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",0,0,0,163048,163048,33554432,256,0,0,4,32,4160,0x0,0x7f20e6604280,16530446811403,16530446836344,16530447076822,16530447164691
|
|
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,163048,163048,32768,256,0,0,12,24,13888,0x0,0x7f20e6623f80,16530451847800,16530451863499,16530451877259,16530451894228
|
|
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,163048,163048,4194304,256,0,0,12,24,14336,0x7f20e952d380,0x7f20e6623fc0,16530451899078,16530451947178,16530452039817,16530452042063
|
|
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,163048,163048,4194304,256,0,0,16,24,15040,0x7f20e952d200,0x7f20e6624000,16530452063892,16530452073097,16530452252455,16530452254685
|
|
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,163048,163048,4194304,256,0,0,16,24,15488,0x7f20e952d080,0x7f20e6624040,16530452269814,16530452277895,16530452458533,16530452460577
|
|
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,163048,163048,4194304,256,0,0,12,24,15936,0x7f20e6dcdf00,0x7f20e6624080,16530452473907,16530452482533,16530452575972,16530452578223
|
|
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,163048,163048,4194304,256,0,0,12,24,16384,0x7f20e6dcdd80,0x7f20e66240c0,16530452594373,16530452602212,16530452694051,16530452696209
|
|
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,163048,163048,4194304,256,0,0,12,24,17088,0x7f20e6dcdc00,0x7f20e6624100,16530452723238,16530452734051,16530452826530,16530452828504
|
|
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,163048,163048,4194304,256,0,0,16,24,17792,0x7f20e6dcda80,0x7f20e6624140,16530452848543,16530452858690,16530453039008,16530453040976
|
|
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,163048,163048,4194304,256,0,0,16,24,18496,0x7f20e6dcd900,0x7f20e6624180,16530453060976,16530453071648,16530453251806,16530453253889
|
|
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,163048,163048,4194304,256,0,0,16,24,19200,0x7f20e6dcd780,0x7f20e66241c0,16530453271708,16530453290206,16530453383645,16530453385794
|
|
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,163048,163048,4194304,256,0,0,16,24,19904,0x7f20e6dcd600,0x7f20e6624200,16530453403703,16530453412605,16530453505404,16530453507509
|
|
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,163048,163048,4194304,256,0,0,12,24,20608,0x7f20e952d480,0x7f20e6624240,16530453527249,16530453537724,16530453630203,16530453632055
|
|
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,163048,163048,4194304,256,0,0,16,24,21312,0x7f20e952d300,0x7f20e6624280,16530453651064,16530453659643,16530453839321,16530453841367
|
|
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,163048,163048,4194304,256,0,0,16,24,22016,0x7f20e952d180,0x7f20e66242c0,16530453855167,16530453864921,16530454045879,16530454047910
|
|
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,163048,163048,4194304,256,0,0,16,24,22720,0x7f20e952d000,0x7f20e6624300,16530454064039,16530454073879,16530454166998,16530454169105
|
|
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,163048,163048,4194304,256,0,0,12,24,23424,0x7f20e6dcde80,0x7f20e6624340,16530454184745,16530454196118,16530454290197,16530454292201
|
|
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,163048,163048,4194304,256,0,0,12,24,24128,0x7f20e6dcdd00,0x7f20e6624380,16530454314390,16530454325077,16530454418836,16530454420876
|
|
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,163048,163048,4194304,256,0,0,16,24,24832,0x7f20e6dcdb80,0x7f20e66243c0,16530454463545,16530454474036,16530454653874,16530454655808
|
|
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,163048,163048,4194304,256,0,0,16,24,25536,0x7f20e6dcda00,0x7f20e6624400,16530454676827,16530454687154,16530454866512,16530454868600
|
|
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,163048,163048,4194304,256,0,0,12,24,26240,0x7f20e6dcd880,0x7f20e6624440,16530454886589,16530454919472,16530455012591,16530455015004
|
|
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,163048,163048,4194304,256,0,0,12,24,26944,0x7f20e6dcd700,0x7f20e6624480,16530455028324,16530455038351,16530455131150,16530455133180
|
|
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,163048,163048,4194304,256,0,0,12,24,27648,0x7f20e952d580,0x7f20e66244c0,16530455154719,16530455165069,16530455257229,16530455258966
|
|
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,163048,163048,4194304,256,0,0,16,24,28608,0x7f20e952d400,0x7f20e6624500,16530455274725,16530455282508,16530455461387,16530455462968
|
|
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,163048,163048,4194304,256,0,0,16,24,29312,0x7f20e952d280,0x7f20e6624540,16530455479567,16530455488107,16530455667465,16530455669051
|
|
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,163048,163048,4194304,256,0,0,12,24,30016,0x7f20e952d100,0x7f20e6624580,16530455682690,16530455690985,16530455782664,16530455784166
|
|
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,163048,163048,4194304,256,0,0,8,24,30976,0x7f20e6dcdf80,0x7f20e66245c0,16530455798906,16530455807464,16530455899143,16530455900672
|
|
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,163048,163048,4194304,256,0,0,12,24,31680,0x7f20e6dcde00,0x7f20e6624600,16530455920811,16530455931463,16530456024582,16530456026178
|
|
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,163048,163048,4194304,256,0,0,16,24,32640,0x7f20e6dcdc80,0x7f20e6624640,16530456041227,16530456050022,16530456229860,16530456231320
|
|
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,163048,163048,4194304,256,0,0,12,24,33600,0x7f20e6dcdb00,0x7f20e6624680,16530456245270,16530456253860,16530456434338,16530456435933
|
|
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,163048,163048,4194304,256,0,0,12,24,34560,0x7f20e6dcd980,0x7f20e66246c0,16530456450202,16530456458658,16530456552897,16530456554408
|
|
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,163048,163048,4194304,256,0,0,8,24,35520,0x7f20e6dcd800,0x7f20e6624700,16530456569398,16530456578977,16530456673216,16530456674684
|
|
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,163048,163048,4194304,256,0,0,12,24,36224,0x7f20e6dcd680,0x7f20e6624740,16530456695153,16530456705216,16530456798335,16530456799769
|
|
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,163048,163048,4194304,256,0,0,12,24,37184,0x7f20e952d500,0x7f20e6624780,16530456814699,16530456823295,16530457004253,16530457005792
|
|
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,163048,163048,4194304,256,0,0,12,24,38144,0x7f20e952d380,0x7f20e66247c0,16530457019441,16530457029533,16530457210971,16530457212484
|
|
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,163048,163048,4194304,256,0,0,12,24,39104,0x7f20e952d200,0x7f20e6624800,16530457226774,16530457236571,16530457330170,16530457331750
|
|
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,163048,163048,4194304,256,0,0,8,24,40320,0x7f20e952d080,0x7f20e6624840,16530457346059,16530457355610,16530457450489,16530457452005
|
|
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,163048,163048,4194304,256,0,0,12,24,41280,0x7f20e6dcdf00,0x7f20e6624880,16530457472135,16530457483129,16530457576888,16530457578321
|
|
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,163048,163048,4194304,256,0,0,12,24,42240,0x7f20e6dcdd80,0x7f20e66248c0,16530457594580,16530457602968,16530457781686,16530457783233
|
|
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,163048,163048,4194304,256,0,0,12,24,43200,0x7f20e6dcdc00,0x7f20e6624900,16530457798053,16530457806326,16530457987124,16530457988576
|
|
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,163048,163048,4194304,256,0,0,8,24,44160,0x7f20e6dcda80,0x7f20e6624940,16530458004245,16530458013204,16530458107923,16530458109651
|
|
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,163048,163048,4194304,256,0,0,12,24,45376,0x7f20e6dcd900,0x7f20e6624980,16530458122901,16530458131443,16530458226162,16530458227857
|
|
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,163048,163048,4194304,256,0,0,12,24,46336,0x7f20e6dcd780,0x7f20e66249c0,16530458246486,16530458258802,16530458351761,16530458353453
|
|
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,163048,163048,4194304,256,0,0,12,24,47552,0x7f20e6dcd600,0x7f20e6624a00,16530458367632,16530458375921,16530458555279,16530458556855
|
|
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,163048,163048,4194304,256,0,0,12,24,48512,0x7f20e952d480,0x7f20e6624a40,16530458571615,16530458580239,16530458761997,16530458763558
|
|
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,163048,163048,4194304,256,0,0,8,24,49472,0x7f20e952d300,0x7f20e6624a80,16530458777837,16530458786477,16530458879116,16530458880683
|
|
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,163048,163048,4194304,256,0,0,12,24,50688,0x7f20e952d180,0x7f20e6624ac0,16530458895043,16530458904396,16530458998315,16530458999809
|
|
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,163048,163048,4194304,256,0,0,12,24,51648,0x7f20e952d000,0x7f20e6624b00,16530459020158,16530459030315,16530459122314,16530459123874
|
|
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,163048,163048,4194304,256,0,0,12,24,52864,0x7f20e6dcde80,0x7f20e6624b40,16530459142144,16530459149834,16530459328872,16530459330457
|
|
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,163048,163048,4194304,256,0,0,12,24,54080,0x7f20e6dcdd00,0x7f20e6624b80,16530459344546,16530459353672,16530459532871,16530459534419
|
|
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,163048,163048,4194304,256,0,0,8,24,55296,0x7f20e6dcdb80,0x7f20e6624bc0,16530459547719,16530459556070,16530459649670,16530459651135
|
|
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,163048,163048,4194304,256,0,0,12,24,56768,0x7f20e6dcda00,0x7f20e6624c00,16530459666365,16530459674309,16530459770308,16530459771901
|
|
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,163048,163048,4194304,256,0,0,12,24,57728,0x7f20e6dcd880,0x7f20e6624c40,16530459792330,16530459803268,16530459897347,16530459898936
|
|
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,163048,163048,4194304,256,0,0,12,24,58944,0x7f20e6dcd700,0x7f20e6624c80,16530459914106,16530459921987,16530460102466,16530460103919
|
|
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,163048,163048,4194304,256,0,0,12,24,60160,0x7f20e952d580,0x7f20e6624cc0,16530460119458,16530460127585,16530460309344,16530460310881
|
|
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,163048,163048,4194304,256,0,0,8,24,61376,0x7f20e952d400,0x7f20e6624d00,16530460327340,16530460335743,16530460430463,16530460431937
|
|
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,163048,163048,4194304,256,0,0,12,24,62848,0x7f20e952d280,0x7f20e6624d40,16530460449266,16530460457182,16530460556221,16530460557772
|
|
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,163048,163048,4194304,256,0,0,12,24,63808,0x7f20e952d100,0x7f20e6624d80,16530460577851,16530460588381,16530460681500,16530460683057
|
|
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,163048,163048,4194304,256,0,0,12,24,65024,0x7f20e6dcdf80,0x7f20e6624dc0,16530460700557,16530460709660,16530460888539,16530460890150
|
|
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,163048,163048,4194304,256,0,0,12,24,66240,0x7f20e6dcde00,0x7f20e6624e00,16530460906319,16530460914458,16530461092697,16530461094182
|
|
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,163048,163048,4194304,256,0,0,8,24,67456,0x7f20e6dcdc80,0x7f20e6624e40,16530461110452,16530461119416,16530461213496,16530461215088
|
|
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,163048,163048,4194304,256,0,0,12,24,68928,0x7f20e6dcdb00,0x7f20e6624e80,16530461228857,16530461238135,16530461343254,16530461344773
|
|
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,163048,163048,4194304,256,0,0,12,24,70144,0x7f20e6dcd980,0x7f20e6624ec0,16530461364653,16530461375094,16530461468053,16530461469569
|
|
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,163048,163048,4194304,256,0,0,12,24,71616,0x7f20e6dcd800,0x7f20e6624f00,16530461485828,16530461493653,16530461673812,16530461675311
|
|
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,163048,163048,4194304,256,0,0,12,24,72832,0x7f20e6dcd680,0x7f20e6624f40,16530461691381,16530461700051,16530461880050,16530461881624
|
|
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,163048,163048,4194304,256,0,0,8,24,74048,0x7f20e952d500,0x7f20e6624f80,16530461896023,16530461904849,16530461998769,16530462000229
|
|
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,163048,163048,4194304,256,0,0,12,24,75776,0x7f20e952d380,0x7f20e6624fc0,16530462016949,16530462024528,16530462131727,16530462133554
|
|
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,163048,163048,4194304,256,0,0,12,24,76992,0x7f20e952d200,0x7f20e6625000,16530462156054,16530462166447,16530462259726,16530462261590
|
|
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,163048,163048,4194304,256,0,0,12,24,78464,0x7f20e952d080,0x7f20e6625040,16530462275899,16530462283726,16530462462925,16530462464502
|
|
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,163048,163048,4194304,256,0,0,12,24,79936,0x7f20e6dcdf00,0x7f20e6625080,16530462478352,16530462486604,16530462666283,16530462667815
|
|
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,163048,163048,4194304,256,0,0,8,24,81408,0x7f20e6dcdd80,0x7f20e66250c0,16530462681844,16530462690603,16530462785322,16530462786921
|
|
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,163048,163048,4194304,256,0,0,12,24,83136,0x7f20e6dcdc00,0x7f20e6625100,16530462800330,16530462808521,16530462923400,16530462924956
|
|
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,163048,163048,4194304,256,0,0,12,24,84352,0x7f20e6dcda80,0x7f20e6625140,16530462958294,16530462968040,16530463061959,16530463063480
|
|
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,163048,163048,4194304,256,0,0,12,24,85824,0x7f20e6dcd900,0x7f20e6625180,16530463079420,16530463087399,16530463266917,16530463268733
|
|
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,163048,163048,4194304,256,0,0,12,24,87296,0x7f20e6dcd780,0x7f20e66251c0,16530463284012,16530463291877,16530463471236,16530463472916
|
|
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,163048,163048,4194304,256,0,0,12,24,88768,0x7f20e6dcd600,0x7f20e6625200,16530463487255,16530463495875,16530463590755,16530463592161
|
|
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,163048,163048,4194304,256,0,0,12,24,90752,0x7f20e952d480,0x7f20e6625240,16530463608561,16530463618114,16530463738753,16530463740366
|
|
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,163048,163048,4194304,256,0,0,12,24,91968,0x7f20e952d300,0x7f20e6625280,16530463760375,16530463771073,16530463864032,16530463865551
|
|
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,163048,163048,4194304,256,0,0,12,24,93440,0x7f20e952d180,0x7f20e66252c0,16530463882231,16530463889952,16530464069470,16530464071084
|
|
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,163048,163048,4194304,256,0,0,12,24,94912,0x7f20e952d000,0x7f20e6625300,16530464088073,16530464096030,16530464275868,16530464277656
|
|
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,163048,163048,4194304,256,0,0,12,24,96384,0x7f20e6dcde80,0x7f20e6625340,16530464293036,16530464301468,16530464396827,16530464398272
|
|
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,163048,163048,4194304,256,0,0,12,24,98368,0x7f20e6dcdd00,0x7f20e6625380,16530464413251,16530464421947,16530464548986,16530464550476
|
|
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,163048,163048,4194304,256,0,0,12,24,99584,0x7f20e6dcdb80,0x7f20e66253c0,16530464571955,16530464582586,16530464676665,16530464678231
|
|
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,163048,163048,4194304,256,0,0,12,24,101312,0x7f20e6dcda00,0x7f20e6625400,16530464694041,16530464702105,16530464882263,16530464883814
|
|
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,163048,163048,4194304,256,0,0,12,24,102784,0x7f20e6dcd880,0x7f20e6625440,16530464899443,16530464907863,16530465087701,16530465089216
|
|
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,163048,163048,4194304,256,0,0,12,24,104256,0x7f20e6dcd700,0x7f20e6625480,16530465104346,16530465112341,16530465206260,16530465207702
|
|
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,163048,163048,4194304,256,0,0,12,24,106240,0x7f20e952d580,0x7f20e66254c0,16530465223532,16530465232180,16530465362259,16530465363806
|
|
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,163048,163048,4194304,256,0,0,12,24,107712,0x7f20e952d400,0x7f20e6625500,16530465383386,16530465394578,16530465487698,16530465489162
|
|
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,163048,163048,4194304,256,0,0,16,24,109440,0x7f20e952d280,0x7f20e6625540,16530465505491,16530465514257,16530465693456,16530465695044
|
|
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,163048,163048,4194304,256,0,0,16,24,111168,0x7f20e952d100,0x7f20e6625580,16530465709284,16530465718256,16530465897774,16530465899217
|
|
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,163048,163048,4194304,256,0,0,8,24,112896,0x7f20e6dcdf80,0x7f20e66255c0,16530465912936,16530465922094,16530466017773,16530466019343
|
|
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,163048,163048,4194304,256,0,0,12,24,115136,0x7f20e6dcde00,0x7f20e6625600,16530466033412,16530466042093,16530466181291,16530466182967
|
|
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,163048,163048,4194304,256,0,0,12,24,116608,0x7f20e6dcdc80,0x7f20e6625640,16530466203866,16530466214411,16530466308650,16530466310292
|
|
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,163048,163048,4194304,256,0,0,16,24,118336,0x7f20e6dcdb00,0x7f20e6625680,16530466324311,16530466332650,16530466512009,16530466513604
|
|
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,163048,163048,4194304,256,0,0,16,24,120064,0x7f20e6dcd980,0x7f20e66256c0,16530466527904,16530466536488,16530466716007,16530466717747
|
|
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,163048,163048,4194304,256,0,0,12,24,121792,0x7f20e6dcd800,0x7f20e6625700,16530466731786,16530466740167,16530466836966,16530466838643
|
|
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,163048,163048,4194304,256,0,0,12,24,124032,0x7f20e6dcd680,0x7f20e6625740,16530466854142,16530466862085,16530467007364,16530467008966
|
|
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,163048,163048,4194304,256,0,0,12,24,125504,0x7f20e952d500,0x7f20e6625780,16530467028126,16530467039364,16530467134883,16530467136562
|
|
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,163048,163048,4194304,256,0,0,12,24,127488,0x7f20e952d380,0x7f20e66257c0,16530467151891,16530467160003,16530467339841,16530467341464
|
|
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,163048,163048,4194304,256,0,0,12,24,129216,0x7f20e952d200,0x7f20e6625800,16530467356124,16530467365441,16530467546399,16530467547887
|
|
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,163048,163048,4194304,256,0,0,12,24,130944,0x7f20e952d080,0x7f20e6625840,16530467561866,16530467570719,16530467670558,16530467672162
|
|
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,163048,163048,4194304,256,0,0,12,24,133440,0x7f20e6dcdf00,0x7f20e6625880,16530467686442,16530467694398,16530467849757,16530467851486
|
|
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,163048,163048,4194304,256,0,0,12,24,134912,0x7f20e6dcdd80,0x7f20e66258c0,16530467872185,16530467882716,16530467977116,16530467978751
|
|
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,163048,163048,4194304,256,0,0,12,24,136896,0x7f20e6dcdc00,0x7f20e6625900,16530467993590,16530468001435,16530468180634,16530468182243
|
|
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,163048,163048,4194304,256,0,0,12,24,138880,0x7f20e6dcda80,0x7f20e6625940,16530468197573,16530468205913,16530468386072,16530468387766
|
|
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,163048,163048,4194304,256,0,0,12,24,140864,0x7f20e6dcd900,0x7f20e6625980,16530468402645,16530468411032,16530468518551,16530468520351
|
|
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,163048,163048,4194304,256,0,0,12,24,143616,0x7f20e6dcd780,0x7f20e66259c0,16530468534361,16530468542870,16530468712789,16530468714264
|
|
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,163048,163048,4194304,256,0,0,12,24,145344,0x7f20e6dcd600,0x7f20e6625a00,16530468734953,16530468745749,16530468841908,16530468843379
|
|
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,163048,163048,4194304,256,0,0,12,24,147584,0x7f20e952d480,0x7f20e6625a40,16530468858359,16530468866548,16530469046866,16530469048372
|
|
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,163048,163048,4194304,256,0,0,12,24,149568,0x7f20e952d300,0x7f20e6625a80,16530469062881,16530469071346,16530469251504,16530469253054
|
|
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,163048,163048,4194304,256,0,0,12,24,151552,0x7f20e952d180,0x7f20e6625ac0,16530469267104,16530469275184,16530469385263,16530469386859
|
|
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,163048,163048,4194304,256,0,0,12,24,154304,0x7f20e952d000,0x7f20e6625b00,16530469400839,16530469408783,16530469590221,16530469591792
|
|
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,163048,163048,4194304,256,0,0,12,24,156288,0x7f20e6dcde80,0x7f20e6625b40,16530469612991,16530469622701,16530469723980,16530469725547
|
|
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,163048,163048,4194304,256,0,0,12,24,158784,0x7f20e6dcdd00,0x7f20e6625b80,16530469740427,16530469748620,16530469931818,16530469933350
|
|
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,163048,163048,4194304,256,0,0,12,24,161024,0x7f20e6dcdb80,0x7f20e6625bc0,16530469949919,16530469957738,16530470144616,16530470146562
|
|
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,163048,163048,4194304,256,0,0,12,24,163264,0x7f20e6dcda00,0x7f20e6625c00,16530470161711,16530470170216,16530470292935,16530470294636
|
|
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,163048,163048,4194304,256,0,0,12,24,166528,0x7f20e6dcd880,0x7f20e6625c40,16530470312936,16530470320935,16530470527653,16530470574146
|
|
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,163048,163048,4194304,256,0,0,12,24,168512,0x7f20e6dcd700,0x7f20e6625c80,16530470590376,16530470601412,16530470712931,16530470714441
|
|
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,163048,163048,4194304,256,0,0,12,24,171264,0x7f20e952d580,0x7f20e6625cc0,16530470729570,16530470738531,16530470923649,16530470925403
|
|
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,163048,163048,4194304,256,0,0,12,24,173760,0x7f20e952d400,0x7f20e6625d00,16530470939823,16530470947969,16530471133407,16530471135026
|
|
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,163048,163048,4194304,256,0,0,12,24,176256,0x7f20e952d280,0x7f20e6625d40,16530471151195,16530471159647,16530471294846,16530471296530
|
|
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,163048,163048,4194304,256,0,0,12,24,179776,0x7f20e952d100,0x7f20e6625d80,16530471310719,16530471318846,16530471551164,16530471594999
|
|
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,163048,163048,4194304,256,0,0,12,24,182272,0x7f20e6dcdf80,0x7f20e6625dc0,16530471611288,16530471622043,16530471748762,16530471750383
|
|
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,163048,163048,4194304,256,0,0,12,24,185536,0x7f20e6dcde00,0x7f20e6625e00,16530471767583,16530471775802,16530471967800,16530471969765
|
|
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,163048,163048,4194304,256,0,0,12,24,188544,0x7f20e6dcdc80,0x7f20e6625e40,16530471984085,16530471992440,16530472186358,16530472188047
|
|
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,163048,163048,4194304,256,0,0,12,24,191552,0x7f20e6dcdb00,0x7f20e6625e80,16530472201487,16530472209238,16530472369716,16530472371330
|
|
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,163048,163048,4194304,256,0,0,12,24,195840,0x7f20e6dcd980,0x7f20e6625ec0,16530472386140,16530472394036,16530472677554,16530472722208
|
|
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,163048,163048,4194304,256,0,0,12,24,198592,0x7f20e6dcd800,0x7f20e6625f00,16530472737617,16530472748433,16530472897232,16530472898741
|
|
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,163048,163048,4194304,256,0,0,12,24,202368,0x7f20e6dcd680,0x7f20e6625f40,16530472915271,16530472923472,16530473131150,16530473150082
|
|
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,163048,163048,4194304,256,0,0,12,24,205888,0x7f20e952d500,0x7f20e6625f80,16530473159962,16530473170189,16530473380908,16530473396913
|
|
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,163048,163048,4194304,256,0,0,12,24,209408,0x7f20e952d380,0x7f20e6625fc0,16530473406033,16530473415787,16530473602186,16530473603655
|
|
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,163048,163048,4194304,256,0,0,12,24,214464,0x7f20e952d200,0x7f20e6626000,16530473618775,16530473626985,16530473961702,16530473977812
|
|
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,163048,163048,4194304,256,0,0,12,24,217728,0x7f20e952d080,0x7f20e6626040,16530473995461,16530474005862,16530474174500,16530474176455
|
|
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,163048,163048,4194304,256,0,0,12,24,222016,0x7f20e6dcdf00,0x7f20e6626080,16530474191654,16530474199620,16530474426338,16530474448625
|
|
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,163048,163048,4194304,256,0,0,12,24,226048,0x7f20e6dcdd80,0x7f20e66260c0,16530474456784,16530474466658,16530474695456,16530474735604
|
|
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,163048,163048,4194304,256,0,0,12,24,230080,0x7f20e6dcdc00,0x7f20e6626100,16530474744504,16530474754815,16530474966493,16530475006804
|
|
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,163048,163048,4194304,256,0,0,12,24,235904,0x7f20e6dcda80,0x7f20e6626140,16530475016394,16530475025533,16530475411289,16530475452468
|
|
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,163048,163048,4194304,256,0,0,12,24,239424,0x7f20e6dcd900,0x7f20e6626180,16530475471297,16530475482009,16530475668887,16530475670510
|
|
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,163048,163048,4194304,256,0,0,12,24,244224,0x7f20e6dcd780,0x7f20e66261c0,16530475685539,16530475693527,16530475944405,16530475984259
|
|
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,163048,163048,4194304,256,0,0,12,24,248768,0x7f20e6dcd600,0x7f20e6626200,16530475992628,16530476002804,16530476251442,16530476291447
|
|
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,163048,163048,4194304,256,0,0,12,24,253312,0x7f20e952d480,0x7f20e6626240,16530476301037,16530476311441,16530476548239,16530476567467
|
|
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,163048,163048,4194304,256,0,0,8,24,255552,0x7f20e952d300,0x7f20e6626280,16530476576767,16530476587279,16530477040395,16530477056369
|
|
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,163048,163048,4194304,256,0,0,12,24,259840,0x7f20e952d180,0x7f20e66262c0,16530477072159,16530477082795,16530477308873,16530477324270
|
|
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,163048,163048,4194304,256,0,0,12,24,265664,0x7f20e952d000,0x7f20e6626300,16530477333429,16530477343432,16530477641830,16530477657347
|
|
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,163048,163048,4194304,256,0,0,12,24,271232,0x7f20e6dcde80,0x7f20e6626340,16530477670077,16530477679429,16530477977667,16530477993575
|
|
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,163048,163048,4194304,256,0,0,8,24,273216,0x7f20e6dcdd00,0x7f20e6626380,16530478006845,16530478016866,16530478313504,16530478333833
|
|
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,163048,163048,4194304,256,0,0,8,24,275712,0x7f20e6dcdb80,0x7f20e66263c0,16530478343262,16530478353183,16530478911418,16530478930541
|
|
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,163048,163048,4194304,256,0,0,12,24,280768,0x7f20e6dcda00,0x7f20e6626400,16530478949110,16530478959258,16530479222456,16530479241610
|
|
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,163048,163048,4194304,256,0,0,12,24,287616,0x7f20e6dcd880,0x7f20e6626440,16530479250059,16530479260375,16530479611572,16530479635545
|
|
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,163048,163048,4194304,256,0,0,12,24,294208,0x7f20e6dcd700,0x7f20e6626480,16530479643395,16530479660052,16530480010769,16530480036440
|
|
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,163048,163048,4194304,256,0,0,8,24,296960,0x7f20e952d580,0x7f20e66264c0,16530480046200,16530480057168,16530480404045,16530480425466
|
|
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,163048,163048,4194304,256,0,0,8,24,299968,0x7f20e952d400,0x7f20e6626500,16530480434426,16530480444205,16530481105159,16530481127481
|
|
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,163048,163048,4194304,256,0,0,8,24,302720,0x7f20e952d280,0x7f20e6626540,16530481144430,16530481154118,16530481602754,16530481623883
|
|
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,163048,163048,4194304,256,0,0,12,24,305472,0x7f20e952d100,0x7f20e6626580,16530481632752,16530481643234,16530482108830,16530482133034
|
|
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,163048,163048,4194304,256,0,0,12,24,308224,0x7f20e6dcdf80,0x7f20e66265c0,16530482142344,16530482152190,16530482613625,16530482636676
|
|
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,163048,163048,4194304,256,0,0,8,24,310976,0x7f20e6dcde00,0x7f20e6626600,16530482646695,16530482656985,16530483109141,16530483130227
|
|
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,163048,163048,4194304,256,0,0,8,24,313216,0x7f20e6dcdc80,0x7f20e6626640,16530483139447,16530483149781,16530484018733,16530484040024
|
|
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,163048,163048,4194304,256,0,0,8,24,315968,0x7f20e6dcdb00,0x7f20e6626680,16530484056404,16530484066893,16530484921605,16530484964620
|
|
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,163048,163048,4194304,256,0,0,12,24,318720,0x7f20e6dcd980,0x7f20e66266c0,16530484973710,16530484983684,16530485868797,16530485912266
|
|
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,163048,163048,4194304,256,0,0,12,24,321472,0x7f20e6dcd800,0x7f20e6626700,16530485920936,16530485931036,16530486812148,16530486859671
|
|
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,163048,163048,4194304,256,0,0,8,24,324224,0x7f20e6dcd680,0x7f20e6626740,16530486870741,16530486880468,16530487740460,16530487785658
|
|
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,163048,163048,4194304,256,0,0,8,24,326464,0x7f20e952d500,0x7f20e6626780,16530487795007,16530487805419,16530489504604,16530489576603
|
|
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,163048,163048,4194304,256,0,0,8,24,329216,0x7f20e952d380,0x7f20e66267c0,16530489593932,16530489604283,16530491270029,16530491339698
|
|
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,163048,163048,4194304,256,0,0,12,24,331968,0x7f20e952d200,0x7f20e6626800,16530491349488,16530491359308,16530493085852,16530493154532
|
|
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,163048,163048,4194304,256,0,0,12,24,334720,0x7f20e952d080,0x7f20e6626840,16530493164952,16530493174012,16530494890796,16530494961456
|
|
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,163048,163048,4194304,256,0,0,8,24,337472,0x7f20e6dcdf00,0x7f20e6626880,16530494972596,16530494982316,16530496656861,16530496723762
|
|
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,163048,163048,4194304,256,0,0,8,24,0,0x7f20e6dcdd80,0x7f20e66268c0,16530496732991,16530496744540,16530500103390,16530500172456
|