717545,67324998.0,64625303.0,811.0,524288.0,0.0,0.0,524288.0,16150043007904,16152863102087,16152863554730,16150043737138
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,148935,148935,4194304,256,0,0,12,24,259840,0x7fe74d4cf180,0x7fe74a4262c0,2908976,2795645,36161994,65536,263403179,363621,363621,21482940.0,18943935.0,1329.0,524288.0,0.0,0.0,524288.0,16150044013572,16152863622570,16152863848492,16150044499161
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,148935,148935,4194304,256,0,0,12,24,265664,0x7fe74d4cf000,0x7fe74a426300,3757512,3647679,47213613,65536,352721188,469688,469688,31614178.0,22819277.0,1456.0,524288.0,0.0,0.0,0.0,16150044768755,16152863906732,16152864204974,16150045334462
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,148935,148935,4194304,256,0,0,12,24,271232,0x7fe74ae2fe80,0x7fe74a426340,3781608,3667293,47410584,65536,349383870,472700,472700,30404846.0,21648357.0,1619.0,524288.0,0.0,0.0,0.0,16150045601846,16152864267534,16152864566416,16150046161434
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,148935,148935,4194304,256,0,0,8,24,273216,0x7fe74ae2fd00,0x7fe74a426380,3866872,3744097,48458514,65536,357113276,483358,483358,46847218.0,44610685.0,1131.0,524288.0,0.0,0.0,524288.0,16150046428308,16152864630257,16152864926578,16150046999635
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,148935,148935,4194304,256,0,0,8,24,275712,0x7fe74ae2fb80,0x7fe74a4263c0,7040472,6924982,89658826,65536,683157916,880058,880058,73356668.0,70050175.0,498.0,524288.0,0.0,0.0,524288.0,16150047267219,16152864984979,16152865542582,16150048088811
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,148935,148935,4194304,256,0,0,12,24,280768,0x7fe74ae2fa00,0x7fe74a426400,3410616,3299066,42692621,65536,316068847,426326,426326,26404886.0,23705675.0,903.0,524288.0,0.0,0.0,524288.0,16150048363295,16152865585942,16152865849304,16150048890643
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,148935,148935,4194304,256,0,0,12,24,287616,0x7fe74ae2f880,0x7fe74a426440,4406832,4292607,55555877,65536,413803479,550853,550853,32485500.0,23649192.0,1488.0,524288.0,0.0,0.0,0.0,16150049158777,16152865882744,16152866233786,16150049775744
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,148935,148935,4194304,256,0,0,12,24,294208,0x7fe74ae2f700,0x7fe74a426480,4415864,4302380,55697218,65536,419462949,551982,551982,29743128.0,20929057.0,1536.0,524288.0,0.0,0.0,0.0,16150050042208,16152866303227,16152866652829,16150050671734
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,148935,148935,4194304,256,0,0,8,24,296960,0x7fe74d4cf580,0x7fe74a4264c0,4502432,4389214,56768971,65536,421066932,562803,562803,54664976.0,52333830.0,965.0,524288.0,0.0,0.0,524288.0,16150050935058,16152866717309,16152867064351,16150051505536
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,148935,148935,4194304,256,0,0,8,24,299968,0x7fe74d4cf400,0x7fe74a426500,8345976,8220667,106412747,65536,804824536,1043246,1043246,79648662.0,76061115.0,463.0,524288.0,0.0,0.0,524288.0,16150051772760,16152867122912,16152867784516,16150052708919
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,148935,148935,4194304,256,0,0,8,24,302720,0x7fe74d4cf280,0x7fe74a426540,5777800,5651936,73216952,65536,546690132,722224,722224,66836826.0,64058712.0,716.0,524288.0,0.0,0.0,524288.0,16150052983463,16152867853636,16152868300999,16150053700307
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,148935,148935,4194304,256,0,0,12,24,305472,0x7fe74d4cf100,0x7fe74a426580,5789552,5670894,73426550,65536,551340219,723693,723693,67610396.0,58608738.0,758.0,524288.0,0.0,0.0,0.0,16150053967281,16152868363879,16152868827882,16150054660146
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,148935,148935,4194304,256,0,0,12,24,308224,0x7fe74ae2ff80,0x7fe74a4265c0,5768840,5655845,73240238,65536,556287167,721104,721104,67589138.0,58578845.0,820.0,524288.0,0.0,0.0,0.0,16150054925750,16152868898762,16152869359725,16150055658024
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,148935,148935,4194304,256,0,0,8,24,310976,0x7fe74ae2fe00,0x7fe74a426600,5815648,5691790,73694185,65536,555545649,726955,726955,66867326.0,64061622.0,700.0,524288.0,0.0,0.0,524288.0,16150055924528,16152869423406,16152869874928,16150056591723
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,148935,148935,4194304,256,0,0,8,24,313216,0x7fe74ae2fc80,0x7fe74a426640,10929976,10812215,140045190,65536,1061240538,1366246,1366246,90366692.0,86264773.0,362.0,524288.0,0.0,0.0,524288.0,16150056859437,16152869911089,16152870780054,16150057994632
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,148935,148935,4194304,256,0,0,8,24,315968,0x7fe74ae2fb00,0x7fe74a426680,10979008,10855033,140563688,65536,1081635781,1372375,1372375,88373544.0,84487583.0,342.0,524288.0,0.0,0.0,524288.0,16150058269026,16152870854134,16152871707099,16150059387491
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,148935,148935,4194304,256,0,0,12,24,318720,0x7fe74ae2f980,0x7fe74a4266c0,10978352,10863387,140666105,65536,1076923641,1372293,1372293,91317948.0,81097970.0,386.0,524288.0,0.0,0.0,0.0,16150059653125,16152871773340,16152872657345,16150060763841
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,148935,148935,4194304,256,0,0,12,24,321472,0x7fe74ae2f800,0x7fe74a426700,10974272,10846512,140523391,65536,1075100765,1371783,1371783,91808648.0,81523333.0,280.0,524288.0,0.0,0.0,0.0,16150061026695,16152872727586,16152873607591,16150062184219
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,148935,148935,4194304,256,0,0,8,24,324224,0x7fe74ae2f680,0x7fe74a426740,10999040,10879393,140962790,65536,1081331346,1374879,1374879,88742218.0,84807407.0,287.0,524288.0,0.0,0.0,524288.0,16150062448193,16152873677671,16152874536397,16150063615738
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,148935,148935,4194304,256,0,0,8,24,326464,0x7fe74d4cf500,0x7fe74a426780,21308208,21183790,274493525,65536,2130513375,2663525,2663525,106173846.0,101224077.0,192.0,524288.0,0.0,0.0,524288.0,16150063881142,16152874603917,16152876302327,16150065871518
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,148935,148935,4194304,256,0,0,8,24,329216,0x7fe74d4cf380,0x7fe74a4267c0,21341376,21228279,275124288,65536,2128373975,2667671,2667671,119928220.0,114633342.0,174.0,524288.0,0.0,0.0,524288.0,16150066105132,16152876402328,16152878066338,16150068065129
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,148935,148935,4194304,256,0,0,12,24,331968,0x7fe74d4cf200,0x7fe74a426800,21370792,21239094,275242436,65536,2129072385,2671348,2671348,122982504.0,111284898.0,215.0,524288.0,0.0,0.0,0.0,16150068288514,16152878159939,16152879883949,16150070321169
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,148935,148935,4194304,256,0,0,12,24,334720,0x7fe74d4cf080,0x7fe74a426840,21347696,21224023,275032892,65536,2123793505,2668461,2668461,127223424.0,115310390.0,251.0,524288.0,0.0,0.0,0.0,16150070530184,16152879977390,16152881692920,16150072572669
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,148935,148935,4194304,256,0,0,8,24,337472,0x7fe74ae2ff00,0x7fe74a426880,21393656,21258001,275460692,65536,2127874713,2674206,2674206,119930134.0,114631505.0,160.0,524288.0,0.0,0.0,524288.0,16150072789985,16152881779321,16152883454211,16150074790750
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,148935,148935,4194304,256,0,0,8,24,0,0x7fe74ae2fd80,0x7fe74a4268c0,42043352,41923906,543378794,65536,4234933995,5255418,5255418,103101520.0,98270320.0,60.0,524288.0,0.0,0.0,524288.0,16150075006726,16152883541891,16152886898872,16150078687914