169 lines
48 KiB
CSV
169 lines
48 KiB
CSV
|
|
Index,KernelName,gpu-id,queue-id,queue-index,pid,tid,grd,wgr,lds,scr,vgpr,sgpr,fbar,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,BeginNs,EndNs,CompleteNs
|
||
|
|
0,"__amd_rocclr_fillBufferAligned.kd",0,0,0,137266,137266,33554432,256,0,0,4,32,4160,0x0,0x7feb78404280,388592,388592,8652,3108744,524288,245654179,3022814,0,998905728,15894714993359,15894007718666,15894865243286,15894865331336
|
||
|
|
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,137266,137266,32768,256,0,0,12,24,13888,0x0,0x7feb78423f80,33345,33345,29846,266768,512,1688520,169915,0,6767260,15894870480071,15894865243286,15894870613861,15894870618498
|
||
|
|
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,137266,137266,4194304,256,0,0,12,24,14336,0x7feb7b479380,0x7feb78423fc0,164243,164243,13776,1313952,65536,75793880,1207030,0,304907864,15894870663287,15894870613861,15894870999942,15894871001980
|
||
|
|
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,137266,137266,4194304,256,0,0,16,24,15040,0x7feb7b479200,0x7feb78424000,311012,311012,25032,2488104,65536,220369599,2380369,0,883205032,15894871046879,15894870999942,15894871421224,15894871423310
|
||
|
|
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,137266,137266,4194304,256,0,0,16,24,15488,0x7feb7b479080,0x7feb78424040,308657,308657,24127,2469264,65536,226647103,2365877,0,908317904,15894871464329,15894871421224,15894871835465,15894871837401
|
||
|
|
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,137266,137266,4194304,256,0,0,12,24,15936,0x7feb78e19f00,0x7feb78424080,165144,165144,13187,1321160,65536,73831679,1213311,0,297058336,15894871879490,15894871835465,15894872158986,15894872160774
|
||
|
|
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,137266,137266,4194304,256,0,0,12,24,16384,0x7feb78e19d80,0x7feb784240c0,164156,164156,14126,1313256,65536,84294041,1207559,0,338907404,15894872201913,15894872158986,15894872476587,15894872478577
|
||
|
|
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,137266,137266,4194304,256,0,0,12,24,17088,0x7feb78e19c00,0x7feb78424100,162777,162777,15583,1302224,65536,108304347,1202534,0,434940288,15894872531885,15894872476587,15894872799628,15894872801399
|
||
|
|
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,137266,137266,4194304,256,0,0,16,24,17792,0x7feb78e19a80,0x7feb78424140,311253,311253,24925,2490032,65536,229765849,2385878,0,920793400,15894872841388,15894872799628,15894873221229,15894873223300
|
||
|
|
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,137266,137266,4194304,256,0,0,16,24,18496,0x7feb78e19900,0x7feb78424180,308878,308878,22822,2471032,65536,219653123,2365388,0,880339632,15894873263099,15894873221229,15894873631310,15894873633251
|
||
|
|
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,137266,137266,4194304,256,0,0,16,24,19200,0x7feb78e19780,0x7feb784241c0,165629,165629,15290,1325040,65536,104084070,1223950,0,418059060,15894873674020,15894873631310,15894873954191,15894873956044
|
||
|
|
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,137266,137266,4194304,256,0,0,16,24,19904,0x7feb78e19600,0x7feb78424200,165211,165211,15379,1321696,65536,97131565,1217717,0,390255640,15894873996273,15894873954191,15894874290192,15894874292216
|
||
|
|
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,137266,137266,4194304,256,0,0,12,24,20608,0x7feb7b479480,0x7feb78424240,163843,163843,15814,1310752,65536,101744377,1207913,0,408701852,15894874344475,15894874290192,15894874620913,15894874622899
|
||
|
|
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,137266,137266,4194304,256,0,0,16,24,21312,0x7feb7b479300,0x7feb78424280,310776,310776,24238,2486216,65536,228479493,2378701,0,915645296,15894874665708,15894874620913,15894875009874,15894875011260
|
||
|
|
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,137266,137266,4194304,256,0,0,16,24,22016,0x7feb7b479180,0x7feb784242c0,310121,310121,23539,2480976,65536,225429864,2371701,0,903447856,15894875053429,15894875009874,15894875390995,15894875392501
|
||
|
|
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,137266,137266,4194304,256,0,0,16,24,22720,0x7feb7b479000,0x7feb78424300,164611,164611,14369,1316896,65536,97262491,1216912,0,390775840,15894875433341,15894875390995,15894875695316,15894875696725
|
||
|
|
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,137266,137266,4194304,256,0,0,12,24,23424,0x7feb78e19e80,0x7feb78424340,163615,163615,14432,1308928,65536,90723452,1204295,0,364622700,15894875738864,15894875695316,15894875990037,15894875991438
|
||
|
|
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,137266,137266,4194304,256,0,0,12,24,24128,0x7feb78e19d00,0x7feb78424380,162622,162622,14980,1300984,65536,92998213,1198071,0,373717096,15894876040277,15894875990037,15894876282038,15894876283532
|
||
|
|
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,137266,137266,4194304,256,0,0,16,24,24832,0x7feb78e19b80,0x7feb784243c0,310143,310143,25534,2481152,65536,226907572,2371715,0,909358808,15894876329571,15894876282038,15894876670679,15894876671963
|
||
|
|
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,137266,137266,4194304,256,0,0,16,24,25536,0x7feb78e19a00,0x7feb78424400,307688,307688,22993,2461512,65536,220767501,2354600,0,884799700,15894876713322,15894876670679,15894877050360,15894877051714
|
||
|
|
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,137266,137266,4194304,256,0,0,12,24,26240,0x7feb78e19880,0x7feb78424440,162931,162931,15479,1303456,65536,105906860,1201053,0,425350160,15894877093713,15894877050360,15894877344281,15894877345728
|
||
|
|
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,137266,137266,4194304,256,0,0,12,24,26944,0x7feb78e19700,0x7feb78424480,163040,163040,14889,1304328,65536,91541817,1199620,0,367897184,15894877387647,15894877344281,15894877638842,15894877640261
|
||
|
|
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,137266,137266,4194304,256,0,0,12,24,27648,0x7feb7b479580,0x7feb784244c0,162639,162639,15165,1301120,65536,102905108,1198351,0,413350384,15894877688960,15894877638842,15894877938843,15894877940265
|
||
|
|
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,137266,137266,4194304,256,0,0,16,24,28608,0x7feb7b479400,0x7feb78424500,308303,308303,24297,2466432,65536,222561882,2360744,0,891975724,15894877984934,15894877938843,15894878332764,15894878334386
|
||
|
|
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,137266,137266,4194304,256,0,0,16,24,29312,0x7feb7b479280,0x7feb78424540,306683,306683,22149,2453472,65536,216977662,2344975,0,869639080,15894878376215,15894878332764,15894878713085,15894878714317
|
||
|
|
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,137266,137266,4194304,256,0,0,12,24,30016,0x7feb7b479100,0x7feb78424580,162468,162468,14924,1299752,65536,99644850,1198914,0,400309008,15894878756406,15894878713085,15894879004606,15894879005961
|
||
|
|
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,137266,137266,4194304,256,0,0,8,24,30976,0x7feb78e19f80,0x7feb784245c0,161940,161940,14512,1295528,65536,91393106,1193077,0,367300960,15894879046730,15894879004606,15894879297407,15894879298654
|
||
|
|
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,137266,137266,4194304,256,0,0,12,24,31680,0x7feb78e19e00,0x7feb78424600,163532,163532,15863,1308264,65536,99891115,1206086,0,401290928,15894879347753,15894879297407,15894879595648,15894879596948
|
||
|
|
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,137266,137266,4194304,256,0,0,16,24,32640,0x7feb78e19c80,0x7feb78424640,307096,307096,24748,2456776,65536,228846757,2352394,0,917119060,15894879637837,15894879595648,15894879981409,15894879982829
|
||
|
|
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,137266,137266,4194304,256,0,0,12,24,33600,0x7feb78e19b00,0x7feb78424680,305980,305980,22693,2447848,65536,220196621,2343359,0,882512860,15894880025518,15894879981409,15894880361410,15894880362761
|
||
|
|
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,137266,137266,4194304,256,0,0,12,24,34560,0x7feb78e19980,0x7feb784246c0,162582,162582,15155,1300664,65536,96941953,1194801,0,389489864,15894880404620,15894880361410,15894880653891,15894880655174
|
||
|
|
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,137266,137266,4194304,256,0,0,8,24,35520,0x7feb78e19800,0x7feb78424700,163716,163716,15973,1309736,65536,82843974,1198348,0,333103368,15894880697523,15894880653891,15894880947012,15894880948348
|
||
|
|
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,137266,137266,4194304,256,0,0,12,24,36224,0x7feb78e19680,0x7feb78424740,162800,162800,14875,1302408,65536,93682640,1198944,0,376456944,15894880996287,15894880947012,15894881245413,15894881246691
|
||
|
|
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,137266,137266,4194304,256,0,0,12,24,37184,0x7feb7b479500,0x7feb78424780,306180,306180,23537,2449448,65536,226445365,2341730,0,907512184,15894881290320,15894881245413,15894881622694,15894881624043
|
||
|
|
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,137266,137266,4194304,256,0,0,12,24,38144,0x7feb7b479380,0x7feb784247c0,308092,308092,23178,2464744,65536,219632527,2361420,0,880259108,15894881665992,15894881622694,15894882002695,15894882003944
|
||
|
|
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,137266,137266,4194304,256,0,0,12,24,39104,0x7feb7b479200,0x7feb78424800,163666,163666,15047,1309336,65536,96272163,1204557,0,386818820,15894882044433,15894882002695,15894882316936,15894882318247
|
||
|
|
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,137266,137266,4194304,256,0,0,8,24,40320,0x7feb7b479080,0x7feb78424840,163538,163538,15399,1308312,65536,88035899,1201828,0,353871708,15894882360326,15894882316936,15894882612457,15894882613931
|
||
|
|
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,137266,137266,4194304,256,0,0,12,24,41280,0x7feb78e19f00,0x7feb78424880,162251,162251,14980,1298016,65536,98643512,1191865,0,396297484,15894882662410,15894882612457,15894882907658,15894882909044
|
||
|
|
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,137266,137266,4194304,256,0,0,12,24,42240,0x7feb78e19d80,0x7feb784248c0,307034,307034,24863,2456280,65536,229361955,2351032,0,919173804,15894882953143,15894882907658,15894883293099,15894883294496
|
||
|
|
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,137266,137266,4194304,256,0,0,12,24,43200,0x7feb78e19c00,0x7feb78424900,306502,306502,22947,2452024,65536,216036096,2342190,0,865874056,15894883334975,15894883293099,15894883674060,15894883675547
|
||
|
|
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,137266,137266,4194304,256,0,0,8,24,44160,0x7feb78e19a80,0x7feb78424940,162608,162608,14826,1300872,65536,90495076,1198929,0,363701912,15894883716176,15894883674060,15894883965101,15894883966351
|
||
|
|
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,137266,137266,4194304,256,0,0,12,24,45376,0x7feb78e19900,0x7feb78424980,163269,163269,15709,1306160,65536,92655380,1199974,0,372344352,15894884009340,15894883965101,15894884263982,15894884265344
|
||
|
|
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,137266,137266,4194304,256,0,0,12,24,46336,0x7feb78e19780,0x7feb784249c0,162580,162580,14090,1300648,65536,87581409,1199027,0,352053868,15894884313413,15894884263982,15894884567182,15894884568487
|
||
|
|
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,137266,137266,4194304,256,0,0,12,24,47552,0x7feb78e19600,0x7feb78424a00,305362,305362,23520,2442904,65536,224431543,2333312,0,899454500,15894884614436,15894884567182,15894884959024,15894884960378
|
||
|
|
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,137266,137266,4194304,256,0,0,12,24,48512,0x7feb7b479480,0x7feb78424a40,302917,302917,21169,2423344,65536,202784311,2312396,0,812867320,15894885002037,15894884959024,15894885339345,15894885340750
|
||
|
|
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,137266,137266,4194304,256,0,0,8,24,49472,0x7feb7b479300,0x7feb78424a80,162346,162346,15203,1298776,65536,94711279,1194519,0,380573888,15894885382689,15894885339345,15894885631506,15894885632873
|
||
|
|
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,137266,137266,4194304,256,0,0,12,24,50688,0x7feb7b479180,0x7feb78424ac0,163011,163011,16470,1304096,65536,97670831,1195321,0,392414320,15894885676622,15894885631506,15894885928627,15894885929927
|
||
|
|
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,137266,137266,4194304,256,0,0,12,24,51648,0x7feb7b479000,0x7feb78424b00,161145,161145,14969,1289168,65536,93620690,1188541,0,376207196,15894885978786,15894885928627,15894886232947,15894886234390
|
||
|
|
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,137266,137266,4194304,256,0,0,12,24,52864,0x7feb78e19e80,0x7feb78424b40,304850,304850,24611,2438808,65536,223847819,2332231,0,897119676,15894886276599,15894886232947,15894886615029,15894886616331
|
||
|
|
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,137266,137266,4194304,256,0,0,12,24,54080,0x7feb78e19d00,0x7feb78424b80,302423,302423,20680,2419392,65536,203006755,2306792,0,813757276,15894886658190,15894886615029,15894886998550,15894887000013
|
||
|
|
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,137266,137266,4194304,256,0,0,8,24,55296,0x7feb78e19b80,0x7feb78424bc0,162788,162788,14575,1302312,65536,82063436,1197836,0,329980080,15894887040112,15894886998550,15894887291991,15894887293246
|
||
|
|
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,137266,137266,4194304,256,0,0,12,24,56768,0x7feb78e19a00,0x7feb78424c00,163283,163283,16135,1306272,65536,99524959,1202673,0,399835012,15894887334025,15894887291991,15894887589911,15894887591330
|
||
|
|
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,137266,137266,4194304,256,0,0,12,24,57728,0x7feb78e19880,0x7feb78424c40,162246,162246,14600,1297976,65536,95937939,1193002,0,385481060,15894887640108,15894887589911,15894887890232,15894887891663
|
||
|
|
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,137266,137266,4194304,256,0,0,12,24,58944,0x7feb78e19700,0x7feb78424c80,303061,303061,23160,2424496,65536,222761328,2317965,0,892775968,15894887935782,15894887890232,15894888273753,15894888275114
|
||
|
|
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,137266,137266,4194304,256,0,0,12,24,60160,0x7feb7b479580,0x7feb78424cc0,301686,301686,21519,2413496,65536,209422238,2302873,0,839418180,15894888316143,15894888273753,15894888650715,15894888652106
|
||
|
|
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,137266,137266,4194304,256,0,0,8,24,61376,0x7feb7b479400,0x7feb78424d00,162150,162150,14369,1297208,65536,86364877,1195547,0,347187896,15894888692585,15894888650715,15894888940795,15894888942169
|
||
|
|
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,137266,137266,4194304,256,0,0,12,24,62848,0x7feb7b479280,0x7feb78424d40,168246,168246,16170,1345976,65536,104785055,1242695,0,420876640,15894888983108,15894888940795,15894889240956,15894889242253
|
||
|
|
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,137266,137266,4194304,256,0,0,12,24,63808,0x7feb7b479100,0x7feb78424d80,162432,162432,14380,1299464,65536,91485471,1196261,0,367668880,15894889291492,15894889240956,15894889536637,15894889538076
|
||
|
|
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,137266,137266,4194304,256,0,0,12,24,65024,0x7feb78e19f80,0x7feb78424dc0,301282,301282,23383,2410264,65536,220183636,2306896,0,882465300,15894889582335,15894889536637,15894889925118,15894889926457
|
||
|
|
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,137266,137266,4194304,256,0,0,12,24,66240,0x7feb78e19e00,0x7feb78424e00,299164,299164,20349,2393320,65536,209686650,2287478,0,840477152,15894889968066,15894889925118,15894890312160,15894890313649
|
||
|
|
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,137266,137266,4194304,256,0,0,8,24,67456,0x7feb78e19c80,0x7feb78424e40,162564,162564,15378,1300520,65536,89589562,1197642,0,360082560,15894890354198,15894890312160,15894890608480,15894890609842
|
||
|
|
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,137266,137266,4194304,256,0,0,12,24,68928,0x7feb78e19b00,0x7feb78424e80,175815,175815,16623,1406528,65536,102723475,1301756,0,412627572,15894890650491,15894890608480,15894890911681,15894890912945
|
||
|
|
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,137266,137266,4194304,256,0,0,12,24,70144,0x7feb78e19980,0x7feb78424ec0,161034,161034,15200,1288280,65536,86974378,1182175,0,349634216,15894890961014,15894890911681,15894891208482,15894891209839
|
||
|
|
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,137266,137266,4194304,256,0,0,12,24,71616,0x7feb78e19800,0x7feb78424f00,303338,303338,23397,2426712,65536,222123389,2324524,0,890228096,15894891250988,15894891208482,15894891593123,15894891594500
|
||
|
|
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,137266,137266,4194304,256,0,0,12,24,72832,0x7feb78e19680,0x7feb78424f40,302644,302644,24096,2421160,65536,220102138,2314929,0,882138596,15894891635379,15894891593123,15894891976324,15894891977682
|
||
|
|
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,137266,137266,4194304,256,0,0,8,24,74048,0x7feb7b479500,0x7feb78424f80,161530,161530,15039,1292248,65536,88186658,1190820,0,354478356,15894892018061,15894891976324,15894892269445,15894892270775
|
||
|
|
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,137266,137266,4194304,256,0,0,12,24,75776,0x7feb7b479380,0x7feb78424fc0,183282,183282,17205,1466264,65536,106336411,1358309,0,427093924,15894892313154,15894892269445,15894892574886,15894892576238
|
||
|
|
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,137266,137266,4194304,256,0,0,12,24,76992,0x7feb7b479200,0x7feb78425000,161855,161855,15298,1294848,65536,97137084,1190867,0,390272908,15894892634847,15894892574886,15894892930567,15894892932010
|
||
|
|
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,137266,137266,4194304,256,0,0,12,24,78464,0x7feb7b479080,0x7feb78425040,303302,303302,23935,2426424,65536,223193275,2321212,0,894502376,15894892973829,15894892930567,15894893314728,15894893316042
|
||
|
|
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,137266,137266,4194304,256,0,0,12,24,79936,0x7feb78e19f00,0x7feb78425080,302234,302234,23572,2417880,65536,219728707,2314332,0,880641544,15894893357881,15894893314728,15894893696810,15894893698183
|
||
|
|
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,137266,137266,4194304,256,0,0,8,24,81408,0x7feb78e19d80,0x7feb784250c0,162720,162720,15713,1301768,65536,89059424,1194860,0,357967720,15894893738712,15894893696810,15894893991850,15894893993207
|
||
|
|
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,137266,137266,4194304,256,0,0,12,24,83136,0x7feb78e19c00,0x7feb78425100,191246,191246,18276,1529976,65536,120323052,1422635,0,483029844,15894894033916,15894893991850,15894894319851,15894894321429
|
||
|
|
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,137266,137266,4194304,256,0,0,12,24,84352,0x7feb78e19a80,0x7feb78425140,161036,161036,14348,1288296,65536,99234935,1186722,0,398664600,15894894369708,15894894319851,15894894617932,15894894619283
|
||
|
|
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,137266,137266,4194304,256,0,0,12,24,85824,0x7feb78e19900,0x7feb78425180,304518,304518,24432,2436152,65536,221810775,2327964,0,888982380,15894894663582,15894894617932,15894895004333,15894895005804
|
||
|
|
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,137266,137266,4194304,256,0,0,12,24,87296,0x7feb78e19780,0x7feb784251c0,300137,300137,22476,2401104,65536,210922588,2297489,0,845419632,15894895047913,15894895004333,15894895385135,15894895386515
|
||
|
|
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,137266,137266,4194304,256,0,0,12,24,88768,0x7feb78e19600,0x7feb78425200,162376,162376,15807,1299016,65536,95618833,1193111,0,384199776,15894895427185,15894895385135,15894895677295,15894895678659
|
||
|
|
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,137266,137266,4194304,256,0,0,12,24,90752,0x7feb7b479480,0x7feb78425240,201226,201226,17970,1609816,65536,124427292,1502376,0,499448776,15894895719358,15894895677295,15894896000496,15894896001902
|
||
|
|
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,137266,137266,4194304,256,0,0,12,24,91968,0x7feb7b479300,0x7feb78425280,161006,161006,14736,1288056,65536,91839477,1184029,0,369087916,15894896050921,15894896000496,15894896300017,15894896301375
|
||
|
|
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,137266,137266,4194304,256,0,0,12,24,93440,0x7feb7b479180,0x7feb784252c0,302017,302017,22435,2416144,65536,209286692,2304993,0,838882972,15894896346684,15894896300017,15894896684178,15894896685676
|
||
|
|
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,137266,137266,4194304,256,0,0,12,24,94912,0x7feb7b479000,0x7feb78425300,297506,297506,20432,2380056,65536,213420238,2276103,0,855414696,15894896726436,15894896684178,15894897064820,15894897066078
|
||
|
|
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,137266,137266,4194304,256,0,0,12,24,96384,0x7feb78e19e80,0x7feb78425340,162385,162385,15674,1299088,65536,98902465,1197237,0,397340368,15894897106477,15894897064820,15894897359380,15894897360791
|
||
|
|
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,137266,137266,4194304,256,0,0,12,24,98368,0x7feb78e19d00,0x7feb78425380,213039,213039,19773,1704320,65536,119569329,1581142,0,480019696,15894897402050,15894897359380,15894897685941,15894897687364
|
||
|
|
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,137266,137266,4194304,256,0,0,12,24,99584,0x7feb78e19b80,0x7feb784253c0,162004,162004,14997,1296040,65536,91208401,1191673,0,366564240,15894897735483,15894897685941,15894897986102,15894897987347
|
||
|
|
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,137266,137266,4194304,256,0,0,12,24,101312,0x7feb78e19a00,0x7feb78425400,300655,300655,23780,2405248,65536,213971806,2293311,0,857620140,15894898028216,15894897986102,15894898376023,15894898377439
|
||
|
|
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,137266,137266,4194304,256,0,0,12,24,102784,0x7feb78e19880,0x7feb78425440,298622,298622,20513,2388984,65536,202082714,2279113,0,810062464,15894898419028,15894898376023,15894898768185,15894898769580
|
||
|
|
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,137266,137266,4194304,256,0,0,12,24,104256,0x7feb78e19700,0x7feb78425480,161036,161036,15594,1288296,65536,97969008,1185517,0,393611768,15894898810299,15894898768185,15894899060825,15894899062113
|
||
|
|
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,137266,137266,4194304,256,0,0,12,24,106240,0x7feb7b479580,0x7feb784254c0,219497,219497,19372,1755984,65536,142532033,1646415,0,571874420,15894899102833,15894899060825,15894899390426,15894899391866
|
||
|
|
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,137266,137266,4194304,256,0,0,12,24,107712,0x7feb7b479400,0x7feb78425500,160454,160454,15262,1283640,65536,90636476,1181822,0,364280912,15894899440695,15894899390426,15894899684187,15894899685550
|
||
|
|
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,137266,137266,4194304,256,0,0,16,24,109440,0x7feb7b479280,0x7feb78425540,298528,298528,22599,2388232,65536,217975175,2283440,0,873633960,15894899729859,15894899684187,15894900064348,15894900065771
|
||
|
|
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,137266,137266,4194304,256,0,0,16,24,111168,0x7feb7b479100,0x7feb78425580,299119,299119,21572,2392960,65536,205986231,2281742,0,825678860,15894900107610,15894900064348,15894900443710,15894900445023
|
||
|
|
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,137266,137266,4194304,256,0,0,8,24,112896,0x7feb78e19f80,0x7feb784255c0,162017,162017,16141,1296144,65536,103038318,1192634,0,413883844,15894900485712,15894900443710,15894900741630,15894900742846
|
||
|
|
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,137266,137266,4194304,256,0,0,12,24,115136,0x7feb78e19e00,0x7feb78425600,229945,229945,19941,1839568,65536,143590288,1725068,0,576106644,15894900783535,15894900741630,15894901076511,15894901077869
|
||
|
|
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,137266,137266,4194304,256,0,0,12,24,116608,0x7feb78e19c80,0x7feb78425640,161727,161727,15296,1293824,65536,90590361,1183509,0,364088508,15894901125808,15894901076511,15894901375232,15894901376712
|
||
|
|
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,137266,137266,4194304,256,0,0,16,24,118336,0x7feb78e19b00,0x7feb78425680,296613,296613,21137,2372912,65536,202994783,2268021,0,813711336,15894901420881,15894901375232,15894901755873,15894901757304
|
||
|
|
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,137266,137266,4194304,256,0,0,16,24,120064,0x7feb78e19980,0x7feb784256c0,297599,297599,20119,2380800,65536,193756104,2270597,0,776758604,15894901798353,15894901755873,15894902135235,15894902136795
|
||
|
|
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,137266,137266,4194304,256,0,0,12,24,121792,0x7feb78e19800,0x7feb78425700,163749,163749,16019,1310000,65536,104308740,1207315,0,418973892,15894902178064,15894902135235,15894902432675,15894902434059
|
||
|
|
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,137266,137266,4194304,256,0,0,12,24,124032,0x7feb78e19680,0x7feb78425740,240824,240824,20254,1926600,65536,147604429,1814984,0,592165992,15894902474668,15894902432675,15894902779876,15894902781111
|
||
|
|
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,137266,137266,4194304,256,0,0,12,24,125504,0x7feb7b479500,0x7feb78425780,161708,161708,15751,1293672,65536,96696834,1189519,0,388521384,15894902828550,15894902779876,15894903071557,15894903072924
|
||
|
|
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,137266,137266,4194304,256,0,0,12,24,127488,0x7feb7b479380,0x7feb784257c0,297436,297436,20634,2379496,65536,202926922,2273349,0,813439448,15894903117373,15894903071557,15894903456678,15894903458006
|
||
|
|
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,137266,137266,4194304,256,0,0,12,24,129216,0x7feb7b479200,0x7feb78425800,297960,297960,21622,2383688,65536,212627975,2276068,0,852246056,15894903499265,15894903456678,15894903834120,15894903835687
|
||
|
|
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,137266,137266,4194304,256,0,0,12,24,130944,0x7feb7b479080,0x7feb78425840,169372,169372,16358,1354984,65536,107703152,1252635,0,432557200,15894903876706,15894903834120,15894904140040,15894904141491
|
||
|
|
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,137266,137266,4194304,256,0,0,12,24,133440,0x7feb78e19f00,0x7feb78425880,258450,258450,21497,2067608,65536,183406441,1958596,0,735368644,15894904182980,15894904140040,15894904496202,15894904497753
|
||
|
|
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,137266,137266,4194304,256,0,0,12,24,134912,0x7feb78e19d80,0x7feb784258c0,160886,160886,15737,1287096,65536,97894685,1183825,0,393307808,15894904545821,15894904496202,15894904790122,15894904791526
|
||
|
|
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,137266,137266,4194304,256,0,0,12,24,136896,0x7feb78e19c00,0x7feb78425900,296337,296337,19661,2370704,65536,202757147,2261138,0,812773480,15894904832675,15894904790122,15894905173164,15894905174467
|
||
|
|
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,137266,137266,4194304,256,0,0,12,24,138880,0x7feb78e19a80,0x7feb78425940,295114,295114,20718,2360920,65536,205051445,2257287,0,821940356,15894905215827,15894905173164,15894905550765,15894905552109
|
||
|
|
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,137266,137266,4194304,256,0,0,12,24,140864,0x7feb78e19900,0x7feb78425980,177864,177864,17245,1422920,65536,106257043,1313746,0,426769116,15894905593008,15894905550765,15894905856046,15894905857452
|
||
|
|
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,137266,137266,4194304,256,0,0,12,24,143616,0x7feb78e19780,0x7feb784259c0,278458,278458,22410,2227672,65536,204275926,2123609,0,818847084,15894905897491,15894905856046,15894906223727,15894906225254
|
||
|
|
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,137266,137266,4194304,256,0,0,12,24,145344,0x7feb78e19600,0x7feb78425a00,160856,160856,15692,1286856,65536,99901719,1184947,0,401342068,15894906274283,15894906223727,15894906527088,15894906528567
|
||
|
|
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,137266,137266,4194304,256,0,0,12,24,147584,0x7feb7b479480,0x7feb78425a40,295730,295730,21985,2365848,65536,208608391,2260396,0,836175784,15894906573836,15894906527088,15894906914609,15894906915949
|
||
|
|
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,137266,137266,4194304,256,0,0,12,24,149568,0x7feb7b479300,0x7feb78425a80,294388,294388,20994,2355112,65536,199821101,2246077,0,801025112,15894906958208,15894906914609,15894907305010,15894907306300
|
||
|
|
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,137266,137266,4194304,256,0,0,12,24,151552,0x7feb7b479180,0x7feb78425ac0,186736,186736,17935,1493896,65536,114266757,1384214,0,458808044,15894907347169,15894907305010,15894907619571,15894907620973
|
||
|
|
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,137266,137266,4194304,256,0,0,12,24,154304,0x7feb7b479000,0x7feb78425b00,299540,299540,23425,2396328,65536,206890031,2283853,0,829310900,15894907662622,15894907619571,15894908005492,15894908006744
|
||
|
|
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,137266,137266,4194304,256,0,0,12,24,156288,0x7feb78e19e80,0x7feb78425b40,171763,171763,16654,1374112,65536,102631448,1264894,0,412275120,15894908054963,15894908005492,15894908312853,15894908314207
|
||
|
|
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,137266,137266,4194304,256,0,0,12,24,158784,0x7feb78e19d00,0x7feb78425b80,297876,297876,20945,2383016,65536,189471275,2260691,0,759624040,15894908354996,15894908312853,15894908693974,15894908695369
|
||
|
|
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,137266,137266,4194304,256,0,0,12,24,161024,0x7feb78e19b80,0x7feb78425bc0,297465,297465,21167,2379728,65536,201709512,2265397,0,808576992,15894908736778,15894908693974,15894909076855,15894909078110
|
||
|
|
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,137266,137266,4194304,256,0,0,12,24,163264,0x7feb78e19a00,0x7feb78425c00,205919,205919,18584,1647360,65536,131702396,1536821,0,528556952,15894909118279,15894909076855,15894909402776,15894909404143
|
||
|
|
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,137266,137266,4194304,256,0,0,12,24,166528,0x7feb78e19880,0x7feb78425c40,341127,341127,26243,2729024,65536,237788492,2610753,0,952906804,15894909444782,15894909402776,15894909812377,15894909831403
|
||
|
|
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,137266,137266,4194304,256,0,0,12,24,168512,0x7feb78e19700,0x7feb78425c80,183756,183756,17694,1470056,65536,111115139,1360691,0,446204768,15894909862503,15894909812377,15894910126938,15894910128267
|
||
|
|
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,137266,137266,4194304,256,0,0,12,24,171264,0x7feb7b479580,0x7feb78425cc0,297075,297075,20157,2376608,65536,192283814,2256545,0,770894728,15894910170406,15894910126938,15894910512699,15894910514188
|
||
|
|
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,137266,137266,4194304,256,0,0,12,24,173760,0x7feb7b479400,0x7feb78425d00,297146,297146,20955,2377176,65536,193535288,2269942,0,775887900,15894910555907,15894910512699,15894910896541,15894910897880
|
||
|
|
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,137266,137266,4194304,256,0,0,12,24,176256,0x7feb7b479280,0x7feb78425d40,225480,225480,19976,1803848,65536,149148928,1691456,0,598344080,15894910938939,15894910896541,15894911233981,15894911235392
|
||
|
|
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,137266,137266,4194304,256,0,0,12,24,179776,0x7feb7b479100,0x7feb78425d80,381033,381033,28241,3048272,65536,272929814,2931573,0,1093475408,15894911280421,15894911233981,15894911670783,15894911691432
|
||
|
|
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,137266,137266,4194304,256,0,0,12,24,182272,0x7feb78e19f80,0x7feb78425dc0,211269,211269,18876,1690160,65536,136960661,1578707,0,549590708,15894911721391,15894911670783,15894912002464,15894912003815
|
||
|
|
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,137266,137266,4194304,256,0,0,12,24,185536,0x7feb78e19e00,0x7feb78425e00,308462,308462,22766,2467704,65536,179558464,2345218,0,719979564,15894912044994,15894912002464,15894912393665,15894912414226
|
||
|
|
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,137266,137266,4194304,256,0,0,12,24,188544,0x7feb78e19c80,0x7feb78425e40,310998,310998,21259,2487992,65536,188782963,2354999,0,756888696,15894912434925,15894912393665,15894912793026,15894912813367
|
||
|
|
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,137266,137266,4194304,256,0,0,12,24,191552,0x7feb78e19b00,0x7feb78425e80,266633,266633,21632,2133072,65536,183597361,2021452,0,736141268,15894912835016,15894912793026,15894913160707,15894913162029
|
||
|
|
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,137266,137266,4194304,256,0,0,12,24,195840,0x7feb78e19980,0x7feb78425ec0,461532,461532,32354,3692264,65536,342689991,3580547,0,1372511488,15894913202498,15894913160707,15894913643909,15894913661118
|
||
|
|
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,137266,137266,4194304,256,0,0,12,24,198592,0x7feb78e19800,0x7feb78425f00,244594,244594,20798,1956760,65536,147037646,1845434,0,589901212,15894913693897,15894913643909,15894914002310,15894914003670
|
||
|
|
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,137266,137266,4194304,256,0,0,12,24,202368,0x7feb78e19680,0x7feb78425f40,334826,334826,23018,2678616,65536,213595265,2561043,0,856150868,15894914044549,15894914002310,15894914421031,15894914440470
|
||
|
|
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,137266,137266,4194304,256,0,0,12,24,205888,0x7feb7b479500,0x7feb78425f80,329712,329712,24332,2637704,65536,225786881,2529422,0,904915740,15894914465160,15894914421031,15894914828392,15894914870361
|
||
|
|
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,137266,137266,4194304,256,0,0,12,24,209408,0x7feb7b479380,0x7feb78425fc0,306022,306022,23484,2448184,65536,216455811,2341186,0,867580756,15894914881011,15894914828392,15894915238793,15894915240063
|
||
|
|
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,137266,137266,4194304,256,0,0,12,24,214464,0x7feb7b479200,0x7feb78426000,542234,542234,35977,4337880,65536,407244227,4226913,0,1630739604,15894915281262,15894915238793,15894915776395,15894915818530
|
||
|
|
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,137266,137266,4194304,256,0,0,12,24,217728,0x7feb7b479080,0x7feb78426040,273982,273982,22414,2191864,65536,188486860,2079468,0,755717804,15894915837840,15894915776395,15894916165516,15894916166902
|
||
|
|
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,137266,137266,4194304,256,0,0,12,24,222016,0x7feb78e19f00,0x7feb78426080,363612,363612,26125,2908904,65536,235589261,2790352,0,944129340,15894916212061,15894916165516,15894916598317,15894916639932
|
||
|
|
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,137266,137266,4194304,256,0,0,12,24,226048,0x7feb78e19d80,0x7feb784260c0,365216,365216,28794,2921736,65536,254621516,2809463,0,1020256860,15894916651211,15894916598317,15894917047279,15894917088872
|
||
|
|
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,137266,137266,4194304,256,0,0,12,24,230080,0x7feb78e19c00,0x7feb78426100,346278,346278,25637,2770232,65536,251339114,2663182,0,1007115036,15894917099802,15894917047279,15894917475120,15894917516922
|
||
|
|
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,137266,137266,4194304,256,0,0,12,24,235904,0x7feb78e19a80,0x7feb78426140,624181,624181,39897,4993456,65536,472657567,4876215,0,1892386616,15894917527722,15894917475120,15894918082322,15894918108059
|
||
|
|
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,137266,137266,4194304,256,0,0,12,24,239424,0x7feb78e19900,0x7feb78426180,303406,303406,23516,2427256,65536,211513171,2319823,0,847802876,15894918132229,15894918082322,15894918481683,15894918483151
|
||
|
|
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,137266,137266,4194304,256,0,0,12,24,244224,0x7feb78e19780,0x7feb784261c0,399148,399148,27126,3193192,65536,272227822,3082455,0,1090695192,15894918523770,15894918481683,15894918938804,15894918984070
|
||
|
|
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,137266,137266,4194304,256,0,0,12,24,248768,0x7feb78e19600,0x7feb78426200,391582,391582,28174,3132664,65536,283431131,3018383,0,1135494116,15894918994419,15894918938804,15894919408246,15894919452669
|
||
|
|
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,137266,137266,4194304,256,0,0,12,24,253312,0x7feb7b479480,0x7feb78426240,387543,387543,28643,3100352,65536,285788143,2986999,0,1144916468,15894919463189,15894919408246,15894919866487,15894919908509
|
||
|
|
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,137266,137266,4194304,256,0,0,8,24,255552,0x7feb7b479300,0x7feb78426280,719444,719444,45389,5755560,65536,545036549,5634032,0,2181885708,15894919919489,15894919866487,15894920538009,15894920579914
|
||
|
|
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,137266,137266,4194304,256,0,0,12,24,259840,0x7feb7b479180,0x7feb784262c0,365211,365211,27523,2921696,65536,259819174,2799689,0,1041039544,15894920599783,15894920538009,15894920989050,15894921031024
|
||
|
|
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,137266,137266,4194304,256,0,0,12,24,265664,0x7feb7b479000,0x7feb78426300,469295,469295,31647,3754368,65536,348077483,3643797,0,1394091256,15894921041934,15894920989050,15894921505692,15894921547632
|
||
|
|
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,137266,137266,4194304,256,0,0,12,24,271232,0x7feb78e19e80,0x7feb78426340,470926,470926,31762,3767416,65536,349861255,3664818,0,1401225640,15894921558712,15894921505692,15894922028573,15894922046671
|
||
|
|
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,137266,137266,4194304,256,0,0,8,24,273216,0x7feb78e19d00,0x7feb78426380,482312,482312,33060,3858504,65536,358301310,3749228,0,1434945948,15894922071471,15894922028573,15894922530495,15894922575519
|
||
|
|
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,137266,137266,4194304,256,0,0,8,24,275712,0x7feb78e19b80,0x7feb784263c0,880603,880603,52839,7044832,65536,678323953,6924837,0,2715036604,15894922586409,15894922530495,15894923308577,15894923353922
|
||
|
|
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,137266,137266,4194304,256,0,0,12,24,280768,0x7feb78e19a00,0x7feb78426400,427178,427178,29788,3417432,65536,314907027,3300921,0,1261390200,15894923372582,15894923308577,15894923795459,15894923837161
|
||
|
|
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,137266,137266,4194304,256,0,0,12,24,287616,0x7feb78e19880,0x7feb78426440,549906,549906,36001,4399256,65536,406233049,4280163,0,1626714868,15894923848091,15894923795459,15894924365060,15894924407078
|
||
|
|
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,137266,137266,4194304,256,0,0,12,24,294208,0x7feb78e19700,0x7feb78426480,551298,551298,36243,4410392,65536,418054579,4304660,0,1674003748,15894924417928,15894924365060,15894924937382,15894924979566
|
||
|
|
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,137266,137266,4194304,256,0,0,8,24,296960,0x7feb7b479580,0x7feb784264c0,563147,563147,36845,4505184,65536,420821559,4394029,0,1685028756,15894924990285,15894924937382,15894925504584,15894925546293
|
||
|
|
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,137266,137266,4194304,256,0,0,8,24,299968,0x7feb7b479400,0x7feb78426500,1043474,1043474,61668,8347800,65536,810049252,8225333,0,3241939340,15894925557173,15894925504584,15894926387946,15894926431833
|
||
|
|
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,137266,137266,4194304,256,0,0,8,24,302720,0x7feb7b479280,0x7feb78426540,723285,723285,45017,5786288,65536,538039442,5656829,0,2153899568,15894926452523,15894926387946,15894927061708,15894927106478
|
||
|
|
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,137266,137266,4194304,256,0,0,12,24,305472,0x7feb7b479100,0x7feb78426580,724912,724912,45200,5799304,65536,547082399,5675487,0,2190070396,15894927117498,15894927061708,15894927748910,15894927793203
|
||
|
|
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,137266,137266,4194304,256,0,0,12,24,308224,0x7feb78e19f80,0x7feb784265c0,722172,722172,44139,5777384,65536,542267422,5664074,0,2170809192,15894927803843,15894927748497,15894928429938,15894928476348
|
||
|
|
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,137266,137266,4194304,256,0,0,8,24,310976,0x7feb78e19e00,0x7feb78426600,727238,727238,45566,5817912,65536,558811332,5698442,0,2236986236,15894928486937,15894928429938,15894929102739,15894929145063
|
||
|
|
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,137266,137266,4194304,256,0,0,8,24,313216,0x7feb78e19c80,0x7feb78426640,1365983,1365983,77039,10927872,65536,1061793463,10813787,0,4248915032,15894929156222,15894929102739,15894930187381,15894930231788
|
||
|
|
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,137266,137266,4194304,256,0,0,8,24,315968,0x7feb78e19b00,0x7feb78426680,1371931,1371931,77227,10975456,65536,1075311214,10846124,0,4302986788,15894930251378,15894930187381,15894931262264,15894931327184
|
||
|
|
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,137266,137266,4194304,256,0,0,12,24,318720,0x7feb78e19980,0x7feb784266c0,1371935,1371935,77688,10975488,65536,1072700862,10859791,0,4292544612,15894931337924,15894931262264,15894932389306,15894932454339
|
||
|
|
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,137266,137266,4194304,256,0,0,12,24,321472,0x7feb78e19800,0x7feb78426700,1372418,1372418,77971,10979352,65536,1077480868,10847179,0,4311663800,15894932465179,15894932389306,15894933510108,15894933573704
|
||
|
|
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,137266,137266,4194304,256,0,0,8,24,324224,0x7feb78e19680,0x7feb78426740,1375422,1375422,77802,11003384,65536,1086131642,10885895,0,4346268764,15894933584384,15894933510108,15894934609631,15894934681130
|
||
|
|
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,137266,137266,4194304,256,0,0,8,24,326464,0x7feb7b479500,0x7feb78426780,2663585,2663585,142912,21308688,65536,2130157038,21188666,0,8522369896,15894934693419,15894934609631,15894936583715,15894936650116
|
||
|
|
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,137266,137266,4194304,256,0,0,8,24,329216,0x7feb7b479380,0x7feb784267c0,2667402,2667402,142574,21339224,65536,2130094686,21225359,0,8522119416,15894936672405,15894936583715,15894938511719,15894938582392
|
||
|
|
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,137266,137266,4194304,256,0,0,12,24,331968,0x7feb7b479200,0x7feb78426800,2673341,2673341,143582,21386736,65536,2124937638,21240855,0,8501491520,15894938594612,15894938511719,15894940505643,15894940573618
|
||
|
|
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,137266,137266,4194304,256,0,0,12,24,334720,0x7feb7b479080,0x7feb78426840,2668646,2668646,143565,21349176,65536,2126765727,21230840,0,8508803204,15894940585548,15894940505643,15894942494928,15894942564113
|
||
|
|
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,137266,137266,4194304,256,0,0,8,24,337472,0x7feb78e19f00,0x7feb78426880,2673755,2673755,143178,21390048,65536,2131133856,21263202,0,8526277168,15894942575933,15894942494928,15894944442292,15894944513930
|
||
|
|
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,137266,137266,4194304,256,0,0,8,24,0,0x7feb78e19d80,0x7feb784268c0,5256031,5256031,273779,42048256,65536,4232023467,41927590,0,16929835504,15894944525220,15894944442292,15894948063740,15894948136289
|