Files
rocm-systems/tests/workloads/SQC/mi100/timestamps.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

169 rader
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",0,0,0,855909,855914,33554432,256,0,0,8,32,6464,0x0,0x7f96d3204180,12074968630846690,12074968630893202,12074968631219119,12074968631310091
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,855909,855914,32768,256,0,0,24,24,12480,0x0,0x7f96d3235100,12074968646192088,12074968646292397,12074968646299117,12074968646304877
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,855909,855914,4194304,256,0,0,24,24,12928,0x7f980336b900,0x7f96d3235140,12074968646353167,12074968646365997,12074968646499116,12074968646502645
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,855909,855914,4194304,256,0,0,36,24,13632,0x7f980336b800,0x7f96d3235180,12074968646549392,12074968646563435,12074968646810313,12074968646888241
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,855909,855914,4194304,256,0,0,28,24,14080,0x7f980336b700,0x7f96d32351c0,12074968646915522,12074968646927592,12074968647170950,12074968647251546
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,855909,855914,4194304,256,0,0,24,24,14528,0x7f980336b600,0x7f96d3235200,12074968647281492,12074968647293989,12074968647419428,12074968647422855
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,855909,855914,4194304,256,0,0,24,24,14976,0x7f980336b500,0x7f96d3235240,12074968647447861,12074968647459428,12074968647583907,12074968647587200
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,855909,855914,4194304,256,0,0,24,24,15424,0x7f980336b400,0x7f96d3235280,12074968647642753,12074968647655107,12074968647778626,12074968647781601
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,855909,855914,4194304,256,0,0,28,24,16128,0x7f980336b300,0x7f96d32352c0,12074968647809914,12074968647821665,12074968648068863,12074968648150627
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,855909,855914,4194304,256,0,0,28,24,16832,0x7f980336ba00,0x7f96d3235300,12074968648172818,12074968648185022,12074968648427580,12074968648505196
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,855909,855914,4194304,256,0,0,24,24,17536,0x7f980336b900,0x7f96d3235340,12074968648527748,12074968648539739,12074968648664058,12074968648667538
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,855909,855914,4194304,256,0,0,24,24,18240,0x7f980336b800,0x7f96d3235380,12074968648695891,12074968648708058,12074968648832377,12074968648835570
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,855909,855914,4194304,256,0,0,24,24,18944,0x7f980336b700,0x7f96d32353c0,12074968648874963,12074968648891737,12074968649016216,12074968649019572
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,855909,855914,4194304,256,0,0,28,24,19904,0x7f980336b600,0x7f96d3235400,12074968649048145,12074968649059895,12074968649310133,12074968649363381
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,855909,855914,4194304,256,0,0,28,24,20608,0x7f980336b500,0x7f96d3235440,12074968649385983,12074968649398133,12074968649647891,12074968649695468
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,855909,855914,4194304,256,0,0,24,24,21312,0x7f980336b400,0x7f96d3235480,12074968649717960,12074968649729810,12074968649854289,12074968649857369
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,855909,855914,4194304,256,0,0,24,24,22016,0x7f980336b300,0x7f96d32354c0,12074968649884219,12074968649895729,12074968650021328,12074968650024700
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,855909,855914,4194304,256,0,0,24,24,22720,0x7f980336ba00,0x7f96d3235500,12074968650064193,12074968650076207,12074968650200686,12074968650203863
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,855909,855914,4194304,256,0,0,28,24,23680,0x7f980336b900,0x7f96d3235540,12074968650231735,12074968650243886,12074968650489004,12074968650511404
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,855909,855914,4194304,256,0,0,28,24,24384,0x7f980336b800,0x7f96d3235580,12074968650533145,12074968650544843,12074968650790281,12074968650836999
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,855909,855914,4194304,256,0,0,24,24,25088,0x7f980336b700,0x7f96d32355c0,12074968650859141,12074968650872841,12074968650997800,12074968651005262
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,855909,855914,4194304,256,0,0,24,24,25792,0x7f980336b600,0x7f96d3235600,12074968651029116,12074968651042279,12074968651167718,12074968651170940
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,855909,855914,4194304,256,0,0,24,24,26496,0x7f980336b500,0x7f96d3235640,12074968651209692,12074968651223718,12074968651348357,12074968651351676
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,855909,855914,4194304,256,0,0,28,24,27712,0x7f980336b400,0x7f96d3235680,12074968651379127,12074968651390917,12074968651647235,12074968651669036
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,855909,855914,4194304,256,0,0,28,24,28416,0x7f980336b300,0x7f96d32356c0,12074968651691297,12074968651704674,12074968651985152,12074968652032982
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,855909,855914,4194304,256,0,0,24,24,29120,0x7f980336ba00,0x7f96d3235700,12074968652055143,12074968652069311,12074968652193950,12074968652197368
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,855909,855914,4194304,256,0,0,24,24,30080,0x7f980336b900,0x7f96d3235740,12074968652224819,12074968652236990,12074968652362749,12074968652366021
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,855909,855914,4194304,256,0,0,24,24,30784,0x7f980336b800,0x7f96d3235780,12074968652402739,12074968652417148,12074968652541627,12074968652544743
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,855909,855914,4194304,256,0,0,28,24,32000,0x7f980336b700,0x7f96d32357c0,12074968652571333,12074968652583707,12074968652830585,12074968652882882
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,855909,855914,4194304,256,0,0,28,24,32960,0x7f980336b600,0x7f96d3235800,12074968652902929,12074968652918424,12074968653165622,12074968653245315
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,855909,855914,4194304,256,0,0,24,24,33920,0x7f980336b500,0x7f96d3235840,12074968653267777,12074968653279861,12074968653404020,12074968653407336
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,855909,855914,4194304,256,0,0,24,24,34880,0x7f980336b400,0x7f96d3235880,12074968653433825,12074968653445140,12074968653570899,12074968653574367
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,855909,855914,4194304,256,0,0,24,24,35840,0x7f980336b300,0x7f96d32358c0,12074968653611896,12074968653623859,12074968653748818,12074968653751927
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,855909,855914,4194304,256,0,0,28,24,37312,0x7f980336ba00,0x7f96d3235900,12074968653781011,12074968653792657,12074968654045935,12074968654124429
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,855909,855914,4194304,256,0,0,28,24,38272,0x7f980336b900,0x7f96d3235940,12074968654146380,12074968654164654,12074968654413772,12074968654490930
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,855909,855914,4194304,256,0,0,24,24,39232,0x7f980336b800,0x7f96d3235980,12074968654511849,12074968654522892,12074968654647531,12074968654650927
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,855909,855914,4194304,256,0,0,24,24,40192,0x7f980336b700,0x7f96d32359c0,12074968654677316,12074968654689130,12074968654815369,12074968654818759
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,855909,855914,4194304,256,0,0,24,24,41152,0x7f980336b600,0x7f96d3235a00,12074968654855507,12074968654868969,12074968654993448,12074968654996720
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,855909,855914,4194304,256,0,0,28,24,42624,0x7f980336b500,0x7f96d3235a40,12074968655028790,12074968655041927,12074968655291045,12074968655345879
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,855909,855914,4194304,256,0,0,28,24,43584,0x7f980336b400,0x7f96d3235a80,12074968655367218,12074968655380165,12074968655625603,12074968655671905
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,855909,855914,4194304,256,0,0,24,24,44544,0x7f980336b300,0x7f96d3235ac0,12074968655695468,12074968655708962,12074968655834241,12074968655837312
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,855909,855914,4194304,256,0,0,24,24,45760,0x7f980336ba00,0x7f96d3235b00,12074968655865765,12074968655877601,12074968656003040,12074968656006236
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,855909,855914,4194304,256,0,0,24,24,46720,0x7f980336b900,0x7f96d3235b40,12074968656043866,12074968656054879,12074968656179518,12074968656182483
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,855909,855914,4194304,256,0,0,28,24,48448,0x7f980336b800,0x7f96d3235b80,12074968656210375,12074968656222078,12074968656481276,12074968656502558
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,855909,855914,4194304,256,0,0,28,24,49408,0x7f980336b700,0x7f96d3235bc0,12074968656525341,12074968656536635,12074968656784473,12074968656808216
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,855909,855914,4194304,256,0,0,24,24,50368,0x7f980336b600,0x7f96d3235c00,12074968656827412,12074968656840473,12074968656965112,12074968656968304
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,855909,855914,4194304,256,0,0,24,24,51584,0x7f980336b500,0x7f96d3235c40,12074968656996616,12074968657013272,12074968657139511,12074968657142728
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,855909,855914,4194304,256,0,0,24,24,52544,0x7f980336b400,0x7f96d3235c80,12074968657182502,12074968657194230,12074968657319189,12074968657322181
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,855909,855914,4194304,256,0,0,28,24,54272,0x7f980336b300,0x7f96d3235cc0,12074968657349302,12074968657361429,12074968657615347,12074968657636466
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,855909,855914,4194304,256,0,0,28,24,55488,0x7f980336ba00,0x7f96d3235d00,12074968657659609,12074968657671506,12074968657918064,12074968657938407
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,855909,855914,4194304,256,0,0,24,24,56704,0x7f980336b900,0x7f96d3235d40,12074968657960357,12074968657973104,12074968658097743,12074968658101029
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,855909,855914,4194304,256,0,0,24,24,58176,0x7f980336b800,0x7f96d3235d80,12074968658128290,12074968658139983,12074968658267182,12074968658270083
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,855909,855914,4194304,256,0,0,24,24,59392,0x7f980336b700,0x7f96d3235dc0,12074968658308705,12074968658320941,12074968658446220,12074968658449256
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,855909,855914,4194304,256,0,0,28,24,61376,0x7f980336b600,0x7f96d3235e00,12074968658478019,12074968658489260,12074968658743658,12074968658768068
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,855909,855914,4194304,256,0,0,28,24,62592,0x7f980336b500,0x7f96d3235e40,12074968658788346,12074968658800137,12074968659044295,12074968659070811
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,855909,855914,4194304,256,0,0,24,24,63808,0x7f980336b400,0x7f96d3235e80,12074968659096338,12074968659109255,12074968659234694,12074968659237841
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,855909,855914,4194304,256,0,0,24,24,65280,0x7f980336b300,0x7f96d3235ec0,12074968659262507,12074968659274053,12074968659401892,12074968659405122
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,855909,855914,4194304,256,0,0,24,24,66496,0x7f980336ba00,0x7f96d3235f00,12074968659442582,12074968659453892,12074968659579331,12074968659582292
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,855909,855914,4194304,256,0,0,28,24,68480,0x7f980336b900,0x7f96d3235f40,12074968659610153,12074968659622371,12074968659874209,12074968659895484
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,855909,855914,4194304,256,0,0,28,24,69696,0x7f980336b800,0x7f96d3235f80,12074968659918637,12074968659930208,12074968660178686,12074968660203967
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,855909,855914,4194304,256,0,0,24,24,70912,0x7f980336b700,0x7f96d3235fc0,12074968660226970,12074968660239166,12074968660363965,12074968660367010
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,855909,855914,4194304,256,0,0,24,24,72384,0x7f980336b600,0x7f96d3236000,12074968660394220,12074968660405404,12074968660543003,12074968660546123
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,855909,855914,4194304,256,0,0,24,24,73600,0x7f980336b500,0x7f96d3236040,12074968660584895,12074968660596443,12074968660722202,12074968660725386
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,855909,855914,4194304,256,0,0,28,24,75840,0x7f980336b400,0x7f96d3236080,12074968660748469,12074968660759642,12074968661027799,12074968661053826
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,855909,855914,4194304,256,0,0,28,24,77056,0x7f980336b300,0x7f96d32360c0,12074968661076027,12074968661089399,12074968661337237,12074968661361658
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,855909,855914,4194304,256,0,0,24,24,78272,0x7f980336ba00,0x7f96d3236100,12074968661383539,12074968661396276,12074968661521075,12074968661524240
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,855909,855914,4194304,256,0,0,24,24,80000,0x7f980336b900,0x7f96d3236140,12074968661550509,12074968661562195,12074968661705234,12074968661708302
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,855909,855914,4194304,256,0,0,24,24,81216,0x7f980336b800,0x7f96d3236180,12074968661745281,12074968661756274,12074968661881393,12074968661884440
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,855909,855914,4194304,256,0,0,28,24,83456,0x7f980336b700,0x7f96d32361c0,12074968661912442,12074968661924752,12074968662177070,12074968662205346
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,855909,855914,4194304,256,0,0,28,24,84928,0x7f980336b600,0x7f96d3236200,12074968662227297,12074968662238510,12074968662484748,12074968662509531
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,855909,855914,4194304,256,0,0,24,24,86400,0x7f980336b500,0x7f96d3236240,12074968662533256,12074968662545867,12074968662671306,12074968662674358
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,855909,855914,4194304,256,0,0,24,24,88128,0x7f980336b400,0x7f96d3236280,12074968662701608,12074968662713226,12074968662862825,12074968662865814
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,855909,855914,4194304,256,0,0,24,24,89600,0x7f980336b300,0x7f96d32362c0,12074968662918642,12074968662930184,12074968663055143,12074968663058582
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,855909,855914,4194304,256,0,0,28,24,92096,0x7f980336ba00,0x7f96d3236300,12074968663088998,12074968663101543,12074968663353541,12074968663379949
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,855909,855914,4194304,256,0,0,28,24,93568,0x7f980336b900,0x7f96d3236340,12074968663401289,12074968663414340,12074968663658498,12074968663682401
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,855909,855914,4194304,256,0,0,24,24,95040,0x7f980336b800,0x7f96d3236380,12074968663703100,12074968663715778,12074968663841217,12074968663844372
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,855909,855914,4194304,256,0,0,24,24,96768,0x7f980336b700,0x7f96d32363c0,12074968663872344,12074968663884257,12074968664041375,12074968664044805
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,855909,855914,4194304,256,0,0,24,24,98240,0x7f980336b600,0x7f96d3236400,12074968664084358,12074968664095455,12074968664220574,12074968664223687
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,855909,855914,4194304,256,0,0,28,24,100736,0x7f980336b500,0x7f96d3236440,12074968664251719,12074968664263773,12074968664518811,12074968664539784
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,855909,855914,4194304,256,0,0,28,24,102208,0x7f980336b400,0x7f96d3236480,12074968664562687,12074968664576091,12074968664821049,12074968664845042
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,855909,855914,4194304,256,0,0,24,24,103680,0x7f980336b300,0x7f96d32364c0,12074968664865079,12074968664877369,12074968665003128,12074968665006371
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,855909,855914,4194304,256,0,0,24,24,105664,0x7f980336ba00,0x7f96d3236500,12074968665034153,12074968665046967,12074968665211766,12074968665214899
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,855909,855914,4194304,256,0,0,24,24,107136,0x7f980336b900,0x7f96d3236540,12074968665252629,12074968665263925,12074968665389524,12074968665392569
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,855909,855914,4194304,256,0,0,28,24,109888,0x7f980336b800,0x7f96d3236580,12074968665420491,12074968665432404,12074968665688722,12074968665709568
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,855909,855914,4194304,256,0,0,28,24,111360,0x7f980336b700,0x7f96d32365c0,12074968665732250,12074968665744882,12074968665992400,12074968666017601
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,855909,855914,4194304,256,0,0,24,24,112832,0x7f980336b600,0x7f96d3236600,12074968666041505,12074968666053199,12074968666178158,12074968666181385
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,855909,855914,4194304,256,0,0,24,24,114816,0x7f980336b500,0x7f96d3236640,12074968666207524,12074968666218798,12074968666390636,12074968666393690
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,855909,855914,4194304,256,0,0,24,24,116288,0x7f980336b400,0x7f96d3236680,12074968666431330,12074968666442796,12074968666568875,12074968666571961
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,855909,855914,4194304,256,0,0,28,24,119040,0x7f980336b300,0x7f96d32366c0,12074968666599692,12074968666611115,12074968666862953,12074968666887447
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,855909,855914,4194304,256,0,0,28,24,120768,0x7f980336ba00,0x7f96d3236700,12074968666907194,12074968666918312,12074968667168710,12074968667201140
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,855909,855914,4194304,256,0,0,24,24,122496,0x7f980336b900,0x7f96d3236740,12074968667222309,12074968667233670,12074968667359589,12074968667362871
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,855909,855914,4194304,256,0,0,24,24,124736,0x7f980336b800,0x7f96d3236780,12074968667391394,12074968667402788,12074968667585507,12074968667588660
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,855909,855914,4194304,256,0,0,24,24,126464,0x7f980336b700,0x7f96d32367c0,12074968667627412,12074968667638946,12074968667766145,12074968667769266
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,855909,855914,4194304,256,0,0,20,24,127936,0x7f980336b600,0x7f96d3236800,12074968667797288,12074968667808865,12074968668072223,12074968668101173
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,855909,855914,4194304,256,0,0,28,24,129664,0x7f980336b500,0x7f96d3236840,12074968668122402,12074968668134142,12074968668383260,12074968668410568
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,855909,855914,4194304,256,0,0,24,24,131392,0x7f980336b400,0x7f96d3236880,12074968668430645,12074968668441500,12074968668567899,12074968668571006
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,855909,855914,4194304,256,0,0,24,24,133632,0x7f980336b300,0x7f96d32368c0,12074968668598888,12074968668612379,12074968668802617,12074968668807726
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,855909,855914,4194304,256,0,0,24,24,135360,0x7f980336ba00,0x7f96d3236900,12074968668842911,12074968668855417,12074968668982616,12074968668985767
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,855909,855914,4194304,256,0,0,20,24,136832,0x7f980336b900,0x7f96d3236940,12074968669018067,12074968669031415,12074968669313653,12074968669338131
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,855909,855914,4194304,256,0,0,28,24,138560,0x7f980336b800,0x7f96d3236980,12074968669359641,12074968669371253,12074968669617811,12074968669641325
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,855909,855914,4194304,256,0,0,24,24,140288,0x7f980336b700,0x7f96d32369c0,12074968669662995,12074968669674610,12074968669801169,12074968669804258
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,855909,855914,4194304,256,0,0,24,24,142784,0x7f980336b600,0x7f96d3236a00,12074968669827451,12074968669838929,12074968670048687,12074968670076854
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,855909,855914,4194304,256,0,0,24,24,144768,0x7f980336b500,0x7f96d3236a40,12074968670108724,12074968670122767,12074968670250446,12074968670253683
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,855909,855914,4194304,256,0,0,20,24,145728,0x7f980336b400,0x7f96d3236a80,12074968670276646,12074968670287565,12074968670593003,12074968670613191
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,855909,855914,4194304,256,0,0,28,24,147712,0x7f980336b300,0x7f96d3236ac0,12074968670638799,12074968670652202,12074968670901480,12074968670925181
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,855909,855914,4194304,256,0,0,24,24,149696,0x7f980336ba00,0x7f96d3236b00,12074968670945579,12074968670958280,12074968671087239,12074968671090809
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,855909,855914,4194304,256,0,0,24,24,152192,0x7f980336b900,0x7f96d3236b40,12074968671119502,12074968671131398,12074968671359877,12074968671388983
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,855909,855914,4194304,256,0,0,24,24,154176,0x7f980336b800,0x7f96d3236b80,12074968671422044,12074968671433636,12074968671562275,12074968671565360
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,855909,855914,4194304,256,0,0,20,24,155648,0x7f980336b700,0x7f96d3236bc0,12074968671593012,12074968671604675,12074968671932832,12074968671956948
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,855909,855914,4194304,256,0,0,28,24,157632,0x7f980336b600,0x7f96d3236c00,12074968671978538,12074968671989632,12074968672242270,12074968672270100
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,855909,855914,4194304,256,0,0,24,24,159616,0x7f980336b500,0x7f96d3236c40,12074968672291690,12074968672304509,12074968672432828,12074968672436049
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,855909,855914,4194304,256,0,0,24,24,162368,0x7f980336b400,0x7f96d3236c80,12074968672462989,12074968672474428,12074968672717306,12074968672736928
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,855909,855914,4194304,256,0,0,24,24,164608,0x7f980336b300,0x7f96d3236cc0,12074968672770530,12074968672781625,12074968672911544,12074968672914758
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,855909,855914,4194304,256,0,0,20,24,166336,0x7f980336ba00,0x7f96d3236d00,12074968672942339,12074968672953784,12074968673328981,12074968673353133
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,855909,855914,4194304,256,0,0,28,24,168576,0x7f980336b900,0x7f96d3236d40,12074968673375434,12074968673388340,12074968673638738,12074968673662277
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,855909,855914,4194304,256,0,0,24,24,170816,0x7f980336b800,0x7f96d3236d80,12074968673685601,12074968673699058,12074968673827537,12074968673830750
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,855909,855914,4194304,256,0,0,24,24,174080,0x7f980336b700,0x7f96d3236dc0,12074968673853513,12074968673864337,12074968674141454,12074968674169420
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,855909,855914,4194304,256,0,0,24,24,176576,0x7f980336b600,0x7f96d3236e00,12074968674200878,12074968674212974,12074968674348653,12074968674352159
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,855909,855914,4194304,256,0,0,20,24,177792,0x7f980336b500,0x7f96d3236e40,12074968674374451,12074968674385772,12074968674807849,12074968674831220
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,855909,855914,4194304,256,0,0,28,24,180288,0x7f980336b400,0x7f96d3236e80,12074968674854894,12074968674865769,12074968675123366,12074968675155212
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,855909,855914,4194304,256,0,0,24,24,182784,0x7f980336b300,0x7f96d3236ec0,12074968675177032,12074968675188486,12074968675324645,12074968675328293
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,855909,855914,4194304,256,0,0,24,24,186304,0x7f980336ba00,0x7f96d3236f00,12074968675352378,12074968675363525,12074968675677762,12074968675705454
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,855909,855914,4194304,256,0,0,24,24,189312,0x7f980336b900,0x7f96d3236f40,12074968675739648,12074968675751041,12074968675902080,12074968675905326
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,855909,855914,4194304,256,0,0,20,24,190784,0x7f980336b800,0x7f96d3236f80,12074968675932867,12074968675944480,12074968676459996,12074968676488209
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,855909,855914,4194304,256,0,0,28,24,193792,0x7f980336b700,0x7f96d3236fc0,12074968676509889,12074968676522555,12074968676819353,12074968676846665
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,855909,855914,4194304,256,0,0,24,24,196800,0x7f980336b600,0x7f96d3237000,12074968676868245,12074968676881112,12074968677035831,12074968677039343
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,855909,855914,4194304,256,0,0,24,24,201088,0x7f980336b500,0x7f96d3237040,12074968677062566,12074968677073751,12074968677458228,12074968677485432
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,855909,855914,4194304,256,0,0,24,24,204608,0x7f980336b400,0x7f96d3237080,12074968677517742,12074968677529107,12074968677704626,12074968677707815
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,855909,855914,4194304,256,0,0,20,24,206080,0x7f980336b300,0x7f96d32370c0,12074968677734385,12074968677745745,12074968678355181,12074968678383471
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,855909,855914,4194304,256,0,0,28,24,209600,0x7f980336ba00,0x7f96d3237100,12074968678410702,12074968678423180,12074968678752937,12074968678780579
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,855909,855914,4194304,256,0,0,24,24,213120,0x7f980336b900,0x7f96d3237140,12074968678804273,12074968678817257,12074968678995175,12074968678998404
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,855909,855914,4194304,256,0,0,24,24,218176,0x7f980336b800,0x7f96d3237180,12074968679031225,12074968679042055,12074968679496931,12074968679528569
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,855909,855914,4194304,256,0,0,24,24,222208,0x7f980336b700,0x7f96d32371c0,12074968679560238,12074968679571811,12074968679770529,12074968679798541
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,855909,855914,4194304,256,0,0,20,24,223936,0x7f980336b600,0x7f96d3237200,12074968679818778,12074968679830689,12074968680532603,12074968680567500
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,855909,855914,4194304,256,0,0,28,24,227968,0x7f980336b500,0x7f96d3237240,12074968680590713,12074968680602203,12074968680974360,12074968681006876
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,855909,855914,4194304,256,0,0,24,24,232000,0x7f980336b400,0x7f96d3237280,12074968681027795,12074968681038999,12074968681241397,12074968681269765
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,855909,855914,4194304,256,0,0,24,24,237824,0x7f980336b300,0x7f96d32372c0,12074968681292958,12074968681305877,12074968681831313,12074968681858529
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,855909,855914,4194304,256,0,0,24,24,242368,0x7f980336ba00,0x7f96d3237300,12074968681891340,12074968681904272,12074968682127310,12074968682157865
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,855909,855914,4194304,256,0,0,20,24,243584,0x7f980336b900,0x7f96d3237340,12074968682179656,12074968682192430,12074968682989383,12074968683017493
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,855909,855914,4194304,256,0,0,28,24,248128,0x7f980336b800,0x7f96d3237380,12074968683040866,12074968683053063,12074968683495619,12074968683523122
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,855909,855914,4194304,256,0,0,24,24,252672,0x7f980336b700,0x7f96d32373c0,12074968683543841,12074968683555139,12074968683780577,12074968683808282
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,855909,855914,4194304,256,0,0,24,24,259264,0x7f980336b600,0x7f96d3237400,12074968683829892,12074968683842817,12074968684438492,12074968684472647
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,855909,855914,4194304,256,0,0,24,24,264832,0x7f980336b500,0x7f96d3237440,12074968684504276,12074968684517371,12074968684786009,12074968684813470
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,855909,855914,4194304,256,0,0,20,24,266304,0x7f980336b400,0x7f96d3237480,12074968684835110,12074968684848249,12074968685832241,12074968685860646
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,855909,855914,4194304,256,0,0,28,24,271872,0x7f980336b300,0x7f96d32374c0,12074968685884090,12074968685896560,12074968686410316,12074968686440434
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,855909,855914,4194304,256,0,0,24,24,277440,0x7f980336ba00,0x7f96d3237500,12074968686464268,12074968686477516,12074968686748393,12074968686772892
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,855909,855914,4194304,256,0,0,12,24,279936,0x7f980336b900,0x7f96d3237540,12074968686794382,12074968686807273,12074968687544227,12074968687572488
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,855909,855914,4194304,256,0,0,24,24,286528,0x7f980336b800,0x7f96d3237580,12074968687603305,12074968687615106,12074968687929504,12074968687957142
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,855909,855914,4194304,256,0,0,20,24,288000,0x7f980336b700,0x7f96d32375c0,12074968687978011,12074968687990463,12074968689161174,12074968689195594
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,855909,855914,4194304,256,0,0,32,24,294592,0x7f980336b600,0x7f96d3237600,12074968689220771,12074968689232053,12074968689842449,12074968689870358
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,855909,855914,4194304,256,0,0,24,24,301184,0x7f980336b500,0x7f96d3237640,12074968689892068,12074968689904528,12074968690252205,12074968690284507
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,855909,855914,4194304,256,0,0,12,24,304960,0x7f980336b400,0x7f96d3237680,12074968690309704,12074968690322765,12074968691199398,12074968691229353
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,855909,855914,4194304,256,0,0,24,24,313600,0x7f980336b300,0x7f96d32376c0,12074968691263948,12074968691278277,12074968691687074,12074968691715988
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,855909,855914,4194304,256,0,0,20,24,314816,0x7f980336ba00,0x7f96d3237700,12074968691738459,12074968691751393,12074968693299381,12074968693352429
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,855909,855914,4194304,256,0,0,20,24,317568,0x7f980336b900,0x7f96d3237740,12074968693376604,12074968693389441,12074968694183356,12074968694238916
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,855909,855914,4194304,256,0,0,12,24,320320,0x7f980336b800,0x7f96d3237780,12074968694258472,12074968694270554,12074968694683352,12074968694733064
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,855909,855914,4194304,256,0,0,12,24,324096,0x7f980336b700,0x7f96d32377c0,12074968694762008,12074968694773751,12074968695931343,12074968695982957
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,855909,855914,4194304,256,0,0,12,24,328896,0x7f980336b600,0x7f96d3237800,12074968696026258,12074968696038383,12074968696823017,12074968696873973
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,855909,855914,4194304,256,0,0,20,24,330112,0x7f980336b500,0x7f96d3237840,12074968696902165,12074968696914057,12074968699965077,12074968700026281
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,855909,855914,4194304,256,0,0,20,24,332864,0x7f980336b400,0x7f96d3237880,12074968700050616,12074968700062356,12074968701603466,12074968701655259
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,855909,855914,4194304,256,0,0,12,24,335616,0x7f980336b300,0x7f96d32378c0,12074968701684222,12074968701695625,12074968702484100,12074968702535985
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,855909,855914,4194304,256,0,0,12,24,339392,0x7f980336ba00,0x7f96d3237900,12074968702558427,12074968702570340,12074968704851764,12074968704903956
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,855909,855914,4194304,256,0,0,12,24,344192,0x7f980336b900,0x7f96d3237940,12074968704938220,12074968704951444,12074968706486474,12074968706542851
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,855909,855914,4194304,256,0,0,20,24,345408,0x7f980336b800,0x7f96d3237980,12074968706566465,12074968706579913,12074968712634433,12074968712691077
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,855909,855914,4194304,256,0,0,20,24,348160,0x7f980336b700,0x7f96d32379c0,12074968712714220,12074968712727873,12074968715769932,12074968715821865
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,855909,855914,4194304,256,0,0,12,24,350912,0x7f980336b600,0x7f96d3237a00,12074968715849917,12074968715862892,12074968717400802,12074968717457044
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,855909,855914,4194304,256,0,0,12,24,0,0x7f980336b500,0x7f96d3237a40,12074968717483353,12074968717496801,12074968722023011,12074968722075988