169 lines
37 KiB
CSV
169 lines
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",0,0,0,208222,208222,33554432,256,0,0,4,32,4160,0x0,0x7f3476804280,17356069269547,17356069295347,17356069536147,17356069651727
|
|
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,208222,208222,32768,256,0,0,12,24,13888,0x0,0x7f3476823f80,17356074343033,17356074359028,17356074372468,17356074389822
|
|
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,208222,208222,4194304,256,0,0,12,24,14336,0x7f34797dd380,0x7f3476823fc0,17356074394882,17356074454708,17356074547348,17356074549478
|
|
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,208222,208222,4194304,256,0,0,16,24,15040,0x7f34797dd200,0x7f3476824000,17356074571827,17356074581748,17356074759508,17356074761572
|
|
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,208222,208222,4194304,256,0,0,16,24,15488,0x7f34797dd080,0x7f3476824040,17356074776842,17356074784948,17356074963668,17356074965807
|
|
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,208222,208222,4194304,256,0,0,12,24,15936,0x7f347713bf00,0x7f3476824080,17356074980267,17356074988468,17356075082068,17356075084194
|
|
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,208222,208222,4194304,256,0,0,12,24,16384,0x7f347713bd80,0x7f34768240c0,17356075099593,17356075107988,17356075200308,17356075202441
|
|
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,208222,208222,4194304,256,0,0,12,24,17088,0x7f347713bc00,0x7f3476824100,17356075229680,17356075240148,17356075332628,17356075334597
|
|
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,208222,208222,4194304,256,0,0,16,24,17792,0x7f347713ba80,0x7f3476824140,17356075351337,17356075360148,17356075539508,17356075541422
|
|
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,208222,208222,4194304,256,0,0,16,24,18496,0x7f347713b900,0x7f3476824180,17356075561871,17356075581588,17356075761588,17356075763766
|
|
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,208222,208222,4194304,256,0,0,16,24,19200,0x7f347713b780,0x7f34768241c0,17356075778746,17356075787508,17356075881428,17356075883623
|
|
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,208222,208222,4194304,256,0,0,16,24,19904,0x7f347713b600,0x7f3476824200,17356075899552,17356075907988,17356076001748,17356076003730
|
|
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,208222,208222,4194304,256,0,0,12,24,20608,0x7f34797dd480,0x7f3476824240,17356076024029,17356076033908,17356076127988,17356076129846
|
|
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,208222,208222,4194304,256,0,0,16,24,21312,0x7f34797dd300,0x7f3476824280,17356076159946,17356076170388,17356076349908,17356076351950
|
|
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,208222,208222,4194304,256,0,0,16,24,22016,0x7f34797dd180,0x7f34768242c0,17356076369540,17356076379028,17356076559829,17356076561845
|
|
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,208222,208222,4194304,256,0,0,16,24,22720,0x7f34797dd000,0x7f3476824300,17356076579604,17356076598549,17356076692309,17356076694441
|
|
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,208222,208222,4194304,256,0,0,12,24,23424,0x7f347713be80,0x7f3476824340,17356076717331,17356076736149,17356076829109,17356076831208
|
|
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,208222,208222,4194304,256,0,0,12,24,24128,0x7f347713bd00,0x7f3476824380,17356076853027,17356076863349,17356076956789,17356076958684
|
|
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,208222,208222,4194304,256,0,0,16,24,24832,0x7f347713bb80,0x7f34768243c0,17356076975074,17356076983669,17356077163029,17356077164979
|
|
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,208222,208222,4194304,256,0,0,16,24,25536,0x7f347713ba00,0x7f3476824400,17356077182239,17356077191509,17356077372149,17356077374044
|
|
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,208222,208222,4194304,256,0,0,12,24,26240,0x7f347713b880,0x7f3476824440,17356077392073,17356077401109,17356077494709,17356077496750
|
|
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,208222,208222,4194304,256,0,0,12,24,26944,0x7f347713b700,0x7f3476824480,17356077513700,17356077522709,17356077616789,17356077618747
|
|
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,208222,208222,4194304,256,0,0,12,24,27648,0x7f34797dd580,0x7f34768244c0,17356077639387,17356077650069,17356077742709,17356077744744
|
|
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,208222,208222,4194304,256,0,0,16,24,28608,0x7f34797dd400,0x7f3476824500,17356077762943,17356077789269,17356077969109,17356077971258
|
|
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,208222,208222,4194304,256,0,0,16,24,29312,0x7f34797dd280,0x7f3476824540,17356077985797,17356077995669,17356078175349,17356078177582
|
|
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,208222,208222,4194304,256,0,0,12,24,30016,0x7f34797dd100,0x7f3476824580,17356078197652,17356078208309,17356078300629,17356078302729
|
|
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,208222,208222,4194304,256,0,0,8,24,30976,0x7f347713bf80,0x7f34768245c0,17356078320579,17356078331349,17356078423349,17356078425506
|
|
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,208222,208222,4194304,256,0,0,12,24,31680,0x7f347713be00,0x7f3476824600,17356078446865,17356078457269,17356078551029,17356078553002
|
|
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,208222,208222,4194304,256,0,0,16,24,32640,0x7f347713bc80,0x7f3476824640,17356078571012,17356078580149,17356078760149,17356078761677
|
|
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,208222,208222,4194304,256,0,0,12,24,33600,0x7f347713bb00,0x7f3476824680,17356078776937,17356078785269,17356078965589,17356078967072
|
|
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,208222,208222,4194304,256,0,0,12,24,34560,0x7f347713b980,0x7f34768246c0,17356078982201,17356078990389,17356079083509,17356079085018
|
|
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,208222,208222,4194304,256,0,0,8,24,35520,0x7f347713b800,0x7f3476824700,17356079099748,17356079108309,17356079201589,17356079203135
|
|
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,208222,208222,4194304,256,0,0,12,24,36224,0x7f347713b680,0x7f3476824740,17356079224625,17356079233909,17356079326549,17356079328142
|
|
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,208222,208222,4194304,256,0,0,12,24,37184,0x7f34797dd500,0x7f3476824780,17356079343372,17356079351349,17356079531349,17356079532757
|
|
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,208222,208222,4194304,256,0,0,12,24,38144,0x7f34797dd380,0x7f34768247c0,17356079549666,17356079558549,17356079739349,17356079740841
|
|
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,208222,208222,4194304,256,0,0,12,24,39104,0x7f34797dd200,0x7f3476824800,17356079754961,17356079763029,17356079856789,17356079858268
|
|
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,208222,208222,4194304,256,0,0,8,24,40320,0x7f34797dd080,0x7f3476824840,17356079872868,17356079881269,17356079975670,17356079977155
|
|
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,208222,208222,4194304,256,0,0,12,24,41280,0x7f347713bf00,0x7f3476824880,17356079997314,17356080007990,17356080100310,17356080101852
|
|
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,208222,208222,4194304,256,0,0,12,24,42240,0x7f347713bd80,0x7f34768248c0,17356080117211,17356080125590,17356080305430,17356080306906
|
|
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,208222,208222,4194304,256,0,0,12,24,43200,0x7f347713bc00,0x7f3476824900,17356080321796,17356080329910,17356080510710,17356080512191
|
|
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,208222,208222,4194304,256,0,0,8,24,44160,0x7f347713ba80,0x7f3476824940,17356080527240,17356080536470,17356080629750,17356080631208
|
|
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,208222,208222,4194304,256,0,0,12,24,45376,0x7f347713b900,0x7f3476824980,17356080646347,17356080654550,17356080748630,17356080750035
|
|
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,208222,208222,4194304,256,0,0,12,24,46336,0x7f347713b780,0x7f34768249c0,17356080769954,17356080780630,17356080874710,17356080876251
|
|
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,208222,208222,4194304,256,0,0,12,24,47552,0x7f347713b600,0x7f3476824a00,17356080891141,17356080899030,17356081078070,17356081079496
|
|
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,208222,208222,4194304,256,0,0,12,24,48512,0x7f34797dd480,0x7f3476824a40,17356081093546,17356081101910,17356081281750,17356081283171
|
|
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,208222,208222,4194304,256,0,0,8,24,49472,0x7f34797dd300,0x7f3476824a80,17356081299760,17356081307670,17356081400790,17356081402297
|
|
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,208222,208222,4194304,256,0,0,12,24,50688,0x7f34797dd180,0x7f3476824ac0,17356081416467,17356081425430,17356081518710,17356081520104
|
|
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,208222,208222,4194304,256,0,0,12,24,51648,0x7f34797dd000,0x7f3476824b00,17356081540524,17356081551190,17356081642710,17356081644331
|
|
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,208222,208222,4194304,256,0,0,12,24,52864,0x7f347713be80,0x7f3476824b40,17356081660521,17356081668790,17356081846230,17356081847706
|
|
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,208222,208222,4194304,256,0,0,12,24,54080,0x7f347713bd00,0x7f3476824b80,17356081863885,17356081871670,17356082050390,17356082051780
|
|
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,208222,208222,4194304,256,0,0,8,24,55296,0x7f347713bb80,0x7f3476824bc0,17356082068020,17356082076150,17356082170230,17356082172147
|
|
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,208222,208222,4194304,256,0,0,12,24,56768,0x7f347713ba00,0x7f3476824c00,17356082187527,17356082195670,17356082290870,17356082292344
|
|
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,208222,208222,4194304,256,0,0,12,24,57728,0x7f347713b880,0x7f3476824c40,17356082313383,17356082323990,17356082417750,17356082419131
|
|
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,208222,208222,4194304,256,0,0,12,24,58944,0x7f347713b700,0x7f3476824c80,17356082434410,17356082442710,17356082621750,17356082623285
|
|
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,208222,208222,4194304,256,0,0,12,24,60160,0x7f34797dd580,0x7f3476824cc0,17356082638365,17356082646550,17356082826550,17356082827980
|
|
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,208222,208222,4194304,256,0,0,8,24,61376,0x7f34797dd400,0x7f3476824d00,17356082842749,17356082850870,17356082944950,17356082946397
|
|
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,208222,208222,4194304,256,0,0,12,24,62848,0x7f34797dd280,0x7f3476824d40,17356082962226,17356082970710,17356083070070,17356083071563
|
|
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,208222,208222,4194304,256,0,0,12,24,63808,0x7f34797dd100,0x7f3476824d80,17356083093123,17356083103670,17356083197270,17356083198740
|
|
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,208222,208222,4194304,256,0,0,12,24,65024,0x7f347713bf80,0x7f3476824dc0,17356083216599,17356083226070,17356083404791,17356083406344
|
|
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,208222,208222,4194304,256,0,0,12,24,66240,0x7f347713be00,0x7f3476824e00,17356083422004,17356083430391,17356083608791,17356083610319
|
|
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,208222,208222,4194304,256,0,0,8,24,67456,0x7f347713bc80,0x7f3476824e40,17356083624589,17356083632471,17356083726551,17356083727986
|
|
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,208222,208222,4194304,256,0,0,12,24,68928,0x7f347713bb00,0x7f3476824e80,17356083743005,17356083751351,17356083856311,17356083857922
|
|
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,208222,208222,4194304,256,0,0,12,24,70144,0x7f347713b980,0x7f3476824ec0,17356083878982,17356083889431,17356083982231,17356083983589
|
|
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,208222,208222,4194304,256,0,0,12,24,71616,0x7f347713b800,0x7f3476824f00,17356083998459,17356084006871,17356084185591,17356084187144
|
|
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,208222,208222,4194304,256,0,0,12,24,72832,0x7f347713b680,0x7f3476824f40,17356084202403,17356084211671,17356084390551,17356084392018
|
|
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,208222,208222,4194304,256,0,0,8,24,74048,0x7f34797dd500,0x7f3476824f80,17356084406418,17356084414871,17356084507991,17356084509435
|
|
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,208222,208222,4194304,256,0,0,12,24,75776,0x7f34797dd380,0x7f3476824fc0,17356084523565,17356084531511,17356084639031,17356084640542
|
|
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,208222,208222,4194304,256,0,0,12,24,76992,0x7f34797dd200,0x7f3476825000,17356084660571,17356084671351,17356084765271,17356084766658
|
|
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,208222,208222,4194304,256,0,0,12,24,78464,0x7f34797dd080,0x7f3476825040,17356084782558,17356084790711,17356084970391,17356084971883
|
|
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,208222,208222,4194304,256,0,0,12,24,79936,0x7f347713bf00,0x7f3476825080,17356084985982,17356084994391,17356085173751,17356085175217
|
|
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,208222,208222,4194304,256,0,0,8,24,81408,0x7f347713bd80,0x7f34768250c0,17356085189327,17356085198391,17356085293111,17356085294464
|
|
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,208222,208222,4194304,256,0,0,12,24,83136,0x7f347713bc00,0x7f3476825100,17356085309564,17356085317911,17356085432631,17356085434171
|
|
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,208222,208222,4194304,256,0,0,12,24,84352,0x7f347713ba80,0x7f3476825140,17356085470020,17356085479351,17356085573751,17356085575197
|
|
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,208222,208222,4194304,256,0,0,12,24,85824,0x7f347713b900,0x7f3476825180,17356085590036,17356085599191,17356085778391,17356085779821
|
|
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,208222,208222,4194304,256,0,0,12,24,87296,0x7f347713b780,0x7f34768251c0,17356085793971,17356085802071,17356085983191,17356085984706
|
|
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,208222,208222,4194304,256,0,0,12,24,88768,0x7f347713b600,0x7f3476825200,17356085998206,17356086006551,17356086101591,17356086103013
|
|
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,208222,208222,4194304,256,0,0,12,24,90752,0x7f34797dd480,0x7f3476825240,17356086120102,17356086128951,17356086249271,17356086250689
|
|
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,208222,208222,4194304,256,0,0,12,24,91968,0x7f34797dd300,0x7f3476825280,17356086272558,17356086283191,17356086377591,17356086379096
|
|
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,208222,208222,4194304,256,0,0,12,24,93440,0x7f34797dd180,0x7f34768252c0,17356086394245,17356086402391,17356086581111,17356086582620
|
|
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,208222,208222,4194304,256,0,0,12,24,94912,0x7f34797dd000,0x7f3476825300,17356086597350,17356086606071,17356086784792,17356086786275
|
|
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,208222,208222,4194304,256,0,0,12,24,96384,0x7f347713be80,0x7f3476825340,17356086801324,17356086809432,17356086904952,17356086906492
|
|
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,208222,208222,4194304,256,0,0,12,24,98368,0x7f347713bd00,0x7f3476825380,17356086921881,17356086930072,17356087057272,17356087058648
|
|
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,208222,208222,4194304,256,0,0,12,24,99584,0x7f347713bb80,0x7f34768253c0,17356087077967,17356087089432,17356087183512,17356087185094
|
|
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,208222,208222,4194304,256,0,0,12,24,101312,0x7f347713ba00,0x7f3476825400,17356087199894,17356087208632,17356087387832,17356087389229
|
|
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,208222,208222,4194304,256,0,0,12,24,102784,0x7f347713b880,0x7f3476825440,17356087404129,17356087412632,17356087592472,17356087593844
|
|
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,208222,208222,4194304,256,0,0,12,24,104256,0x7f347713b700,0x7f3476825480,17356087608463,17356087616792,17356087710872,17356087712330
|
|
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,208222,208222,4194304,256,0,0,12,24,106240,0x7f34797dd580,0x7f34768254c0,17356087726970,17356087735032,17356087865272,17356087866736
|
|
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,208222,208222,4194304,256,0,0,12,24,107712,0x7f34797dd400,0x7f3476825500,17356087887176,17356087897752,17356087990872,17356087992313
|
|
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,208222,208222,4194304,256,0,0,16,24,109440,0x7f34797dd280,0x7f3476825540,17356088008323,17356088017592,17356088196792,17356088198288
|
|
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,208222,208222,4194304,256,0,0,16,24,111168,0x7f34797dd100,0x7f3476825580,17356088213377,17356088221592,17356088400792,17356088402222
|
|
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,208222,208222,4194304,256,0,0,8,24,112896,0x7f347713bf80,0x7f34768255c0,17356088417142,17356088425432,17356088521272,17356088522719
|
|
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,208222,208222,4194304,256,0,0,12,24,115136,0x7f347713be00,0x7f3476825600,17356088537889,17356088546232,17356088685112,17356088686555
|
|
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,208222,208222,4194304,256,0,0,12,24,116608,0x7f347713bc80,0x7f3476825640,17356088707534,17356088717752,17356088812312,17356088813681
|
|
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,208222,208222,4194304,256,0,0,16,24,118336,0x7f347713bb00,0x7f3476825680,17356088829331,17356088837432,17356089015832,17356089017276
|
|
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,208222,208222,4194304,256,0,0,16,24,120064,0x7f347713b980,0x7f34768256c0,17356089031086,17356089042872,17356089221912,17356089223391
|
|
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,208222,208222,4194304,256,0,0,12,24,121792,0x7f347713b800,0x7f3476825700,17356089238330,17356089246712,17356089343832,17356089345267
|
|
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,208222,208222,4194304,256,0,0,12,24,124032,0x7f347713b680,0x7f3476825740,17356089361187,17356089369752,17356089515512,17356089516933
|
|
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,208222,208222,4194304,256,0,0,12,24,125504,0x7f34797dd500,0x7f3476825780,17356089537262,17356089547992,17356089642712,17356089644230
|
|
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,208222,208222,4194304,256,0,0,12,24,127488,0x7f34797dd380,0x7f34768257c0,17356089659599,17356089667352,17356089848152,17356089849634
|
|
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,208222,208222,4194304,256,0,0,12,24,129216,0x7f34797dd200,0x7f3476825800,17356089866644,17356089874712,17356090056312,17356090057699
|
|
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,208222,208222,4194304,256,0,0,12,24,130944,0x7f34797dd080,0x7f3476825840,17356090074468,17356090092792,17356090192633,17356090194205
|
|
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,208222,208222,4194304,256,0,0,12,24,133440,0x7f347713bf00,0x7f3476825880,17356090209205,17356090217593,17356090372633,17356090374170
|
|
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,208222,208222,4194304,256,0,0,12,24,134912,0x7f347713bd80,0x7f34768258c0,17356090394480,17356090404953,17356090500633,17356090502257
|
|
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,208222,208222,4194304,256,0,0,12,24,136896,0x7f347713bc00,0x7f3476825900,17356090518987,17356090527353,17356090705433,17356090707012
|
|
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,208222,208222,4194304,256,0,0,12,24,138880,0x7f347713ba80,0x7f3476825940,17356090722151,17356090730233,17356090910873,17356090912296
|
|
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,208222,208222,4194304,256,0,0,12,24,140864,0x7f347713b900,0x7f3476825980,17356090925916,17356090933753,17356091041113,17356091042473
|
|
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,208222,208222,4194304,256,0,0,12,24,143616,0x7f347713b780,0x7f34768259c0,17356091056982,17356091066233,17356091236313,17356091237798
|
|
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,208222,208222,4194304,256,0,0,12,24,145344,0x7f347713b600,0x7f3476825a00,17356091258377,17356091268313,17356091364153,17356091365644
|
|
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,208222,208222,4194304,256,0,0,12,24,147584,0x7f34797dd480,0x7f3476825a40,17356091380184,17356091388313,17356091568633,17356091570199
|
|
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,208222,208222,4194304,256,0,0,12,24,149568,0x7f34797dd300,0x7f3476825a80,17356091584828,17356091593433,17356091774393,17356091775793
|
|
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,208222,208222,4194304,256,0,0,12,24,151552,0x7f34797dd180,0x7f3476825ac0,17356091790463,17356091798873,17356091909113,17356091910620
|
|
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,208222,208222,4194304,256,0,0,12,24,154304,0x7f34797dd000,0x7f3476825b00,17356091925349,17356091933433,17356092114553,17356092116034
|
|
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,208222,208222,4194304,256,0,0,12,24,156288,0x7f347713be80,0x7f3476825b40,17356092137784,17356092147033,17356092247833,17356092249291
|
|
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,208222,208222,4194304,256,0,0,12,24,158784,0x7f347713bd00,0x7f3476825b80,17356092264931,17356092273433,17356092458073,17356092459585
|
|
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,208222,208222,4194304,256,0,0,12,24,161024,0x7f347713bb80,0x7f3476825bc0,17356092474345,17356092482393,17356092668473,17356092669910
|
|
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,208222,208222,4194304,256,0,0,12,24,163264,0x7f347713ba00,0x7f3476825c00,17356092684269,17356092693113,17356092815353,17356092816896
|
|
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,208222,208222,4194304,256,0,0,12,24,166528,0x7f347713b880,0x7f3476825c40,17356092831536,17356092839993,17356093046233,17356093067229
|
|
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,208222,208222,4194304,256,0,0,12,24,168512,0x7f347713b700,0x7f3476825c80,17356093083199,17356093093753,17356093204953,17356093206456
|
|
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,208222,208222,4194304,256,0,0,12,24,171264,0x7f34797dd580,0x7f3476825cc0,17356093223935,17356093232633,17356093416473,17356093417950
|
|
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,208222,208222,4194304,256,0,0,12,24,173760,0x7f34797dd400,0x7f3476825d00,17356093432370,17356093440953,17356093627514,17356093628985
|
|
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,208222,208222,4194304,256,0,0,12,24,176256,0x7f34797dd280,0x7f3476825d40,17356093644774,17356093652954,17356093787194,17356093788610
|
|
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,208222,208222,4194304,256,0,0,12,24,179776,0x7f34797dd100,0x7f3476825d80,17356093804730,17356093812474,17356094044474,17356094066433
|
|
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,208222,208222,4194304,256,0,0,12,24,182272,0x7f347713bf80,0x7f3476825dc0,17356094093002,17356094103834,17356094230234,17356094231719
|
|
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,208222,208222,4194304,256,0,0,12,24,185536,0x7f347713be00,0x7f3476825e00,17356094249238,17356094257594,17356094448154,17356094449613
|
|
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,208222,208222,4194304,256,0,0,12,24,188544,0x7f347713bc80,0x7f3476825e40,17356094464163,17356094472794,17356094665114,17356094666537
|
|
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,208222,208222,4194304,256,0,0,12,24,191552,0x7f347713bb00,0x7f3476825e80,17356094681357,17356094689754,17356094849914,17356094851312
|
|
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,208222,208222,4194304,256,0,0,12,24,195840,0x7f347713b980,0x7f3476825ec0,17356094865422,17356094873434,17356095156954,17356095180094
|
|
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,208222,208222,4194304,256,0,0,12,24,198592,0x7f347713b800,0x7f3476825f00,17356095196493,17356095207354,17356095356954,17356095358419
|
|
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,208222,208222,4194304,256,0,0,12,24,202368,0x7f347713b680,0x7f3476825f40,17356095375949,17356095383834,17356095595834,17356095617632
|
|
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,208222,208222,4194304,256,0,0,12,24,205888,0x7f34797dd500,0x7f3476825f80,17356095626632,17356095636314,17356095844954,17356095867246
|
|
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,208222,208222,4194304,256,0,0,12,24,209408,0x7f34797dd380,0x7f3476825fc0,17356095876395,17356095886234,17356096071994,17356096073340
|
|
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,208222,208222,4194304,256,0,0,12,24,214464,0x7f34797dd200,0x7f3476826000,17356096088350,17356096096474,17356096431034,17356096450170
|
|
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,208222,208222,4194304,256,0,0,12,24,217728,0x7f34797dd080,0x7f3476826040,17356096466540,17356096476954,17356096644634,17356096646125
|
|
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,208222,208222,4194304,256,0,0,12,24,222016,0x7f347713bf00,0x7f3476826080,17356096662145,17356096670394,17356096897434,17356096916438
|
|
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,208222,208222,4194304,256,0,0,12,24,226048,0x7f347713bd80,0x7f34768260c0,17356096925218,17356096935514,17356097163675,17356097182621
|
|
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,208222,208222,4194304,256,0,0,12,24,230080,0x7f347713bc00,0x7f3476826100,17356097192141,17356097202235,17356097413275,17356097432144
|
|
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,208222,208222,4194304,256,0,0,12,24,235904,0x7f347713ba80,0x7f3476826140,17356097443254,17356097452155,17356097838075,17356097853833
|
|
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,208222,208222,4194304,256,0,0,12,24,239424,0x7f347713b900,0x7f3476826180,17356097870823,17356097881115,17356098067675,17356098069268
|
|
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,208222,208222,4194304,256,0,0,12,24,244224,0x7f347713b780,0x7f34768261c0,17356098096017,17356098106875,17356098357275,17356098375670
|
|
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,208222,208222,4194304,256,0,0,12,24,248768,0x7f347713b600,0x7f3476826200,17356098385289,17356098395355,17356098643035,17356098662062
|
|
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,208222,208222,4194304,256,0,0,12,24,253312,0x7f34797dd480,0x7f3476826240,17356098671712,17356098681915,17356098918555,17356098937835
|
|
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,208222,208222,4194304,256,0,0,8,24,255552,0x7f34797dd300,0x7f3476826280,17356098949524,17356098959995,17356099412635,17356099431322
|
|
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,208222,208222,4194304,256,0,0,12,24,259840,0x7f34797dd180,0x7f34768262c0,17356099448501,17356099459035,17356099685275,17356099704085
|
|
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,208222,208222,4194304,256,0,0,12,24,265664,0x7f34797dd000,0x7f3476826300,17356099713124,17356099723355,17356100021755,17356100040806
|
|
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,208222,208222,4194304,256,0,0,12,24,271232,0x7f347713be80,0x7f3476826340,17356100050305,17356100059675,17356100358235,17356100380697
|
|
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,208222,208222,4194304,256,0,0,8,24,273216,0x7f347713bd00,0x7f3476826380,17356100390876,17356100401116,17356100697276,17356100719278
|
|
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,208222,208222,4194304,256,0,0,8,24,275712,0x7f347713bb80,0x7f34768263c0,17356100728558,17356100738396,17356101296636,17356101318352
|
|
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,208222,208222,4194304,256,0,0,12,24,280768,0x7f347713ba00,0x7f3476826400,17356101334792,17356101345436,17356101608796,17356101627164
|
|
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,208222,208222,4194304,256,0,0,12,24,287616,0x7f347713b880,0x7f3476826440,17356101641354,17356101651516,17356102002556,17356102021144
|
|
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,208222,208222,4194304,256,0,0,12,24,294208,0x7f347713b700,0x7f3476826480,17356102030393,17356102040956,17356102391356,17356102414553
|
|
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,208222,208222,4194304,256,0,0,8,24,296960,0x7f34797dd580,0x7f34768264c0,17356102424433,17356102434716,17356102781596,17356102800563
|
|
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,208222,208222,4194304,256,0,0,8,24,299968,0x7f34797dd400,0x7f3476826500,17356102813053,17356102822876,17356103484476,17356103506014
|
|
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,208222,208222,4194304,256,0,0,8,24,302720,0x7f34797dd280,0x7f3476826540,17356103524284,17356103533436,17356103980797,17356104002561
|
|
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,208222,208222,4194304,256,0,0,12,24,305472,0x7f34797dd100,0x7f3476826580,17356104012211,17356104021917,17356104486557,17356104508018
|
|
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,208222,208222,4194304,256,0,0,12,24,308224,0x7f347713bf80,0x7f34768265c0,17356104516618,17356104526717,17356104987517,17356105009495
|
|
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,208222,208222,4194304,256,0,0,8,24,310976,0x7f347713be00,0x7f3476826600,17356105018325,17356105028477,17356105480957,17356105502562
|
|
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,208222,208222,4194304,256,0,0,8,24,313216,0x7f347713bc80,0x7f3476826640,17356105511002,17356105521277,17356106389117,17356106412638
|
|
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,208222,208222,4194304,256,0,0,8,24,315968,0x7f347713bb00,0x7f3476826680,17356106429997,17356106440797,17356107295198,17356107317884
|
|
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,208222,208222,4194304,256,0,0,12,24,318720,0x7f347713b980,0x7f34768266c0,17356107328004,17356107338238,17356108223038,17356108245140
|
|
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,208222,208222,4194304,256,0,0,12,24,321472,0x7f347713b800,0x7f3476826700,17356108254369,17356108264638,17356109144158,17356109165915
|
|
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,208222,208222,4194304,256,0,0,8,24,324224,0x7f347713b680,0x7f3476826740,17356109178345,17356109194238,17356110053438,17356110081851
|
|
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,208222,208222,4194304,256,0,0,8,24,326464,0x7f34797dd500,0x7f3476826780,17356110095281,17356110105278,17356111804159,17356111873694
|
|
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,208222,208222,4194304,256,0,0,8,24,329216,0x7f34797dd380,0x7f34768267c0,17356111892593,17356111902559,17356113567839,17356113637747
|
|
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,208222,208222,4194304,256,0,0,12,24,331968,0x7f34797dd200,0x7f3476826800,17356113650757,17356113667039,17356115392160,17356115461829
|
|
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,208222,208222,4194304,256,0,0,12,24,334720,0x7f34797dd080,0x7f3476826840,17356115471368,17356115482400,17356117198080,17356117265691
|
|
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,208222,208222,4194304,256,0,0,8,24,337472,0x7f347713bf00,0x7f3476826880,17356117276961,17356117292160,17356118965761,17356119041354
|
|
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,208222,208222,4194304,256,0,0,8,24,0,0x7f347713bd80,0x7f34768268c0,17356119051644,17356119062401,17356122419522,17356122490824
|