169 라인
39 KiB
CSV
169 라인
39 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_fillBuffer.kd",0,0,0,860241,860246,33554432,256,0,0,8,32,6464,0x0,0x7f22fa804180,12075076321911995,12075076321956559,12075076322280876,12075076322370868
|
|
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,860241,860246,32768,256,0,0,24,24,12480,0x0,0x7f22fa835100,12075076336802477,12075076336906869,12075076336914069,12075076336919785
|
|
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,860241,860246,4194304,256,0,0,24,24,12928,0x7f242a8aa900,0x7f22fa835140,12075076336963797,12075076336979349,12075076337114228,12075076337117783
|
|
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,860241,860246,4194304,256,0,0,36,24,13632,0x7f242a8aa800,0x7f22fa835180,12075076337164389,12075076337181427,12075076337431025,12075076337510703
|
|
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,860241,860246,4194304,256,0,0,28,24,14080,0x7f242a8aa700,0x7f22fa8351c0,12075076337536461,12075076337548464,12075076337795022,12075076337872696
|
|
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,860241,860246,4194304,256,0,0,24,24,14528,0x7f242a8aa600,0x7f22fa835200,12075076337895198,12075076337907821,12075076338033260,12075076338036891
|
|
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,860241,860246,4194304,256,0,0,24,24,14976,0x7f242a8aa500,0x7f22fa835240,12075076338065143,12075076338076779,12075076338201738,12075076338204933
|
|
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,860241,860246,4194304,256,0,0,24,24,15424,0x7f242a8aa400,0x7f22fa835280,12075076338258312,12075076338269898,12075076338394217,12075076338397010
|
|
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,860241,860246,4194304,256,0,0,28,24,16128,0x7f242a8aa300,0x7f22fa8352c0,12075076338423970,12075076338436136,12075076338680774,12075076338758131
|
|
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,860241,860246,4194304,256,0,0,28,24,16832,0x7f242a8aaa00,0x7f22fa835300,12075076338778208,12075076338791013,12075076339036451,12075076339114443
|
|
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,860241,860246,4194304,256,0,0,24,24,17536,0x7f242a8aa900,0x7f22fa835340,12075076339136084,12075076339148290,12075076339273089,12075076339276504
|
|
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,860241,860246,4194304,256,0,0,24,24,18240,0x7f242a8aa800,0x7f22fa835380,12075076339303445,12075076339315649,12075076339440928,12075076339444026
|
|
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,860241,860246,4194304,256,0,0,24,24,18944,0x7f242a8aa700,0x7f22fa8353c0,12075076339483078,12075076339494687,12075076339619646,12075076339622668
|
|
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,860241,860246,4194304,256,0,0,28,24,19904,0x7f242a8aa600,0x7f22fa835400,12075076339648686,12075076339660766,12075076339906684,12075076339929909
|
|
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,860241,860246,4194304,256,0,0,28,24,20608,0x7f242a8aa500,0x7f22fa835440,12075076339951529,12075076339963323,12075076340209081,12075076340258389
|
|
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,860241,860246,4194304,256,0,0,24,24,21312,0x7f242a8aa400,0x7f22fa835480,12075076340280931,12075076340294040,12075076340418359,12075076340421302
|
|
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,860241,860246,4194304,256,0,0,24,24,22016,0x7f242a8aa300,0x7f22fa8354c0,12075076340443293,12075076340454999,12075076340580118,12075076340583093
|
|
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,860241,860246,4194304,256,0,0,24,24,22720,0x7f242a8aaa00,0x7f22fa835500,12075076340621364,12075076340634037,12075076340758836,12075076340761925
|
|
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,860241,860246,4194304,256,0,0,28,24,23680,0x7f242a8aa900,0x7f22fa835540,12075076340788314,12075076340801556,12075076341049074,12075076341097739
|
|
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,860241,860246,4194304,256,0,0,28,24,24384,0x7f242a8aa800,0x7f22fa835580,12075076341119590,12075076341133393,12075076341377071,12075076341425749
|
|
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,860241,860246,4194304,256,0,0,24,24,25088,0x7f242a8aa700,0x7f22fa8355c0,12075076341446096,12075076341459790,12075076341584429,12075076341587349
|
|
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,860241,860246,4194304,256,0,0,24,24,25792,0x7f242a8aa600,0x7f22fa835600,12075076341614309,12075076341625709,12075076341750668,12075076341753718
|
|
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,860241,860246,4194304,256,0,0,24,24,26496,0x7f242a8aa500,0x7f22fa835640,12075076341790136,12075076341802987,12075076341927146,12075076341930196
|
|
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,860241,860246,4194304,256,0,0,28,24,27712,0x7f242a8aa400,0x7f22fa835680,12075076341957006,12075076341970506,12075076342214824,12075076342292349
|
|
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,860241,860246,4194304,256,0,0,28,24,28416,0x7f242a8aa300,0x7f22fa8356c0,12075076342314280,12075076342326023,12075076342570341,12075076342647509
|
|
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,860241,860246,4194304,256,0,0,24,24,29120,0x7f242a8aaa00,0x7f22fa835700,12075076342668097,12075076342680740,12075076342805379,12075076342808679
|
|
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,860241,860246,4194304,256,0,0,24,24,30080,0x7f242a8aa900,0x7f22fa835740,12075076342835669,12075076342847138,12075076342971937,12075076342975248
|
|
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,860241,860246,4194304,256,0,0,24,24,30784,0x7f242a8aa800,0x7f22fa835780,12075076343014651,12075076343026657,12075076343151296,12075076343154391
|
|
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,860241,860246,4194304,256,0,0,28,24,32000,0x7f242a8aa700,0x7f22fa8357c0,12075076343181822,12075076343193855,12075076343440093,12075076343517315
|
|
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,860241,860246,4194304,256,0,0,28,24,32960,0x7f242a8aa600,0x7f22fa835800,12075076343541190,12075076343552892,12075076343795770,12075076343873247
|
|
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,860241,860246,4194304,256,0,0,24,24,33920,0x7f242a8aa500,0x7f22fa835840,12075076343893615,12075076343907769,12075076344032248,12075076344036019
|
|
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,860241,860246,4194304,256,0,0,24,24,34880,0x7f242a8aa400,0x7f22fa835880,12075076344063571,12075076344075608,12075076344201367,12075076344204513
|
|
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,860241,860246,4194304,256,0,0,24,24,35840,0x7f242a8aa300,0x7f22fa8358c0,12075076344241161,12075076344255766,12075076344380725,12075076344383565
|
|
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,860241,860246,4194304,256,0,0,28,24,37312,0x7f242a8aaa00,0x7f22fa835900,12075076344409714,12075076344422005,12075076344673043,12075076344728566
|
|
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,860241,860246,4194304,256,0,0,28,24,38272,0x7f242a8aa900,0x7f22fa835940,12075076344748864,12075076344768722,12075076345013360,12075076345041368
|
|
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,860241,860246,4194304,256,0,0,24,24,39232,0x7f242a8aa800,0x7f22fa835980,12075076345062457,12075076345074159,12075076345198798,12075076345201846
|
|
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,860241,860246,4194304,256,0,0,24,24,40192,0x7f242a8aa700,0x7f22fa8359c0,12075076345229868,12075076345241518,12075076345366957,12075076345370069
|
|
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,860241,860246,4194304,256,0,0,24,24,41152,0x7f242a8aa600,0x7f22fa835a00,12075076345406015,12075076345418476,12075076345542475,12075076345545454
|
|
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,860241,860246,4194304,256,0,0,28,24,42624,0x7f242a8aa500,0x7f22fa835a40,12075076345573076,12075076345584875,12075076345829353,12075076345851343
|
|
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,860241,860246,4194304,256,0,0,28,24,43584,0x7f242a8aa400,0x7f22fa835a80,12075076345874786,12075076345886632,12075076346129990,12075076346159476
|
|
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,860241,860246,4194304,256,0,0,24,24,44544,0x7f242a8aa300,0x7f22fa835ac0,12075076346183721,12075076346196229,12075076346321348,12075076346324372
|
|
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,860241,860246,4194304,256,0,0,24,24,45760,0x7f242a8aaa00,0x7f22fa835b00,12075076346351022,12075076346363108,12075076346488707,12075076346491743
|
|
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,860241,860246,4194304,256,0,0,24,24,46720,0x7f242a8aa900,0x7f22fa835b40,12075076346529072,12075076346540546,12075076346665505,12075076346668522
|
|
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,860241,860246,4194304,256,0,0,28,24,48448,0x7f242a8aa800,0x7f22fa835b80,12075076346695081,12075076346708225,12075076346963903,12075076346984609
|
|
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,860241,860246,4194304,256,0,0,28,24,49408,0x7f242a8aa700,0x7f22fa835bc0,12075076347010758,12075076347023422,12075076347273820,12075076347298362
|
|
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,860241,860246,4194304,256,0,0,24,24,50368,0x7f242a8aa600,0x7f22fa835c00,12075076347317628,12075076347330460,12075076347454939,12075076347457848
|
|
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,860241,860246,4194304,256,0,0,24,24,51584,0x7f242a8aa500,0x7f22fa835c40,12075076347484097,12075076347495738,12075076347622457,12075076347625259
|
|
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,860241,860246,4194304,256,0,0,24,24,52544,0x7f242a8aa400,0x7f22fa835c80,12075076347662699,12075076347674137,12075076347800056,12075076347803060
|
|
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,860241,860246,4194304,256,0,0,28,24,54272,0x7f242a8aa300,0x7f22fa835cc0,12075076347829539,12075076347841015,12075076348093973,12075076348123566
|
|
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,860241,860246,4194304,256,0,0,28,24,55488,0x7f242a8aaa00,0x7f22fa835d00,12075076348144354,12075076348157173,12075076348400690,12075076348425226
|
|
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,860241,860246,4194304,256,0,0,24,24,56704,0x7f242a8aa900,0x7f22fa835d40,12075076348446105,12075076348457650,12075076348583089,12075076348585925
|
|
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,860241,860246,4194304,256,0,0,24,24,58176,0x7f242a8aa800,0x7f22fa835d80,12075076348610881,12075076348622289,12075076348750767,12075076348753586
|
|
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,860241,860246,4194304,256,0,0,24,24,59392,0x7f242a8aa700,0x7f22fa835dc0,12075076348789142,12075076348801327,12075076348926286,12075076348929052
|
|
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,860241,860246,4194304,256,0,0,28,24,61376,0x7f242a8aa600,0x7f22fa835e00,12075076348955391,12075076348966926,12075076349225163,12075076349254377
|
|
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,860241,860246,4194304,256,0,0,28,24,62592,0x7f242a8aa500,0x7f22fa835e40,12075076349277139,12075076349288683,12075076349535241,12075076349559414
|
|
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,860241,860246,4194304,256,0,0,24,24,63808,0x7f242a8aa400,0x7f22fa835e80,12075076349582517,12075076349596040,12075076349721799,12075076349724611
|
|
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,860241,860246,4194304,256,0,0,24,24,65280,0x7f242a8aa300,0x7f22fa835ec0,12075076349752162,12075076349764839,12075076349893318,12075076349896190
|
|
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,860241,860246,4194304,256,0,0,24,24,66496,0x7f242a8aaa00,0x7f22fa835f00,12075076349932978,12075076349945477,12075076350070116,12075076350073199
|
|
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,860241,860246,4194304,256,0,0,28,24,68480,0x7f242a8aa900,0x7f22fa835f40,12075076350100319,12075076350112196,12075076350370753,12075076350392783
|
|
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,860241,860246,4194304,256,0,0,28,24,69696,0x7f242a8aa800,0x7f22fa835f80,12075076350415835,12075076350427873,12075076350674431,12075076350699252
|
|
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,860241,860246,4194304,256,0,0,24,24,70912,0x7f242a8aa700,0x7f22fa835fc0,12075076350721614,12075076350734430,12075076350858909,12075076350861904
|
|
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,860241,860246,4194304,256,0,0,24,24,72384,0x7f242a8aa600,0x7f22fa836000,12075076350887592,12075076350899549,12075076351035708,12075076351038923
|
|
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,860241,860246,4194304,256,0,0,24,24,73600,0x7f242a8aa500,0x7f22fa836040,12075076351077725,12075076351089947,12075076351214746,12075076351217625
|
|
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,860241,860246,4194304,256,0,0,28,24,75840,0x7f242a8aa400,0x7f22fa836080,12075076351243604,12075076351255066,12075076351507064,12075076351531138
|
|
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,860241,860246,4194304,256,0,0,28,24,77056,0x7f242a8aa300,0x7f22fa8360c0,12075076351550334,12075076351563703,12075076351811061,12075076351834121
|
|
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,860241,860246,4194304,256,0,0,24,24,78272,0x7f242a8aaa00,0x7f22fa836100,12075076351854218,12075076351866741,12075076351991860,12075076351994679
|
|
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,860241,860246,4194304,256,0,0,24,24,80000,0x7f242a8aa900,0x7f22fa836140,12075076352025938,12075076352038739,12075076352180978,12075076352184362
|
|
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,860241,860246,4194304,256,0,0,24,24,81216,0x7f242a8aa800,0x7f22fa836180,12075076352219016,12075076352231697,12075076352356816,12075076352359838
|
|
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,860241,860246,4194304,256,0,0,28,24,83456,0x7f242a8aa700,0x7f22fa8361c0,12075076352387029,12075076352400656,12075076352659694,12075076352687517
|
|
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,860241,860246,4194304,256,0,0,28,24,84928,0x7f242a8aa600,0x7f22fa836200,12075076352706643,12075076352719053,12075076352963371,12075076352990690
|
|
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,860241,860246,4194304,256,0,0,24,24,86400,0x7f242a8aa500,0x7f22fa836240,12075076353019424,12075076353032971,12075076353158410,12075076353161528
|
|
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,860241,860246,4194304,256,0,0,24,24,88128,0x7f242a8aa400,0x7f22fa836280,12075076353186074,12075076353200649,12075076353349928,12075076353352934
|
|
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,860241,860246,4194304,256,0,0,24,24,89600,0x7f242a8aa300,0x7f22fa8362c0,12075076353404610,12075076353419527,12075076353545606,12075076353548727
|
|
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,860241,860246,4194304,256,0,0,28,24,92096,0x7f242a8aaa00,0x7f22fa836300,12075076353574215,12075076353585606,12075076353841124,12075076353869203
|
|
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,860241,860246,4194304,256,0,0,28,24,93568,0x7f242a8aa900,0x7f22fa836340,12075076353888609,12075076353900163,12075076354145601,12075076354177977
|
|
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,860241,860246,4194304,256,0,0,24,24,95040,0x7f242a8aa800,0x7f22fa836380,12075076354198796,12075076354210880,12075076354336159,12075076354339146
|
|
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,860241,860246,4194304,256,0,0,24,24,96768,0x7f242a8aa700,0x7f22fa8363c0,12075076354365455,12075076354377279,12075076354535038,12075076354537886
|
|
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,860241,860246,4194304,256,0,0,24,24,98240,0x7f242a8aa600,0x7f22fa836400,12075076354575015,12075076354586077,12075076354711196,12075076354714073
|
|
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,860241,860246,4194304,256,0,0,28,24,100736,0x7f242a8aa500,0x7f22fa836440,12075076354740432,12075076354751676,12075076355005754,12075076355030090
|
|
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,860241,860246,4194304,256,0,0,28,24,102208,0x7f242a8aa400,0x7f22fa836480,12075076355050238,12075076355062073,12075076355310071,12075076355333685
|
|
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,860241,860246,4194304,256,0,0,24,24,103680,0x7f242a8aa300,0x7f22fa8364c0,12075076355354924,12075076355366710,12075076355492309,12075076355495215
|
|
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,860241,860246,4194304,256,0,0,24,24,105664,0x7f242a8aaa00,0x7f22fa836500,12075076355520001,12075076355533429,12075076355699188,12075076355702089
|
|
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,860241,860246,4194304,256,0,0,24,24,107136,0x7f242a8aa900,0x7f22fa836540,12075076355737515,12075076355750547,12075076355875826,12075076355878778
|
|
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,860241,860246,4194304,256,0,0,28,24,109888,0x7f242a8aa800,0x7f22fa836580,12075076355904465,12075076355916946,12075076356184143,12075076356211726
|
|
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,860241,860246,4194304,256,0,0,28,24,111360,0x7f242a8aa700,0x7f22fa8365c0,12075076356232655,12075076356245903,12075076356491021,12075076356518697
|
|
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,860241,860246,4194304,256,0,0,24,24,112832,0x7f242a8aa600,0x7f22fa836600,12075076356540948,12075076356553580,12075076356678539,12075076356681479
|
|
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,860241,860246,4194304,256,0,0,24,24,114816,0x7f242a8aa500,0x7f22fa836640,12075076356707828,12075076356720459,12075076356892937,12075076356895928
|
|
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,860241,860246,4194304,256,0,0,24,24,116288,0x7f242a8aa400,0x7f22fa836680,12075076356932436,12075076356944937,12075076357070536,12075076357073728
|
|
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,860241,860246,4194304,256,0,0,28,24,119040,0x7f242a8aa300,0x7f22fa8366c0,12075076357099546,12075076357111495,12075076357364453,12075076357393683
|
|
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,860241,860246,4194304,256,0,0,28,24,120768,0x7f242a8aaa00,0x7f22fa836700,12075076357413299,12075076357426373,12075076357671811,12075076357694973
|
|
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,860241,860246,4194304,256,0,0,24,24,122496,0x7f242a8aa900,0x7f22fa836740,12075076357715080,12075076357727650,12075076357853409,12075076357856333
|
|
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,860241,860246,4194304,256,0,0,24,24,124736,0x7f242a8aa800,0x7f22fa836780,12075076357881920,12075076357894529,12075076358076927,12075076358079908
|
|
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,860241,860246,4194304,256,0,0,24,24,126464,0x7f242a8aa700,0x7f22fa8367c0,12075076358118279,12075076358130367,12075076358255646,12075076358258600
|
|
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,860241,860246,4194304,256,0,0,20,24,127936,0x7f242a8aa600,0x7f22fa836800,12075076358284218,12075076358296605,12075076358559963,12075076358587511
|
|
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,860241,860246,4194304,256,0,0,28,24,129664,0x7f242a8aa500,0x7f22fa836840,12075076358607398,12075076358619962,12075076358866360,12075076358893470
|
|
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,860241,860246,4194304,256,0,0,24,24,131392,0x7f242a8aa400,0x7f22fa836880,12075076358913637,12075076358926520,12075076359052439,12075076359055681
|
|
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,860241,860246,4194304,256,0,0,24,24,133632,0x7f242a8aa300,0x7f22fa8368c0,12075076359082421,12075076359095318,12075076359286517,12075076359290949
|
|
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,860241,860246,4194304,256,0,0,24,24,135360,0x7f242a8aaa00,0x7f22fa836900,12075076359325232,12075076359338036,12075076359465715,12075076359468789
|
|
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,860241,860246,4194304,256,0,0,20,24,136832,0x7f242a8aa900,0x7f22fa836940,12075076359495609,12075076359507955,12075076359790192,12075076359810664
|
|
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,860241,860246,4194304,256,0,0,28,24,138560,0x7f242a8aa800,0x7f22fa836980,12075076359832545,12075076359845232,12075076360093390,12075076360120370
|
|
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,860241,860246,4194304,256,0,0,24,24,140288,0x7f242a8aa700,0x7f22fa8369c0,12075076360141569,12075076360155309,12075076360281068,12075076360284244
|
|
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,860241,860246,4194304,256,0,0,24,24,142784,0x7f242a8aa600,0x7f22fa836a00,12075076360311255,12075076360323628,12075076360533226,12075076360557452
|
|
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,860241,860246,4194304,256,0,0,24,24,144768,0x7f242a8aa500,0x7f22fa836a40,12075076360587879,12075076360600905,12075076360728904,12075076360731916
|
|
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,860241,860246,4194304,256,0,0,20,24,145728,0x7f242a8aa400,0x7f22fa836a80,12075076360757264,12075076360770184,12075076361077061,12075076361105801
|
|
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,860241,860246,4194304,256,0,0,28,24,147712,0x7f242a8aa300,0x7f22fa836ac0,12075076361125929,12075076361137381,12075076361384419,12075076361411990
|
|
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,860241,860246,4194304,256,0,0,24,24,149696,0x7f242a8aaa00,0x7f22fa836b00,12075076361433951,12075076361446658,12075076361573857,12075076361576997
|
|
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,860241,860246,4194304,256,0,0,24,24,152192,0x7f242a8aa900,0x7f22fa836b40,12075076361603667,12075076361614977,12075076361842495,12075076361870523
|
|
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,860241,860246,4194304,256,0,0,24,24,154176,0x7f242a8aa800,0x7f22fa836b80,12075076361901470,12075076361914494,12075076362041693,12075076362045117
|
|
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,860241,860246,4194304,256,0,0,20,24,155648,0x7f242a8aa700,0x7f22fa836bc0,12075076362071306,12075076362082653,12075076362410650,12075076362442726
|
|
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,860241,860246,4194304,256,0,0,28,24,157632,0x7f242a8aa600,0x7f22fa836c00,12075076362463535,12075076362474809,12075076362725207,12075076362752542
|
|
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,860241,860246,4194304,256,0,0,24,24,159616,0x7f242a8aa500,0x7f22fa836c40,12075076362772529,12075076362784247,12075076362913046,12075076362915995
|
|
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,860241,860246,4194304,256,0,0,24,24,162368,0x7f242a8aa400,0x7f22fa836c80,12075076362941733,12075076362953205,12075076363196723,12075076363221092
|
|
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,860241,860246,4194304,256,0,0,24,24,164608,0x7f242a8aa300,0x7f22fa836cc0,12075076363251759,12075076363265203,12075076363394961,12075076363397981
|
|
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,860241,860246,4194304,256,0,0,20,24,166336,0x7f242a8aaa00,0x7f22fa836d00,12075076363420753,12075076363431921,12075076363807118,12075076363831146
|
|
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,860241,860246,4194304,256,0,0,28,24,168576,0x7f242a8aa900,0x7f22fa836d40,12075076363851404,12075076363864077,12075076364118955,12075076364146442
|
|
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,860241,860246,4194304,256,0,0,24,24,170816,0x7f242a8aa800,0x7f22fa836d80,12075076364170356,12075076364183595,12075076364313193,12075076364316208
|
|
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,860241,860246,4194304,256,0,0,24,24,174080,0x7f242a8aa700,0x7f22fa836dc0,12075076364342066,12075076364354633,12075076364633191,12075076364656460
|
|
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,860241,860246,4194304,256,0,0,24,24,176576,0x7f242a8aa600,0x7f22fa836e00,12075076364687918,12075076364700710,12075076364835749,12075076364839039
|
|
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,860241,860246,4194304,256,0,0,20,24,177792,0x7f242a8aa500,0x7f22fa836e40,12075076364865508,12075076364877829,12075076365300225,12075076365328609
|
|
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,860241,860246,4194304,256,0,0,28,24,180288,0x7f242a8aa400,0x7f22fa836e80,12075076365350780,12075076365363744,12075076365619422,12075076365646900
|
|
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,860241,860246,4194304,256,0,0,24,24,182784,0x7f242a8aa300,0x7f22fa836ec0,12075076365667308,12075076365680062,12075076365815421,12075076365818379
|
|
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,860241,860246,4194304,256,0,0,24,24,186304,0x7f242a8aaa00,0x7f22fa836f00,12075076365844838,12075076365856220,12075076366170298,12075076366199067
|
|
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,860241,860246,4194304,256,0,0,24,24,189312,0x7f242a8aa900,0x7f22fa836f40,12075076366232278,12075076366243737,12075076366394136,12075076366397295
|
|
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,860241,860246,4194304,256,0,0,20,24,190784,0x7f242a8aa800,0x7f22fa836f80,12075076366423664,12075076366435575,12075076366951891,12075076366979527
|
|
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,860241,860246,4194304,256,0,0,28,24,193792,0x7f242a8aa700,0x7f22fa836fc0,12075076367005385,12075076367018290,12075076367315728,12075076367347250
|
|
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,860241,860246,4194304,256,0,0,24,24,196800,0x7f242a8aa600,0x7f22fa837000,12075076367366456,12075076367379567,12075076367533966,12075076367537083
|
|
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,860241,860246,4194304,256,0,0,24,24,201088,0x7f242a8aa500,0x7f22fa837040,12075076367563342,12075076367574925,12075076367958762,12075076367985687
|
|
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,860241,860246,4194304,256,0,0,24,24,204608,0x7f242a8aa400,0x7f22fa837080,12075076368027344,12075076368040041,12075076368216680,12075076368220072
|
|
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,860241,860246,4194304,256,0,0,20,24,206080,0x7f242a8aa300,0x7f22fa8370c0,12075076368246171,12075076368257640,12075076368866594,12075076368893975
|
|
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,860241,860246,4194304,256,0,0,28,24,209600,0x7f242a8aaa00,0x7f22fa837100,12075076368915154,12075076368927714,12075076369255391,12075076369285973
|
|
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,860241,860246,4194304,256,0,0,24,24,213120,0x7f242a8aa900,0x7f22fa837140,12075076369310028,12075076369322910,12075076369500349,12075076369503367
|
|
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,860241,860246,4194304,256,0,0,24,24,218176,0x7f242a8aa800,0x7f22fa837180,12075076369529886,12075076369542268,12075076369997305,12075076370025588
|
|
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,860241,860246,4194304,256,0,0,24,24,222208,0x7f242a8aa700,0x7f22fa8371c0,12075076370057487,12075076370070424,12075076370308182,12075076370335233
|
|
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,860241,860246,4194304,256,0,0,20,24,223936,0x7f242a8aa600,0x7f22fa837200,12075076370355992,12075076370369301,12075076371071695,12075076371100355
|
|
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,860241,860246,4194304,256,0,0,28,24,227968,0x7f242a8aa500,0x7f22fa837240,12075076371122085,12075076371135055,12075076371506572,12075076371533350
|
|
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,860241,860246,4194304,256,0,0,24,24,232000,0x7f242a8aa400,0x7f22fa837280,12075076371554910,12075076371568651,12075076371770729,12075076371798212
|
|
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,860241,860246,4194304,256,0,0,24,24,237824,0x7f242a8aa300,0x7f22fa8372c0,12075076371818299,12075076371831049,12075076372356644,12075076372391825
|
|
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,860241,860246,4194304,256,0,0,24,24,242368,0x7f242a8aaa00,0x7f22fa837300,12075076372423534,12075076372436804,12075076372660002,12075076372686853
|
|
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,860241,860246,4194304,256,0,0,20,24,243584,0x7f242a8aa900,0x7f22fa837340,12075076372708574,12075076372721281,12075076373518554,12075076373545809
|
|
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,860241,860246,4194304,256,0,0,28,24,248128,0x7f242a8aa800,0x7f22fa837380,12075076373566999,12075076373579834,12075076373997110,12075076374025070
|
|
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,860241,860246,4194304,256,0,0,24,24,252672,0x7f242a8aa700,0x7f22fa8373c0,12075076374045278,12075076374056630,12075076374281588,12075076374308146
|
|
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,860241,860246,4194304,256,0,0,24,24,259264,0x7f242a8aa600,0x7f22fa837400,12075076374329726,12075076374342387,12075076374938382,12075076374965317
|
|
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,860241,860246,4194304,256,0,0,24,24,264832,0x7f242a8aa500,0x7f22fa837440,12075076374996024,12075076375012301,12075076375280779,12075076375311210
|
|
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,860241,860246,4194304,256,0,0,20,24,266304,0x7f242a8aa400,0x7f22fa837480,12075076375334133,12075076375346539,12075076376329570,12075076376358056
|
|
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,860241,860246,4194304,256,0,0,28,24,271872,0x7f242a8aa300,0x7f22fa8374c0,12075076376377862,12075076376390850,12075076376903805,12075076376930349
|
|
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,860241,860246,4194304,256,0,0,24,24,277440,0x7f242a8aaa00,0x7f22fa837500,12075076376953182,12075076376966525,12075076377237082,12075076377271132
|
|
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,860241,860246,4194304,256,0,0,12,24,279936,0x7f242a8aa900,0x7f22fa837540,12075076377291771,12075076377304602,12075076378040915,12075076378069145
|
|
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,860241,860246,4194304,256,0,0,24,24,286528,0x7f242a8aa800,0x7f22fa837580,12075076378100484,12075076378113555,12075076378456752,12075076378484097
|
|
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,860241,860246,4194304,256,0,0,20,24,288000,0x7f242a8aa700,0x7f22fa8375c0,12075076378505356,12075076378516911,12075076379685381,12075076379713862
|
|
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,860241,860246,4194304,256,0,0,32,24,294592,0x7f242a8aa600,0x7f22fa837600,12075076379735262,12075076379748101,12075076380358975,12075076380386913
|
|
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,860241,860246,4194304,256,0,0,24,24,301184,0x7f242a8aa500,0x7f22fa837640,12075076380409264,12075076380421855,12075076380740252,12075076380767199
|
|
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,860241,860246,4194304,256,0,0,12,24,304960,0x7f242a8aa400,0x7f22fa837680,12075076380788920,12075076380801692,12075076381678644,12075076381706214
|
|
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,860241,860246,4194304,256,0,0,24,24,313600,0x7f242a8aa300,0x7f22fa8376c0,12075076381739086,12075076381752403,12075076382163280,12075076382191546
|
|
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,860241,860246,4194304,256,0,0,20,24,314816,0x7f242a8aaa00,0x7f22fa837700,12075076382215301,12075076382228239,12075076383777506,12075076383829641
|
|
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,860241,860246,4194304,256,0,0,20,24,317568,0x7f242a8aa900,0x7f22fa837740,12075076383850559,12075076383863585,12075076384656698,12075076384713533
|
|
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,860241,860246,4194304,256,0,0,12,24,320320,0x7f242a8aa800,0x7f22fa837780,12075076384735614,12075076384749011,12075076385162288,12075076385216889
|
|
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,860241,860246,4194304,256,0,0,12,24,324096,0x7f242a8aa700,0x7f22fa8377c0,12075076385238679,12075076385252366,12075076386410278,12075076386461241
|
|
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,860241,860246,4194304,256,0,0,12,24,328896,0x7f242a8aa600,0x7f22fa837800,12075076386492269,12075076386505797,12075076387291072,12075076387342238
|
|
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,860241,860246,4194304,256,0,0,20,24,330112,0x7f242a8aa500,0x7f22fa837840,12075076387364760,12075076387378111,12075076390428329,12075076390479879
|
|
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,860241,860246,4194304,256,0,0,20,24,332864,0x7f242a8aa400,0x7f22fa837880,12075076390500337,12075076390513449,12075076392054558,12075076392105761
|
|
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,860241,860246,4194304,256,0,0,12,24,335616,0x7f242a8aa300,0x7f22fa8378c0,12075076392130016,12075076392143517,12075076392931831,12075076392981177
|
|
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,860241,860246,4194304,256,0,0,12,24,339392,0x7f242a8aaa00,0x7f22fa837900,12075076393005823,12075076393018871,12075076395300134,12075076395355810
|
|
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,860241,860246,4194304,256,0,0,12,24,344192,0x7f242a8aa900,0x7f22fa837940,12075076395391527,12075076395403654,12075076396938843,12075076396990117
|
|
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,860241,860246,4194304,256,0,0,20,24,345408,0x7f242a8aa800,0x7f22fa837980,12075076397017188,12075076397030682,12075076403085519,12075076403136610
|
|
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,860241,860246,4194304,256,0,0,20,24,348160,0x7f242a8aa700,0x7f22fa8379c0,12075076403162248,12075076403175438,12075076406216696,12075076406268019
|
|
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,860241,860246,4194304,256,0,0,12,24,350912,0x7f242a8aa600,0x7f22fa837a00,12075076406295079,12075076406308536,12075076407846285,12075076407897407
|
|
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,860241,860246,4194304,256,0,0,12,24,0,0x7f242a8aa500,0x7f22fa837a40,12075076407922945,12075076407934764,12075076412460012,12075076412517132
|