Dieser Commit ist enthalten in:
colramos-amd
2022-11-04 14:49:36 -05:00
Commit 62d130b458
9127 geänderte Dateien mit 371405 neuen und 0 gelöschten Zeilen
@@ -0,0 +1,168 @@
Index,KernelName,gpu-id,queue-id,queue-index,pid,tid,grd,wgr,lds,scr,vgpr,sgpr,fbar,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,BeginNs,EndNs,CompleteNs
0,"__amd_rocclr_fillBuffer.kd",0,0,0,937062,937067,33554432,256,0,0,8,32,6464,0x0,0x7f30a5604180,499674,499674,16219,3997400,524288,371768834,3801967,0,1501859028,12076634246773666,12076634492293789,12076634492615709,12076634492722711
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,937062,937067,32768,256,0,0,24,24,12480,0x0,0x7f30a5635100,27467,27467,20214,219744,512,1126759,75366,0,4521000,12076634507281913,12076634507609674,12076634507615914,12076634507624380
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,937062,937067,4194304,256,0,0,24,24,12928,0x7f31b1191900,0x7f30a5635140,217853,217853,21633,1742832,65536,133671007,1576099,0,536498696,12076634507695903,12076634507934314,12076634508067113,12076634508071402
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,937062,937067,4194304,256,0,0,36,24,13632,0x7f31b1191800,0x7f30a5635180,389621,389621,26804,3116976,65536,253060814,2948271,0,1014058364,12076634508150749,12076634508354473,12076634508602952,12076634508672009
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,937062,937067,4194304,256,0,0,28,24,14080,0x7f31b1191700,0x7f30a56351c0,403772,403772,26436,3230184,65536,276105211,3052243,0,1106238632,12076634508705912,12076634508912072,12076634509168551,12076634509238653
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,937062,937067,4194304,256,0,0,24,24,14528,0x7f31b1191600,0x7f30a5635200,217957,217957,19106,1743664,65536,133545621,1580634,0,535998284,12076634509266064,12076634509473830,12076634509607270,12076634509610645
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,937062,937067,4194304,256,0,0,24,24,14976,0x7f31b1191500,0x7f30a5635240,229069,229069,19969,1832560,65536,121094689,1662134,0,486187148,12076634509672260,12076634509869669,12076634510009989,12076634510013484
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,937062,937067,4194304,256,0,0,24,24,15424,0x7f31b1191400,0x7f30a5635280,212108,212108,18602,1696872,65536,156194765,1531178,0,626596552,12076634510103422,12076634510288548,12076634510418468,12076634510421754
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,937062,937067,4194304,256,0,0,28,24,16128,0x7f31b1191300,0x7f30a56352c0,395493,395493,31193,3163952,65536,350214228,2994677,0,1402673352,12076634510485032,12076634510682148,12076634510933987,12076634510974372
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,937062,937067,4194304,256,0,0,28,24,16832,0x7f31b1191a00,0x7f30a5635300,467516,467516,17173,3740136,65536,304554434,3042045,0,1220032660,12076634511021389,12076634511221666,12076634511520386,12076634511586971
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,937062,937067,4194304,256,0,0,24,24,17536,0x7f31b1191900,0x7f30a5635340,225357,225357,22606,1802864,65536,126884404,1624746,0,509347128,12076634511614202,12076634511821665,12076634511958625,12076634511961738
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,937062,937067,4194304,256,0,0,24,24,18240,0x7f31b1191800,0x7f30a5635380,214853,214853,19943,1718832,65536,138156049,1552593,0,554439388,12076634512019917,12076634512227264,12076634512358624,12076634512362043
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,937062,937067,4194304,256,0,0,24,24,18944,0x7f31b1191700,0x7f30a56353c0,212085,212085,21709,1696688,65536,162677854,1518896,0,652530312,12076634512440970,12076634512621503,12076634512750303,12076634512753651
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,937062,937067,4194304,256,0,0,28,24,19904,0x7f31b1191600,0x7f30a5635400,448589,448589,14903,3588720,65536,352429805,2980195,0,1411536664,12076634512815597,12076634513007902,12076634513294302,12076634513361963
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,937062,937067,4194304,256,0,0,28,24,20608,0x7f31b1191500,0x7f30a5635440,398365,398365,30407,3186928,65536,322399376,3015454,0,1291412136,12076634513388011,12076634513596861,12076634513850621,12076634513916414
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,937062,937067,4194304,256,0,0,24,24,21312,0x7f31b1191400,0x7f30a5635480,212733,212733,21416,1701872,65536,152200936,1534437,0,610620496,12076634513941962,12076634514154300,12076634514284220,12076634514287725
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,937062,937067,4194304,256,0,0,24,24,22016,0x7f31b1191300,0x7f30a56354c0,212636,212636,21337,1701096,65536,160391048,1536825,0,643379376,12076634514348127,12076634514545339,12076634514675419,12076634514678532
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,937062,937067,4194304,256,0,0,24,24,22720,0x7f31b1191a00,0x7f30a5635500,222621,222621,21873,1780976,65536,144958356,1613854,0,581645868,12076634514752189,12076634514932378,12076634515069178,12076634515072334
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,937062,937067,4194304,256,0,0,28,24,23680,0x7f31b1191900,0x7f30a5635540,397556,397556,30136,3180456,65536,341121024,3002753,0,1366301448,12076634515133218,12076634515327737,12076634515581337,12076634515646482
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,937062,937067,4194304,256,0,0,28,24,24384,0x7f31b1191800,0x7f30a5635580,403172,403172,24087,3225384,65536,224707461,3040116,0,900648000,12076634515675667,12076634515871416,12076634516129336,12076634516199712
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,937062,937067,4194304,256,0,0,24,24,25088,0x7f31b1191700,0x7f30a56355c0,216284,216284,24062,1730280,65536,126988676,1563585,0,509770336,12076634516228164,12076634516426135,12076634516558295,12076634516561545
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,937062,937067,4194304,256,0,0,24,24,25792,0x7f31b1191600,0x7f30a5635600,219124,219124,22867,1753000,65536,136862429,1589426,0,549267012,12076634516622708,12076634516813174,12076634516948054,12076634516951169
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,937062,937067,4194304,256,0,0,24,24,26496,0x7f31b1191500,0x7f30a5635640,213709,213709,22349,1709680,65536,157553694,1533157,0,632031676,12076634517030537,12076634517211413,12076634517341493,12076634517344561
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,937062,937067,4194304,256,0,0,28,24,27712,0x7f31b1191400,0x7f30a5635680,399981,399981,28230,3199856,65536,292218439,3025047,0,1170691640,12076634517402739,12076634517594932,12076634517850932,12076634517917136
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,937062,937067,4194304,256,0,0,28,24,28416,0x7f31b1191300,0x7f30a56356c0,405413,405413,28751,3243312,65536,293488110,3058758,0,1175768556,12076634517942824,12076634518149171,12076634518407570,12076634518473942
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,937062,937067,4194304,256,0,0,24,24,29120,0x7f31b1191a00,0x7f30a5635700,210541,210541,18560,1684336,65536,158231458,1524200,0,634744128,12076634518498998,12076634518696210,12076634518825490,12076634518828672
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,937062,937067,4194304,256,0,0,24,24,30080,0x7f31b1191900,0x7f30a5635740,221165,221165,25093,1769328,65536,153672197,1587171,0,616501944,12076634518889094,12076634519077649,12076634519212209,12076634519215481
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,937062,937067,4194304,256,0,0,24,24,30784,0x7f31b1191800,0x7f30a5635780,214733,214733,20244,1717872,65536,146270057,1557059,0,586895320,12076634519290751,12076634519467568,12076634519599568,12076634519602501
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,937062,937067,4194304,256,0,0,28,24,32000,0x7f31b1191700,0x7f30a56357c0,395148,395148,31161,3161192,65536,348917173,2987788,0,1397488220,12076634519664046,12076634519856527,12076634520109807,12076634520179775
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,937062,937067,4194304,256,0,0,28,24,32960,0x7f31b1191600,0x7f30a5635800,391717,391717,30699,3133744,65536,352352859,2970795,0,1411229772,12076634520210833,12076634520405326,12076634520656205,12076634520723025
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,937062,937067,4194304,256,0,0,24,24,33920,0x7f31b1191500,0x7f30a5635840,211165,211165,22356,1689328,65536,159141992,1519622,0,638391120,12076634520747351,12076634520946445,12076634521075405,12076634521078877
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,937062,937067,4194304,256,0,0,24,24,34880,0x7f31b1191400,0x7f30a5635880,222669,222669,22358,1781360,65536,140744300,1613811,0,564813204,12076634521142015,12076634521321964,12076634521459724,12076634521462892
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,937062,937067,4194304,256,0,0,24,24,35840,0x7f31b1191300,0x7f30a56358c0,210276,210276,22634,1682216,65536,138811194,1514446,0,557073360,12076634521536088,12076634521712523,12076634521841163,12076634521844321
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,937062,937067,4194304,256,0,0,28,24,37312,0x7f31b1191a00,0x7f30a5635900,410381,410381,24119,3283056,65536,309213186,3095322,0,1238665668,12076634521904974,12076634522099402,12076634522362922,12076634522429620
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,937062,937067,4194304,256,0,0,28,24,38272,0x7f31b1191900,0x7f30a5635940,397700,397700,29036,3181608,65536,290946828,3013211,0,1165600192,12076634522455268,12076634522659721,12076634522913640,12076634522980154
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,937062,937067,4194304,256,0,0,24,24,39232,0x7f31b1191800,0x7f30a5635980,222484,222484,22018,1779880,65536,128990349,1612365,0,517801864,12076634523013546,12076634523210600,12076634523347879,12076634523351094
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,937062,937067,4194304,256,0,0,24,24,40192,0x7f31b1191700,0x7f30a56359c0,222764,222764,24204,1782120,65536,146331742,1615165,0,587163692,12076634523411156,12076634523601639,12076634523738919,12076634523742191
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,937062,937067,4194304,256,0,0,24,24,41152,0x7f31b1191600,0x7f30a5635a00,212021,212021,22550,1696176,65536,157151524,1525336,0,630423560,12076634523815207,12076634523991078,12076634524121478,12076634524125254
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,937062,937067,4194304,256,0,0,28,24,42624,0x7f31b1191500,0x7f30a5635a40,401045,401045,26402,3208368,65536,336390145,3004654,0,1347376740,12076634524185225,12076634524375077,12076634524632037,12076634524698570
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,937062,937067,4194304,256,0,0,28,24,43584,0x7f31b1191400,0x7f30a5635a80,401900,401900,26390,3215208,65536,295687943,3049472,0,1184568052,12076634524722816,12076634524918436,12076634525176195,12076634525244576
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,937062,937067,4194304,256,0,0,24,24,44544,0x7f31b1191300,0x7f30a5635ac0,211773,211773,25302,1694192,65536,150606101,1519106,0,604274304,12076634525273139,12076634525467875,12076634525597154,12076634525600558
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,937062,937067,4194304,256,0,0,24,24,45760,0x7f31b1191a00,0x7f30a5635b00,220996,220996,25671,1767976,65536,155539914,1586010,0,623980732,12076634525660279,12076634525852834,12076634525988034,12076634525991365
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,937062,937067,4194304,256,0,0,24,24,46720,0x7f31b1191900,0x7f30a5635b40,218309,218309,23155,1746480,65536,153186453,1572643,0,614577888,12076634526065333,12076634526243073,12076634526376673,12076634526380178
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,937062,937067,4194304,256,0,0,28,24,48448,0x7f31b1191800,0x7f30a5635b80,413652,413652,33352,3309224,65536,288767588,3135220,0,1156887128,12076634526440901,12076634526625632,12076634526892192,12076634526958564
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,937062,937067,4194304,256,0,0,28,24,49408,0x7f31b1191700,0x7f30a5635bc0,398316,398316,33638,3186536,65536,340782112,3013266,0,1364942872,12076634526986887,12076634527187231,12076634527441950,12076634527482839
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,937062,937067,4194304,256,0,0,24,24,50368,0x7f31b1191600,0x7f30a5635c00,205276,205276,21119,1642216,65536,171403607,1481515,0,687438856,12076634527516492,12076634527715070,12076634527841149,12076634527844392
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,937062,937067,4194304,256,0,0,24,24,51584,0x7f31b1191500,0x7f30a5635c40,220756,220756,26419,1766056,65536,159827176,1589517,0,641144504,12076634527905185,12076634528120349,12076634528256349,12076634528259995
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,937062,937067,4194304,256,0,0,24,24,52544,0x7f31b1191400,0x7f30a5635c80,214117,214117,22063,1712944,65536,148578942,1546808,0,596133776,12076634528333842,12076634528514748,12076634528646268,12076634528649429
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,937062,937067,4194304,256,0,0,28,24,54272,0x7f31b1191300,0x7f30a5635cc0,414036,414036,32477,3312296,65536,326939111,3126424,0,1309573220,12076634528709702,12076634528904027,12076634529170587,12076634529238565
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,937062,937067,4194304,256,0,0,28,24,55488,0x7f31b1191a00,0x7f30a5635d00,389733,389733,31059,3117872,65536,341729609,2953917,0,1368736252,12076634529266878,12076634529463066,12076634529713785,12076634529779682
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,937062,937067,4194304,256,0,0,24,24,56704,0x7f31b1191900,0x7f30a5635d40,219156,219156,22779,1753256,65536,151748826,1574610,0,608822620,12076634529804548,12076634530000025,12076634530134264,12076634530137818
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,937062,937067,4194304,256,0,0,24,24,58176,0x7f31b1191800,0x7f30a5635d80,223341,223341,26808,1786736,65536,159849644,1611787,0,641246944,12076634530199333,12076634530387384,12076634530525624,12076634530529216
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,937062,937067,4194304,256,0,0,24,24,59392,0x7f31b1191700,0x7f30a5635dc0,214917,214917,25443,1719344,65536,162346752,1524728,0,651208456,12076634530601581,12076634530778263,12076634530908023,12076634530911397
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,937062,937067,4194304,256,0,0,28,24,61376,0x7f31b1191600,0x7f30a5635e00,408484,408484,31258,3267880,65536,320329657,3092366,0,1283139824,12076634530971860,12076634531165142,12076634531428822,12076634531469916
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,937062,937067,4194304,256,0,0,28,24,62592,0x7f31b1191500,0x7f30a5635e40,392756,392756,33027,3142056,65536,334521193,2972456,0,1339901580,12076634531509049,12076634531687221,12076634531939700,12076634532015320
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,937062,937067,4194304,256,0,0,24,24,63808,0x7f31b1191400,0x7f30a5635e80,279308,279308,14600,2234472,65536,144221695,1546141,0,578708168,12076634532041669,12076634532250260,12076634532424979,12076634532428349
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,937062,937067,4194304,256,0,0,24,24,65280,0x7f31b1191300,0x7f30a5635ec0,226748,226748,29457,1813992,65536,178093356,1602668,0,714235712,12076634532488801,12076634532676339,12076634532814258,12076634532817633
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,937062,937067,4194304,256,0,0,24,24,66496,0x7f31b1191a00,0x7f30a5635f00,212613,212613,24369,1700912,65536,161056055,1531647,0,646065348,12076634532892883,12076634533076338,12076634533207058,12076634533210664
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,937062,937067,4194304,256,0,0,28,24,68480,0x7f31b1191900,0x7f30a5635f40,412309,412309,32858,3298480,65536,334313937,3122389,0,1339107212,12076634533272058,12076634533460977,12076634533726416,12076634533793017
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,937062,937067,4194304,256,0,0,28,24,69696,0x7f31b1191800,0x7f30a5635f80,398371,398371,32510,3186976,65536,340219487,3015834,0,1362692336,12076634533821500,12076634534015056,12076634534271375,12076634534338342
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,937062,937067,4194304,256,0,0,24,24,70912,0x7f31b1191700,0x7f30a5635fc0,228188,228188,26741,1825512,65536,149209986,1647545,0,598707016,12076634534364611,12076634534562895,12076634534702894,12076634534706386
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,937062,937067,4194304,256,0,0,24,24,72384,0x7f31b1191600,0x7f30a5636000,225708,225708,27996,1805672,65536,177250903,1624430,0,710843524,12076634534768331,12076634534956494,12076634535096813,12076634535100429
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,937062,937067,4194304,256,0,0,24,24,73600,0x7f31b1191500,0x7f30a5636040,211220,211220,22475,1689768,65536,160254032,1514284,0,642854776,12076634535174577,12076634535353933,12076634535483213,12076634535486688
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,937062,937067,4194304,256,0,0,28,24,75840,0x7f31b1191400,0x7f30a5636080,412789,412789,34054,3302320,65536,296733323,3121128,0,1188766220,12076634535547371,12076634535732812,12076634535999531,12076634536067077
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,937062,937067,4194304,256,0,0,28,24,77056,0x7f31b1191300,0x7f30a56360c0,398948,398948,26692,3191592,65536,249430262,3001335,0,999539228,12076634536092825,12076634536295051,12076634536551850,12076634536615818
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,937062,937067,4194304,256,0,0,24,24,78272,0x7f31b1191a00,0x7f30a5636100,219732,219732,21810,1757864,65536,146729488,1589753,0,588782344,12076634536640754,12076634536837610,12076634536973129,12076634536976529
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,937062,937067,4194304,256,0,0,24,24,80000,0x7f31b1191900,0x7f30a5636140,231853,231853,26909,1854832,65536,196977740,1689369,0,789781756,12076634537038584,12076634537226409,12076634537370248,12076634537373768
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,937062,937067,4194304,256,0,0,24,24,81216,0x7f31b1191800,0x7f30a5636180,217245,217245,22366,1737968,65536,149848899,1578330,0,601235936,12076634537446193,12076634537621608,12076634537755847,12076634537759095
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,937062,937067,4194304,256,0,0,28,24,83456,0x7f31b1191700,0x7f30a56361c0,412789,412789,33823,3302320,65536,328378877,3136724,0,1315331968,12076634537819016,12076634538011047,12076634538278246,12076634538344273
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,937062,937067,4194304,256,0,0,28,24,84928,0x7f31b1191600,0x7f30a5636200,443228,443228,14224,3545832,65536,352134637,2957912,0,1410361884,12076634538370261,12076634538570246,12076634538857285,12076634538923270
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,937062,937067,4194304,256,0,0,24,24,86400,0x7f31b1191500,0x7f30a5636240,222836,222836,24641,1782696,65536,145710036,1601147,0,584707564,12076634538947946,12076634539151204,12076634539287684,12076634539291164
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,937062,937067,4194304,256,0,0,24,24,88128,0x7f31b1191400,0x7f30a5636280,239925,239925,25988,1919408,65536,208509762,1760336,0,835909668,12076634539352438,12076634539539364,12076634539689443,12076634539692852
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,937062,937067,4194304,256,0,0,24,24,89600,0x7f31b1191300,0x7f30a56362c0,222461,222461,24485,1779696,65536,148799551,1614425,0,597037216,12076634539780374,12076634539956803,12076634540093762,12076634540097414
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,937062,937067,4194304,256,0,0,28,24,92096,0x7f31b1191a00,0x7f30a5636300,413860,413860,32816,3310888,65536,342079203,3146167,0,1370187588,12076634540157266,12076634540344802,12076634540613441,12076634540679657
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,937062,937067,4194304,256,0,0,28,24,93568,0x7f31b1191900,0x7f30a5636340,400508,400508,30364,3204072,65536,325601236,3033729,0,1304223612,12076634540707349,12076634540900960,12076634541159040,12076634541228759
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,937062,937067,4194304,256,0,0,24,24,95040,0x7f31b1191800,0x7f30a5636380,215420,215420,22810,1723368,65536,152585967,1559429,0,612212692,12076634541255168,12076634541456959,12076634541590079,12076634541593427
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,937062,937067,4194304,256,0,0,24,24,96768,0x7f31b1191700,0x7f30a56363c0,255541,255541,30610,2044336,65536,222286816,1859187,0,890991504,12076634541652958,12076634541839998,12076634541998398,12076634542006746
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,937062,937067,4194304,256,0,0,24,24,98240,0x7f31b1191600,0x7f30a5636400,216668,216668,22070,1733352,65536,155741010,1570265,0,624841512,12076634542076425,12076634542254077,12076634542388157,12076634542391301
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,937062,937067,4194304,256,0,0,28,24,100736,0x7f31b1191500,0x7f30a5636440,417628,417628,34074,3341032,65536,333216758,3118039,0,1334683008,12076634542450792,12076634542640317,12076634542910716,12076634542957294
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,937062,937067,4194304,256,0,0,28,24,102208,0x7f31b1191400,0x7f30a5636480,397324,397324,30824,3178600,65536,337128771,3018503,0,1350334456,12076634542981539,12076634543186555,12076634543443355,12076634543488522
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,937062,937067,4194304,256,0,0,24,24,103680,0x7f31b1191300,0x7f30a56364c0,225229,225229,24290,1801840,65536,142448607,1626904,0,571637828,12076634543530180,12076634543704954,12076634543843994,12076634543847129
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,937062,937067,4194304,256,0,0,24,24,105664,0x7f31b1191a00,0x7f30a5636500,262797,262797,28081,2102384,65536,233830271,1940837,0,937170592,12076634543909976,12076634544116153,12076634544281593,12076634544284773
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,937062,937067,4194304,256,0,0,24,24,107136,0x7f31b1191900,0x7f30a5636540,221141,221141,24416,1769136,65536,144513711,1597678,0,579896612,12076634544358721,12076634544537752,12076634544673752,12076634544677273
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,937062,937067,4194304,256,0,0,28,24,109888,0x7f31b1191800,0x7f30a5636580,408485,408485,36448,3267888,65536,324005800,3077103,0,1297869708,12076634544736423,12076634544931832,12076634545196471,12076634545265778
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,937062,937067,4194304,256,0,0,28,24,111360,0x7f31b1191700,0x7f30a56365c0,398084,398084,38085,3184680,65536,335870488,2989272,0,1345296084,12076634545291696,12076634545487190,12076634545741750,12076634545808177
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,937062,937067,4194304,256,0,0,24,24,112832,0x7f31b1191600,0x7f30a5636600,225389,225389,23366,1803120,65536,143201439,1633713,0,574668904,12076634545835267,12076634546034069,12076634546174229,12076634546177504
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,937062,937067,4194304,256,0,0,24,24,114816,0x7f31b1191500,0x7f30a5636640,274788,274788,30015,2198312,65536,245834907,2034390,0,985205140,12076634546240341,12076634546426388,12076634546599348,12076634546602735
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,937062,937067,4194304,256,0,0,24,24,116288,0x7f31b1191400,0x7f30a5636680,212845,212845,21768,1702768,65536,154990814,1519836,0,621814824,12076634546674859,12076634546851027,12076634546982387,12076634546985697
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,937062,937067,4194304,256,0,0,28,24,119040,0x7f31b1191300,0x7f30a56366c0,406924,406924,36478,3255400,65536,315620737,3056185,0,1264314736,12076634547046330,12076634547239506,12076634547502386,12076634547567880
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,937062,937067,4194304,256,0,0,28,24,120768,0x7f31b1191a00,0x7f30a5636700,395605,395605,32088,3164848,65536,318104197,2984256,0,1274235812,12076634547596163,12076634547788305,12076634548044305,12076634548112944
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,937062,937067,4194304,256,0,0,24,24,122496,0x7f31b1191900,0x7f30a5636740,228092,228092,25336,1824744,65536,143630960,1655089,0,576381056,12076634548138692,12076634548339344,12076634548480304,12076634548483744
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,937062,937067,4194304,256,0,0,24,24,124736,0x7f31b1191800,0x7f30a5636780,288765,288765,29964,2310128,65536,259925815,2149141,0,1041559524,12076634548543705,12076634548728143,12076634548911663,12076634548915016
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,937062,937067,4194304,256,0,0,24,24,126464,0x7f31b1191700,0x7f30a56367c0,226421,226421,25398,1811376,65536,145020314,1625891,0,581981220,12076634549021955,12076634549203822,12076634549343342,12076634549347000
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,937062,937067,4194304,256,0,0,20,24,127936,0x7f31b1191600,0x7f30a5636800,411885,411885,36923,3295088,65536,377379464,3118343,0,1511338396,12076634549406931,12076634549594221,12076634549861421,12076634549902813
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,937062,937067,4194304,256,0,0,28,24,129664,0x7f31b1191500,0x7f30a5636840,400772,400772,29019,3206184,65536,270661366,3012149,0,1084466864,12076634549939552,12076634550131340,12076634550390059,12076634550456674
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,937062,937067,4194304,256,0,0,24,24,131392,0x7f31b1191400,0x7f30a5636880,223493,223493,28641,1787952,65536,156747337,1596842,0,628841760,12076634550483403,12076634550681099,12076634550818218,12076634550821683
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,937062,937067,4194304,256,0,0,24,24,133632,0x7f31b1191300,0x7f30a56368c0,300748,300748,31432,2405992,65536,272500640,2248458,0,1091849984,12076634550885241,12076634551073738,12076634551264457,12076634551332072
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,937062,937067,4194304,256,0,0,24,24,135360,0x7f31b1191a00,0x7f30a5636900,221837,221837,24841,1774704,65536,154654268,1601667,0,620482812,12076634551376685,12076634551554377,12076634551691497,12076634551694897
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,937062,937067,4194304,256,0,0,20,24,136832,0x7f31b1191900,0x7f30a5636940,436893,436893,39784,3495152,65536,402285022,3324829,0,1610960776,12076634551755520,12076634551941416,12076634552225095,12076634552292028
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,937062,937067,4194304,256,0,0,28,24,138560,0x7f31b1191800,0x7f30a5636980,400429,400429,33584,3203440,65536,329960243,3008473,0,1321683344,12076634552320531,12076634552515655,12076634552773094,12076634552839366
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,937062,937067,4194304,256,0,0,24,24,140288,0x7f31b1191700,0x7f30a56369c0,220708,220708,27469,1765672,65536,151431805,1583632,0,607560160,12076634552864162,12076634553076133,12076634553212453,12076634553215966
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,937062,937067,4194304,256,0,0,24,24,142784,0x7f31b1191600,0x7f30a5636a00,330308,330308,32883,2642472,65536,300457787,2479819,0,1203689148,12076634553276469,12076634553467493,12076634553678052,12076634553744239
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,937062,937067,4194304,256,0,0,24,24,144768,0x7f31b1191500,0x7f30a5636a40,223524,223524,23556,1788200,65536,157776974,1611436,0,632997452,12076634553780316,12076634553964291,12076634554102531,12076634554106102
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,937062,937067,4194304,256,0,0,20,24,145728,0x7f31b1191400,0x7f30a5636a80,470173,470173,40408,3761392,65536,437901688,3595251,0,1753426996,12076634554166254,12076634554354531,12076634554661730,12076634554727688
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,937062,937067,4194304,256,0,0,28,24,147712,0x7f31b1191300,0x7f30a5636ac0,405245,405245,34161,3241968,65536,335140714,3063259,0,1342389428,12076634554754929,12076634554951169,12076634555213249,12076634555279745
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,937062,937067,4194304,256,0,0,24,24,149696,0x7f31b1191a00,0x7f30a5636b00,225836,225836,22182,1806696,65536,154006034,1634745,0,617898908,12076634555304291,12076634555503466,12076634555643946,12076634555651266
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,937062,937067,4194304,256,0,0,24,24,152192,0x7f31b1191900,0x7f30a5636b40,356653,356653,35781,2853232,65536,325389722,2683365,0,1303415364,12076634555706769,12076634555893704,12076634556121223,12076634556189638
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,937062,937067,4194304,256,0,0,24,24,154176,0x7f31b1191800,0x7f30a5636b80,218700,218700,25714,1749608,65536,154046907,1576350,0,618063224,12076634556229913,12076634556409383,12076634556544902,12076634556548375
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,937062,937067,4194304,256,0,0,20,24,155648,0x7f31b1191700,0x7f30a5636bc0,503797,503797,43958,4030384,65536,471894300,3865747,0,1889397832,12076634556611292,12076634556801222,12076634557130821,12076634557200308
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,937062,937067,4194304,256,0,0,28,24,157632,0x7f31b1191600,0x7f30a5636c00,407340,407340,28640,3258728,65536,312702803,3052368,0,1252629116,12076634557226436,12076634557424421,12076634557688420,12076634557729282
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,937062,937067,4194304,256,0,0,24,24,159616,0x7f31b1191500,0x7f30a5636c40,226132,226132,25877,1809064,65536,153078598,1635564,0,614185492,12076634557772462,12076634557950339,12076634558090179,12076634558093649
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,937062,937067,4194304,256,0,0,24,24,162368,0x7f31b1191400,0x7f30a5636c80,381924,381924,36449,3055400,65536,349844373,2887948,0,1401225252,12076634558156556,12076634558340738,12076634558586178,12076634558653100
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,937062,937067,4194304,256,0,0,24,24,164608,0x7f31b1191300,0x7f30a5636cc0,225636,225636,28452,1805096,65536,163004818,1620463,0,653901864,12076634558689598,12076634558868257,12076634559008577,12076634559012278
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,937062,937067,4194304,256,0,0,20,24,166336,0x7f31b1191a00,0x7f30a5636d00,575053,575053,46909,4600432,65536,542304783,4444623,0,2171037532,12076634559063984,12076634559260256,12076634559638336,12076634559704396
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,937062,937067,4194304,256,0,0,28,24,168576,0x7f31b1191900,0x7f30a5636d40,407580,407580,33723,3260648,65536,300540763,3069434,0,1203998740,12076634559729943,12076634559931455,12076634560195934,12076634560262333
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,937062,937067,4194304,256,0,0,24,24,170816,0x7f31b1191800,0x7f30a5636d80,221692,221692,25854,1773544,65536,161817687,1597624,0,649149348,12076634560287300,12076634560486494,12076634560624573,12076634560628034
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,937062,937067,4194304,256,0,0,24,24,174080,0x7f31b1191700,0x7f30a5636dc0,479652,479652,16068,3837224,65536,400919451,3297056,0,1605528676,12076634560680361,12076634560872413,12076634561182652,12076634561253146
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,937062,937067,4194304,256,0,0,24,24,176576,0x7f31b1191600,0x7f30a5636e00,226229,226229,27604,1809840,65536,171830292,1631065,0,689219544,12076634561291798,12076634561482171,12076634561622011,12076634561625890
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,937062,937067,4194304,256,0,0,20,24,177792,0x7f31b1191500,0x7f30a5636e40,642308,642308,49986,5138472,65536,610109508,4982908,0,2442259024,12076634561686523,12076634561873050,12076634562297370,12076634562320632
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,937062,937067,4194304,256,0,0,28,24,180288,0x7f31b1191400,0x7f30a5636e80,405085,405085,38149,3240688,65536,316171611,3009971,0,1266529976,12076634562375825,12076634562555289,12076634562816408,12076634562837233
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,937062,937067,4194304,256,0,0,24,24,182784,0x7f31b1191300,0x7f30a5636ec0,224084,224084,25472,1792680,65536,181419219,1619155,0,727554372,12076634562893057,12076634563075768,12076634563215447,12076634563219103
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,937062,937067,4194304,256,0,0,24,24,186304,0x7f31b1191a00,0x7f30a5636f00,486588,486588,42862,3892712,65536,454898081,3728515,0,1821450016,12076634563280988,12076634563480887,12076634563795926,12076634563817416
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,937062,937067,4194304,256,0,0,24,24,189312,0x7f31b1191900,0x7f30a5636f40,242541,242541,26466,1940336,65536,213332854,1779150,0,855228180,12076634563892296,12076634564077046,12076634564229205,12076634564232879
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,937062,937067,4194304,256,0,0,20,24,190784,0x7f31b1191800,0x7f30a5636f80,784108,784108,60015,6272872,65536,750338005,6105956,0,3003173004,12076634564285056,12076634564488245,12076634565005523,12076634565048666
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,937062,937067,4194304,256,0,0,28,24,193792,0x7f31b1191700,0x7f30a5636fc0,462325,462325,41381,3698608,65536,395240212,3527463,0,1582802604,12076634565094482,12076634565274643,12076634565577202,12076634565643924
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,937062,937067,4194304,256,0,0,24,24,196800,0x7f31b1191600,0x7f30a5637000,246109,246109,27784,1968880,65536,217168109,1806572,0,870553892,12076634565678829,12076634565865202,12076634566019761,12076634566023700
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,937062,937067,4194304,256,0,0,24,24,201088,0x7f31b1191500,0x7f30a5637040,592933,592933,48021,4743472,65536,560063963,4582944,0,2242112928,12076634566085235,12076634566269841,12076634566656240,12076634566723241
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,937062,937067,4194304,256,0,0,24,24,204608,0x7f31b1191400,0x7f30a5637080,280285,280285,32285,2242288,65536,249208230,2057641,0,998719992,12076634566764228,12076634566942639,12076634567118159,12076634567121853
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,937062,937067,4194304,256,0,0,20,24,206080,0x7f31b1191300,0x7f30a56370c0,941756,941756,14101,7534056,65536,890432974,7231462,0,3563553184,12076634567184139,12076634567381838,12076634568006157,12076634568057143
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,937062,937067,4194304,256,0,0,28,24,209600,0x7f31b1191a00,0x7f30a5637100,507660,507660,43040,4061288,65536,461305602,3890339,0,1847067668,12076634568083071,12076634568279756,12076634568611435,12076634568675082
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,937062,937067,4194304,256,0,0,24,24,213120,0x7f31b1191900,0x7f30a5637140,280405,280405,28596,2243248,65536,253336450,2087346,0,1015233064,12076634568699477,12076634568894155,12076634569072874,12076634569076559
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,937062,937067,4194304,256,0,0,24,24,218176,0x7f31b1191800,0x7f30a5637180,697597,697597,54537,5580784,65536,664191411,5417658,0,2658618900,12076634569137282,12076634569324714,12076634569780713,12076634569820142
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,937062,937067,4194304,256,0,0,24,24,222208,0x7f31b1191700,0x7f30a56371c0,311908,311908,30116,2495272,65536,284878944,2343878,0,1141402000,12076634569871588,12076634570055592,12076634570255592,12076634570322897
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,937062,937067,4194304,256,0,0,20,24,223936,0x7f31b1191600,0x7f30a5637200,1074565,1074565,15319,8596528,65536,1026825089,8361806,0,4109121200,12076634570348595,12076634570543431,12076634571254629,12076634571321024
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,937062,937067,4194304,256,0,0,28,24,227968,0x7f31b1191500,0x7f30a5637240,569653,569653,48021,4557232,65536,530371934,4383864,0,2123328560,12076634571346331,12076634571549829,12076634571923908,12076634571989848
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,937062,937067,4194304,256,0,0,24,24,232000,0x7f31b1191400,0x7f30a5637280,317245,317245,31036,2537968,65536,289326641,2381524,0,1159204808,12076634572019904,12076634572227907,12076634572431907,12076634572500057
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,937062,937067,4194304,256,0,0,24,24,237824,0x7f31b1191300,0x7f30a56372c0,802213,802213,60272,6417712,65536,768040034,6253577,0,3074015504,12076634572524202,12076634572719586,12076634573245505,12076634573312158
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,937062,937067,4194304,256,0,0,24,24,242368,0x7f31b1191a00,0x7f30a5637300,347797,347797,32627,2782384,65536,318789642,2623936,0,1277049252,12076634573353665,12076634573529664,12076634573753184,12076634573818800
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,937062,937067,4194304,256,0,0,20,24,243584,0x7f31b1191900,0x7f30a5637340,1208453,1208453,86374,9667632,65536,1168332366,9488416,0,4675150496,12076634573846241,12076634574053983,12076634574853821,12076634574922784
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,937062,937067,4194304,256,0,0,28,24,248128,0x7f31b1191800,0x7f30a5637380,638796,638796,50862,5110376,65536,604054320,4952300,0,2418060228,12076634574954663,12076634575159741,12076634575582300,12076634575648644
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,937062,937067,4194304,256,0,0,24,24,252672,0x7f31b1191700,0x7f30a56373c0,353580,353580,33948,2828648,65536,324112464,2665953,0,1298340420,12076634575673781,12076634575870139,12076634576097178,12076634576165074
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,937062,937067,4194304,256,0,0,24,24,259264,0x7f31b1191600,0x7f30a5637400,907972,907972,66668,7263784,65536,871808204,7100172,0,3489082580,12076634576192956,12076634576392698,12076634576989176,12076634577055932
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,937062,937067,4194304,256,0,0,24,24,264832,0x7f31b1191500,0x7f30a5637440,420029,420029,39580,3360240,65536,386607378,3170786,0,1548333812,12076634577092850,12076634577279576,12076634577549015,12076634577615372
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,937062,937067,4194304,256,0,0,20,24,266304,0x7f31b1191400,0x7f30a5637480,1486188,1486188,99240,11889512,65536,1446440968,11735967,0,5787585524,12076634577639457,12076634577835895,12076634578822292,12076634578892327
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,937062,937067,4194304,256,0,0,28,24,271872,0x7f31b1191300,0x7f30a56374c0,779469,779469,62018,6235760,65536,741190979,6050695,0,2966600364,12076634578918406,12076634579119252,12076634579634931,12076634579684581
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,937062,937067,4194304,256,0,0,24,24,277440,0x7f31b1191a00,0x7f30a5637500,421452,421452,38444,3371624,65536,390033242,3211048,0,1562019048,12076634579709507,12076634579904850,12076634580177649,12076634580247919
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,937062,937067,4194304,256,0,0,12,24,279936,0x7f31b1191900,0x7f30a5637540,1125589,1125589,79521,9004720,65536,1088541766,8842982,0,4355992024,12076634580276031,12076634580473649,12076634581212847,12076634581268868
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,937062,937067,4194304,256,0,0,24,24,286528,0x7f31b1191800,0x7f30a5637580,487197,487197,42516,3897584,65536,454902748,3736289,0,1821503676,12076634581309874,12076634581489006,12076634581805326,12076634581854848
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,937062,937067,4194304,256,0,0,20,24,288000,0x7f31b1191700,0x7f30a56375c0,1768453,1768453,117917,14147632,65536,1724990770,13979184,0,6901783928,12076634581883371,12076634582092845,12076634583267082,12076634583563887
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,937062,937067,4194304,256,0,0,32,24,294592,0x7f31b1191600,0x7f30a5637600,918692,918692,64768,7349544,65536,807675935,7172718,0,3232557552,12076634583598371,12076634583798721,12076634584410400,12076634584459012
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,937062,937067,4194304,256,0,0,24,24,301184,0x7f31b1191500,0x7f30a5637640,495188,495188,44861,3961512,65536,462565391,3791743,0,1852172552,12076634584494178,12076634584679519,12076634585000798,12076634585094735
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,937062,937067,4194304,256,0,0,12,24,304960,0x7f31b1191400,0x7f30a5637680,1336324,1336324,91200,10690600,65536,1298621629,10526806,0,5196313352,12076634585122847,12076634585329598,12076634586208316,12076634586259401
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,937062,937067,4194304,256,0,0,24,24,313600,0x7f31b1191300,0x7f30a56376c0,630380,630380,53869,5043048,65536,590581195,4863819,0,2364224928,12076634586306950,12076634586488795,12076634586899354,12076634586946790
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,937062,937067,4194304,256,0,0,20,24,314816,0x7f31b1191a00,0x7f30a5637700,2331940,2331940,149601,18655528,65536,2284557933,18495718,0,9140053388,12076634586979761,12076634587190394,12076634588740950,12076634588791461
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,937062,937067,4194304,256,0,0,20,24,317568,0x7f31b1191900,0x7f30a5637740,1199868,1199868,85074,9598952,65536,1161498246,9433358,0,4647813612,12076634588825635,12076634589030229,12076634589826548,12076634589875217
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,937062,937067,4194304,256,0,0,12,24,320320,0x7f31b1191800,0x7f30a5637780,639124,639124,50051,5113000,65536,608084295,4952297,0,2434171872,12076634589900133,12076634590105267,12076634590520306,12076634590569148
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,937062,937067,4194304,256,0,0,12,24,324096,0x7f31b1191700,0x7f30a56377c0,1757892,1757892,117158,14063144,65536,1714873517,13896555,0,6861319168,12076634590598723,12076634590790705,12076634591950063,12076634592004989
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,937062,937067,4194304,256,0,0,12,24,328896,0x7f31b1191600,0x7f30a5637800,1197780,1197780,82504,9582248,65536,1162231712,9420247,0,4650752948,12076634592045584,12076634592226382,12076634593012780,12076634593059921
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,937062,937067,4194304,256,0,0,20,24,330112,0x7f31b1191500,0x7f30a5637840,4583812,4583812,211273,36670504,65536,4515494636,36504397,0,18063799832,12076634593107028,12076634593282380,12076634596337893,12076634596388553
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,937062,937067,4194304,256,0,0,20,24,332864,0x7f31b1191400,0x7f30a5637880,2324436,2324436,151493,18595496,65536,2275127854,18421263,0,9102333000,12076634596420652,12076634596617732,12076634598164129,12076634598235348
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,937062,937067,4194304,256,0,0,12,24,335616,0x7f31b1191300,0x7f30a56378c0,1201508,1201508,82495,9612072,65536,1164122494,9454092,0,4658313948,12076634598267928,12076634598462688,12076634599253246,12076634599321308
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,937062,937067,4194304,256,0,0,12,24,339392,0x7f31b1191a00,0x7f30a5637900,3443268,3443268,214620,27546152,65536,3385357309,27381420,0,13543259488,12076634599342307,12076634599558206,12076634601841081,12076634601909913
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,937062,937067,4194304,256,0,0,12,24,344192,0x7f31b1191900,0x7f30a5637940,2323188,2323188,149197,18585512,65536,2274824901,18413418,0,9101128852,12076634601955628,12076634602146200,12076634603681556,12076634603750837
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,937062,937067,4194304,256,0,0,20,24,345408,0x7f31b1191800,0x7f30a5637980,9085596,9085596,472686,72684776,65536,8976560945,72523826,0,35908064460,12076634603782336,12076634603982356,12076634610042502,12076634610114464
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,937062,937067,4194304,256,0,0,20,24,348160,0x7f31b1191700,0x7f30a56379c0,4572572,4572572,211846,36580584,65536,4502571004,36416224,0,18012108720,12076634610150401,12076634610350021,12076634613397535,12076634613464596
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,937062,937067,4194304,256,0,0,12,24,350912,0x7f31b1191600,0x7f30a5637a00,2327092,2327092,149864,18616744,65536,2280060719,18455117,0,9122067764,12076634613497297,12076634613694974,12076634615234810,12076634615302405
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,937062,937067,4194304,256,0,0,12,24,0,0x7f31b1191500,0x7f30a5637a40,6811828,6811828,339834,54494632,65536,6722926938,54334488,0,26893535824,12076634615338832,12076634615533667,12076634620063098,12076634620137478
1 Index KernelName gpu-id queue-id queue-index pid tid grd wgr lds scr vgpr sgpr fbar sig obj GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES DispatchNs BeginNs EndNs CompleteNs
2 0 __amd_rocclr_fillBuffer.kd 0 0 0 937062 937067 33554432 256 0 0 8 32 6464 0x0 0x7f30a5604180 499674 499674 16219 3997400 524288 371768834 3801967 0 1501859028 12076634246773666 12076634492293789 12076634492615709 12076634492722711
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 937062 937067 32768 256 0 0 24 24 12480 0x0 0x7f30a5635100 27467 27467 20214 219744 512 1126759 75366 0 4521000 12076634507281913 12076634507609674 12076634507615914 12076634507624380
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 4 937062 937067 4194304 256 0 0 24 24 12928 0x7f31b1191900 0x7f30a5635140 217853 217853 21633 1742832 65536 133671007 1576099 0 536498696 12076634507695903 12076634507934314 12076634508067113 12076634508071402
5 3 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 6 937062 937067 4194304 256 0 0 36 24 13632 0x7f31b1191800 0x7f30a5635180 389621 389621 26804 3116976 65536 253060814 2948271 0 1014058364 12076634508150749 12076634508354473 12076634508602952 12076634508672009
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 8 937062 937067 4194304 256 0 0 28 24 14080 0x7f31b1191700 0x7f30a56351c0 403772 403772 26436 3230184 65536 276105211 3052243 0 1106238632 12076634508705912 12076634508912072 12076634509168551 12076634509238653
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 10 937062 937067 4194304 256 0 0 24 24 14528 0x7f31b1191600 0x7f30a5635200 217957 217957 19106 1743664 65536 133545621 1580634 0 535998284 12076634509266064 12076634509473830 12076634509607270 12076634509610645
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 12 937062 937067 4194304 256 0 0 24 24 14976 0x7f31b1191500 0x7f30a5635240 229069 229069 19969 1832560 65536 121094689 1662134 0 486187148 12076634509672260 12076634509869669 12076634510009989 12076634510013484
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 14 937062 937067 4194304 256 0 0 24 24 15424 0x7f31b1191400 0x7f30a5635280 212108 212108 18602 1696872 65536 156194765 1531178 0 626596552 12076634510103422 12076634510288548 12076634510418468 12076634510421754
10 8 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 16 937062 937067 4194304 256 0 0 28 24 16128 0x7f31b1191300 0x7f30a56352c0 395493 395493 31193 3163952 65536 350214228 2994677 0 1402673352 12076634510485032 12076634510682148 12076634510933987 12076634510974372
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 18 937062 937067 4194304 256 0 0 28 24 16832 0x7f31b1191a00 0x7f30a5635300 467516 467516 17173 3740136 65536 304554434 3042045 0 1220032660 12076634511021389 12076634511221666 12076634511520386 12076634511586971
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 20 937062 937067 4194304 256 0 0 24 24 17536 0x7f31b1191900 0x7f30a5635340 225357 225357 22606 1802864 65536 126884404 1624746 0 509347128 12076634511614202 12076634511821665 12076634511958625 12076634511961738
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 22 937062 937067 4194304 256 0 0 24 24 18240 0x7f31b1191800 0x7f30a5635380 214853 214853 19943 1718832 65536 138156049 1552593 0 554439388 12076634512019917 12076634512227264 12076634512358624 12076634512362043
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 24 937062 937067 4194304 256 0 0 24 24 18944 0x7f31b1191700 0x7f30a56353c0 212085 212085 21709 1696688 65536 162677854 1518896 0 652530312 12076634512440970 12076634512621503 12076634512750303 12076634512753651
15 13 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 26 937062 937067 4194304 256 0 0 28 24 19904 0x7f31b1191600 0x7f30a5635400 448589 448589 14903 3588720 65536 352429805 2980195 0 1411536664 12076634512815597 12076634513007902 12076634513294302 12076634513361963
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 28 937062 937067 4194304 256 0 0 28 24 20608 0x7f31b1191500 0x7f30a5635440 398365 398365 30407 3186928 65536 322399376 3015454 0 1291412136 12076634513388011 12076634513596861 12076634513850621 12076634513916414
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 30 937062 937067 4194304 256 0 0 24 24 21312 0x7f31b1191400 0x7f30a5635480 212733 212733 21416 1701872 65536 152200936 1534437 0 610620496 12076634513941962 12076634514154300 12076634514284220 12076634514287725
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 32 937062 937067 4194304 256 0 0 24 24 22016 0x7f31b1191300 0x7f30a56354c0 212636 212636 21337 1701096 65536 160391048 1536825 0 643379376 12076634514348127 12076634514545339 12076634514675419 12076634514678532
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 34 937062 937067 4194304 256 0 0 24 24 22720 0x7f31b1191a00 0x7f30a5635500 222621 222621 21873 1780976 65536 144958356 1613854 0 581645868 12076634514752189 12076634514932378 12076634515069178 12076634515072334
20 18 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 36 937062 937067 4194304 256 0 0 28 24 23680 0x7f31b1191900 0x7f30a5635540 397556 397556 30136 3180456 65536 341121024 3002753 0 1366301448 12076634515133218 12076634515327737 12076634515581337 12076634515646482
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 38 937062 937067 4194304 256 0 0 28 24 24384 0x7f31b1191800 0x7f30a5635580 403172 403172 24087 3225384 65536 224707461 3040116 0 900648000 12076634515675667 12076634515871416 12076634516129336 12076634516199712
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 40 937062 937067 4194304 256 0 0 24 24 25088 0x7f31b1191700 0x7f30a56355c0 216284 216284 24062 1730280 65536 126988676 1563585 0 509770336 12076634516228164 12076634516426135 12076634516558295 12076634516561545
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 42 937062 937067 4194304 256 0 0 24 24 25792 0x7f31b1191600 0x7f30a5635600 219124 219124 22867 1753000 65536 136862429 1589426 0 549267012 12076634516622708 12076634516813174 12076634516948054 12076634516951169
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 44 937062 937067 4194304 256 0 0 24 24 26496 0x7f31b1191500 0x7f30a5635640 213709 213709 22349 1709680 65536 157553694 1533157 0 632031676 12076634517030537 12076634517211413 12076634517341493 12076634517344561
25 23 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 46 937062 937067 4194304 256 0 0 28 24 27712 0x7f31b1191400 0x7f30a5635680 399981 399981 28230 3199856 65536 292218439 3025047 0 1170691640 12076634517402739 12076634517594932 12076634517850932 12076634517917136
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 48 937062 937067 4194304 256 0 0 28 24 28416 0x7f31b1191300 0x7f30a56356c0 405413 405413 28751 3243312 65536 293488110 3058758 0 1175768556 12076634517942824 12076634518149171 12076634518407570 12076634518473942
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 50 937062 937067 4194304 256 0 0 24 24 29120 0x7f31b1191a00 0x7f30a5635700 210541 210541 18560 1684336 65536 158231458 1524200 0 634744128 12076634518498998 12076634518696210 12076634518825490 12076634518828672
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 52 937062 937067 4194304 256 0 0 24 24 30080 0x7f31b1191900 0x7f30a5635740 221165 221165 25093 1769328 65536 153672197 1587171 0 616501944 12076634518889094 12076634519077649 12076634519212209 12076634519215481
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 54 937062 937067 4194304 256 0 0 24 24 30784 0x7f31b1191800 0x7f30a5635780 214733 214733 20244 1717872 65536 146270057 1557059 0 586895320 12076634519290751 12076634519467568 12076634519599568 12076634519602501
30 28 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 56 937062 937067 4194304 256 0 0 28 24 32000 0x7f31b1191700 0x7f30a56357c0 395148 395148 31161 3161192 65536 348917173 2987788 0 1397488220 12076634519664046 12076634519856527 12076634520109807 12076634520179775
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 58 937062 937067 4194304 256 0 0 28 24 32960 0x7f31b1191600 0x7f30a5635800 391717 391717 30699 3133744 65536 352352859 2970795 0 1411229772 12076634520210833 12076634520405326 12076634520656205 12076634520723025
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 60 937062 937067 4194304 256 0 0 24 24 33920 0x7f31b1191500 0x7f30a5635840 211165 211165 22356 1689328 65536 159141992 1519622 0 638391120 12076634520747351 12076634520946445 12076634521075405 12076634521078877
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 62 937062 937067 4194304 256 0 0 24 24 34880 0x7f31b1191400 0x7f30a5635880 222669 222669 22358 1781360 65536 140744300 1613811 0 564813204 12076634521142015 12076634521321964 12076634521459724 12076634521462892
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 64 937062 937067 4194304 256 0 0 24 24 35840 0x7f31b1191300 0x7f30a56358c0 210276 210276 22634 1682216 65536 138811194 1514446 0 557073360 12076634521536088 12076634521712523 12076634521841163 12076634521844321
35 33 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 66 937062 937067 4194304 256 0 0 28 24 37312 0x7f31b1191a00 0x7f30a5635900 410381 410381 24119 3283056 65536 309213186 3095322 0 1238665668 12076634521904974 12076634522099402 12076634522362922 12076634522429620
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 68 937062 937067 4194304 256 0 0 28 24 38272 0x7f31b1191900 0x7f30a5635940 397700 397700 29036 3181608 65536 290946828 3013211 0 1165600192 12076634522455268 12076634522659721 12076634522913640 12076634522980154
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 70 937062 937067 4194304 256 0 0 24 24 39232 0x7f31b1191800 0x7f30a5635980 222484 222484 22018 1779880 65536 128990349 1612365 0 517801864 12076634523013546 12076634523210600 12076634523347879 12076634523351094
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 72 937062 937067 4194304 256 0 0 24 24 40192 0x7f31b1191700 0x7f30a56359c0 222764 222764 24204 1782120 65536 146331742 1615165 0 587163692 12076634523411156 12076634523601639 12076634523738919 12076634523742191
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 74 937062 937067 4194304 256 0 0 24 24 41152 0x7f31b1191600 0x7f30a5635a00 212021 212021 22550 1696176 65536 157151524 1525336 0 630423560 12076634523815207 12076634523991078 12076634524121478 12076634524125254
40 38 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 76 937062 937067 4194304 256 0 0 28 24 42624 0x7f31b1191500 0x7f30a5635a40 401045 401045 26402 3208368 65536 336390145 3004654 0 1347376740 12076634524185225 12076634524375077 12076634524632037 12076634524698570
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 78 937062 937067 4194304 256 0 0 28 24 43584 0x7f31b1191400 0x7f30a5635a80 401900 401900 26390 3215208 65536 295687943 3049472 0 1184568052 12076634524722816 12076634524918436 12076634525176195 12076634525244576
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 80 937062 937067 4194304 256 0 0 24 24 44544 0x7f31b1191300 0x7f30a5635ac0 211773 211773 25302 1694192 65536 150606101 1519106 0 604274304 12076634525273139 12076634525467875 12076634525597154 12076634525600558
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 82 937062 937067 4194304 256 0 0 24 24 45760 0x7f31b1191a00 0x7f30a5635b00 220996 220996 25671 1767976 65536 155539914 1586010 0 623980732 12076634525660279 12076634525852834 12076634525988034 12076634525991365
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 84 937062 937067 4194304 256 0 0 24 24 46720 0x7f31b1191900 0x7f30a5635b40 218309 218309 23155 1746480 65536 153186453 1572643 0 614577888 12076634526065333 12076634526243073 12076634526376673 12076634526380178
45 43 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 86 937062 937067 4194304 256 0 0 28 24 48448 0x7f31b1191800 0x7f30a5635b80 413652 413652 33352 3309224 65536 288767588 3135220 0 1156887128 12076634526440901 12076634526625632 12076634526892192 12076634526958564
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 88 937062 937067 4194304 256 0 0 28 24 49408 0x7f31b1191700 0x7f30a5635bc0 398316 398316 33638 3186536 65536 340782112 3013266 0 1364942872 12076634526986887 12076634527187231 12076634527441950 12076634527482839
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 90 937062 937067 4194304 256 0 0 24 24 50368 0x7f31b1191600 0x7f30a5635c00 205276 205276 21119 1642216 65536 171403607 1481515 0 687438856 12076634527516492 12076634527715070 12076634527841149 12076634527844392
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 92 937062 937067 4194304 256 0 0 24 24 51584 0x7f31b1191500 0x7f30a5635c40 220756 220756 26419 1766056 65536 159827176 1589517 0 641144504 12076634527905185 12076634528120349 12076634528256349 12076634528259995
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 94 937062 937067 4194304 256 0 0 24 24 52544 0x7f31b1191400 0x7f30a5635c80 214117 214117 22063 1712944 65536 148578942 1546808 0 596133776 12076634528333842 12076634528514748 12076634528646268 12076634528649429
50 48 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 96 937062 937067 4194304 256 0 0 28 24 54272 0x7f31b1191300 0x7f30a5635cc0 414036 414036 32477 3312296 65536 326939111 3126424 0 1309573220 12076634528709702 12076634528904027 12076634529170587 12076634529238565
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 98 937062 937067 4194304 256 0 0 28 24 55488 0x7f31b1191a00 0x7f30a5635d00 389733 389733 31059 3117872 65536 341729609 2953917 0 1368736252 12076634529266878 12076634529463066 12076634529713785 12076634529779682
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 100 937062 937067 4194304 256 0 0 24 24 56704 0x7f31b1191900 0x7f30a5635d40 219156 219156 22779 1753256 65536 151748826 1574610 0 608822620 12076634529804548 12076634530000025 12076634530134264 12076634530137818
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 102 937062 937067 4194304 256 0 0 24 24 58176 0x7f31b1191800 0x7f30a5635d80 223341 223341 26808 1786736 65536 159849644 1611787 0 641246944 12076634530199333 12076634530387384 12076634530525624 12076634530529216
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 104 937062 937067 4194304 256 0 0 24 24 59392 0x7f31b1191700 0x7f30a5635dc0 214917 214917 25443 1719344 65536 162346752 1524728 0 651208456 12076634530601581 12076634530778263 12076634530908023 12076634530911397
55 53 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 106 937062 937067 4194304 256 0 0 28 24 61376 0x7f31b1191600 0x7f30a5635e00 408484 408484 31258 3267880 65536 320329657 3092366 0 1283139824 12076634530971860 12076634531165142 12076634531428822 12076634531469916
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 108 937062 937067 4194304 256 0 0 28 24 62592 0x7f31b1191500 0x7f30a5635e40 392756 392756 33027 3142056 65536 334521193 2972456 0 1339901580 12076634531509049 12076634531687221 12076634531939700 12076634532015320
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 110 937062 937067 4194304 256 0 0 24 24 63808 0x7f31b1191400 0x7f30a5635e80 279308 279308 14600 2234472 65536 144221695 1546141 0 578708168 12076634532041669 12076634532250260 12076634532424979 12076634532428349
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 112 937062 937067 4194304 256 0 0 24 24 65280 0x7f31b1191300 0x7f30a5635ec0 226748 226748 29457 1813992 65536 178093356 1602668 0 714235712 12076634532488801 12076634532676339 12076634532814258 12076634532817633
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 114 937062 937067 4194304 256 0 0 24 24 66496 0x7f31b1191a00 0x7f30a5635f00 212613 212613 24369 1700912 65536 161056055 1531647 0 646065348 12076634532892883 12076634533076338 12076634533207058 12076634533210664
60 58 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 116 937062 937067 4194304 256 0 0 28 24 68480 0x7f31b1191900 0x7f30a5635f40 412309 412309 32858 3298480 65536 334313937 3122389 0 1339107212 12076634533272058 12076634533460977 12076634533726416 12076634533793017
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 118 937062 937067 4194304 256 0 0 28 24 69696 0x7f31b1191800 0x7f30a5635f80 398371 398371 32510 3186976 65536 340219487 3015834 0 1362692336 12076634533821500 12076634534015056 12076634534271375 12076634534338342
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 120 937062 937067 4194304 256 0 0 24 24 70912 0x7f31b1191700 0x7f30a5635fc0 228188 228188 26741 1825512 65536 149209986 1647545 0 598707016 12076634534364611 12076634534562895 12076634534702894 12076634534706386
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 122 937062 937067 4194304 256 0 0 24 24 72384 0x7f31b1191600 0x7f30a5636000 225708 225708 27996 1805672 65536 177250903 1624430 0 710843524 12076634534768331 12076634534956494 12076634535096813 12076634535100429
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 124 937062 937067 4194304 256 0 0 24 24 73600 0x7f31b1191500 0x7f30a5636040 211220 211220 22475 1689768 65536 160254032 1514284 0 642854776 12076634535174577 12076634535353933 12076634535483213 12076634535486688
65 63 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 126 937062 937067 4194304 256 0 0 28 24 75840 0x7f31b1191400 0x7f30a5636080 412789 412789 34054 3302320 65536 296733323 3121128 0 1188766220 12076634535547371 12076634535732812 12076634535999531 12076634536067077
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 128 937062 937067 4194304 256 0 0 28 24 77056 0x7f31b1191300 0x7f30a56360c0 398948 398948 26692 3191592 65536 249430262 3001335 0 999539228 12076634536092825 12076634536295051 12076634536551850 12076634536615818
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 130 937062 937067 4194304 256 0 0 24 24 78272 0x7f31b1191a00 0x7f30a5636100 219732 219732 21810 1757864 65536 146729488 1589753 0 588782344 12076634536640754 12076634536837610 12076634536973129 12076634536976529
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 132 937062 937067 4194304 256 0 0 24 24 80000 0x7f31b1191900 0x7f30a5636140 231853 231853 26909 1854832 65536 196977740 1689369 0 789781756 12076634537038584 12076634537226409 12076634537370248 12076634537373768
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 134 937062 937067 4194304 256 0 0 24 24 81216 0x7f31b1191800 0x7f30a5636180 217245 217245 22366 1737968 65536 149848899 1578330 0 601235936 12076634537446193 12076634537621608 12076634537755847 12076634537759095
70 68 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 136 937062 937067 4194304 256 0 0 28 24 83456 0x7f31b1191700 0x7f30a56361c0 412789 412789 33823 3302320 65536 328378877 3136724 0 1315331968 12076634537819016 12076634538011047 12076634538278246 12076634538344273
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 138 937062 937067 4194304 256 0 0 28 24 84928 0x7f31b1191600 0x7f30a5636200 443228 443228 14224 3545832 65536 352134637 2957912 0 1410361884 12076634538370261 12076634538570246 12076634538857285 12076634538923270
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 140 937062 937067 4194304 256 0 0 24 24 86400 0x7f31b1191500 0x7f30a5636240 222836 222836 24641 1782696 65536 145710036 1601147 0 584707564 12076634538947946 12076634539151204 12076634539287684 12076634539291164
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 142 937062 937067 4194304 256 0 0 24 24 88128 0x7f31b1191400 0x7f30a5636280 239925 239925 25988 1919408 65536 208509762 1760336 0 835909668 12076634539352438 12076634539539364 12076634539689443 12076634539692852
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 144 937062 937067 4194304 256 0 0 24 24 89600 0x7f31b1191300 0x7f30a56362c0 222461 222461 24485 1779696 65536 148799551 1614425 0 597037216 12076634539780374 12076634539956803 12076634540093762 12076634540097414
75 73 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 146 937062 937067 4194304 256 0 0 28 24 92096 0x7f31b1191a00 0x7f30a5636300 413860 413860 32816 3310888 65536 342079203 3146167 0 1370187588 12076634540157266 12076634540344802 12076634540613441 12076634540679657
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 148 937062 937067 4194304 256 0 0 28 24 93568 0x7f31b1191900 0x7f30a5636340 400508 400508 30364 3204072 65536 325601236 3033729 0 1304223612 12076634540707349 12076634540900960 12076634541159040 12076634541228759
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 150 937062 937067 4194304 256 0 0 24 24 95040 0x7f31b1191800 0x7f30a5636380 215420 215420 22810 1723368 65536 152585967 1559429 0 612212692 12076634541255168 12076634541456959 12076634541590079 12076634541593427
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 152 937062 937067 4194304 256 0 0 24 24 96768 0x7f31b1191700 0x7f30a56363c0 255541 255541 30610 2044336 65536 222286816 1859187 0 890991504 12076634541652958 12076634541839998 12076634541998398 12076634542006746
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 154 937062 937067 4194304 256 0 0 24 24 98240 0x7f31b1191600 0x7f30a5636400 216668 216668 22070 1733352 65536 155741010 1570265 0 624841512 12076634542076425 12076634542254077 12076634542388157 12076634542391301
80 78 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 156 937062 937067 4194304 256 0 0 28 24 100736 0x7f31b1191500 0x7f30a5636440 417628 417628 34074 3341032 65536 333216758 3118039 0 1334683008 12076634542450792 12076634542640317 12076634542910716 12076634542957294
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 158 937062 937067 4194304 256 0 0 28 24 102208 0x7f31b1191400 0x7f30a5636480 397324 397324 30824 3178600 65536 337128771 3018503 0 1350334456 12076634542981539 12076634543186555 12076634543443355 12076634543488522
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 160 937062 937067 4194304 256 0 0 24 24 103680 0x7f31b1191300 0x7f30a56364c0 225229 225229 24290 1801840 65536 142448607 1626904 0 571637828 12076634543530180 12076634543704954 12076634543843994 12076634543847129
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 162 937062 937067 4194304 256 0 0 24 24 105664 0x7f31b1191a00 0x7f30a5636500 262797 262797 28081 2102384 65536 233830271 1940837 0 937170592 12076634543909976 12076634544116153 12076634544281593 12076634544284773
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 164 937062 937067 4194304 256 0 0 24 24 107136 0x7f31b1191900 0x7f30a5636540 221141 221141 24416 1769136 65536 144513711 1597678 0 579896612 12076634544358721 12076634544537752 12076634544673752 12076634544677273
85 83 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 166 937062 937067 4194304 256 0 0 28 24 109888 0x7f31b1191800 0x7f30a5636580 408485 408485 36448 3267888 65536 324005800 3077103 0 1297869708 12076634544736423 12076634544931832 12076634545196471 12076634545265778
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 168 937062 937067 4194304 256 0 0 28 24 111360 0x7f31b1191700 0x7f30a56365c0 398084 398084 38085 3184680 65536 335870488 2989272 0 1345296084 12076634545291696 12076634545487190 12076634545741750 12076634545808177
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 170 937062 937067 4194304 256 0 0 24 24 112832 0x7f31b1191600 0x7f30a5636600 225389 225389 23366 1803120 65536 143201439 1633713 0 574668904 12076634545835267 12076634546034069 12076634546174229 12076634546177504
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 172 937062 937067 4194304 256 0 0 24 24 114816 0x7f31b1191500 0x7f30a5636640 274788 274788 30015 2198312 65536 245834907 2034390 0 985205140 12076634546240341 12076634546426388 12076634546599348 12076634546602735
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 174 937062 937067 4194304 256 0 0 24 24 116288 0x7f31b1191400 0x7f30a5636680 212845 212845 21768 1702768 65536 154990814 1519836 0 621814824 12076634546674859 12076634546851027 12076634546982387 12076634546985697
90 88 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 176 937062 937067 4194304 256 0 0 28 24 119040 0x7f31b1191300 0x7f30a56366c0 406924 406924 36478 3255400 65536 315620737 3056185 0 1264314736 12076634547046330 12076634547239506 12076634547502386 12076634547567880
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 178 937062 937067 4194304 256 0 0 28 24 120768 0x7f31b1191a00 0x7f30a5636700 395605 395605 32088 3164848 65536 318104197 2984256 0 1274235812 12076634547596163 12076634547788305 12076634548044305 12076634548112944
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 180 937062 937067 4194304 256 0 0 24 24 122496 0x7f31b1191900 0x7f30a5636740 228092 228092 25336 1824744 65536 143630960 1655089 0 576381056 12076634548138692 12076634548339344 12076634548480304 12076634548483744
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 182 937062 937067 4194304 256 0 0 24 24 124736 0x7f31b1191800 0x7f30a5636780 288765 288765 29964 2310128 65536 259925815 2149141 0 1041559524 12076634548543705 12076634548728143 12076634548911663 12076634548915016
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 184 937062 937067 4194304 256 0 0 24 24 126464 0x7f31b1191700 0x7f30a56367c0 226421 226421 25398 1811376 65536 145020314 1625891 0 581981220 12076634549021955 12076634549203822 12076634549343342 12076634549347000
95 93 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 186 937062 937067 4194304 256 0 0 20 24 127936 0x7f31b1191600 0x7f30a5636800 411885 411885 36923 3295088 65536 377379464 3118343 0 1511338396 12076634549406931 12076634549594221 12076634549861421 12076634549902813
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 188 937062 937067 4194304 256 0 0 28 24 129664 0x7f31b1191500 0x7f30a5636840 400772 400772 29019 3206184 65536 270661366 3012149 0 1084466864 12076634549939552 12076634550131340 12076634550390059 12076634550456674
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 190 937062 937067 4194304 256 0 0 24 24 131392 0x7f31b1191400 0x7f30a5636880 223493 223493 28641 1787952 65536 156747337 1596842 0 628841760 12076634550483403 12076634550681099 12076634550818218 12076634550821683
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 192 937062 937067 4194304 256 0 0 24 24 133632 0x7f31b1191300 0x7f30a56368c0 300748 300748 31432 2405992 65536 272500640 2248458 0 1091849984 12076634550885241 12076634551073738 12076634551264457 12076634551332072
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 194 937062 937067 4194304 256 0 0 24 24 135360 0x7f31b1191a00 0x7f30a5636900 221837 221837 24841 1774704 65536 154654268 1601667 0 620482812 12076634551376685 12076634551554377 12076634551691497 12076634551694897
100 98 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 196 937062 937067 4194304 256 0 0 20 24 136832 0x7f31b1191900 0x7f30a5636940 436893 436893 39784 3495152 65536 402285022 3324829 0 1610960776 12076634551755520 12076634551941416 12076634552225095 12076634552292028
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 198 937062 937067 4194304 256 0 0 28 24 138560 0x7f31b1191800 0x7f30a5636980 400429 400429 33584 3203440 65536 329960243 3008473 0 1321683344 12076634552320531 12076634552515655 12076634552773094 12076634552839366
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 200 937062 937067 4194304 256 0 0 24 24 140288 0x7f31b1191700 0x7f30a56369c0 220708 220708 27469 1765672 65536 151431805 1583632 0 607560160 12076634552864162 12076634553076133 12076634553212453 12076634553215966
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 202 937062 937067 4194304 256 0 0 24 24 142784 0x7f31b1191600 0x7f30a5636a00 330308 330308 32883 2642472 65536 300457787 2479819 0 1203689148 12076634553276469 12076634553467493 12076634553678052 12076634553744239
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 204 937062 937067 4194304 256 0 0 24 24 144768 0x7f31b1191500 0x7f30a5636a40 223524 223524 23556 1788200 65536 157776974 1611436 0 632997452 12076634553780316 12076634553964291 12076634554102531 12076634554106102
105 103 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 206 937062 937067 4194304 256 0 0 20 24 145728 0x7f31b1191400 0x7f30a5636a80 470173 470173 40408 3761392 65536 437901688 3595251 0 1753426996 12076634554166254 12076634554354531 12076634554661730 12076634554727688
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 208 937062 937067 4194304 256 0 0 28 24 147712 0x7f31b1191300 0x7f30a5636ac0 405245 405245 34161 3241968 65536 335140714 3063259 0 1342389428 12076634554754929 12076634554951169 12076634555213249 12076634555279745
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 210 937062 937067 4194304 256 0 0 24 24 149696 0x7f31b1191a00 0x7f30a5636b00 225836 225836 22182 1806696 65536 154006034 1634745 0 617898908 12076634555304291 12076634555503466 12076634555643946 12076634555651266
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 212 937062 937067 4194304 256 0 0 24 24 152192 0x7f31b1191900 0x7f30a5636b40 356653 356653 35781 2853232 65536 325389722 2683365 0 1303415364 12076634555706769 12076634555893704 12076634556121223 12076634556189638
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 214 937062 937067 4194304 256 0 0 24 24 154176 0x7f31b1191800 0x7f30a5636b80 218700 218700 25714 1749608 65536 154046907 1576350 0 618063224 12076634556229913 12076634556409383 12076634556544902 12076634556548375
110 108 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 216 937062 937067 4194304 256 0 0 20 24 155648 0x7f31b1191700 0x7f30a5636bc0 503797 503797 43958 4030384 65536 471894300 3865747 0 1889397832 12076634556611292 12076634556801222 12076634557130821 12076634557200308
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 218 937062 937067 4194304 256 0 0 28 24 157632 0x7f31b1191600 0x7f30a5636c00 407340 407340 28640 3258728 65536 312702803 3052368 0 1252629116 12076634557226436 12076634557424421 12076634557688420 12076634557729282
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 220 937062 937067 4194304 256 0 0 24 24 159616 0x7f31b1191500 0x7f30a5636c40 226132 226132 25877 1809064 65536 153078598 1635564 0 614185492 12076634557772462 12076634557950339 12076634558090179 12076634558093649
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 222 937062 937067 4194304 256 0 0 24 24 162368 0x7f31b1191400 0x7f30a5636c80 381924 381924 36449 3055400 65536 349844373 2887948 0 1401225252 12076634558156556 12076634558340738 12076634558586178 12076634558653100
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 224 937062 937067 4194304 256 0 0 24 24 164608 0x7f31b1191300 0x7f30a5636cc0 225636 225636 28452 1805096 65536 163004818 1620463 0 653901864 12076634558689598 12076634558868257 12076634559008577 12076634559012278
115 113 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 226 937062 937067 4194304 256 0 0 20 24 166336 0x7f31b1191a00 0x7f30a5636d00 575053 575053 46909 4600432 65536 542304783 4444623 0 2171037532 12076634559063984 12076634559260256 12076634559638336 12076634559704396
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 228 937062 937067 4194304 256 0 0 28 24 168576 0x7f31b1191900 0x7f30a5636d40 407580 407580 33723 3260648 65536 300540763 3069434 0 1203998740 12076634559729943 12076634559931455 12076634560195934 12076634560262333
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 230 937062 937067 4194304 256 0 0 24 24 170816 0x7f31b1191800 0x7f30a5636d80 221692 221692 25854 1773544 65536 161817687 1597624 0 649149348 12076634560287300 12076634560486494 12076634560624573 12076634560628034
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 232 937062 937067 4194304 256 0 0 24 24 174080 0x7f31b1191700 0x7f30a5636dc0 479652 479652 16068 3837224 65536 400919451 3297056 0 1605528676 12076634560680361 12076634560872413 12076634561182652 12076634561253146
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 234 937062 937067 4194304 256 0 0 24 24 176576 0x7f31b1191600 0x7f30a5636e00 226229 226229 27604 1809840 65536 171830292 1631065 0 689219544 12076634561291798 12076634561482171 12076634561622011 12076634561625890
120 118 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 236 937062 937067 4194304 256 0 0 20 24 177792 0x7f31b1191500 0x7f30a5636e40 642308 642308 49986 5138472 65536 610109508 4982908 0 2442259024 12076634561686523 12076634561873050 12076634562297370 12076634562320632
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 238 937062 937067 4194304 256 0 0 28 24 180288 0x7f31b1191400 0x7f30a5636e80 405085 405085 38149 3240688 65536 316171611 3009971 0 1266529976 12076634562375825 12076634562555289 12076634562816408 12076634562837233
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 240 937062 937067 4194304 256 0 0 24 24 182784 0x7f31b1191300 0x7f30a5636ec0 224084 224084 25472 1792680 65536 181419219 1619155 0 727554372 12076634562893057 12076634563075768 12076634563215447 12076634563219103
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 242 937062 937067 4194304 256 0 0 24 24 186304 0x7f31b1191a00 0x7f30a5636f00 486588 486588 42862 3892712 65536 454898081 3728515 0 1821450016 12076634563280988 12076634563480887 12076634563795926 12076634563817416
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 244 937062 937067 4194304 256 0 0 24 24 189312 0x7f31b1191900 0x7f30a5636f40 242541 242541 26466 1940336 65536 213332854 1779150 0 855228180 12076634563892296 12076634564077046 12076634564229205 12076634564232879
125 123 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 246 937062 937067 4194304 256 0 0 20 24 190784 0x7f31b1191800 0x7f30a5636f80 784108 784108 60015 6272872 65536 750338005 6105956 0 3003173004 12076634564285056 12076634564488245 12076634565005523 12076634565048666
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 248 937062 937067 4194304 256 0 0 28 24 193792 0x7f31b1191700 0x7f30a5636fc0 462325 462325 41381 3698608 65536 395240212 3527463 0 1582802604 12076634565094482 12076634565274643 12076634565577202 12076634565643924
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 250 937062 937067 4194304 256 0 0 24 24 196800 0x7f31b1191600 0x7f30a5637000 246109 246109 27784 1968880 65536 217168109 1806572 0 870553892 12076634565678829 12076634565865202 12076634566019761 12076634566023700
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 252 937062 937067 4194304 256 0 0 24 24 201088 0x7f31b1191500 0x7f30a5637040 592933 592933 48021 4743472 65536 560063963 4582944 0 2242112928 12076634566085235 12076634566269841 12076634566656240 12076634566723241
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 254 937062 937067 4194304 256 0 0 24 24 204608 0x7f31b1191400 0x7f30a5637080 280285 280285 32285 2242288 65536 249208230 2057641 0 998719992 12076634566764228 12076634566942639 12076634567118159 12076634567121853
130 128 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 256 937062 937067 4194304 256 0 0 20 24 206080 0x7f31b1191300 0x7f30a56370c0 941756 941756 14101 7534056 65536 890432974 7231462 0 3563553184 12076634567184139 12076634567381838 12076634568006157 12076634568057143
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 258 937062 937067 4194304 256 0 0 28 24 209600 0x7f31b1191a00 0x7f30a5637100 507660 507660 43040 4061288 65536 461305602 3890339 0 1847067668 12076634568083071 12076634568279756 12076634568611435 12076634568675082
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 260 937062 937067 4194304 256 0 0 24 24 213120 0x7f31b1191900 0x7f30a5637140 280405 280405 28596 2243248 65536 253336450 2087346 0 1015233064 12076634568699477 12076634568894155 12076634569072874 12076634569076559
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 262 937062 937067 4194304 256 0 0 24 24 218176 0x7f31b1191800 0x7f30a5637180 697597 697597 54537 5580784 65536 664191411 5417658 0 2658618900 12076634569137282 12076634569324714 12076634569780713 12076634569820142
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 264 937062 937067 4194304 256 0 0 24 24 222208 0x7f31b1191700 0x7f30a56371c0 311908 311908 30116 2495272 65536 284878944 2343878 0 1141402000 12076634569871588 12076634570055592 12076634570255592 12076634570322897
135 133 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 266 937062 937067 4194304 256 0 0 20 24 223936 0x7f31b1191600 0x7f30a5637200 1074565 1074565 15319 8596528 65536 1026825089 8361806 0 4109121200 12076634570348595 12076634570543431 12076634571254629 12076634571321024
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 268 937062 937067 4194304 256 0 0 28 24 227968 0x7f31b1191500 0x7f30a5637240 569653 569653 48021 4557232 65536 530371934 4383864 0 2123328560 12076634571346331 12076634571549829 12076634571923908 12076634571989848
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 270 937062 937067 4194304 256 0 0 24 24 232000 0x7f31b1191400 0x7f30a5637280 317245 317245 31036 2537968 65536 289326641 2381524 0 1159204808 12076634572019904 12076634572227907 12076634572431907 12076634572500057
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 272 937062 937067 4194304 256 0 0 24 24 237824 0x7f31b1191300 0x7f30a56372c0 802213 802213 60272 6417712 65536 768040034 6253577 0 3074015504 12076634572524202 12076634572719586 12076634573245505 12076634573312158
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 274 937062 937067 4194304 256 0 0 24 24 242368 0x7f31b1191a00 0x7f30a5637300 347797 347797 32627 2782384 65536 318789642 2623936 0 1277049252 12076634573353665 12076634573529664 12076634573753184 12076634573818800
140 138 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 276 937062 937067 4194304 256 0 0 20 24 243584 0x7f31b1191900 0x7f30a5637340 1208453 1208453 86374 9667632 65536 1168332366 9488416 0 4675150496 12076634573846241 12076634574053983 12076634574853821 12076634574922784
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 278 937062 937067 4194304 256 0 0 28 24 248128 0x7f31b1191800 0x7f30a5637380 638796 638796 50862 5110376 65536 604054320 4952300 0 2418060228 12076634574954663 12076634575159741 12076634575582300 12076634575648644
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 280 937062 937067 4194304 256 0 0 24 24 252672 0x7f31b1191700 0x7f30a56373c0 353580 353580 33948 2828648 65536 324112464 2665953 0 1298340420 12076634575673781 12076634575870139 12076634576097178 12076634576165074
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 282 937062 937067 4194304 256 0 0 24 24 259264 0x7f31b1191600 0x7f30a5637400 907972 907972 66668 7263784 65536 871808204 7100172 0 3489082580 12076634576192956 12076634576392698 12076634576989176 12076634577055932
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 284 937062 937067 4194304 256 0 0 24 24 264832 0x7f31b1191500 0x7f30a5637440 420029 420029 39580 3360240 65536 386607378 3170786 0 1548333812 12076634577092850 12076634577279576 12076634577549015 12076634577615372
145 143 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 286 937062 937067 4194304 256 0 0 20 24 266304 0x7f31b1191400 0x7f30a5637480 1486188 1486188 99240 11889512 65536 1446440968 11735967 0 5787585524 12076634577639457 12076634577835895 12076634578822292 12076634578892327
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 288 937062 937067 4194304 256 0 0 28 24 271872 0x7f31b1191300 0x7f30a56374c0 779469 779469 62018 6235760 65536 741190979 6050695 0 2966600364 12076634578918406 12076634579119252 12076634579634931 12076634579684581
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 290 937062 937067 4194304 256 0 0 24 24 277440 0x7f31b1191a00 0x7f30a5637500 421452 421452 38444 3371624 65536 390033242 3211048 0 1562019048 12076634579709507 12076634579904850 12076634580177649 12076634580247919
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 292 937062 937067 4194304 256 0 0 12 24 279936 0x7f31b1191900 0x7f30a5637540 1125589 1125589 79521 9004720 65536 1088541766 8842982 0 4355992024 12076634580276031 12076634580473649 12076634581212847 12076634581268868
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 294 937062 937067 4194304 256 0 0 24 24 286528 0x7f31b1191800 0x7f30a5637580 487197 487197 42516 3897584 65536 454902748 3736289 0 1821503676 12076634581309874 12076634581489006 12076634581805326 12076634581854848
150 148 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 296 937062 937067 4194304 256 0 0 20 24 288000 0x7f31b1191700 0x7f30a56375c0 1768453 1768453 117917 14147632 65536 1724990770 13979184 0 6901783928 12076634581883371 12076634582092845 12076634583267082 12076634583563887
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 298 937062 937067 4194304 256 0 0 32 24 294592 0x7f31b1191600 0x7f30a5637600 918692 918692 64768 7349544 65536 807675935 7172718 0 3232557552 12076634583598371 12076634583798721 12076634584410400 12076634584459012
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 300 937062 937067 4194304 256 0 0 24 24 301184 0x7f31b1191500 0x7f30a5637640 495188 495188 44861 3961512 65536 462565391 3791743 0 1852172552 12076634584494178 12076634584679519 12076634585000798 12076634585094735
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 302 937062 937067 4194304 256 0 0 12 24 304960 0x7f31b1191400 0x7f30a5637680 1336324 1336324 91200 10690600 65536 1298621629 10526806 0 5196313352 12076634585122847 12076634585329598 12076634586208316 12076634586259401
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 304 937062 937067 4194304 256 0 0 24 24 313600 0x7f31b1191300 0x7f30a56376c0 630380 630380 53869 5043048 65536 590581195 4863819 0 2364224928 12076634586306950 12076634586488795 12076634586899354 12076634586946790
155 153 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 306 937062 937067 4194304 256 0 0 20 24 314816 0x7f31b1191a00 0x7f30a5637700 2331940 2331940 149601 18655528 65536 2284557933 18495718 0 9140053388 12076634586979761 12076634587190394 12076634588740950 12076634588791461
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 308 937062 937067 4194304 256 0 0 20 24 317568 0x7f31b1191900 0x7f30a5637740 1199868 1199868 85074 9598952 65536 1161498246 9433358 0 4647813612 12076634588825635 12076634589030229 12076634589826548 12076634589875217
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 310 937062 937067 4194304 256 0 0 12 24 320320 0x7f31b1191800 0x7f30a5637780 639124 639124 50051 5113000 65536 608084295 4952297 0 2434171872 12076634589900133 12076634590105267 12076634590520306 12076634590569148
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 312 937062 937067 4194304 256 0 0 12 24 324096 0x7f31b1191700 0x7f30a56377c0 1757892 1757892 117158 14063144 65536 1714873517 13896555 0 6861319168 12076634590598723 12076634590790705 12076634591950063 12076634592004989
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 314 937062 937067 4194304 256 0 0 12 24 328896 0x7f31b1191600 0x7f30a5637800 1197780 1197780 82504 9582248 65536 1162231712 9420247 0 4650752948 12076634592045584 12076634592226382 12076634593012780 12076634593059921
160 158 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 316 937062 937067 4194304 256 0 0 20 24 330112 0x7f31b1191500 0x7f30a5637840 4583812 4583812 211273 36670504 65536 4515494636 36504397 0 18063799832 12076634593107028 12076634593282380 12076634596337893 12076634596388553
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 318 937062 937067 4194304 256 0 0 20 24 332864 0x7f31b1191400 0x7f30a5637880 2324436 2324436 151493 18595496 65536 2275127854 18421263 0 9102333000 12076634596420652 12076634596617732 12076634598164129 12076634598235348
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 320 937062 937067 4194304 256 0 0 12 24 335616 0x7f31b1191300 0x7f30a56378c0 1201508 1201508 82495 9612072 65536 1164122494 9454092 0 4658313948 12076634598267928 12076634598462688 12076634599253246 12076634599321308
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 322 937062 937067 4194304 256 0 0 12 24 339392 0x7f31b1191a00 0x7f30a5637900 3443268 3443268 214620 27546152 65536 3385357309 27381420 0 13543259488 12076634599342307 12076634599558206 12076634601841081 12076634601909913
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 324 937062 937067 4194304 256 0 0 12 24 344192 0x7f31b1191900 0x7f30a5637940 2323188 2323188 149197 18585512 65536 2274824901 18413418 0 9101128852 12076634601955628 12076634602146200 12076634603681556 12076634603750837
165 163 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 326 937062 937067 4194304 256 0 0 20 24 345408 0x7f31b1191800 0x7f30a5637980 9085596 9085596 472686 72684776 65536 8976560945 72523826 0 35908064460 12076634603782336 12076634603982356 12076634610042502 12076634610114464
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 328 937062 937067 4194304 256 0 0 20 24 348160 0x7f31b1191700 0x7f30a56379c0 4572572 4572572 211846 36580584 65536 4502571004 36416224 0 18012108720 12076634610150401 12076634610350021 12076634613397535 12076634613464596
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 330 937062 937067 4194304 256 0 0 12 24 350912 0x7f31b1191600 0x7f30a5637a00 2327092 2327092 149864 18616744 65536 2280060719 18455117 0 9122067764 12076634613497297 12076634613694974 12076634615234810 12076634615302405
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 332 937062 937067 4194304 256 0 0 12 24 0 0x7f31b1191500 0x7f30a5637a40 6811828 6811828 339834 54494632 65536 6722926938 54334488 0 26893535824 12076634615338832 12076634615533667 12076634620063098 12076634620137478