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",0,0,0,23354,23354,33554432,256,0,0,4,32,4160,0x0,0x7f4663004280,14234006550491,14234006575542,14234006812983,14234006923263
|
|
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,23354,23354,32768,256,0,0,12,24,13888,0x0,0x7f4663023f80,14234011564888,14234011579879,14234011592839,14234011610787
|
|
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,23354,23354,4194304,256,0,0,12,24,14336,0x7f466603c380,0x7f4663023fc0,14234011615137,14234011664520,14234011757320,14234011759374
|
|
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,23354,23354,4194304,256,0,0,16,24,15040,0x7f466603c200,0x7f4663024000,14234011780813,14234011790440,14234011969001,14234011970949
|
|
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,23354,23354,4194304,256,0,0,16,24,15488,0x7f466603c080,0x7f4663024040,14234011985119,14234011993161,14234012171721,14234012173735
|
|
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,23354,23354,4194304,256,0,0,12,24,15936,0x7f4663a0ff00,0x7f4663024080,14234012188165,14234012196042,14234012289802,14234012291943
|
|
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,23354,23354,4194304,256,0,0,12,24,16384,0x7f4663a0fd80,0x7f46630240c0,14234012306963,14234012314922,14234012407402,14234012409490
|
|
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,23354,23354,4194304,256,0,0,12,24,17088,0x7f4663a0fc00,0x7f4663024100,14234012436020,14234012446602,14234012538123,14234012540198
|
|
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,23354,23354,4194304,256,0,0,16,24,17792,0x7f4663a0fa80,0x7f4663024140,14234012559197,14234012568043,14234012746924,14234012748893
|
|
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,23354,23354,4194304,256,0,0,16,24,18496,0x7f4663a0f900,0x7f4663024180,14234012767903,14234012788844,14234012968524,14234012970869
|
|
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,23354,23354,4194304,256,0,0,16,24,19200,0x7f4663a0f780,0x7f46630241c0,14234012985479,14234012993964,14234013086925,14234013088876
|
|
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,23354,23354,4194304,256,0,0,16,24,19904,0x7f4663a0f600,0x7f4663024200,14234013106556,14234013120685,14234013214125,14234013215964
|
|
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,23354,23354,4194304,256,0,0,12,24,20608,0x7f466603c480,0x7f4663024240,14234013239213,14234013256845,14234013349966,14234013351991
|
|
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,23354,23354,4194304,256,0,0,16,24,21312,0x7f466603c300,0x7f4663024280,14234013374451,14234013384206,14234013562446,14234013564357
|
|
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,23354,23354,4194304,256,0,0,16,24,22016,0x7f466603c180,0x7f46630242c0,14234013583296,14234013593007,14234013773007,14234013774942
|
|
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,23354,23354,4194304,256,0,0,16,24,22720,0x7f466603c000,0x7f4663024300,14234013791032,14234013800207,14234013893328,14234013895380
|
|
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,23354,23354,4194304,256,0,0,12,24,23424,0x7f4663a0fe80,0x7f4663024340,14234013913680,14234013929328,14234014022128,14234014024017
|
|
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,23354,23354,4194304,256,0,0,12,24,24128,0x7f4663a0fd00,0x7f4663024380,14234014044747,14234014054928,14234014148209,14234014150085
|
|
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,23354,23354,4194304,256,0,0,16,24,24832,0x7f4663a0fb80,0x7f46630243c0,14234014165154,14234014173969,14234014353329,14234014355261
|
|
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,23354,23354,4194304,256,0,0,16,24,25536,0x7f4663a0fa00,0x7f4663024400,14234014371520,14234014380369,14234014560530,14234014562416
|
|
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,23354,23354,4194304,256,0,0,12,24,26240,0x7f4663a0f880,0x7f4663024440,14234014578666,14234014586770,14234014680210,14234014682244
|
|
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,23354,23354,4194304,256,0,0,12,24,26944,0x7f4663a0f700,0x7f4663024480,14234014700024,14234014708371,14234014801491,14234014803621
|
|
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,23354,23354,4194304,256,0,0,12,24,27648,0x7f466603c580,0x7f46630244c0,14234014823431,14234014834291,14234014925971,14234014927949
|
|
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,23354,23354,4194304,256,0,0,16,24,28608,0x7f466603c400,0x7f4663024500,14234014951198,14234014966132,14234015144852,14234015146834
|
|
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,23354,23354,4194304,256,0,0,16,24,29312,0x7f466603c280,0x7f4663024540,14234015161034,14234015171252,14234015351573,14234015353610
|
|
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,23354,23354,4194304,256,0,0,12,24,30016,0x7f466603c100,0x7f4663024580,14234015370610,14234015379573,14234015471573,14234015473548
|
|
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,23354,23354,4194304,256,0,0,8,24,30976,0x7f4663a0ff80,0x7f46630245c0,14234015489058,14234015497813,14234015589974,14234015592005
|
|
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,23354,23354,4194304,256,0,0,12,24,31680,0x7f4663a0fe00,0x7f4663024600,14234015612325,14234015622614,14234015715414,14234015717523
|
|
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,23354,23354,4194304,256,0,0,16,24,32640,0x7f4663a0fc80,0x7f4663024640,14234015735663,14234015745974,14234015925495,14234015927409
|
|
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,23354,23354,4194304,256,0,0,12,24,33600,0x7f4663a0fb00,0x7f4663024680,14234015946528,14234015969335,14234016149336,14234016151144
|
|
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,23354,23354,4194304,256,0,0,12,24,34560,0x7f4663a0f980,0x7f46630246c0,14234016166454,14234016175416,14234016268856,14234016270842
|
|
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,23354,23354,4194304,256,0,0,8,24,35520,0x7f4663a0f800,0x7f4663024700,14234016287351,14234016296056,14234016390297,14234016392229
|
|
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,23354,23354,4194304,256,0,0,12,24,36224,0x7f4663a0f680,0x7f4663024740,14234016414009,14234016423737,14234016517177,14234016519137
|
|
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,23354,23354,4194304,256,0,0,12,24,37184,0x7f466603c500,0x7f4663024780,14234016536486,14234016546297,14234016726458,14234016728462
|
|
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,23354,23354,4194304,256,0,0,12,24,38144,0x7f466603c380,0x7f46630247c0,14234016744812,14234016756858,14234016938779,14234016940528
|
|
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,23354,23354,4194304,256,0,0,12,24,39104,0x7f466603c200,0x7f4663024800,14234016954948,14234016965499,14234017059099,14234017060926
|
|
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,23354,23354,4194304,256,0,0,8,24,40320,0x7f466603c080,0x7f4663024840,14234017079085,14234017087419,14234017181500,14234017183433
|
|
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,23354,23354,4194304,256,0,0,12,24,41280,0x7f4663a0ff00,0x7f4663024880,14234017204383,14234017214780,14234017307580,14234017309520
|
|
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,23354,23354,4194304,256,0,0,12,24,42240,0x7f4663a0fd80,0x7f46630248c0,14234017328870,14234017344380,14234017523421,14234017525356
|
|
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,23354,23354,4194304,256,0,0,12,24,43200,0x7f4663a0fc00,0x7f4663024900,14234017545266,14234017555421,14234017736222,14234017738042
|
|
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,23354,23354,4194304,256,0,0,8,24,44160,0x7f4663a0fa80,0x7f4663024940,14234017759461,14234017768862,14234017862302,14234017864199
|
|
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,23354,23354,4194304,256,0,0,12,24,45376,0x7f4663a0f900,0x7f4663024980,14234017883879,14234017894302,14234017989022,14234017990967
|
|
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,23354,23354,4194304,256,0,0,12,24,46336,0x7f4663a0f780,0x7f46630249c0,14234018010896,14234018021503,14234018115263,14234018117354
|
|
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,23354,23354,4194304,256,0,0,12,24,47552,0x7f4663a0f600,0x7f4663024a00,14234018130334,14234018139263,14234018318944,14234018320900
|
|
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,23354,23354,4194304,256,0,0,12,24,48512,0x7f466603c480,0x7f4663024a40,14234018339889,14234018360704,14234018541024,14234018542995
|
|
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,23354,23354,4194304,256,0,0,8,24,49472,0x7f466603c300,0x7f4663024a80,14234018563335,14234018574145,14234018666945,14234018668963
|
|
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,23354,23354,4194304,256,0,0,12,24,50688,0x7f466603c180,0x7f4663024ac0,14234018689242,14234018699905,14234018793025,14234018795060
|
|
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,23354,23354,4194304,256,0,0,12,24,51648,0x7f466603c000,0x7f4663024b00,14234018816040,14234018826625,14234018918626,14234018920688
|
|
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,23354,23354,4194304,256,0,0,12,24,52864,0x7f4663a0fe80,0x7f4663024b40,14234018942367,14234018958466,14234019136867,14234019138283
|
|
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,23354,23354,4194304,256,0,0,12,24,54080,0x7f4663a0fd00,0x7f4663024b80,14234019153363,14234019161827,14234019341347,14234019342969
|
|
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,23354,23354,4194304,256,0,0,8,24,55296,0x7f4663a0fb80,0x7f4663024bc0,14234019356779,14234019364387,14234019458148,14234019459647
|
|
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,23354,23354,4194304,256,0,0,12,24,56768,0x7f4663a0fa00,0x7f4663024c00,14234019475866,14234019483908,14234019578948,14234019580324
|
|
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,23354,23354,4194304,256,0,0,12,24,57728,0x7f4663a0f880,0x7f4663024c40,14234019601674,14234019612548,14234019706469,14234019707781
|
|
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,23354,23354,4194304,256,0,0,12,24,58944,0x7f4663a0f700,0x7f4663024c80,14234019723121,14234019731109,14234019909829,14234019911167
|
|
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,23354,23354,4194304,256,0,0,12,24,60160,0x7f466603c580,0x7f4663024cc0,14234019926707,14234019935429,14234020117030,14234020118473
|
|
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,23354,23354,4194304,256,0,0,8,24,61376,0x7f466603c400,0x7f4663024d00,14234020133303,14234020141990,14234020235751,14234020237221
|
|
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,23354,23354,4194304,256,0,0,12,24,62848,0x7f466603c280,0x7f4663024d40,14234020253490,14234020260871,14234020361031,14234020362438
|
|
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,23354,23354,4194304,256,0,0,12,24,63808,0x7f466603c100,0x7f4663024d80,14234020384148,14234020394471,14234020487751,14234020489165
|
|
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,23354,23354,4194304,256,0,0,12,24,65024,0x7f4663a0ff80,0x7f4663024dc0,14234020506515,14234020514632,14234020695272,14234020696751
|
|
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,23354,23354,4194304,256,0,0,12,24,66240,0x7f4663a0fe00,0x7f4663024e00,14234020712461,14234020720232,14234020900873,14234020902207
|
|
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,23354,23354,4194304,256,0,0,8,24,67456,0x7f4663a0fc80,0x7f4663024e40,14234020917947,14234020925993,14234021019913,14234021021235
|
|
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,23354,23354,4194304,256,0,0,12,24,68928,0x7f4663a0fb00,0x7f4663024e80,14234021036554,14234021044713,14234021148394,14234021149712
|
|
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,23354,23354,4194304,256,0,0,12,24,70144,0x7f4663a0f980,0x7f4663024ec0,14234021170931,14234021181354,14234021273994,14234021275339
|
|
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,23354,23354,4194304,256,0,0,12,24,71616,0x7f4663a0f800,0x7f4663024f00,14234021290999,14234021298954,14234021478635,14234021479945
|
|
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,23354,23354,4194304,256,0,0,12,24,72832,0x7f4663a0f680,0x7f4663024f40,14234021496515,14234021504555,14234021686636,14234021688021
|
|
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,23354,23354,4194304,256,0,0,8,24,74048,0x7f466603c500,0x7f4663024f80,14234021703261,14234021711116,14234021805036,14234021806358
|
|
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,23354,23354,4194304,256,0,0,12,24,75776,0x7f466603c380,0x7f4663024fc0,14234021820638,14234021829996,14234021936717,14234021938086
|
|
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,23354,23354,4194304,256,0,0,12,24,76992,0x7f466603c200,0x7f4663025000,14234021958555,14234021969517,14234022064237,14234022065793
|
|
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,23354,23354,4194304,256,0,0,12,24,78464,0x7f466603c080,0x7f4663025040,14234022114642,14234022125517,14234022304238,14234022305688
|
|
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,23354,23354,4194304,256,0,0,12,24,79936,0x7f4663a0ff00,0x7f4663025080,14234022320438,14234022328398,14234022507279,14234022508744
|
|
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,23354,23354,4194304,256,0,0,8,24,81408,0x7f4663a0fd80,0x7f46630250c0,14234022523274,14234022531439,14234022626159,14234022627702
|
|
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,23354,23354,4194304,256,0,0,12,24,83136,0x7f4663a0fc00,0x7f4663025100,14234022641921,14234022649679,14234022764720,14234022766199
|
|
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,23354,23354,4194304,256,0,0,12,24,84352,0x7f4663a0fa80,0x7f4663025140,14234022802508,14234022811920,14234022906000,14234022907316
|
|
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,23354,23354,4194304,256,0,0,12,24,85824,0x7f4663a0f900,0x7f4663025180,14234022923026,14234022930800,14234023109521,14234023110862
|
|
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,23354,23354,4194304,256,0,0,12,24,87296,0x7f4663a0f780,0x7f46630251c0,14234023125771,14234023133841,14234023312402,14234023313738
|
|
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,23354,23354,4194304,256,0,0,12,24,88768,0x7f4663a0f600,0x7f4663025200,14234023327777,14234023335602,14234023430322,14234023431885
|
|
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,23354,23354,4194304,256,0,0,12,24,90752,0x7f466603c480,0x7f4663025240,14234023446615,14234023456402,14234023576723,14234023578072
|
|
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,23354,23354,4194304,256,0,0,12,24,91968,0x7f466603c300,0x7f4663025280,14234023599102,14234023609523,14234023702963,14234023704399
|
|
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,23354,23354,4194304,256,0,0,12,24,93440,0x7f466603c180,0x7f46630252c0,14234023719949,14234023728083,14234023908404,14234023909945
|
|
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,23354,23354,4194304,256,0,0,12,24,94912,0x7f466603c000,0x7f4663025300,14234023924085,14234023931924,14234024114645,14234024115971
|
|
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,23354,23354,4194304,256,0,0,12,24,96384,0x7f4663a0fe80,0x7f4663025340,14234024130981,14234024140245,14234024235285,14234024236679
|
|
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,23354,23354,4194304,256,0,0,12,24,98368,0x7f4663a0fd00,0x7f4663025380,14234024251948,14234024260885,14234024387446,14234024388675
|
|
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,23354,23354,4194304,256,0,0,12,24,99584,0x7f4663a0fb80,0x7f46630253c0,14234024409575,14234024419926,14234024514806,14234024516113
|
|
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,23354,23354,4194304,256,0,0,12,24,101312,0x7f4663a0fa00,0x7f4663025400,14234024532103,14234024540886,14234024719767,14234024721169
|
|
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,23354,23354,4194304,256,0,0,12,24,102784,0x7f4663a0f880,0x7f4663025440,14234024736028,14234024744247,14234024924567,14234024926024
|
|
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,23354,23354,4194304,256,0,0,12,24,104256,0x7f4663a0f700,0x7f4663025480,14234024940834,14234024949688,14234025043928,14234025045302
|
|
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,23354,23354,4194304,256,0,0,12,24,106240,0x7f466603c580,0x7f46630254c0,14234025059912,14234025069208,14234025199608,14234025200949
|
|
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,23354,23354,4194304,256,0,0,12,24,107712,0x7f466603c400,0x7f4663025500,14234025222008,14234025232569,14234025325529,14234025326906
|
|
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,23354,23354,4194304,256,0,0,16,24,109440,0x7f466603c280,0x7f4663025540,14234025343066,14234025353209,14234025531770,14234025533152
|
|
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,23354,23354,4194304,256,0,0,16,24,111168,0x7f466603c100,0x7f4663025580,14234025548482,14234025557210,14234025736410,14234025737768
|
|
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,23354,23354,4194304,256,0,0,8,24,112896,0x7f4663a0ff80,0x7f46630255c0,14234025753557,14234025761850,14234025856411,14234025857895
|
|
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,23354,23354,4194304,256,0,0,12,24,115136,0x7f4663a0fe00,0x7f4663025600,14234025874235,14234025882811,14234026020891,14234026022252
|
|
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,23354,23354,4194304,256,0,0,12,24,116608,0x7f4663a0fc80,0x7f4663025640,14234026042862,14234026053372,14234026148092,14234026149689
|
|
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,23354,23354,4194304,256,0,0,16,24,118336,0x7f4663a0fb00,0x7f4663025680,14234026166029,14234026173692,14234026353053,14234026354705
|
|
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,23354,23354,4194304,256,0,0,16,24,120064,0x7f4663a0f980,0x7f46630256c0,14234026368835,14234026377533,14234026557053,14234026558591
|
|
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,23354,23354,4194304,256,0,0,12,24,121792,0x7f4663a0f800,0x7f4663025700,14234026573301,14234026581373,14234026678174,14234026679728
|
|
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,23354,23354,4194304,256,0,0,12,24,124032,0x7f4663a0f680,0x7f4663025740,14234026694798,14234026702654,14234026847934,14234026849455
|
|
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,23354,23354,4194304,256,0,0,12,24,125504,0x7f466603c500,0x7f4663025780,14234026869165,14234026879935,14234026975135,14234026976642
|
|
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,23354,23354,4194304,256,0,0,12,24,127488,0x7f466603c380,0x7f46630257c0,14234026991722,14234026999615,14234027179936,14234027181548
|
|
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,23354,23354,4194304,256,0,0,12,24,129216,0x7f466603c200,0x7f4663025800,14234027195458,14234027203296,14234027383136,14234027384494
|
|
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,23354,23354,4194304,256,0,0,12,24,130944,0x7f466603c080,0x7f4663025840,14234027397454,14234027406336,14234027506497,14234027507992
|
|
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,23354,23354,4194304,256,0,0,12,24,133440,0x7f4663a0ff00,0x7f4663025880,14234027521831,14234027530657,14234027686017,14234027687418
|
|
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,23354,23354,4194304,256,0,0,12,24,134912,0x7f4663a0fd80,0x7f46630258c0,14234027707587,14234027718498,14234027813218,14234027814705
|
|
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,23354,23354,4194304,256,0,0,12,24,136896,0x7f4663a0fc00,0x7f4663025900,14234027829365,14234027838018,14234028017859,14234028019271
|
|
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,23354,23354,4194304,256,0,0,12,24,138880,0x7f4663a0fa80,0x7f4663025940,14234028036131,14234028043779,14234028224899,14234028226317
|
|
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,23354,23354,4194304,256,0,0,12,24,140864,0x7f4663a0f900,0x7f4663025980,14234028240686,14234028248579,14234028356420,14234028357724
|
|
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,23354,23354,4194304,256,0,0,12,24,143616,0x7f4663a0f780,0x7f46630259c0,14234028371384,14234028380740,14234028551461,14234028552780
|
|
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,23354,23354,4194304,256,0,0,12,24,145344,0x7f4663a0f600,0x7f4663025a00,14234028572720,14234028583461,14234028679461,14234028680837
|
|
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,23354,23354,4194304,256,0,0,12,24,147584,0x7f466603c480,0x7f4663025a40,14234028696357,14234028704261,14234028885702,14234028887143
|
|
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,23354,23354,4194304,256,0,0,12,24,149568,0x7f466603c300,0x7f4663025a80,14234028901153,14234028909862,14234029091142,14234029092499
|
|
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,23354,23354,4194304,256,0,0,12,24,151552,0x7f466603c180,0x7f4663025ac0,14234029106699,14234029114663,14234029225543,14234029226786
|
|
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,23354,23354,4194304,256,0,0,12,24,154304,0x7f466603c000,0x7f4663025b00,14234029241296,14234029249543,14234029430504,14234029432032
|
|
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,23354,23354,4194304,256,0,0,12,24,156288,0x7f4663a0fe80,0x7f4663025b40,14234029452842,14234029462824,14234029563464,14234029564879
|
|
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,23354,23354,4194304,256,0,0,12,24,158784,0x7f4663a0fd00,0x7f4663025b80,14234029580619,14234029588744,14234029773065,14234029774385
|
|
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,23354,23354,4194304,256,0,0,12,24,161024,0x7f4663a0fb80,0x7f4663025bc0,14234029789455,14234029798185,14234029983306,14234029984621
|
|
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,23354,23354,4194304,256,0,0,12,24,163264,0x7f4663a0fa00,0x7f4663025c00,14234029999770,14234030008106,14234030130186,14234030131908
|
|
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,23354,23354,4194304,256,0,0,12,24,166528,0x7f4663a0f880,0x7f4663025c40,14234030146117,14234030154506,14234030360907,14234030407682
|
|
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,23354,23354,4194304,256,0,0,12,24,168512,0x7f4663a0f700,0x7f4663025c80,14234030422602,14234030433387,14234030543788,14234030545239
|
|
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,23354,23354,4194304,256,0,0,12,24,171264,0x7f466603c580,0x7f4663025cc0,14234030561159,14234030569548,14234030751948,14234030753545
|
|
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,23354,23354,4194304,256,0,0,12,24,173760,0x7f466603c400,0x7f4663025d00,14234030768235,14234030775949,14234030962189,14234030963851
|
|
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,23354,23354,4194304,256,0,0,12,24,176256,0x7f466603c280,0x7f4663025d40,14234030979420,14234030987149,14234031121390,14234031123048
|
|
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,23354,23354,4194304,256,0,0,12,24,179776,0x7f466603c100,0x7f4663025d80,14234031136337,14234031144110,14234031376111,14234031419942
|
|
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,23354,23354,4194304,256,0,0,12,24,182272,0x7f4663a0ff80,0x7f4663025dc0,14234031434221,14234031445071,14234031571311,14234031572698
|
|
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,23354,23354,4194304,256,0,0,12,24,185536,0x7f4663a0fe00,0x7f4663025e00,14234031588388,14234031596272,14234031788272,14234031789594
|
|
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,23354,23354,4194304,256,0,0,12,24,188544,0x7f4663a0fc80,0x7f4663025e40,14234031804754,14234031813392,14234032007633,14234032009040
|
|
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,23354,23354,4194304,256,0,0,12,24,191552,0x7f4663a0fb00,0x7f4663025e80,14234032024559,14234032032593,14234032192274,14234032193786
|
|
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,23354,23354,4194304,256,0,0,12,24,195840,0x7f4663a0f980,0x7f4663025ec0,14234032209005,14234032216914,14234032500275,14234032519999
|
|
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,23354,23354,4194304,256,0,0,12,24,198592,0x7f4663a0f800,0x7f4663025f00,14234032534009,14234032544755,14234032694195,14234032695556
|
|
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,23354,23354,4194304,256,0,0,12,24,202368,0x7f4663a0f680,0x7f4663025f40,14234032711065,14234032720756,14234032928596,14234032944521
|
|
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,23354,23354,4194304,256,0,0,12,24,205888,0x7f466603c500,0x7f4663025f80,14234032952530,14234032962836,14234033173557,14234033190286
|
|
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,23354,23354,4194304,256,0,0,12,24,209408,0x7f466603c380,0x7f4663025fc0,14234033197855,14234033208597,14234033394358,14234033395701
|
|
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,23354,23354,4194304,256,0,0,12,24,214464,0x7f466603c200,0x7f4663026000,14234033409521,14234033418358,14234033752759,14234033768894
|
|
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,23354,23354,4194304,256,0,0,12,24,217728,0x7f466603c080,0x7f4663026040,14234033783503,14234033794199,14234033962200,14234033963640
|
|
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,23354,23354,4194304,256,0,0,12,24,222016,0x7f4663a0ff00,0x7f4663026080,14234033978459,14234033987960,14234034217081,14234034238254
|
|
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,23354,23354,4194304,256,0,0,12,24,226048,0x7f4663a0fd80,0x7f46630260c0,14234034248614,14234034263641,14234034493242,14234034513209
|
|
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,23354,23354,4194304,256,0,0,12,24,230080,0x7f4663a0fc00,0x7f4663026100,14234034520728,14234034530682,14234034741883,14234034761103
|
|
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,23354,23354,4194304,256,0,0,12,24,235904,0x7f4663a0fa80,0x7f4663026140,14234034769323,14234034778683,14234035164284,14234035183925
|
|
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,23354,23354,4194304,256,0,0,12,24,239424,0x7f4663a0f900,0x7f4663026180,14234035199404,14234035210045,14234035396765,14234035398090
|
|
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,23354,23354,4194304,256,0,0,12,24,244224,0x7f4663a0f780,0x7f46630261c0,14234035413920,14234035421725,14234035671326,14234035691224
|
|
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,23354,23354,4194304,256,0,0,12,24,248768,0x7f4663a0f600,0x7f4663026200,14234035698684,14234035708766,14234035955967,14234035977289
|
|
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,23354,23354,4194304,256,0,0,12,24,253312,0x7f466603c480,0x7f4663026240,14234035985058,14234035995327,14234036231968,14234036251033
|
|
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,23354,23354,4194304,256,0,0,8,24,255552,0x7f466603c300,0x7f4663026280,14234036258623,14234036268928,14234036721890,14234036741333
|
|
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,23354,23354,4194304,256,0,0,12,24,259840,0x7f466603c180,0x7f46630262c0,14234036755243,14234036766370,14234036992131,14234037008577
|
|
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,23354,23354,4194304,256,0,0,12,24,265664,0x7f466603c000,0x7f4663026300,14234037016317,14234037026691,14234037324772,14234037340111
|
|
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,23354,23354,4194304,256,0,0,12,24,271232,0x7f4663a0fe80,0x7f4663026340,14234037348360,14234037358052,14234037656933,14234037676034
|
|
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,23354,23354,4194304,256,0,0,8,24,273216,0x7f4663a0fd00,0x7f4663026380,14234037684054,14234037694534,14234037990695,14234038008917
|
|
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,23354,23354,4194304,256,0,0,8,24,275712,0x7f4663a0fb80,0x7f46630263c0,14234038016897,14234038026855,14234038584457,14234038605655
|
|
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,23354,23354,4194304,256,0,0,12,24,280768,0x7f4663a0fa00,0x7f4663026400,14234038620254,14234038631017,14234038894858,14234038918328
|
|
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,23354,23354,4194304,256,0,0,12,24,287616,0x7f4663a0f880,0x7f4663026440,14234038925798,14234038936138,14234039287499,14234039309170
|
|
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,23354,23354,4194304,256,0,0,12,24,294208,0x7f4663a0f700,0x7f4663026480,14234039316740,14234039329259,14234039679981,14234039701842
|
|
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,23354,23354,4194304,256,0,0,8,24,296960,0x7f466603c580,0x7f46630264c0,14234039709552,14234039719981,14234040066542,14234040085434
|
|
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,23354,23354,4194304,256,0,0,8,24,299968,0x7f466603c400,0x7f4663026500,14234040092814,14234040103022,14234040764465,14234040786660
|
|
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,23354,23354,4194304,256,0,0,8,24,302720,0x7f466603c280,0x7f4663026540,14234040802370,14234040812465,14234041260306,14234041281970
|
|
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,23354,23354,4194304,256,0,0,12,24,305472,0x7f466603c100,0x7f4663026580,14234041289510,14234041299987,14234041764628,14234041780550
|
|
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,23354,23354,4194304,256,0,0,12,24,308224,0x7f4663a0ff80,0x7f46630265c0,14234041788109,14234041798388,14234042260150,14234042284069
|
|
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,23354,23354,4194304,256,0,0,8,24,310976,0x7f4663a0fe00,0x7f4663026600,14234042291059,14234042301750,14234042753592,14234042776989
|
|
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,23354,23354,4194304,256,0,0,8,24,313216,0x7f4663a0fc80,0x7f4663026640,14234042784379,14234042794872,14234043663995,14234043685950
|
|
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,23354,23354,4194304,256,0,0,8,24,315968,0x7f4663a0fb00,0x7f4663026680,14234043700620,14234043711515,14234044565918,14234044588602
|
|
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,23354,23354,4194304,256,0,0,12,24,318720,0x7f4663a0f980,0x7f46630266c0,14234044596322,14234044606718,14234045492322,14234045516113
|
|
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,23354,23354,4194304,256,0,0,12,24,321472,0x7f4663a0f800,0x7f4663026700,14234045524063,14234045534562,14234046414085,14234046440364
|
|
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,23354,23354,4194304,256,0,0,8,24,324224,0x7f4663a0f680,0x7f4663026740,14234046453264,14234046467205,14234047325608,14234047373635
|
|
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,23354,23354,4194304,256,0,0,8,24,326464,0x7f466603c500,0x7f4663026780,14234047381445,14234047400009,14234049098735,14234049168468
|
|
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,23354,23354,4194304,256,0,0,8,24,329216,0x7f466603c380,0x7f46630267c0,14234049185618,14234049196175,14234050861621,14234050931482
|
|
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,23354,23354,4194304,256,0,0,12,24,331968,0x7f466603c200,0x7f4663026800,14234050941852,14234050951381,14234052676988,14234052748595
|
|
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,23354,23354,4194304,256,0,0,12,24,334720,0x7f466603c080,0x7f4663026840,14234052756475,14234052767228,14234054481954,14234054555358
|
|
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,23354,23354,4194304,256,0,0,8,24,337472,0x7f4663a0ff00,0x7f4663026880,14234054564958,14234054580194,14234056254761,14234056326162
|
|
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,23354,23354,4194304,256,0,0,8,24,0,0x7f4663a0fd80,0x7f46630268c0,14234056334182,14234056350761,14234059707413,14234059779711
|