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

169 lignes
37 KiB
CSV

Index,KernelName,gpu-id,queue-id,queue-index,pid,tid,grd,wgr,lds,scr,vgpr,sgpr,fbar,sig,obj,DispatchNs,BeginNs,EndNs,CompleteNs
0,"__amd_rocclr_fillBufferAligned.kd",0,0,0,238434,238434,33554432,256,0,0,4,32,4160,0x0,0x7fd647c04280,17853365225848,17853365250419,17853365490099,17853365576439
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,238434,238434,32768,256,0,0,12,24,13888,0x0,0x7fd647c23f80,17853370260633,17853370276021,17853370289461,17853370306822
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,238434,238434,4194304,256,0,0,12,24,14336,0x7fd66e582380,0x7fd647c23fc0,17853370311482,17853370360501,17853370452981,17853370455238
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,238434,238434,4194304,256,0,0,16,24,15040,0x7fd66e582200,0x7fd647c24000,17853370476128,17853370485781,17853370665621,17853370667633
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,238434,238434,4194304,256,0,0,16,24,15488,0x7fd66e582080,0x7fd647c24040,17853370682173,17853370690581,17853370869302,17853370871458
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,238434,238434,4194304,256,0,0,12,24,15936,0x7fd66c109f00,0x7fd647c24080,17853370885518,17853370893622,17853370987062,17853370989065
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,238434,238434,4194304,256,0,0,12,24,16384,0x7fd66c109d80,0x7fd647c240c0,17853371004375,17853371012662,17853371104502,17853371106392
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,238434,238434,4194304,256,0,0,12,24,17088,0x7fd66c109c00,0x7fd647c24100,17853371133792,17853371144022,17853371236022,17853371238009
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,238434,238434,4194304,256,0,0,16,24,17792,0x7fd66c109a80,0x7fd647c24140,17853371255939,17853371265302,17853371443702,17853371445714
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,238434,238434,4194304,256,0,0,16,24,18496,0x7fd66c109900,0x7fd647c24180,17853371463453,17853371472022,17853371651702,17853371653619
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,238434,238434,4194304,256,0,0,16,24,19200,0x7fd66c109780,0x7fd647c241c0,17853371670068,17853371752342,17853371846102,17853371848234
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,238434,238434,4194304,256,0,0,16,24,19904,0x7fd66c109600,0x7fd647c24200,17853371887383,17853371900822,17853371993462,17853371995550
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,238434,238434,4194304,256,0,0,12,24,20608,0x7fd66e582480,0x7fd647c24240,17853372038389,17853372048342,17853372141302,17853372143427
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,238434,238434,4194304,256,0,0,16,24,21312,0x7fd66e582300,0x7fd647c24280,17853372165016,17853372175222,17853372354902,17853372356961
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,238434,238434,4194304,256,0,0,16,24,22016,0x7fd66e582180,0x7fd647c242c0,17853372378331,17853372387862,17853372568183,17853372570076
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,238434,238434,4194304,256,0,0,16,24,22720,0x7fd66e582000,0x7fd647c24300,17853372588936,17853372598743,17853372692663,17853372694633
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,238434,238434,4194304,256,0,0,12,24,23424,0x7fd66c109e80,0x7fd647c24340,17853372716233,17853372727383,17853372821303,17853372823280
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,238434,238434,4194304,256,0,0,12,24,24128,0x7fd66c109d00,0x7fd647c24380,17853372856349,17853372866263,17853372959543,17853372961476
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,238434,238434,4194304,256,0,0,16,24,24832,0x7fd66c109b80,0x7fd647c243c0,17853372983426,17853372992823,17853373172183,17853373174171
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,238434,238434,4194304,256,0,0,16,24,25536,0x7fd66c109a00,0x7fd647c24400,17853373193601,17853373204663,17853373384023,17853373386026
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,238434,238434,4194304,256,0,0,12,24,26240,0x7fd66c109880,0x7fd647c24440,17853373404926,17853373416343,17853373509623,17853373511723
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,238434,238434,4194304,256,0,0,12,24,26944,0x7fd66c109700,0x7fd647c24480,17853373532722,17853373543543,17853373636983,17853373639060
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,238434,238434,4194304,256,0,0,12,24,27648,0x7fd66e582580,0x7fd647c244c0,17853373670989,17853373682423,17853373775383,17853373777356
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,238434,238434,4194304,256,0,0,16,24,28608,0x7fd66e582400,0x7fd647c24500,17853373797266,17853373807383,17853373986583,17853373988551
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,238434,238434,4194304,256,0,0,16,24,29312,0x7fd66e582280,0x7fd647c24540,17853374006851,17853374017463,17853374197944,17853374200306
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,238434,238434,4194304,256,0,0,12,24,30016,0x7fd66e582100,0x7fd647c24580,17853374221155,17853374232664,17853374325304,17853374327363
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,238434,238434,4194304,256,0,0,8,24,30976,0x7fd66c109f80,0x7fd647c245c0,17853374350282,17853374359704,17853374452184,17853374454200
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,238434,238434,4194304,256,0,0,12,24,31680,0x7fd66c109e00,0x7fd647c24600,17853374488439,17853374498104,17853374591224,17853374593276
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,238434,238434,4194304,256,0,0,16,24,32640,0x7fd66c109c80,0x7fd647c24640,17853374612836,17853374623864,17853374803224,17853374805211
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,238434,238434,4194304,256,0,0,12,24,33600,0x7fd66c109b00,0x7fd647c24680,17853374824170,17853374833944,17853375015064,17853375016616
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,238434,238434,4194304,256,0,0,12,24,34560,0x7fd66c109980,0x7fd647c246c0,17853375035915,17853375044344,17853375138584,17853375140343
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,238434,238434,4194304,256,0,0,8,24,35520,0x7fd66c109800,0x7fd647c24700,17853375161562,17853375171544,17853375265784,17853375267459
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,238434,238434,4194304,256,0,0,12,24,36224,0x7fd66c109680,0x7fd647c24740,17853375300689,17853375310264,17853375404504,17853375406006
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,238434,238434,4194304,256,0,0,12,24,37184,0x7fd66e582500,0x7fd647c24780,17853375427215,17853375436984,17853375616824,17853375618571
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,238434,238434,4194304,256,0,0,12,24,38144,0x7fd66e582380,0x7fd647c247c0,17853375637680,17853375647704,17853375826745,17853375828305
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,238434,238434,4194304,256,0,0,12,24,39104,0x7fd66e582200,0x7fd647c24800,17853375848345,17853375857465,17853375951225,17853375952902
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,238434,238434,4194304,256,0,0,8,24,40320,0x7fd66e582080,0x7fd647c24840,17853375972742,17853375983705,17853376077945,17853376079429
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,238434,238434,4194304,256,0,0,12,24,41280,0x7fd66c109f00,0x7fd647c24880,17853376111698,17853376121785,17853376216185,17853376217666
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,238434,238434,4194304,256,0,0,12,24,42240,0x7fd66c109d80,0x7fd647c248c0,17853376237695,17853376248185,17853376427545,17853376428970
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,238434,238434,4194304,256,0,0,12,24,43200,0x7fd66c109c00,0x7fd647c24900,17853376448540,17853376458425,17853376639225,17853376640755
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,238434,238434,4194304,256,0,0,8,24,44160,0x7fd66c109a80,0x7fd647c24940,17853376661135,17853376671865,17853376766265,17853376767712
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,238434,238434,4194304,256,0,0,12,24,45376,0x7fd66c109900,0x7fd647c24980,17853376787452,17853376796505,17853376891545,17853376893089
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,238434,238434,4194304,256,0,0,12,24,46336,0x7fd66c109780,0x7fd647c249c0,17853376925198,17853376934905,17853377029465,17853377030986
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,238434,238434,4194304,256,0,0,12,24,47552,0x7fd66c109600,0x7fd647c24a00,17853377051455,17853377061785,17853377240665,17853377242080
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,238434,238434,4194304,256,0,0,12,24,48512,0x7fd66e582480,0x7fd647c24a40,17853377261540,17853377271225,17853377451225,17853377452725
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,238434,238434,4194304,256,0,0,8,24,49472,0x7fd66e582300,0x7fd647c24a80,17853377471865,17853377481785,17853377574746,17853377576232
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,238434,238434,4194304,256,0,0,12,24,50688,0x7fd66e582180,0x7fd647c24ac0,17853377595852,17853377605626,17853377699386,17853377700889
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,238434,238434,4194304,256,0,0,12,24,51648,0x7fd66e582000,0x7fd647c24b00,17853377733238,17853377742906,17853377834906,17853377836396
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,238434,238434,4194304,256,0,0,12,24,52864,0x7fd66c109e80,0x7fd647c24b40,17853377857845,17853377867546,17853378046426,17853378047970
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,238434,238434,4194304,256,0,0,12,24,54080,0x7fd66c109d00,0x7fd647c24b80,17853378067680,17853378076986,17853378255546,17853378257345
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,238434,238434,4194304,256,0,0,8,24,55296,0x7fd66c109b80,0x7fd647c24bc0,17853378277035,17853378285466,17853378380346,17853378381882
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,238434,238434,4194304,256,0,0,12,24,56768,0x7fd66c109a00,0x7fd647c24c00,17853378401721,17853378410586,17853378506266,17853378507719
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,238434,238434,4194304,256,0,0,12,24,57728,0x7fd66c109880,0x7fd647c24c40,17853378540478,17853378550426,17853378644026,17853378645675
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,238434,238434,4194304,256,0,0,12,24,58944,0x7fd66c109700,0x7fd647c24c80,17853378665435,17853378676026,17853378857466,17853378858970
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,238434,238434,4194304,256,0,0,12,24,60160,0x7fd66e582580,0x7fd647c24cc0,17853378878800,17853378890106,17853379070906,17853379072325
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,238434,238434,4194304,256,0,0,8,24,61376,0x7fd66e582400,0x7fd647c24d00,17853379092714,17853379102906,17853379197946,17853379199752
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,238434,238434,4194304,256,0,0,12,24,62848,0x7fd66e582280,0x7fd647c24d40,17853379220781,17853379230266,17853379330747,17853379332398
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,238434,238434,4194304,256,0,0,12,24,63808,0x7fd66e582100,0x7fd647c24d80,17853379365488,17853379375867,17853379470907,17853379472345
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,238434,238434,4194304,256,0,0,12,24,65024,0x7fd66c109f80,0x7fd647c24dc0,17853379492904,17853379502747,17853379681627,17853379683210
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,238434,238434,4194304,256,0,0,12,24,66240,0x7fd66c109e00,0x7fd647c24e00,17853379702729,17853379712507,17853379890267,17853379891804
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,238434,238434,4194304,256,0,0,8,24,67456,0x7fd66c109c80,0x7fd647c24e40,17853379911654,17853379922907,17853380017467,17853380019001
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,238434,238434,4194304,256,0,0,12,24,68928,0x7fd66c109b00,0x7fd647c24e80,17853380038641,17853380049307,17853380153947,17853380155388
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,238434,238434,4194304,256,0,0,12,24,70144,0x7fd66c109980,0x7fd647c24ec0,17853380187807,17853380197467,17853380290107,17853380291675
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,238434,238434,4194304,256,0,0,12,24,71616,0x7fd66c109800,0x7fd647c24f00,17853380311304,17853380320667,17853380501627,17853380503139
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,238434,238434,4194304,256,0,0,12,24,72832,0x7fd66c109680,0x7fd647c24f40,17853380524119,17853380533947,17853380712827,17853380714314
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,238434,238434,4194304,256,0,0,8,24,74048,0x7fd66e582500,0x7fd647c24f80,17853380734164,17853380743387,17853380836667,17853380838191
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,238434,238434,4194304,256,0,0,12,24,75776,0x7fd66e582380,0x7fd647c24fc0,17853380857990,17853380866907,17853380974108,17853380975668
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,238434,238434,4194304,256,0,0,12,24,76992,0x7fd66e582200,0x7fd647c25000,17853381008227,17853381018268,17853381112188,17853381113684
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,238434,238434,4194304,256,0,0,12,24,78464,0x7fd66e582080,0x7fd647c25040,17853381134304,17853381144668,17853381324348,17853381325819
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,238434,238434,4194304,256,0,0,12,24,79936,0x7fd66c109f00,0x7fd647c25080,17853381345468,17853381354908,17853381535068,17853381536564
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,238434,238434,4194304,256,0,0,8,24,81408,0x7fd66c109d80,0x7fd647c250c0,17853381556203,17853381566268,17853381661628,17853381663040
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,238434,238434,4194304,256,0,0,12,24,83136,0x7fd66c109c00,0x7fd647c25100,17853381683210,17853381692668,17853381808348,17853381809847
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,238434,238434,4194304,256,0,0,12,24,84352,0x7fd66c109a80,0x7fd647c25140,17853381864385,17853381874108,17853381968668,17853381970133
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,238434,238434,4194304,256,0,0,12,24,85824,0x7fd66c109900,0x7fd647c25180,17853381990282,17853382001308,17853382180828,17853382182618
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,238434,238434,4194304,256,0,0,12,24,87296,0x7fd66c109780,0x7fd647c251c0,17853382205157,17853382215228,17853382393788,17853382395292
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,238434,238434,4194304,256,0,0,12,24,88768,0x7fd66c109600,0x7fd647c25200,17853382415522,17853382425948,17853382521308,17853382522839
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,238434,238434,4194304,256,0,0,12,24,90752,0x7fd66e582480,0x7fd647c25240,17853382542919,17853382553468,17853382674909,17853382676325
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,238434,238434,4194304,256,0,0,12,24,91968,0x7fd66e582300,0x7fd647c25280,17853382708895,17853382718589,17853382813629,17853382815162
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,238434,238434,4194304,256,0,0,12,24,93440,0x7fd66e582180,0x7fd647c252c0,17853382835241,17853382845949,17853383025949,17853383027487
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,238434,238434,4194304,256,0,0,12,24,94912,0x7fd66e582000,0x7fd647c25300,17853383043876,17853383051709,17853383230909,17853383232362
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,238434,238434,4194304,256,0,0,12,24,96384,0x7fd66c109e80,0x7fd647c25340,17853383248671,17853383256029,17853383351869,17853383353359
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,238434,238434,4194304,256,0,0,12,24,98368,0x7fd66c109d00,0x7fd647c25380,17853383369318,17853383378909,17853383504989,17853383506405
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,238434,238434,4194304,256,0,0,12,24,99584,0x7fd66c109b80,0x7fd647c253c0,17853383526794,17853383537309,17853383631069,17853383632452
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,238434,238434,4194304,256,0,0,12,24,101312,0x7fd66c109a00,0x7fd647c25400,17853383648041,17853383656349,17853383836989,17853383838427
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,238434,238434,4194304,256,0,0,12,24,102784,0x7fd66c109880,0x7fd647c25440,17853383852226,17853383860189,17853384041629,17853384043042
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,238434,238434,4194304,256,0,0,12,24,104256,0x7fd66c109700,0x7fd647c25480,17853384057181,17853384066589,17853384160989,17853384162419
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,238434,238434,4194304,256,0,0,12,24,106240,0x7fd66e582580,0x7fd647c254c0,17853384176678,17853384185469,17853384316029,17853384317535
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,238434,238434,4194304,256,0,0,12,24,107712,0x7fd66e582400,0x7fd647c25500,17853384338694,17853384349949,17853384443230,17853384444592
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,238434,238434,4194304,256,0,0,16,24,109440,0x7fd66e582280,0x7fd647c25540,17853384461571,17853384469470,17853384648030,17853384649437
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,238434,238434,4194304,256,0,0,16,24,111168,0x7fd66e582100,0x7fd647c25580,17853384664166,17853384672510,17853384851390,17853384852782
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,238434,238434,4194304,256,0,0,8,24,112896,0x7fd66c109f80,0x7fd647c255c0,17853384867081,17853384876510,17853384972350,17853384973879
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,238434,238434,4194304,256,0,0,12,24,115136,0x7fd66c109e00,0x7fd647c25600,17853384989388,17853384998910,17853385137310,17853385138755
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,238434,238434,4194304,256,0,0,12,24,116608,0x7fd66c109c80,0x7fd647c25640,17853385160014,17853385170910,17853385266110,17853385267521
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,238434,238434,4194304,256,0,0,16,24,118336,0x7fd66c109b00,0x7fd647c25680,17853385282121,17853385291070,17853385470110,17853385471546
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,238434,238434,4194304,256,0,0,16,24,120064,0x7fd66c109980,0x7fd647c256c0,17853385485536,17853385494910,17853385674430,17853385675901
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,238434,238434,4194304,256,0,0,12,24,121792,0x7fd66c109800,0x7fd647c25700,17853385690091,17853385698430,17853385796030,17853385797378
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,238434,238434,4194304,256,0,0,12,24,124032,0x7fd66c109680,0x7fd647c25740,17853385813418,17853385823230,17853385967710,17853385969114
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,238434,238434,4194304,256,0,0,12,24,125504,0x7fd66e582500,0x7fd647c25780,17853385989584,17853386000990,17853386098111,17853386099511
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,238434,238434,4194304,256,0,0,12,24,127488,0x7fd66e582380,0x7fd647c257c0,17853386113341,17853386121631,17853386305951,17853386307376
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,238434,238434,4194304,256,0,0,12,24,129216,0x7fd66e582200,0x7fd647c25800,17853386322405,17853386330111,17853386513311,17853386514861
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,238434,238434,4194304,256,0,0,12,24,130944,0x7fd66e582080,0x7fd647c25840,17853386529440,17853386537471,17853386638431,17853386639847
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,238434,238434,4194304,256,0,0,12,24,133440,0x7fd66c109f00,0x7fd647c25880,17853386654497,17853386662591,17853386817631,17853386819163
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,238434,238434,4194304,256,0,0,12,24,134912,0x7fd66c109d80,0x7fd647c258c0,17853386839453,17853386849951,17853386945791,17853386947310
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,238434,238434,4194304,256,0,0,12,24,136896,0x7fd66c109c00,0x7fd647c25900,17853386962329,17853386970111,17853387148511,17853387150065
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,238434,238434,4194304,256,0,0,12,24,138880,0x7fd66c109a80,0x7fd647c25940,17853387165734,17853387173471,17853387353951,17853387355540
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,238434,238434,4194304,256,0,0,12,24,140864,0x7fd66c109900,0x7fd647c25980,17853387369959,17853387377951,17853387485151,17853387486846
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,238434,238434,4194304,256,0,0,12,24,143616,0x7fd66c109780,0x7fd647c259c0,17853387501446,17853387509311,17853387680671,17853387682132
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,238434,238434,4194304,256,0,0,12,24,145344,0x7fd66c109600,0x7fd647c25a00,17853387703421,17853387713951,17853387809632,17853387811158
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,238434,238434,4194304,256,0,0,12,24,147584,0x7fd66e582480,0x7fd647c25a40,17853387827178,17853387835392,17853388016192,17853388017593
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,238434,238434,4194304,256,0,0,12,24,149568,0x7fd66e582300,0x7fd647c25a80,17853388032093,17853388040192,17853388219872,17853388221448
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,238434,238434,4194304,256,0,0,12,24,151552,0x7fd66e582180,0x7fd647c25ac0,17853388236758,17853388246912,17853388356832,17853388358395
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,238434,238434,4194304,256,0,0,12,24,154304,0x7fd66e582000,0x7fd647c25b00,17853388373444,17853388382752,17853388564512,17853388566070
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,238434,238434,4194304,256,0,0,12,24,156288,0x7fd66c109e80,0x7fd647c25b40,17853388587589,17853388597472,17853388700032,17853388701426
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,238434,238434,4194304,256,0,0,12,24,158784,0x7fd66c109d00,0x7fd647c25b80,17853388717986,17853388725952,17853388911872,17853388913381
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,238434,238434,4194304,256,0,0,12,24,161024,0x7fd66c109b80,0x7fd647c25bc0,17853388927261,17853388935392,17853389119872,17853389121236
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,238434,238434,4194304,256,0,0,12,24,163264,0x7fd66c109a00,0x7fd647c25c00,17853389134835,17853389143872,17853389265792,17853389267312
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,238434,238434,4194304,256,0,0,12,24,166528,0x7fd66c109880,0x7fd647c25c40,17853389282602,17853389292032,17853389498273,17853389519406
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,238434,238434,4194304,256,0,0,12,24,168512,0x7fd66c109700,0x7fd647c25c80,17853389535666,17853389546593,17853389656833,17853389658282
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,238434,238434,4194304,256,0,0,12,24,171264,0x7fd66e582580,0x7fd647c25cc0,17853389674412,17853389682913,17853389865633,17853389867207
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,238434,238434,4194304,256,0,0,12,24,173760,0x7fd66e582400,0x7fd647c25d00,17853389882317,17853389892193,17853390078433,17853390079932
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,238434,238434,4194304,256,0,0,12,24,176256,0x7fd66e582280,0x7fd647c25d40,17853390096002,17853390105473,17853390240033,17853390241438
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,238434,238434,4194304,256,0,0,12,24,179776,0x7fd66e582100,0x7fd647c25d80,17853390254848,17853390262753,17853390494753,17853390510641
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,238434,238434,4194304,256,0,0,12,24,182272,0x7fd66c109f80,0x7fd647c25dc0,17853390525931,17853390537633,17853390664673,17853390666187
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,238434,238434,4194304,256,0,0,12,24,185536,0x7fd66c109e00,0x7fd647c25e00,17853390680587,17853390688673,17853390878433,17853390880072
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,238434,238434,4194304,256,0,0,12,24,188544,0x7fd66c109c80,0x7fd647c25e40,17853390894582,17853390902753,17853391095233,17853391096667
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,238434,238434,4194304,256,0,0,12,24,191552,0x7fd66c109b00,0x7fd647c25e80,17853391111176,17853391119233,17853391279074,17853391280522
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,238434,238434,4194304,256,0,0,12,24,195840,0x7fd66c109980,0x7fd647c25ec0,17853391295262,17853391303394,17853391586594,17853391627604
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,238434,238434,4194304,256,0,0,12,24,198592,0x7fd66c109800,0x7fd647c25f00,17853391644153,17853391654914,17853391803234,17853391804749
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,238434,238434,4194304,256,0,0,12,24,202368,0x7fd66c109680,0x7fd647c25f40,17853391821579,17853391828994,17853392036514,17853392077102
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,238434,238434,4194304,256,0,0,12,24,205888,0x7fd66e582500,0x7fd647c25f80,17853392084762,17853392095234,17853392302434,17853392319066
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,238434,238434,4194304,256,0,0,12,24,209408,0x7fd66e582380,0x7fd647c25fc0,17853392326686,17853392336674,17853392522594,17853392524041
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,238434,238434,4194304,256,0,0,12,24,214464,0x7fd66e582200,0x7fd647c26000,17853392538891,17853392548834,17853392882914,17853392899062
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,238434,238434,4194304,256,0,0,12,24,217728,0x7fd66e582080,0x7fd647c26040,17853392915042,17853392925635,17853393093315,17853393094777
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,238434,238434,4194304,256,0,0,12,24,222016,0x7fd66c109f00,0x7fd647c26080,17853393109927,17853393118595,17853393347715,17853393365050
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,238434,238434,4194304,256,0,0,12,24,226048,0x7fd66c109d80,0x7fd647c260c0,17853393373070,17853393383235,17853393612995,17853393628784
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,238434,238434,4194304,256,0,0,12,24,230080,0x7fd66c109c00,0x7fd647c26100,17853393636584,17853393646595,17853393858435,17853393874138
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,238434,238434,4194304,256,0,0,12,24,235904,0x7fd66c109a80,0x7fd647c26140,17853393882958,17853393892995,17853394278435,17853394322967
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,238434,238434,4194304,256,0,0,12,24,239424,0x7fd66c109900,0x7fd647c26180,17853394339686,17853394349795,17853394536995,17853394538511
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,238434,238434,4194304,256,0,0,12,24,244224,0x7fd66c109780,0x7fd647c261c0,17853394553111,17853394560995,17853394811396,17853394854953
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,238434,238434,4194304,256,0,0,12,24,248768,0x7fd66c109600,0x7fd647c26200,17853394862603,17853394872996,17853395122276,17853395162696
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,238434,238434,4194304,256,0,0,12,24,253312,0x7fd66e582480,0x7fd647c26240,17853395169996,17853395180356,17853395416996,17853395460938
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,238434,238434,4194304,256,0,0,8,24,255552,0x7fd66e582300,0x7fd647c26280,17853395468628,17853395479076,17853395932996,17853395973596
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,238434,238434,4194304,256,0,0,12,24,259840,0x7fd66e582180,0x7fd647c262c0,17853395988605,17853395999396,17853396224676,17853396264908
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,238434,238434,4194304,256,0,0,12,24,265664,0x7fd66e582000,0x7fd647c26300,17853396272678,17853396282756,17853396580997,17853396621420
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,238434,238434,4194304,256,0,0,12,24,271232,0x7fd66c109e80,0x7fd647c26340,17853396630769,17853396640357,17853396938597,17853396981901
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,238434,238434,4194304,256,0,0,8,24,273216,0x7fd66c109d00,0x7fd647c26380,17853396990180,17853397000357,17853397296677,17853397316172
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,238434,238434,4194304,256,0,0,8,24,275712,0x7fd66c109b80,0x7fd647c263c0,17853397323962,17853397334437,17853397891557,17853397907428
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,238434,238434,4194304,256,0,0,12,24,280768,0x7fd66c109a00,0x7fd647c26400,17853397922097,17853397932997,17853398196838,17853398244909
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,238434,238434,4194304,256,0,0,12,24,287616,0x7fd66c109880,0x7fd647c26440,17853398253159,17853398263558,17853398614758,17853398660249
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,238434,238434,4194304,256,0,0,12,24,294208,0x7fd66c109700,0x7fd647c26480,17853398667379,17853398682118,17853399033478,17853399076959
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,238434,238434,4194304,256,0,0,8,24,296960,0x7fd66e582580,0x7fd647c264c0,17853399085538,17853399095718,17853399443238,17853399483669
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,238434,238434,4194304,256,0,0,8,24,299968,0x7fd66e582400,0x7fd647c26500,17853399491198,17853399501478,17853400162439,17853400210121
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,238434,238434,4194304,256,0,0,8,24,302720,0x7fd66e582280,0x7fd647c26540,17853400226560,17853400236199,17853400684039,17853400727478
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,238434,238434,4194304,256,0,0,12,24,305472,0x7fd66e582100,0x7fd647c26580,17853400734908,17853400745479,17853401209159,17853401254555
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,238434,238434,4194304,256,0,0,12,24,308224,0x7fd66c109f80,0x7fd647c265c0,17853401262935,17853401273639,17853401735560,17853401753193
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,238434,238434,4194304,256,0,0,8,24,310976,0x7fd66c109e00,0x7fd647c26600,17853401764152,17853401789160,17853402241160,17853402289999
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,238434,238434,4194304,256,0,0,8,24,313216,0x7fd66c109c80,0x7fd647c26640,17853402298769,17853402309000,17853403177961,17853403226186
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,238434,238434,4194304,256,0,0,8,24,315968,0x7fd66c109b00,0x7fd647c26680,17853403242506,17853403253481,17853404107561,17853404153433
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,238434,238434,4194304,256,0,0,12,24,318720,0x7fd66c109980,0x7fd647c266c0,17853404161333,17853404171881,17853405057482,17853405102819
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,238434,238434,4194304,256,0,0,12,24,321472,0x7fd66c109800,0x7fd647c26700,17853405113659,17853405145162,17853406024842,17853406071935
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,238434,238434,4194304,256,0,0,8,24,324224,0x7fd66c109680,0x7fd647c26740,17853406085685,17853406101482,17853406961163,17853407010752
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,238434,238434,4194304,256,0,0,8,24,326464,0x7fd66e582500,0x7fd647c26780,17853407019172,17853407029483,17853408726284,17853408800448
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,238434,238434,4194304,256,0,0,8,24,329216,0x7fd66e582380,0x7fd647c267c0,17853408816517,17853408827084,17853410491885,17853410563814
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,238434,238434,4194304,256,0,0,12,24,331968,0x7fd66e582200,0x7fd647c26800,17853410572544,17853410582925,17853412306926,17853412372679
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,238434,238434,4194304,256,0,0,12,24,334720,0x7fd66e582080,0x7fd647c26840,17853412383399,17853412402126,17853414117007,17853414187994
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,238434,238434,4194304,256,0,0,8,24,337472,0x7fd66c109f00,0x7fd647c26880,17853414196694,17853414207087,17853415879888,17853415948540
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,238434,238434,4194304,256,0,0,8,24,0,0x7fd66c109d80,0x7fd647c268c0,17853415957550,17853415981168,17853419338290,17853419414415