169 lines
53 KiB
CSV
169 lines
53 KiB
CSV
Index,KernelName,gpu-id,queue-id,queue-index,pid,tid,grd,wgr,lds,scr,vgpr,sgpr,fbar,sig,obj,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,CPC_ME1_DC0_SPI_BUSY,DispatchNs,BeginNs,EndNs,CompleteNs
|
|
0,__amd_rocclr_fillBufferAligned.kd,0,0,0,160404,160404,33554432,256,0,0,4,32,4160,0x0,0x7fa4dea04280,3054296,2965383,524288,381786,381786,381786,0,302,381283,8404,518,1217,380421,0,8701,369195,16455596020581,16459814018450,16459814257808,16455745747285
|
|
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,160404,160404,32768,256,0,0,12,24,13888,0x0,0x7fa4dea23f80,267264,159891,512,33407,33407,33407,0,302,32864,11021,515,1348,32461,0,29902,496,16455750923166,16459819051039,16459819064319,16455751060640
|
|
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,160404,160404,4194304,256,0,0,12,24,14336,0x7fa4e1915380,0x7fa4dea23fc0,1319368,1215750,65536,164920,164920,164920,0,302,164718,9883,1995,2856,161253,0,14318,148256,16455751096469,16459819137118,16459819229437,16455751438626
|
|
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,160404,160404,4194304,256,0,0,16,24,15040,0x7fa4e1915200,0x7fa4dea24000,2489752,2379046,65536,311218,311218,311218,0,302,307656,11070,1988,2776,305679,0,23304,282357,16455751475174,16459819264477,16459819445275,16455751854050
|
|
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,160404,160404,4194304,256,0,0,16,24,15488,0x7fa4e1915080,0x7fa4dea24040,2469336,2369608,65536,308666,308666,308666,0,302,311430,11212,1984,2854,306219,0,25159,282507,16455751887389,16459819471035,16459819650713,16455752260654
|
|
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,160404,160404,4194304,256,0,0,12,24,15936,0x7fa4df17df00,0x7fa4dea24080,1323944,1218548,65536,165492,165492,165492,0,302,164586,10023,1998,2765,162934,0,13812,149631,16455752292943,16459819675993,16459819769592,16455752574662
|
|
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,160404,160404,4194304,256,0,0,12,24,16384,0x7fa4df17dd80,0x7fa4dea240c0,1317936,1212442,65536,164741,164741,164741,0,302,164490,9682,1993,2872,160757,0,14503,148317,16455752607511,16459819795351,16459819887190,16455752884450
|
|
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,160404,160404,4194304,256,0,0,12,24,17088,0x7fa4df17dc00,0x7fa4dea24100,1312856,1212873,65536,164106,164106,164106,0,302,163192,9986,2023,2782,160795,0,14269,145183,16455752929538,16459819927030,16459820019029,16455753193628
|
|
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,160404,160404,4194304,256,0,0,16,24,17792,0x7fa4df17da80,0x7fa4dea24140,2473128,2368675,65536,309140,309140,309140,0,302,309598,11293,1984,3102,308107,0,23994,282600,16455753225227,16459820052469,16459820231827,16455753592963
|
|
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,160404,160404,4194304,256,0,0,16,24,18496,0x7fa4df17d900,0x7fa4dea24180,2468464,2363247,65536,308557,308557,308557,0,302,310648,10897,1999,2856,303659,0,23464,283744,16455753624442,16459820274067,16459820454065,16455754007727
|
|
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,160404,160404,4194304,256,0,0,16,24,19200,0x7fa4df17d780,0x7fa4dea241c0,1323328,1219401,65536,165415,165415,165415,0,302,164270,10099,2000,2872,161555,0,13902,146548,16455754039826,16459820482705,16459820575984,16455754352924
|
|
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,160404,160404,4194304,256,0,0,16,24,19904,0x7fa4df17d600,0x7fa4dea24200,1332256,1227054,65536,166531,166531,166531,0,302,164304,9919,1995,2870,161729,0,14747,147355,16455754385552,16459820608143,16459820701422,16455754668651
|
|
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,160404,160404,4194304,256,0,0,12,24,20608,0x7fa4e1915480,0x7fa4dea24240,1312112,1206560,65536,164013,164013,164013,0,302,163256,9919,2000,2862,160085,0,15267,147399,16455754710170,16459820745582,16459820839181,16455754981889
|
|
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,160404,160404,4194304,256,0,0,16,24,21312,0x7fa4e1915300,0x7fa4dea24280,2480504,2379791,65536,310062,310062,310062,0,302,308304,11324,2129,2854,306595,0,24884,282739,16455755016558,16459820871501,16459821050859,16455755380344
|
|
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,160404,160404,4194304,256,0,0,16,24,22016,0x7fa4e1915180,0x7fa4dea242c0,2462736,2356547,65536,307841,307841,307841,0,302,305976,10794,1995,3563,303584,0,23454,283988,16455755413363,16459821083179,16459821263977,16455755750410
|
|
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,160404,160404,4194304,256,0,0,16,24,22720,0x7fa4e1915000,0x7fa4dea24300,1313352,1214777,65536,164168,164168,164168,0,302,164008,9994,2003,2866,160013,0,15081,148687,16455755783578,16459821306856,16459821400775,16455756031679
|
|
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,160404,160404,4194304,256,0,0,12,24,23424,0x7fa4df17de80,0x7fa4dea24340,1312360,1209599,65536,164044,164044,164044,0,302,163574,10005,1992,2871,159639,0,14973,146142,16455756063728,16459821431655,16459821525254,16455756319398
|
|
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,160404,160404,4194304,256,0,0,12,24,24128,0x7fa4df17dd00,0x7fa4dea24380,1303488,1203745,65536,162935,162935,162935,0,302,162441,9789,1985,3348,159632,0,15221,145411,16455756359276,16459821558694,16459821652293,16455756602627
|
|
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,160404,160404,4194304,256,0,0,16,24,24832,0x7fa4df17db80,0x7fa4dea243c0,2472760,2367442,65536,309094,309094,309094,0,302,308963,11266,1985,2728,306896,0,24611,281824,16455756636326,16459821691653,16459821870851,16455756971193
|
|
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,160404,160404,4194304,256,0,0,16,24,25536,0x7fa4df17da00,0x7fa4dea24400,2445032,2341714,65536,305628,305628,305628,0,302,307625,10898,1985,3275,301991,0,22414,283687,16455757003461,16459821900130,16459822079809,16455757339179
|
|
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,160404,160404,4194304,256,0,0,12,24,26240,0x7fa4df17d880,0x7fa4dea24440,1316024,1210007,65536,164502,164502,164502,0,302,163087,9709,2450,2951,160039,0,15364,147073,16455757371837,16459822111808,16459822204927,16455757627187
|
|
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,160404,160404,4194304,256,0,0,12,24,26944,0x7fa4df17d700,0x7fa4dea24480,1308648,1208056,65536,163580,163580,163580,0,302,162705,9984,1991,3459,161393,0,14495,146670,16455757660616,16459822234207,16459822327966,16455757910867
|
|
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,160404,160404,4194304,256,0,0,12,24,27648,0x7fa4e1915580,0x7fa4dea244c0,1314040,1209377,65536,164254,164254,164254,0,302,161513,10164,2311,2886,159722,0,15040,146331,16455757951565,16459822362846,16459822454525,16455758198185
|
|
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,160404,160404,4194304,256,0,0,16,24,28608,0x7fa4e1915400,0x7fa4dea24500,2461808,2359696,65536,307725,307725,307725,0,302,306681,11332,1988,2879,305571,0,24570,280073,16455758233164,16459822482685,16459822663003,16455758573501
|
|
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,160404,160404,4194304,256,0,0,16,24,29312,0x7fa4e1915280,0x7fa4dea24540,2445408,2346821,65536,305675,305675,305675,0,302,305411,10994,1984,2850,305172,0,23174,283305,16455758606970,16459822687963,16459822868761,16455758946597
|
|
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,160404,160404,4194304,256,0,0,12,24,30016,0x7fa4e1915100,0x7fa4dea24580,1304416,1206732,65536,163051,163051,163051,0,302,162320,9879,1983,2864,159065,0,15465,145448,16455758979475,16459822898360,16459822991320,16455759231126
|
|
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,160404,160404,4194304,256,0,0,8,24,30976,0x7fa4df17df80,0x7fa4dea245c0,1292624,1192112,65536,161577,161577,161577,0,302,161738,10023,2327,2862,159710,0,14882,144440,16455759263864,16459823035799,16459823128758,16455759514515
|
|
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,160404,160404,4194304,256,0,0,12,24,31680,0x7fa4df17de00,0x7fa4dea24600,1299504,1195350,65536,162437,162437,162437,0,302,162706,9967,2001,3543,159614,0,15804,144282,16455759553613,16459823162198,16459823255317,16455759801724
|
|
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,160404,160404,4194304,256,0,0,16,24,32640,0x7fa4df17dc80,0x7fa4dea24640,2433968,2330320,65536,304245,304245,304245,0,302,303350,10988,1983,3405,300231,0,24696,280416,16455759835042,16459823287637,16459823467635,16455760179709
|
|
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,160404,160404,4194304,256,0,0,12,24,33600,0x7fa4df17db00,0x7fa4dea24680,2458592,2349905,65536,307323,307323,307323,0,302,306006,10884,1983,2875,304208,0,23040,282682,16455760212128,16459823496275,16459823676913,16455760549035
|
|
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,160404,160404,4194304,256,0,0,12,24,34560,0x7fa4df17d980,0x7fa4dea246c0,1306368,1206741,65536,163295,163295,163295,0,302,162758,9781,1980,2871,159761,0,15689,145267,16455760581394,16459823701712,16459823795632,16455760831274
|
|
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,160404,160404,4194304,256,0,0,8,24,35520,0x7fa4df17d800,0x7fa4dea24700,1312664,1207040,65536,164082,164082,164082,0,302,163488,9940,1990,2876,160507,0,14596,145853,16455760863973,16459823837071,16459823931150,16455761112193
|
|
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,160404,160404,4194304,256,0,0,12,24,36224,0x7fa4df17d680,0x7fa4dea24740,1321872,1221256,65536,165233,165233,165233,0,302,162147,9969,1996,2867,159560,0,14896,146899,16455761151432,16459823964430,16459824057869,16455761400102
|
|
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,160404,160404,4194304,256,0,0,12,24,37184,0x7fa4e1915500,0x7fa4dea24780,2464696,2361632,65536,308086,308086,308086,0,302,305139,11036,1983,2868,302387,0,25078,277529,16455761434921,16459824088429,16459824268107,16455761769668
|
|
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,160404,160404,4194304,256,0,0,12,24,38144,0x7fa4e1915380,0x7fa4dea247c0,2461392,2360425,65536,307673,307673,307673,0,302,305427,11076,1992,2885,302946,0,22532,279743,16455761802247,16459824295307,16459824476265,16455762140324
|
|
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,160404,160404,4194304,256,0,0,12,24,39104,0x7fa4e1915200,0x7fa4dea24800,1305624,1202597,65536,163202,163202,163202,0,302,163011,9848,2116,2880,159231,0,14593,145780,16455762173892,16459824504105,16459824598024,16455762426873
|
|
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,160404,160404,4194304,256,0,0,8,24,40320,0x7fa4e1915080,0x7fa4dea24840,1312352,1206067,65536,164043,164043,164043,0,302,162703,9864,1993,3147,159734,0,14886,146334,16455762460281,16459824627943,16459824723142,16455762709792
|
|
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,160404,160404,4194304,256,0,0,12,24,41280,0x7fa4df17df00,0x7fa4dea24880,1302088,1203236,65536,162760,162760,162760,0,302,161701,9943,1993,2869,160224,0,15067,145543,16455762749290,16459824757382,16459824850181,16455762993401
|
|
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,160404,160404,4194304,256,0,0,12,24,42240,0x7fa4df17dd80,0x7fa4dea248c0,2447448,2340620,65536,305930,305930,305930,0,302,306203,10999,2416,2857,304190,0,24364,280881,16455763027530,16459824879781,16459825060899,16455763361757
|
|
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,160404,160404,4194304,256,0,0,12,24,43200,0x7fa4df17dc00,0x7fa4dea24900,2435088,2331196,65536,304385,304385,304385,0,302,302129,10817,1984,2855,301237,0,22689,280140,16455763394095,16459825085859,16459825265377,16455763730143
|
|
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,160404,160404,4194304,256,0,0,8,24,44160,0x7fa4df17da80,0x7fa4dea24940,1303768,1197820,65536,162970,162970,162970,0,302,162394,9810,1993,2863,159358,0,14254,145251,16455763762461,16459825308256,16459825402656,16455764015832
|
|
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,160404,160404,4194304,256,0,0,12,24,45376,0x7fa4df17d900,0x7fa4dea24980,1314168,1209506,65536,164270,164270,164270,0,302,162606,10031,1987,2875,160011,0,15001,145418,16455764047910,16459825432095,16459825526654,16455764297721
|
|
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,160404,160404,4194304,256,0,0,12,24,46336,0x7fa4df17d780,0x7fa4dea249c0,1304744,1204371,65536,163092,163092,163092,0,302,162100,9832,1988,2858,159243,0,14453,145734,16455764339509,16459825560894,16459825655293,16455764579600
|
|
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,160404,160404,4194304,256,0,0,12,24,47552,0x7fa4df17d600,0x7fa4dea24a00,2454656,2342887,65536,306831,306831,306831,0,302,302128,11151,1988,2856,303326,0,23478,279679,16455764613389,16459825694973,16459825874011,16455764949186
|
|
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,160404,160404,4194304,256,0,0,12,24,48512,0x7fa4e1915480,0x7fa4dea24a40,2423448,2319468,65536,302930,302930,302930,0,302,301962,10721,2444,2775,299256,0,20799,278985,16455764982385,16459825906011,16459826086489,16455765316392
|
|
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,160404,160404,4194304,256,0,0,8,24,49472,0x7fa4e1915300,0x7fa4dea24a80,1296960,1194187,65536,162119,162119,162119,0,302,160548,9766,1982,2861,158093,0,14973,144909,16455765348480,16459826124088,16459826216567,16455765598171
|
|
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,160404,160404,4194304,256,0,0,12,24,50688,0x7fa4e1915180,0x7fa4dea24ac0,1299568,1196131,65536,162445,162445,162445,0,302,161718,10124,2002,2864,158747,0,15905,144007,16455765631050,16459826246807,16459826340406,16455765880130
|
|
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,160404,160404,4194304,256,0,0,12,24,51648,0x7fa4e1915000,0x7fa4dea24b00,1290392,1193104,65536,161298,161298,161298,0,302,161640,9771,2780,2850,158150,0,14711,145019,16455765920139,16459826376246,16459826468245,16455766159269
|
|
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,160404,160404,4194304,256,0,0,12,24,52864,0x7fa4df17de80,0x7fa4dea24b40,2422784,2315632,65536,302847,302847,302847,0,302,301018,10861,1984,2858,300004,0,22382,278312,16455766192818,16459826507925,16459826687443,16455766536935
|
|
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,160404,160404,4194304,256,0,0,12,24,54080,0x7fa4df17dd00,0x7fa4dea24b80,2434008,2326432,65536,304250,304250,304250,0,302,301824,10836,1982,2854,299344,0,22937,276973,16455766569704,16459826714482,16459826893201,16455766906861
|
|
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,160404,160404,4194304,256,0,0,8,24,55296,0x7fa4df17db80,0x7fa4dea24bc0,1305496,1205247,65536,163186,163186,163186,0,302,162598,9852,2602,2856,160212,0,14997,147179,16455766939259,16459826918480,16459827012720,16455767189110
|
|
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,160404,160404,4194304,256,0,0,12,24,56768,0x7fa4df17da00,0x7fa4dea24c00,1307864,1200590,65536,163482,163482,163482,0,302,162718,10124,2002,2874,160292,0,16732,144298,16455767221458,16459827039599,16459827135438,16455767473149
|
|
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,160404,160404,4194304,256,0,0,12,24,57728,0x7fa4df17d880,0x7fa4dea24c40,1302200,1197947,65536,162774,162774,162774,0,302,161680,10010,1984,2868,159446,0,14897,144270,16455767512877,16459827168718,16459827262317,16455767758038
|
|
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,160404,160404,4194304,256,0,0,12,24,58944,0x7fa4df17d700,0x7fa4dea24c80,2425960,2318236,65536,303244,303244,303244,0,302,300174,10933,1984,2867,297837,0,23743,277455,16455767792436,16459827288077,16459827466955,16455768124864
|
|
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,160404,160404,4194304,256,0,0,12,24,60160,0x7fa4e1915580,0x7fa4dea24cc0,2419872,2315057,65536,302483,302483,302483,0,302,302910,10812,1988,2861,299245,0,22219,278343,16455768158882,16459827491755,16459827673193,16455768495029
|
|
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,160404,160404,4194304,256,0,0,8,24,61376,0x7fa4e1915400,0x7fa4dea24d00,1302664,1203867,65536,162832,162832,162832,0,302,163166,9878,1978,3219,159399,0,15354,145529,16455768527638,16459827698153,16459827793192,16455768782078
|
|
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,160404,160404,4194304,256,0,0,12,24,62848,0x7fa4e1915280,0x7fa4dea24d40,1351264,1247322,65536,168907,168907,168907,0,302,168605,9912,1985,2861,167423,0,16211,151208,16455768814917,16459827820711,16459827920070,16455769068187
|
|
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,160404,160404,4194304,256,0,0,12,24,63808,0x7fa4e1915100,0x7fa4dea24d80,1297224,1195508,65536,162152,162152,162152,0,302,161547,9831,1979,2821,159531,0,15350,145397,16455769108436,16459827952390,16459828045829,16455769357336
|
|
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,160404,160404,4194304,256,0,0,12,24,65024,0x7fa4df17df80,0x7fa4dea24dc0,2413576,2308979,65536,301696,301696,301696,0,302,299849,10964,1983,2856,298478,0,22947,275716,16455769391345,16459828071589,16459828250947,16455769726052
|
|
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,160404,160404,4194304,256,0,0,12,24,66240,0x7fa4df17de00,0x7fa4dea24e00,2413176,2306522,65536,301646,301646,301646,0,302,299161,10963,1985,2858,296594,0,22449,275842,16455769758191,16459828277507,16459828458145,16455770091858
|
|
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,160404,160404,4194304,256,0,0,8,24,67456,0x7fa4df17dc80,0x7fa4dea24e40,1317816,1214625,65536,164726,164726,164726,0,302,162915,9976,2005,2860,160442,0,15371,145323,16455770124497,16459828485185,16459828580704,16455770380247
|
|
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,160404,160404,4194304,256,0,0,12,24,68928,0x7fa4df17db00,0x7fa4dea24e80,1400440,1299378,65536,175054,175054,175054,0,302,176321,10107,1984,2853,174437,0,16173,157632,16455770412186,16459828607744,16459828711903,16455770675815
|
|
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,160404,160404,4194304,256,0,0,12,24,70144,0x7fa4df17d980,0x7fa4dea24ec0,1284472,1182639,65536,160558,160558,160558,0,302,159819,9939,1978,2862,157820,0,15099,143263,16455770715324,16459828744542,16459828836861,16455770963884
|
|
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,160404,160404,4194304,256,0,0,12,24,71616,0x7fa4df17d800,0x7fa4dea24f00,2424240,2317645,65536,303029,303029,303029,0,302,303919,11024,1987,2856,301015,0,23976,276661,16455770995883,16459828861341,16459829041499,16455771338540
|
|
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,160404,160404,4194304,256,0,0,12,24,72832,0x7fa4df17d680,0x7fa4dea24f40,2413496,2307512,65536,301686,301686,301686,0,302,298577,11047,1991,2859,300012,0,21751,276544,16455771371319,16459829068219,16459829248537,16455771708076
|
|
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,160404,160404,4194304,256,0,0,8,24,74048,0x7fa4e1915500,0x7fa4dea24f80,1299552,1192694,65536,162443,162443,162443,0,302,161757,10159,1996,2868,158141,0,15318,144438,16455771740454,16459829274617,16459829367896,16455771989885
|
|
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,160404,160404,4194304,256,0,0,12,24,75776,0x7fa4e1915380,0x7fa4dea24fc0,1455320,1353288,65536,181914,181914,181914,0,302,182203,10235,1983,3394,179322,0,16944,163221,16455772022183,16459829393976,16459829500855,16455772284413
|
|
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,160404,160404,4194304,256,0,0,12,24,76992,0x7fa4e1915200,0x7fa4dea25000,1300752,1199343,65536,162593,162593,162593,0,302,160367,10103,2000,3502,158767,0,15825,143569,16455772338001,16459829533494,16459829628213,16455772571612
|
|
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,160404,160404,4194304,256,0,0,12,24,78464,0x7fa4e1915080,0x7fa4dea25040,2401688,2298207,65536,300210,300210,300210,0,302,301019,11026,1994,3430,295942,0,23478,276562,16455772605281,16459829654613,16459829834771,16455772944978
|
|
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,160404,160404,4194304,256,0,0,12,24,79936,0x7fa4df17df00,0x7fa4dea25080,2409880,2309181,65536,301234,301234,301234,0,302,303561,10869,2261,2812,298081,0,21518,276823,16455772977147,16459829860371,16459830040369,16455773312504
|
|
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,160404,160404,4194304,256,0,0,8,24,81408,0x7fa4df17dd80,0x7fa4dea250c0,1307168,1203521,65536,163395,163395,163395,0,302,162519,9774,1993,2857,159883,0,15315,144811,16455773344713,16459830065169,16459830160048,16455773601653
|
|
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,160404,160404,4194304,256,0,0,12,24,83136,0x7fa4df17dc00,0x7fa4dea25100,1539272,1428310,65536,192408,192408,192408,0,302,191485,10299,1983,2857,188579,0,18186,171533,16455773633441,16459830185648,16459830301167,16455773906211
|
|
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,160404,160404,4194304,256,0,0,12,24,84352,0x7fa4df17da80,0x7fa4dea25140,1288856,1189423,65536,161106,161106,161106,0,302,160987,9945,1981,2856,157602,0,15029,143949,16455773946199,16459830346926,16459830440525,16455774198710
|
|
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,160404,160404,4194304,256,0,0,12,24,85824,0x7fa4df17d900,0x7fa4dea25180,2426416,2322037,65536,303301,303301,303301,0,302,299491,10993,1981,2854,295678,0,22811,276059,16455774230768,16459830465805,16459830646123,16455774581785
|
|
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,160404,160404,4194304,256,0,0,12,24,87296,0x7fa4df17d780,0x7fa4dea251c0,2419416,2316863,65536,302426,302426,302426,0,302,297511,10650,2477,2855,295688,0,21807,275113,16455774614574,16459830669963,16459830849801,16455774952101
|
|
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,160404,160404,4194304,256,0,0,12,24,88768,0x7fa4df17d600,0x7fa4dea25200,1307472,1202961,65536,163433,163433,163433,0,302,163397,10039,1980,2848,159101,0,15978,145846,16455774985629,16459830873801,16459830968520,16455775234160
|
|
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,160404,160404,4194304,256,0,0,12,24,90752,0x7fa4e1915480,0x7fa4dea25240,1622168,1510392,65536,202770,202770,202770,0,302,202187,10397,2045,2856,198587,0,18036,180606,16455775267148,16459830993640,16459831113479,16455775544848
|
|
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,160404,160404,4194304,256,0,0,12,24,91968,0x7fa4e1915300,0x7fa4dea25280,1294056,1192499,65536,161756,161756,161756,0,302,161091,9826,1997,2867,158447,0,15654,144068,16455775585786,16459831145318,16459831238917,16455775826147
|
|
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,160404,160404,4194304,256,0,0,12,24,93440,0x7fa4e1915180,0x7fa4dea252c0,2405520,2302777,65536,300689,300689,300689,0,302,300287,11198,1986,2858,298643,0,23729,277899,16455775858676,16459831263237,16459831443555,16455776199193
|
|
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,160404,160404,4194304,256,0,0,12,24,94912,0x7fa4e1915000,0x7fa4dea25300,2400232,2295419,65536,300028,300028,300028,0,302,300209,10766,2084,2857,294602,0,21371,275268,16455776232571,16459831467555,16459831647073,16455776567138
|
|
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,160404,160404,4194304,256,0,0,12,24,96384,0x7fa4df17de80,0x7fa4dea25340,1300288,1196068,65536,162535,162535,162535,0,302,162454,10034,1999,2867,159071,0,15814,144589,16455776599807,16459831672833,16459831767552,16455776848878
|
|
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,160404,160404,4194304,256,0,0,12,24,98368,0x7fa4df17dd00,0x7fa4dea25380,1685304,1580856,65536,210662,210662,210662,0,302,210483,10410,1984,2845,207881,0,19002,190060,16455776880936,16459831791872,16459831918911,16455777168065
|
|
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,160404,160404,4194304,256,0,0,12,24,99584,0x7fa4df17db80,0x7fa4dea253c0,1288624,1186903,65536,161077,161077,161077,0,302,160660,9839,2551,2860,159591,0,14635,143609,16455777207664,16459831950910,16459832045149,16455777461254
|
|
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,160404,160404,4194304,256,0,0,12,24,101312,0x7fa4df17da00,0x7fa4dea25400,2381520,2279362,65536,297689,297689,297689,0,302,298143,10990,1983,2858,293125,0,22636,274286,16455777493653,16459832068989,16459832247707,16455777828510
|
|
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,160404,160404,4194304,256,0,0,12,24,102784,0x7fa4df17d880,0x7fa4dea25440,2399040,2297487,65536,299879,299879,299879,0,302,298960,10821,2452,2864,295113,0,21943,275142,16455777861029,16459832271707,16459832451865,16455778197966
|
|
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,160404,160404,4194304,256,0,0,12,24,104256,0x7fa4df17d700,0x7fa4dea25480,1286400,1186146,65536,160799,160799,160799,0,302,162335,9995,2009,2873,160086,0,16156,143712,16455778230494,16459832476985,16459832571544,16455778486934
|
|
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,160404,160404,4194304,256,0,0,12,24,106240,0x7fa4e1915580,0x7fa4dea254c0,1757424,1647049,65536,219677,219677,219677,0,302,220088,10626,1982,2877,216242,0,19822,196694,16455778520023,16459832596184,16459832726903,16455778814072
|
|
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,160404,160404,4194304,256,0,0,12,24,107712,0x7fa4e1915400,0x7fa4dea25500,1294568,1186472,65536,161820,161820,161820,0,302,160234,9890,1981,3698,158003,0,15308,144336,16455778854500,16459832759222,16459832852181,16455779108470
|
|
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,160404,160404,4194304,256,0,0,16,24,109440,0x7fa4e1915280,0x7fa4dea25540,2392888,2287887,65536,299110,299110,299110,0,302,298112,10867,1973,2862,294777,0,22679,274102,16455779141859,16459832879701,16459833058739,16455779475536
|
|
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,160404,160404,4194304,256,0,0,16,24,111168,0x7fa4e1915100,0x7fa4dea25580,2401992,2289811,65536,300248,300248,300248,0,302,296774,10738,1987,2853,295442,0,22225,275361,16455779508625,16459833082899,16459833262897,16455779844452
|
|
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,160404,160404,4194304,256,0,0,8,24,112896,0x7fa4df17df80,0x7fa4dea255c0,1305656,1201517,65536,163206,163206,163206,0,302,161242,9983,2001,2857,159450,0,15761,143699,16455779877421,16459833288017,16459833383536,16455780127861
|
|
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,160404,160404,4194304,256,0,0,12,24,115136,0x7fa4df17de00,0x7fa4dea25600,1835888,1728820,65536,229485,229485,229485,0,302,230330,10630,1993,2854,226969,0,20133,206619,16455780160520,16459833407376,16459833546414,16455780451169
|
|
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,160404,160404,4194304,256,0,0,12,24,116608,0x7fa4df17dc80,0x7fa4dea25640,1286440,1184750,65536,160804,160804,160804,0,302,161344,9928,1988,2872,157846,0,15832,143531,16455780491367,16459833580014,16459833674733,16455780733488
|
|
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,160404,160404,4194304,256,0,0,16,24,118336,0x7fa4df17db00,0x7fa4dea25680,2383424,2279919,65536,297927,297927,297927,0,302,296358,10745,1978,2859,293936,0,20764,273545,16455780765587,16459833700973,16459833882891,16455781104664
|
|
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,160404,160404,4194304,256,0,0,16,24,120064,0x7fa4df17d980,0x7fa4dea256c0,2388856,2286605,65536,298606,298606,298606,0,302,300358,10742,1983,2860,295300,0,21804,274850,16455781137012,16459833908331,16459834089929,16455781476229
|
|
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,160404,160404,4194304,256,0,0,12,24,121792,0x7fa4df17d800,0x7fa4dea25700,1313456,1215418,65536,164181,164181,164181,0,302,165292,10225,2012,3659,160574,0,15454,145307,16455781508568,16459834116329,16459834213608,16455781760528
|
|
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,160404,160404,4194304,256,0,0,12,24,124032,0x7fa4df17d680,0x7fa4dea25740,1919368,1807963,65536,239920,239920,239920,0,302,237985,10670,1978,2859,235837,0,20212,216222,16455781792887,16459834239048,16459834384486,16455782092975
|
|
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,160404,160404,4194304,256,0,0,12,24,125504,0x7fa4e1915500,0x7fa4dea25780,1291672,1186562,65536,161458,161458,161458,0,302,160940,9958,1986,2850,158079,0,15259,144740,16455782134114,16459834418246,16459834514245,16455782388634
|
|
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,160404,160404,4194304,256,0,0,12,24,127488,0x7fa4e1915380,0x7fa4dea257c0,2388120,2281798,65536,298514,298514,298514,0,302,297125,10718,1993,2856,293906,0,20863,274592,16455782421403,16459834539525,16459834719203,16455782757750
|
|
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,160404,160404,4194304,256,0,0,12,24,129216,0x7fa4e1915200,0x7fa4dea25800,2390256,2281848,65536,298781,298781,298781,0,302,297372,10626,1987,2854,296749,0,20412,275088,16455782790769,16459834742243,16459834922081,16455783127606
|
|
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,160404,160404,4194304,256,0,0,12,24,130944,0x7fa4e1915080,0x7fa4dea25840,1367216,1260259,65536,170901,170901,170901,0,302,170601,10015,1981,2841,168434,0,16533,150533,16455783159834,16459834947360,16459835047839,16455783418554
|
|
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,160404,160404,4194304,256,0,0,12,24,133440,0x7fa4df17df00,0x7fa4dea25880,2073824,1962299,65536,259227,259227,259227,0,302,258964,10861,1990,2847,256744,0,21179,234585,16455783452133,16459835074079,16459835229598,16455783768351
|
|
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,160404,160404,4194304,256,0,0,12,24,134912,0x7fa4df17dd80,0x7fa4dea258c0,1287496,1186190,65536,160936,160936,160936,0,302,161393,10076,2008,2865,157458,0,16069,142943,16455783808239,16459835264157,16459835358876,16455784057380
|
|
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,160404,160404,4194304,256,0,0,12,24,136896,0x7fa4df17dc00,0x7fa4dea25900,2378112,2272096,65536,297263,297263,297263,0,302,296072,10630,1980,2856,292857,0,20523,273942,16455784089709,16459835383836,16459835562394,16455784427076
|
|
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,160404,160404,4194304,256,0,0,12,24,138880,0x7fa4df17da80,0x7fa4dea25940,2373424,2264706,65536,296677,296677,296677,0,302,296052,10851,1990,2859,293568,0,20830,272748,16455784459774,16459835587674,16459835767352,16455784797701
|
|
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,160404,160404,4194304,256,0,0,12,24,140864,0x7fa4df17d900,0x7fa4dea25980,1426448,1320448,65536,178305,178305,178305,0,302,179040,10084,1979,2864,175601,0,17178,159309,16455784829610,16459835793432,16459835900471,16455785091690
|
|
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,160404,160404,4194304,256,0,0,12,24,143616,0x7fa4df17d780,0x7fa4dea259c0,2243128,2131517,65536,280390,280390,280390,0,302,280672,11034,2010,2883,276790,0,22466,256112,16455785123559,16459835926871,16459836097749,16455785449056
|
|
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,160404,160404,4194304,256,0,0,12,24,145344,0x7fa4df17d600,0x7fa4dea25a00,1298512,1198584,65536,162313,162313,162313,0,302,161284,9990,2159,2868,157347,0,16198,144054,16455785489515,16459836131189,16459836226868,16455785733205
|
|
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,160404,160404,4194304,256,0,0,12,24,147584,0x7fa4e1915480,0x7fa4dea25a40,2380240,2267768,65536,297529,297529,297529,0,302,295128,10694,1982,2861,293122,0,21619,273587,16455785766304,16459836253427,16459836433426,16455786102831
|
|
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,160404,160404,4194304,256,0,0,12,24,149568,0x7fa4e1915300,0x7fa4dea25a80,2372944,2273074,65536,296617,296617,296617,0,302,294446,10900,1989,2849,293088,0,21322,271797,16455786136420,16459836459185,16459836639824,16455786478156
|
|
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,160404,160404,4194304,256,0,0,12,24,151552,0x7fa4e1915180,0x7fa4dea25ac0,1492576,1383501,65536,186571,186571,186571,0,302,186776,10247,1980,2858,183631,0,17719,166727,16455786511615,16459836664303,16459836773902,16455786777795
|
|
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,160404,160404,4194304,256,0,0,12,24,154304,0x7fa4e1915000,0x7fa4dea25b00,2402512,2292175,65536,300313,300313,300313,0,302,299105,11231,2000,2854,297369,0,23652,274190,16455786811294,16459836797742,16459836979020,16455787150531
|
|
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,160404,160404,4194304,256,0,0,12,24,156288,0x7fa4df17de80,0x7fa4dea25b40,1374040,1270875,65536,171754,171754,171754,0,302,171424,10216,1978,2848,167823,0,16860,151743,16455787190419,16459837011500,16459837113419,16455787456439
|
|
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,160404,160404,4194304,256,0,0,12,24,158784,0x7fa4df17dd00,0x7fa4dea25b80,2398768,2277363,65536,299845,299845,299845,0,302,298103,10556,1987,2773,294772,0,20837,276952,16455787490437,16459837138859,16459837321577,16455787827884
|
|
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,160404,160404,4194304,256,0,0,12,24,161024,0x7fa4df17db80,0x7fa4dea25bc0,2379488,2255075,65536,297435,297435,297435,0,302,298599,10571,2001,2861,295739,0,20052,275208,16455787861403,16459837347497,16459837531175,16455788200670
|
|
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,160404,160404,4194304,256,0,0,12,24,163264,0x7fa4df17da00,0x7fa4dea25c00,1652944,1538836,65536,206617,206617,206617,0,302,205530,10316,1983,2855,203192,0,18539,185814,16455788232639,16459837558534,16459837680773,16455788513508
|
|
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,160404,160404,4194304,256,0,0,12,24,166528,0x7fa4df17d880,0x7fa4dea25c40,2716912,2608658,65536,339613,339613,339613,0,302,339967,11294,1983,3553,338157,0,25564,311658,16455788546017,16459837706533,16459837913251,16455788930282
|
|
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,160404,160404,4194304,256,0,0,12,24,168512,0x7fa4df17d700,0x7fa4dea25c80,1465744,1363230,65536,183217,183217,183217,0,302,183306,10315,1978,2859,180632,0,17747,163958,16455788949911,16459837962370,16459838073729,16455789221371
|
|
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,160404,160404,4194304,256,0,0,12,24,171264,0x7fa4e1915580,0x7fa4dea25cc0,2365360,2249828,65536,295669,295669,295669,0,302,295351,10619,1986,2862,295260,0,20792,274338,16455789256059,16459838101889,16459838286687,16455789595896
|
|
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,160404,160404,4194304,256,0,0,12,24,173760,0x7fa4e1915400,0x7fa4dea25d00,2394888,2277860,65536,299360,299360,299360,0,302,301421,10732,1992,2869,295174,0,20994,274687,16455789628565,16459838311807,16459838497405,16455789967012
|
|
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,160404,160404,4194304,256,0,0,12,24,176256,0x7fa4e1915280,0x7fa4dea25d40,1803392,1692900,65536,225423,225423,225423,0,302,225331,10622,1988,3610,222616,0,19616,203319,16455790000191,16459838522845,16459838657564,16455790301549
|
|
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,160404,160404,4194304,256,0,0,12,24,179776,0x7fa4e1915100,0x7fa4dea25d80,3046136,2933967,65536,380766,380766,380766,0,302,380945,11632,2009,2871,378348,0,27845,350455,16455790334318,16459838681723,16459838913721,16455790768711
|
|
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,160404,160404,4194304,256,0,0,12,24,182272,0x7fa4df17df80,0x7fa4dea25dc0,1689024,1577596,65536,211127,211127,211127,0,302,210601,10552,1978,3565,208607,0,19194,189381,16455790787631,16459838983800,16459839110039,16455791072370
|
|
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,160404,160404,4194304,256,0,0,12,24,185536,0x7fa4df17de00,0x7fa4dea25e00,2452920,2338387,65536,306614,306614,306614,0,302,303981,11163,1982,2857,303985,0,23959,281436,16455791106538,16459839134519,16459839329077,16455791495573
|
|
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,160404,160404,4194304,256,0,0,12,24,188544,0x7fa4df17dc80,0x7fa4dea25e40,2493536,2350810,65536,311691,311691,311691,0,302,313129,10884,1984,2855,307657,0,21901,285776,16455791506873,16459839354517,16459839549715,16455791913897
|
|
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,160404,160404,4194304,256,0,0,12,24,191552,0x7fa4df17db00,0x7fa4dea25e80,2127720,2020824,65536,265964,265964,265964,0,302,265921,10866,1984,2856,263032,0,21800,241530,16455791924787,16459839573554,16459839734193,16455792256194
|
|
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,160404,160404,4194304,256,0,0,12,24,195840,0x7fa4df17d980,0x7fa4dea25ec0,3693904,3582511,65536,461737,461737,461737,0,302,460857,12055,2753,3484,459384,0,31588,426959,16455792288193,16459839759153,16459840042350,16455792770324
|
|
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,160404,160404,4194304,256,0,0,12,24,198592,0x7fa4df17d800,0x7fa4dea25f00,1945672,1845665,65536,243208,243208,243208,0,302,242954,10685,1979,2856,240760,0,20816,219698,16455792789354,16459840112589,16459840262348,16455793095822
|
|
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,160404,160404,4194304,256,0,0,12,24,202368,0x7fa4df17d680,0x7fa4dea25f40,2679216,2562304,65536,334901,334901,334901,0,302,332929,11200,2302,2858,330635,0,23385,310213,16455793130421,16459840288107,16459840496745,16455793512646
|
|
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,160404,160404,4194304,256,0,0,12,24,205888,0x7fa4e1915500,0x7fa4dea25f80,2659976,2539669,65536,332496,332496,332496,0,302,328280,11344,2348,2850,327963,0,24068,306442,16455793527455,16459840558025,16459840764743,16455793910461
|
|
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,160404,160404,4194304,256,0,0,12,24,209408,0x7fa4e1915380,0x7fa4dea25fc0,2456952,2348100,65536,307118,307118,307118,0,302,306137,11219,1989,3234,304212,0,23876,280418,16455793926980,16459840826502,16459841012420,16455794273027
|
|
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,160404,160404,4194304,256,0,0,12,24,214464,0x7fa4e1915200,0x7fa4dea26000,4339496,4228742,65536,542436,542436,542436,0,302,544108,12972,2279,2884,539838,0,35914,505008,16455794307655,16459841037700,16459841372256,16455794845565
|
|
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,160404,160404,4194304,256,0,0,12,24,217728,0x7fa4e1915080,0x7fa4dea26040,2184424,2074572,65536,273052,273052,273052,0,302,271359,10923,1998,2879,269204,0,22264,248023,16455794864144,16459841417216,16459841584894,16455795201471
|
|
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,160404,160404,4194304,256,0,0,12,24,222016,0x7fa4df17df00,0x7fa4dea26080,2947416,2834049,65536,368426,368426,368426,0,302,366126,11494,1995,2858,363568,0,25990,336478,16455795236310,16459841610014,16459841838812,16455795658563
|
|
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,160404,160404,4194304,256,0,0,12,24,226048,0x7fa4df17dd80,0x7fa4dea260c0,2923400,2816323,65536,365424,365424,365424,0,302,365277,11889,1980,2847,361478,0,29178,333718,16455795669763,16459841873212,16459842103289,16455796106026
|
|
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,160404,160404,4194304,256,0,0,12,24,230080,0x7fa4df17dc00,0x7fa4dea26100,2780648,2671271,65536,347580,347580,347580,0,302,346393,11581,2002,2866,344702,0,25700,318886,16455796117396,16459842148409,16459842359927,16455796534340
|
|
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,160404,160404,4194304,256,0,0,12,24,235904,0x7fa4df17da80,0x7fa4dea26140,4998192,4878999,65536,624773,624773,624773,0,302,623941,13172,1979,3344,621441,0,40093,581740,16455796545099,16459842398966,16459842784882,16455797137856
|
|
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,160404,160404,4194304,256,0,0,12,24,239424,0x7fa4df17d900,0x7fa4dea26180,2432192,2321616,65536,304023,304023,304023,0,302,303469,11259,1985,2860,300575,0,23889,277806,16455797156716,16459842828402,16459843014480,16455797501032
|
|
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,160404,160404,4194304,256,0,0,12,24,244224,0x7fa4df17d780,0x7fa4dea261c0,3174160,3069908,65536,396769,396769,396769,0,302,398077,11804,1985,3542,393868,0,27786,366242,16455797534991,16459843039440,16459843288877,16455797956385
|
|
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,160404,160404,4194304,256,0,0,12,24,248768,0x7fa4df17d600,0x7fa4dea26200,3131216,3022543,65536,391401,391401,391401,0,302,390713,11547,1985,2854,388958,0,27950,362846,16455797971014,16459843351117,16459843599434,16455798431677
|
|
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,160404,160404,4194304,256,0,0,12,24,253312,0x7fa4e1915480,0x7fa4dea26240,3100528,2990806,65536,387565,387565,387565,0,302,387865,11639,2764,2863,386044,0,27863,357762,16455798442746,16459843661514,16459843898951,16455798894989
|
|
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,160404,160404,4194304,256,0,0,8,24,255552,0x7fa4e1915300,0x7fa4dea26280,5747248,5634568,65536,718405,718405,718405,0,302,718669,14144,1989,2849,717066,0,45015,671238,16455798905498,16459843960711,16459844415106,16455799564403
|
|
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,160404,160404,4194304,256,0,0,12,24,259840,0x7fa4e1915180,0x7fa4dea262c0,2916576,2804807,65536,364571,364571,364571,0,302,363952,11555,1991,2852,360506,0,26611,335118,16455799583402,16459844484865,16459844710943,16455800006936
|
|
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,160404,160404,4194304,256,0,0,12,24,265664,0x7fa4e1915000,0x7fa4dea26300,3754320,3653751,65536,469289,469289,469289,0,302,468313,12192,1974,3076,465341,0,32235,435591,16455800017685,16459844772863,16459845070780,16455800527876
|
|
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,160404,160404,4194304,256,0,0,12,24,271232,0x7fa4df17de80,0x7fa4dea26340,3780312,3677623,65536,472538,472538,472538,0,302,471486,12289,1983,2857,468151,0,32146,437240,16455800538425,16459845111739,16459845410296,16455801043406
|
|
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,160404,160404,4194304,256,0,0,8,24,273216,0x7fa4df17dd00,0x7fa4dea26380,3867328,3755881,65536,483415,483415,483415,0,302,484215,12290,1979,2854,480712,0,33514,447552,16455801053976,16459845448696,16459845745013,16455801555576
|
|
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,160404,160404,4194304,256,0,0,8,24,275712,0x7fa4df17db80,0x7fa4dea263c0,7038864,6928585,65536,879857,879857,879857,0,302,880408,15075,2364,2863,877849,0,52888,823542,16455801566496,16459845787893,16459846345647,16455802340196
|
|
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,160404,160404,4194304,256,0,0,12,24,280768,0x7fa4df17da00,0x7fa4dea26400,3420136,3306909,65536,427516,427516,427516,0,302,426665,11889,1987,2868,423858,0,29963,393627,16455802359925,16459846419726,16459846683244,16455802831697
|
|
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,160404,160404,4194304,256,0,0,12,24,287616,0x7fa4df17d880,0x7fa4dea26440,4387064,4284369,65536,548382,548382,548382,0,302,548706,12730,1977,2855,547464,0,35893,512573,16455802842607,16459846747883,16459847098759,16455803405205
|
|
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,160404,160404,4194304,256,0,0,12,24,294208,0x7fa4df17d700,0x7fa4dea26480,4420232,4316073,65536,552528,552528,552528,0,302,550357,12746,1983,2850,548734,0,35631,513345,16455803416105,16459847172679,16459847523075,16455803975473
|
|
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,160404,160404,4194304,256,0,0,8,24,296960,0x7fa4e1915580,0x7fa4dea264c0,4505280,4392775,65536,563159,563159,563159,0,302,563312,13121,1988,2860,560110,0,36992,524418,16455803986203,16459847586275,16459847933631,16455804539921
|
|
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,160404,160404,4194304,256,0,0,8,24,299968,0x7fa4e1915400,0x7fa4dea26500,8328112,8221147,65536,1041013,1041013,1041013,0,302,1041397,16179,1994,2863,1039515,0,61225,978130,16455804550891,16459847995231,16459848656664,16455805412838
|
|
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,160404,160404,4194304,256,0,0,8,24,302720,0x7fa4e1915280,0x7fa4dea26540,5770040,5659672,65536,721254,721254,721254,0,302,721414,14162,1994,2862,718518,0,44774,674116,16455805431707,16459848727703,16459849174899,16455806053823
|
|
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,160404,160404,4194304,256,0,0,12,24,305472,0x7fa4e1915100,0x7fa4dea26580,5789080,5671472,65536,723634,723634,723634,0,302,723413,13942,2140,2887,720116,0,45522,675148,16455806069412,16459849236978,16459849702094,16455806744846
|
|
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,160404,160404,4194304,256,0,0,12,24,308224,0x7fa4df17df80,0x7fa4dea265c0,5779840,5665403,65536,722479,722479,722479,0,302,723012,14099,1985,2803,719455,0,45239,674724,16455806755986,16459849767533,16459850230248,16455807428240
|
|
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,160404,160404,4194304,256,0,0,8,24,310976,0x7fa4df17de00,0x7fa4dea26600,5815432,5696511,65536,726928,726928,726928,0,302,724965,13809,1978,3397,723415,0,45253,678914,16455807438810,16459850296328,16459850749123,16455808121763
|
|
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,160404,160404,4194304,256,0,0,8,24,313216,0x7fa4df17dc80,0x7fa4dea26640,10937192,10813152,65536,1367148,1367148,1367148,0,302,1368697,18219,2246,2858,1365600,0,77946,1288492,16455808132613,16459850814882,16459851685274,16455809225601
|
|
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,160404,160404,4194304,256,0,0,8,24,315968,0x7fa4df17db00,0x7fa4dea26680,10964392,10847231,65536,1370548,1370548,1370548,0,302,1370271,18344,1987,2860,1367847,0,77513,1289984,16455809244270,16459851757913,16459852611665,16455810335458
|
|
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,160404,160404,4194304,256,0,0,12,24,318720,0x7fa4df17d980,0x7fa4dea266c0,10992872,10863103,65536,1374108,1374108,1374108,0,302,1374472,18270,1990,2864,1371593,0,77740,1294475,16455810346737,16459852679664,16459853565255,16455811479784
|
|
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,160404,160404,4194304,256,0,0,12,24,321472,0x7fa4df17d800,0x7fa4dea26700,10966968,10847229,65536,1370870,1370870,1370870,0,302,1370743,18248,2458,2860,1367996,0,77467,1290818,16455811491423,16459853631814,16459854512286,16455812616200
|
|
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,160404,160404,4194304,256,0,0,8,24,324224,0x7fa4df17d680,0x7fa4dea26740,11011488,10884514,65536,1376435,1376435,1376435,0,302,1375492,18166,1990,2860,1372950,0,77321,1295109,16455812627040,16459854589245,16459855450036,16455813729097
|
|
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,160404,160404,4194304,256,0,0,8,24,326464,0x7fa4e1915500,0x7fa4dea26780,21315392,21186254,65536,2664423,2664423,2664423,0,302,2662927,26888,1984,2853,2661083,0,142564,2516378,16455813740147,16459855516916,16459857217059,16455815696001
|
|
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,160404,160404,4194304,256,0,0,8,24,329216,0x7fa4e1915380,0x7fa4dea267c0,21363016,21232803,65536,2670376,2670376,2670376,0,302,2668444,26984,1988,2868,2666482,0,142637,2525415,16455815715451,16459857313218,16459858979761,16455817626487
|
|
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,160404,160404,4194304,256,0,0,12,24,331968,0x7fa4e1915200,0x7fa4dea26800,21349320,21239724,65536,2668664,2668664,2668664,0,302,2670123,26928,1985,2857,2666445,0,144071,2524469,16455817637907,16459859072080,16459860798303,16455819622720
|
|
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,160404,160404,4194304,256,0,0,12,24,334720,0x7fa4e1915080,0x7fa4dea26840,21367280,21231303,65536,2670909,2670909,2670909,0,302,2670788,26949,1984,2862,2667713,0,143628,2523988,16455819634510,16459860911902,16459862627405,16455821603674
|
|
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,160404,160404,4194304,256,0,0,8,24,337472,0x7fa4df17df00,0x7fa4dea26880,21376560,21264518,65536,2672069,2672069,2672069,0,302,2672852,27184,1991,2772,2673975,0,143359,2526542,16455821614774,16459862726444,16459864400827,16455823540860
|
|
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,160404,160404,4194304,256,0,0,8,24,0,0x7fa4df17dd80,0x7fa4dea268c0,42063856,41926181,65536,5257981,5257981,5257981,0,302,5257452,44432,1981,2867,5255318,0,273863,4980459,16455823552009,16459864489946,16459867849753,16455827171680
|