989e29cf81
Signed-off-by: Jose Santos <josantos@login1.hpcfund>
169 lines
39 KiB
CSV
169 lines
39 KiB
CSV
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,grd,Workgroup_Size,LDS_Per_Workgroup,scr,vgpr,SGPR,fbar,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
|
|
0,"__amd_rocclr_fillBuffer.kd",0,0,0,876012,876017,33554432,256,0,0,8,32,6464,0x0,0x7ff524c04180,12075448588620347,12075448588665738,12075448588990532,12075448589097193
|
|
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,876012,876017,32768,256,0,0,24,24,12480,0x0,0x7ff524c35100,12075448603446801,12075448603567040,12075448603573600,12075448603579378
|
|
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,876012,876017,4194304,256,0,0,24,24,12928,0x7ff6307be900,0x7ff524c35140,12075448603623450,12075448603638079,12075448603768636,12075448603772236
|
|
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,876012,876017,4194304,256,0,0,36,24,13632,0x7ff6307be800,0x7ff524c35180,12075448603813703,12075448603824795,12075448604074551,12075448604175065
|
|
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,876012,876017,4194304,256,0,0,28,24,14080,0x7ff6307be700,0x7ff524c351c0,12075448604200332,12075448604212309,12075448604456464,12075448604553699
|
|
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,876012,876017,4194304,256,0,0,24,24,14528,0x7ff6307be600,0x7ff524c35200,12075448604578545,12075448604590222,12075448604715500,12075448604718866
|
|
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,876012,876017,4194304,256,0,0,24,24,14976,0x7ff6307be500,0x7ff524c35240,12075448604744082,12075448604755339,12075448604880937,12075448604884463
|
|
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,876012,876017,4194304,256,0,0,24,24,15424,0x7ff6307be400,0x7ff524c35280,12075448604934015,12075448604945576,12075448605069734,12075448605072974
|
|
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,876012,876017,4194304,256,0,0,28,24,16128,0x7ff6307be300,0x7ff524c352c0,12075448605098782,12075448605110693,12075448605357409,12075448605454002
|
|
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,876012,876017,4194304,256,0,0,28,24,16832,0x7ff6307bea00,0x7ff524c35300,12075448605473949,12075448605488127,12075448605732122,12075448605829229
|
|
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,876012,876017,4194304,256,0,0,24,24,17536,0x7ff6307be900,0x7ff524c35340,12075448605848695,12075448605861560,12075448605986198,12075448605989888
|
|
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,876012,876017,4194304,256,0,0,24,24,18240,0x7ff6307be800,0x7ff524c35380,12075448606021456,12075448606033237,12075448606157555,12075448606160956
|
|
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,876012,876017,4194304,256,0,0,24,24,18944,0x7ff6307be700,0x7ff524c353c0,12075448606198185,12075448606209714,12075448606334352,12075448606337754
|
|
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,876012,876017,4194304,256,0,0,28,24,19904,0x7ff6307be600,0x7ff524c35400,12075448606363081,12075448606374191,12075448606619947,12075448606691932
|
|
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,876012,876017,4194304,256,0,0,28,24,20608,0x7ff6307be500,0x7ff524c35440,12075448606712440,12075448606723945,12075448606968901,12075448607066098
|
|
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,876012,876017,4194304,256,0,0,24,24,21312,0x7ff6307be400,0x7ff524c35480,12075448607084762,12075448607099619,12075448607224897,12075448607228530
|
|
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,876012,876017,4194304,256,0,0,24,24,22016,0x7ff6307be300,0x7ff524c354c0,12075448607252464,12075448607263936,12075448607389054,12075448607392715
|
|
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,876012,876017,4194304,256,0,0,24,24,22720,0x7ff6307bea00,0x7ff524c35500,12075448607428962,12075448607441533,12075448607565691,12075448607569273
|
|
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,876012,876017,4194304,256,0,0,28,24,23680,0x7ff6307be900,0x7ff524c35540,12075448607594089,12075448607606810,12075448607858166,12075448607930524
|
|
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,876012,876017,4194304,256,0,0,28,24,24384,0x7ff6307be800,0x7ff524c35580,12075448607949830,12075448607960244,12075448608205680,12075448608275776
|
|
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,876012,876017,4194304,256,0,0,24,24,25088,0x7ff6307be700,0x7ff524c355c0,12075448608294731,12075448608305838,12075448608430956,12075448608434220
|
|
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,876012,876017,4194304,256,0,0,24,24,25792,0x7ff6307be600,0x7ff524c35600,12075448608459337,12075448608470155,12075448608595593,12075448608599057
|
|
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,876012,876017,4194304,256,0,0,24,24,26496,0x7ff6307be500,0x7ff524c35640,12075448608633861,12075448608644712,12075448608768710,12075448608772068
|
|
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,876012,876017,4194304,256,0,0,28,24,27712,0x7ff6307be400,0x7ff524c35680,12075448608797856,12075448608809829,12075448609054465,12075448609121367
|
|
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,876012,876017,4194304,256,0,0,28,24,28416,0x7ff6307be300,0x7ff524c356c0,12075448609141014,12075448609153503,12075448609399259,12075448609465116
|
|
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,876012,876017,4194304,256,0,0,24,24,29120,0x7ff6307bea00,0x7ff524c35700,12075448609486135,12075448609497337,12075448609620855,12075448609623961
|
|
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,876012,876017,4194304,256,0,0,24,24,30080,0x7ff6307be900,0x7ff524c35740,12075448609652494,12075448609663735,12075448609789172,12075448609792344
|
|
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,876012,876017,4194304,256,0,0,24,24,30784,0x7ff6307be800,0x7ff524c35780,12075448609827400,12075448609839732,12075448609964369,12075448609967360
|
|
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,876012,876017,4194304,256,0,0,28,24,32000,0x7ff6307be700,0x7ff524c357c0,12075448609993138,12075448610004529,12075448610252844,12075448610319634
|
|
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,876012,876017,4194304,256,0,0,28,24,32960,0x7ff6307be600,0x7ff524c35800,12075448610338449,12075448610349483,12075448610594439,12075448610672420
|
|
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,876012,876017,4194304,256,0,0,24,24,33920,0x7ff6307be500,0x7ff524c35840,12075448610691996,12075448610702597,12075448610827555,12075448610830714
|
|
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,876012,876017,4194304,256,0,0,24,24,34880,0x7ff6307be400,0x7ff524c35880,12075448610855129,12075448610866274,12075448610991392,12075448610995090
|
|
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,876012,876017,4194304,256,0,0,24,24,35840,0x7ff6307be300,0x7ff524c358c0,12075448611035274,12075448611046431,12075448611170749,12075448611174012
|
|
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,876012,876017,4194304,256,0,0,28,24,37312,0x7ff6307bea00,0x7ff524c35900,12075448611199469,12075448611211068,12075448611462744,12075448611540203
|
|
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,876012,876017,4194304,256,0,0,28,24,38272,0x7ff6307be900,0x7ff524c35940,12075448611563967,12075448611575382,12075448611823057,12075448611900602
|
|
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,876012,876017,4194304,256,0,0,24,24,39232,0x7ff6307be800,0x7ff524c35980,12075448611921872,12075448611933135,12075448612058413,12075448612062243
|
|
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,876012,876017,4194304,256,0,0,24,24,40192,0x7ff6307be700,0x7ff524c359c0,12075448612090175,12075448612101773,12075448612227530,12075448612231337
|
|
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,876012,876017,4194304,256,0,0,24,24,41152,0x7ff6307be600,0x7ff524c35a00,12075448612269688,12075448612280809,12075448612405287,12075448612408516
|
|
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,876012,876017,4194304,256,0,0,28,24,42624,0x7ff6307be500,0x7ff524c35a40,12075448612437170,12075448612448647,12075448612694402,12075448612750342
|
|
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,876012,876017,4194304,256,0,0,28,24,43584,0x7ff6307be400,0x7ff524c35a80,12075448612778965,12075448612790561,12075448613034076,12075448613064405
|
|
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,876012,876017,4194304,256,0,0,24,24,44544,0x7ff6307be300,0x7ff524c35ac0,12075448613086887,12075448613099035,12075448613223993,12075448613227298
|
|
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,876012,876017,4194304,256,0,0,24,24,45760,0x7ff6307bea00,0x7ff524c35b00,12075448613254068,12075448613265112,12075448613391350,12075448613394729
|
|
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,876012,876017,4194304,256,0,0,24,24,46720,0x7ff6307be900,0x7ff524c35b40,12075448613431908,12075448613442709,12075448613568147,12075448613571357
|
|
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,876012,876017,4194304,256,0,0,28,24,48448,0x7ff6307be800,0x7ff524c35b80,12075448613595983,12075448613607027,12075448613866382,12075448613891052
|
|
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,876012,876017,4194304,256,0,0,28,24,49408,0x7ff6307be700,0x7ff524c35bc0,12075448613911159,12075448613922061,12075448614167337,12075448614193474
|
|
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,876012,876017,4194304,256,0,0,24,24,50368,0x7ff6307be600,0x7ff524c35c00,12075448614212549,12075448614223336,12075448614348134,12075448614351527
|
|
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,876012,876017,4194304,256,0,0,24,24,51584,0x7ff6307be500,0x7ff524c35c40,12075448614376023,12075448614387013,12075448614513571,12075448614516454
|
|
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,876012,876017,4194304,256,0,0,24,24,52544,0x7ff6307be400,0x7ff524c35c80,12075448614552661,12075448614564610,12075448614689728,12075448614693112
|
|
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,876012,876017,4194304,256,0,0,28,24,54272,0x7ff6307be300,0x7ff524c35cc0,12075448614717958,12075448614729087,12075448614982363,12075448615012896
|
|
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,876012,876017,4194304,256,0,0,28,24,55488,0x7ff6307bea00,0x7ff524c35d00,12075448615032543,12075448615045242,12075448615290678,12075448615318454
|
|
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,876012,876017,4194304,256,0,0,24,24,56704,0x7ff6307be900,0x7ff524c35d40,12075448615337440,12075448615350356,12075448615475154,12075448615478502
|
|
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,876012,876017,4194304,256,0,0,24,24,58176,0x7ff6307be800,0x7ff524c35d80,12075448615502737,12075448615515154,12075448615644271,12075448615647616
|
|
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,876012,876017,4194304,256,0,0,24,24,59392,0x7ff6307be700,0x7ff524c35dc0,12075448615681659,12075448615693711,12075448615819148,12075448615822491
|
|
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,876012,876017,4194304,256,0,0,28,24,61376,0x7ff6307be600,0x7ff524c35e00,12075448615847267,12075448615858508,12075448616112583,12075448616146363
|
|
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,876012,876017,4194304,256,0,0,28,24,62592,0x7ff6307be500,0x7ff524c35e40,12075448616167362,12075448616180102,12075448616426498,12075448616456900
|
|
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,876012,876017,4194304,256,0,0,24,24,63808,0x7ff6307be400,0x7ff524c35e80,12075448616478911,12075448616489697,12075448616614815,12075448616618020
|
|
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,876012,876017,4194304,256,0,0,24,24,65280,0x7ff6307be300,0x7ff524c35ec0,12075448616643297,12075448616654334,12075448616783132,12075448616786493
|
|
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,876012,876017,4194304,256,0,0,24,24,66496,0x7ff6307bea00,0x7ff524c35f00,12075448616821808,12075448616832731,12075448616958169,12075448616961398
|
|
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,876012,876017,4194304,256,0,0,28,24,68480,0x7ff6307be900,0x7ff524c35f40,12075448616986965,12075448617000568,12075448617259924,12075448617288095
|
|
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,876012,876017,4194304,256,0,0,28,24,69696,0x7ff6307be800,0x7ff524c35f80,12075448617307461,12075448617319763,12075448617569838,12075448617593102
|
|
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,876012,876017,4194304,256,0,0,24,24,70912,0x7ff6307be700,0x7ff524c35fc0,12075448617612478,12075448617625037,12075448617750155,12075448617753400
|
|
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,876012,876017,4194304,256,0,0,24,24,72384,0x7ff6307be600,0x7ff524c36000,12075448617779017,12075448617792234,12075448617928392,12075448617931671
|
|
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,876012,876017,4194304,256,0,0,24,24,73600,0x7ff6307be500,0x7ff524c36040,12075448617968239,12075448617980551,12075448618105029,12075448618108500
|
|
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,876012,876017,4194304,256,0,0,28,24,75840,0x7ff6307be400,0x7ff524c36080,12075448618134127,12075448618146308,12075448618401024,12075448618424096
|
|
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,876012,876017,4194304,256,0,0,28,24,77056,0x7ff6307be300,0x7ff524c360c0,12075448618444704,12075448618457663,12075448618704219,12075448618727390
|
|
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,876012,876017,4194304,256,0,0,24,24,78272,0x7ff6307bea00,0x7ff524c36100,12075448618746926,12075448618757818,12075448618882456,12075448618886035
|
|
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,876012,876017,4194304,256,0,0,24,24,80000,0x7ff6307be900,0x7ff524c36140,12075448618911963,12075448618922935,12075448619065652,12075448619069205
|
|
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,876012,876017,4194304,256,0,0,24,24,81216,0x7ff6307be800,0x7ff524c36180,12075448619104731,12075448619115412,12075448619240689,12075448619244140
|
|
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,876012,876017,4194304,256,0,0,28,24,83456,0x7ff6307be700,0x7ff524c361c0,12075448619269708,12075448619282609,12075448619541804,12075448619569896
|
|
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,876012,876017,4194304,256,0,0,28,24,84928,0x7ff6307be600,0x7ff524c36200,12075448619588821,12075448619601643,12075448619845479,12075448619872388
|
|
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,876012,876017,4194304,256,0,0,24,24,86400,0x7ff6307be500,0x7ff524c36240,12075448619894970,12075448619907558,12075448620032996,12075448620036513
|
|
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,876012,876017,4194304,256,0,0,24,24,88128,0x7ff6307be400,0x7ff524c36280,12075448620062932,12075448620073795,12075448620223552,12075448620227027
|
|
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,876012,876017,4194304,256,0,0,24,24,89600,0x7ff6307be300,0x7ff524c362c0,12075448620279805,12075448620290431,12075448620416349,12075448620419855
|
|
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,876012,876017,4194304,256,0,0,28,24,92096,0x7ff6307bea00,0x7ff524c36300,12075448620443950,12075448620455548,12075448620707864,12075448620731114
|
|
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,876012,876017,4194304,256,0,0,28,24,93568,0x7ff6307be900,0x7ff524c36340,12075448620751792,12075448620762583,12075448621008499,12075448621036271
|
|
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,876012,876017,4194304,256,0,0,24,24,95040,0x7ff6307be800,0x7ff524c36380,12075448621055757,12075448621068658,12075448621193616,12075448621197120
|
|
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,876012,876017,4194304,256,0,0,24,24,96768,0x7ff6307be700,0x7ff524c363c0,12075448621222807,12075448621235695,12075448621394892,12075448621398504
|
|
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,876012,876017,4194304,256,0,0,24,24,98240,0x7ff6307be600,0x7ff524c36400,12075448621434551,12075448621445131,12075448621569929,12075448621573229
|
|
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,876012,876017,4194304,256,0,0,28,24,100736,0x7ff6307be500,0x7ff524c36440,12075448621599848,12075448621611368,12075448621866244,12075448621886982
|
|
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,876012,876017,4194304,256,0,0,28,24,102208,0x7ff6307be400,0x7ff524c36480,12075448621908822,12075448621921923,12075448622166879,12075448622197419
|
|
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,876012,876017,4194304,256,0,0,24,24,103680,0x7ff6307be300,0x7ff524c364c0,12075448622220191,12075448622231198,12075448622356956,12075448622360732
|
|
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,876012,876017,4194304,256,0,0,24,24,105664,0x7ff6307bea00,0x7ff524c36500,12075448622385849,12075448622397115,12075448622562072,12075448622565473
|
|
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,876012,876017,4194304,256,0,0,24,24,107136,0x7ff6307be900,0x7ff524c36540,12075448622600658,12075448622611671,12075448622736309,12075448622739757
|
|
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,876012,876017,4194304,256,0,0,28,24,109888,0x7ff6307be800,0x7ff524c36580,12075448622764903,12075448622775988,12075448623035184,12075448623068628
|
|
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,876012,876017,4194304,256,0,0,28,24,111360,0x7ff6307be700,0x7ff524c365c0,12075448623088214,12075448623099343,12075448623346859,12075448623375218
|
|
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,876012,876017,4194304,256,0,0,24,24,112832,0x7ff6307be600,0x7ff524c36600,12075448623396297,12075448623408937,12075448623534855,12075448623538501
|
|
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,876012,876017,4194304,256,0,0,24,24,114816,0x7ff6307be500,0x7ff524c36640,12075448623563006,12075448623574375,12075448623747012,12075448623750365
|
|
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,876012,876017,4194304,256,0,0,24,24,116288,0x7ff6307be400,0x7ff524c36680,12075448623786061,12075448623797411,12075448623923009,12075448623926412
|
|
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,876012,876017,4194304,256,0,0,28,24,119040,0x7ff6307be300,0x7ff524c366c0,12075448623951529,12075448623963168,12075448624216924,12075448624245655
|
|
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,876012,876017,4194304,256,0,0,28,24,120768,0x7ff6307bea00,0x7ff524c36700,12075448624264099,12075448624275802,12075448624524758,12075448624548087
|
|
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,876012,876017,4194304,256,0,0,24,24,122496,0x7ff6307be900,0x7ff524c36740,12075448624568726,12075448624580437,12075448624706835,12075448624710239
|
|
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,876012,876017,4194304,256,0,0,24,24,124736,0x7ff6307be800,0x7ff524c36780,12075448624735365,12075448624747474,12075448624929551,12075448624932963
|
|
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,876012,876017,4194304,256,0,0,24,24,126464,0x7ff6307be700,0x7ff524c367c0,12075448624969661,12075448624981550,12075448625107148,12075448625110913
|
|
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,876012,876017,4194304,256,0,0,20,24,127936,0x7ff6307be600,0x7ff524c36800,12075448625137062,12075448625149227,12075448625412423,12075448625435757
|
|
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,876012,876017,4194304,256,0,0,28,24,129664,0x7ff6307be500,0x7ff524c36840,12075448625455714,12075448625467782,12075448625714658,12075448625734252
|
|
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,876012,876017,4194304,256,0,0,24,24,131392,0x7ff6307be400,0x7ff524c36880,12075448625754099,12075448625766177,12075448625892415,12075448625896092
|
|
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,876012,876017,4194304,256,0,0,24,24,133632,0x7ff6307be300,0x7ff524c368c0,12075448625921991,12075448625932894,12075448626123611,12075448626128254
|
|
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,876012,876017,4194304,256,0,0,24,24,135360,0x7ff6307bea00,0x7ff524c36900,12075448626162087,12075448626172730,12075448626299608,12075448626303079
|
|
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,876012,876017,4194304,256,0,0,20,24,136832,0x7ff6307be900,0x7ff524c36940,12075448626328215,12075448626341047,12075448626622802,12075448626650284
|
|
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,876012,876017,4194304,256,0,0,28,24,138560,0x7ff6307be800,0x7ff524c36980,12075448626670141,12075448626682481,12075448626930797,12075448626954199
|
|
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,876012,876017,4194304,256,0,0,24,24,140288,0x7ff6307be700,0x7ff524c369c0,12075448626974507,12075448626985676,12075448627110634,12075448627114447
|
|
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,876012,876017,4194304,256,0,0,24,24,142784,0x7ff6307be600,0x7ff524c36a00,12075448627139754,12075448627150793,12075448627359909,12075448627387254
|
|
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,876012,876017,4194304,256,0,0,24,24,144768,0x7ff6307be500,0x7ff524c36a40,12075448627417089,12075448627427748,12075448627555106,12075448627558532
|
|
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,876012,876017,4194304,256,0,0,20,24,145728,0x7ff6307be400,0x7ff524c36a80,12075448627583108,12075448627594625,12075448627900860,12075448627928259
|
|
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,876012,876017,4194304,256,0,0,28,24,147712,0x7ff6307be300,0x7ff524c36ac0,12075448627948056,12075448627959739,12075448628207575,12075448628242223
|
|
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,876012,876017,4194304,256,0,0,24,24,149696,0x7ff6307bea00,0x7ff524c36b00,12075448628262019,12075448628273174,12075448628400851,12075448628404334
|
|
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,876012,876017,4194304,256,0,0,24,24,152192,0x7ff6307be900,0x7ff524c36b40,12075448628429010,12075448628441811,12075448628669487,12075448628696347
|
|
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,876012,876017,4194304,256,0,0,24,24,154176,0x7ff6307be800,0x7ff524c36b80,12075448628728196,12075448628738925,12075448628864683,12075448628868216
|
|
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,876012,876017,4194304,256,0,0,20,24,155648,0x7ff6307be700,0x7ff524c36bc0,12075448628893222,12075448628903883,12075448629231877,12075448629256678
|
|
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,876012,876017,4194304,256,0,0,28,24,157632,0x7ff6307be600,0x7ff524c36c00,12075448629276615,12075448629287236,12075448629537312,12075448629564410
|
|
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,876012,876017,4194304,256,0,0,24,24,159616,0x7ff6307be500,0x7ff524c36c40,12075448629585449,12075448629596671,12075448629724828,12075448629728305
|
|
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,876012,876017,4194304,256,0,0,24,24,162368,0x7ff6307be400,0x7ff524c36c80,12075448629753471,12075448629764348,12075448630008824,12075448630032780
|
|
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,876012,876017,4194304,256,0,0,24,24,164608,0x7ff6307be300,0x7ff524c36cc0,12075448630063497,12075448630075702,12075448630204980,12075448630208477
|
|
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,876012,876017,4194304,256,0,0,20,24,166336,0x7ff6307bea00,0x7ff524c36d00,12075448630234515,12075448630245300,12075448630619853,12075448630642964
|
|
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,876012,876017,4194304,256,0,0,28,24,168576,0x7ff6307be900,0x7ff524c36d40,12075448630662380,12075448630672972,12075448630926888,12075448630953862
|
|
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,876012,876017,4194304,256,0,0,24,24,170816,0x7ff6307be800,0x7ff524c36d80,12075448630976554,12075448630988967,12075448631119204,12075448631123006
|
|
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,876012,876017,4194304,256,0,0,24,24,174080,0x7ff6307be700,0x7ff524c36dc0,12075448631148303,12075448631158884,12075448631436959,12075448631464100
|
|
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,876012,876017,4194304,256,0,0,24,24,176576,0x7ff6307be600,0x7ff524c36e00,12075448631494367,12075448631504958,12075448631641595,12075448631645137
|
|
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,876012,876017,4194304,256,0,0,20,24,177792,0x7ff6307be500,0x7ff524c36e40,12075448631670233,12075448631681755,12075448632104147,12075448632132563
|
|
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,876012,876017,4194304,256,0,0,28,24,180288,0x7ff6307be400,0x7ff524c36e80,12075448632153512,12075448632165586,12075448632421422,12075448632448299
|
|
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,876012,876017,4194304,256,0,0,24,24,182784,0x7ff6307be300,0x7ff524c36ec0,12075448632468457,12075448632480621,12075448632615979,12075448632619618
|
|
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,876012,876017,4194304,256,0,0,24,24,186304,0x7ff6307bea00,0x7ff524c36f00,12075448632643833,12075448632655978,12075448632969413,12075448632996178
|
|
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,876012,876017,4194304,256,0,0,24,24,189312,0x7ff6307be900,0x7ff524c36f40,12075448633033357,12075448633045571,12075448633197249,12075448633200958
|
|
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,876012,876017,4194304,256,0,0,20,24,190784,0x7ff6307be800,0x7ff524c36f80,12075448633227357,12075448633243808,12075448633760439,12075448633787959
|
|
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,876012,876017,4194304,256,0,0,28,24,193792,0x7ff6307be700,0x7ff524c36fc0,12075448633808467,12075448633820758,12075448634118353,12075448634151455
|
|
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,876012,876017,4194304,256,0,0,24,24,196800,0x7ff6307be600,0x7ff524c37000,12075448634171121,12075448634183632,12075448634337069,12075448634340777
|
|
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,876012,876017,4194304,256,0,0,24,24,201088,0x7ff6307be500,0x7ff524c37040,12075448634365813,12075448634377868,12075448634762502,12075448634789621
|
|
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,876012,876017,4194304,256,0,0,24,24,204608,0x7ff6307be400,0x7ff524c37080,12075448634820338,12075448634832260,12075448635007777,12075448635011713
|
|
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,876012,876017,4194304,256,0,0,20,24,206080,0x7ff6307be300,0x7ff524c370c0,12075448635037241,12075448635049697,12075448635659926,12075448635687339
|
|
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,876012,876017,4194304,256,0,0,28,24,209600,0x7ff6307bea00,0x7ff524c37100,12075448635706865,12075448635718965,12075448636048239,12075448636076352
|
|
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,876012,876017,4194304,256,0,0,24,24,213120,0x7ff6307be900,0x7ff524c37140,12075448636098904,12075448636109838,12075448636288075,12075448636291702
|
|
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,876012,876017,4194304,256,0,0,24,24,218176,0x7ff6307be800,0x7ff524c37180,12075448636317019,12075448636327595,12075448636783267,12075448636810096
|
|
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,876012,876017,4194304,256,0,0,24,24,222208,0x7ff6307be700,0x7ff524c371c0,12075448636841063,12075448636853505,12075448637052222,12075448637080899
|
|
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,876012,876017,4194304,256,0,0,20,24,223936,0x7ff6307be600,0x7ff524c37200,12075448637099584,12075448637111901,12075448637814609,12075448637844208
|
|
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,876012,876017,4194304,256,0,0,28,24,227968,0x7ff6307be500,0x7ff524c37240,12075448637865016,12075448637875888,12075448638248521,12075448638276631
|
|
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,876012,876017,4194304,256,0,0,24,24,232000,0x7ff6307be400,0x7ff524c37280,12075448638297049,12075448638307880,12075448638510757,12075448638537225
|
|
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,876012,876017,4194304,256,0,0,24,24,237824,0x7ff6307be300,0x7ff524c372c0,12075448638556902,12075448638567876,12075448639093147,12075448639122032
|
|
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,876012,876017,4194304,256,0,0,24,24,242368,0x7ff6307bea00,0x7ff524c37300,12075448639155104,12075448639166586,12075448639390902,12075448639417922
|
|
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,876012,876017,4194304,256,0,0,20,24,243584,0x7ff6307be900,0x7ff524c37340,12075448639439713,12075448639452021,12075448640250087,12075448640278872
|
|
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,876012,876017,4194304,256,0,0,28,24,248128,0x7ff6307be800,0x7ff524c37380,12075448640299330,12075448640311206,12075448640730719,12075448640757321
|
|
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,876012,876017,4194304,256,0,0,24,24,252672,0x7ff6307be700,0x7ff524c373c0,12075448640778872,12075448640789918,12075448641014874,12075448641042111
|
|
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,876012,876017,4194304,256,0,0,24,24,259264,0x7ff6307be600,0x7ff524c37400,12075448641064142,12075448641074553,12075448641671822,12075448641698741
|
|
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,876012,876017,4194304,256,0,0,24,24,264832,0x7ff6307be500,0x7ff524c37440,12075448641729258,12075448641739981,12075448642009577,12075448642038372
|
|
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,876012,876017,4194304,256,0,0,20,24,266304,0x7ff6307be400,0x7ff524c37480,12075448642056846,12075448642067816,12075448643052919,12075448643080128
|
|
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,876012,876017,4194304,256,0,0,28,24,271872,0x7ff6307be300,0x7ff524c374c0,12075448643099324,12075448643110198,12075448643642348,12075448643669504
|
|
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,876012,876017,4194304,256,0,0,24,24,277440,0x7ff6307bea00,0x7ff524c37500,12075448643692506,12075448643703307,12075448643973543,12075448644000048
|
|
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,876012,876017,4194304,256,0,0,12,24,279936,0x7ff6307be900,0x7ff524c37540,12075448644027950,12075448644038822,12075448644775929,12075448644809031
|
|
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,876012,876017,4194304,256,0,0,24,24,286528,0x7ff6307be800,0x7ff524c37580,12075448644839668,12075448644850008,12075448645165202,12075448645199227
|
|
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,876012,876017,4194304,256,0,0,20,24,288000,0x7ff6307be700,0x7ff524c375c0,12075448645219204,12075448645231441,12075448646402461,12075448646430695
|
|
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,876012,876017,4194304,256,0,0,32,24,294592,0x7ff6307be600,0x7ff524c37600,12075448646450472,12075448646462300,12075448647073489,12075448647102373
|
|
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,876012,876017,4194304,256,0,0,24,24,301184,0x7ff6307be500,0x7ff524c37640,12075448647122260,12075448647132368,12075448647480202,12075448647507166
|
|
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,876012,876017,4194304,256,0,0,12,24,304960,0x7ff6307be400,0x7ff524c37680,12075448647529257,12075448647541481,12075448648419386,12075448648448746
|
|
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,876012,876017,4194304,256,0,0,24,24,313600,0x7ff6307be300,0x7ff524c376c0,12075448648481466,12075448648493625,12075448648903858,12075448648934639
|
|
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,876012,876017,4194304,256,0,0,20,24,314816,0x7ff6307bea00,0x7ff524c37700,12075448648957301,12075448648969456,12075448650517590,12075448650593972
|
|
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,876012,876017,4194304,256,0,0,20,24,317568,0x7ff6307be900,0x7ff524c37740,12075448650613919,12075448650626548,12075448651420454,12075448651492562
|
|
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,876012,876017,4194304,256,0,0,12,24,320320,0x7ff6307be800,0x7ff524c37780,12075448651511668,12075448651523245,12075448651936839,12075448652012208
|
|
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,876012,876017,4194304,256,0,0,12,24,324096,0x7ff6307be700,0x7ff524c377c0,12075448652033948,12075448652045636,12075448653204019,12075448653274915
|
|
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,876012,876017,4194304,256,0,0,12,24,328896,0x7ff6307be600,0x7ff524c37800,12075448653306584,12075448653319857,12075448654105126,12075448654176280
|
|
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,876012,876017,4194304,256,0,0,20,24,330112,0x7ff6307be500,0x7ff524c37840,12075448654197319,12075448654209444,12075448657262039,12075448657333117
|
|
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,876012,876017,4194304,256,0,0,20,24,332864,0x7ff6307be400,0x7ff524c37880,12075448657353645,12075448657365077,12075448658905855,12075448658976912
|
|
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,876012,876017,4194304,256,0,0,12,24,335616,0x7ff6307be300,0x7ff524c378c0,12075448659004353,12075448659017533,12075448659806961,12075448659879439
|
|
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,876012,876017,4194304,256,0,0,12,24,339392,0x7ff6307bea00,0x7ff524c37900,12075448659899316,12075448659912880,12075448662193806,12075448662268058
|
|
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,876012,876017,4194304,256,0,0,12,24,344192,0x7ff6307be900,0x7ff524c37940,12075448662298956,12075448662312044,12075448663846742,12075448663917654
|
|
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,876012,876017,4194304,256,0,0,20,24,345408,0x7ff6307be800,0x7ff524c37980,12075448663938352,12075448663949940,12075448670006171,12075448670080427
|
|
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,876012,876017,4194304,256,0,0,20,24,348160,0x7ff6307be700,0x7ff524c379c0,12075448670100334,12075448670112089,12075448673154444,12075448673225692
|
|
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,876012,876017,4194304,256,0,0,12,24,350912,0x7ff6307be600,0x7ff524c37a00,12075448673247753,12075448673259243,12075448674798580,12075448674869087
|
|
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,876012,876017,4194304,256,0,0,12,24,0,0x7ff6307be500,0x7ff524c37a40,12075448674889224,12075448674900499,12075448679427632,12075448679502498
|