169 lines
39 KiB
CSV
169 lines
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",0,0,0,881008,881013,33554432,256,0,0,8,32,6464,0x0,0x7f1646a04180,12075541612917956,12075541612965894,12075541613290531,12075541613400493
|
|
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,881008,881013,32768,256,0,0,24,24,12480,0x0,0x7f1646a35100,12075541628364443,12075541628465232,12075541628472112,12075541628477513
|
|
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,881008,881013,4194304,256,0,0,24,24,12928,0x7f17769fb900,0x7f1646a35140,12075541628523428,12075541628536752,12075541628671150,12075541628674439
|
|
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,881008,881013,4194304,256,0,0,36,24,13632,0x7f17769fb800,0x7f1646a35180,12075541628718781,12075541628733070,12075541628977388,12075541629073801
|
|
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,881008,881013,4194304,256,0,0,28,24,14080,0x7f17769fb700,0x7f1646a351c0,12075541629100591,12075541629112586,12075541629355304,12075541629451183
|
|
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,881008,881013,4194304,256,0,0,24,24,14528,0x7f17769fb600,0x7f1646a35200,12075541629476640,12075541629488903,12075541629614342,12075541629617381
|
|
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,881008,881013,4194304,256,0,0,24,24,14976,0x7f17769fb500,0x7f1646a35240,12075541629644943,12075541629656901,12075541629782020,12075541629784883
|
|
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,881008,881013,4194304,256,0,0,24,24,15424,0x7f17769fb400,0x7f1646a35280,12075541629837210,12075541629850180,12075541629974819,12075541629977471
|
|
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,881008,881013,4194304,256,0,0,28,24,16128,0x7f17769fb300,0x7f1646a352c0,12075541630010743,12075541630024098,12075541630270816,12075541630369279
|
|
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,881008,881013,4194304,256,0,0,28,24,16832,0x7f17769fba00,0x7f1646a35300,12075541630390699,12075541630405055,12075541630650172,12075541630747011
|
|
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,881008,881013,4194304,256,0,0,24,24,17536,0x7f17769fb900,0x7f1646a35340,12075541630769953,12075541630782331,12075541630906970,12075541630910084
|
|
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,881008,881013,4194304,256,0,0,24,24,18240,0x7f17769fb800,0x7f1646a35380,12075541630935812,12075541630947770,12075541631072089,12075541631075241
|
|
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,881008,881013,4194304,256,0,0,24,24,18944,0x7f17769fb700,0x7f1646a353c0,12075541631115526,12075541631127608,12075541631251767,12075541631254514
|
|
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,881008,881013,4194304,256,0,0,28,24,19904,0x7f17769fb600,0x7f1646a35400,12075541631280983,12075541631292726,12075541631542484,12075541631613872
|
|
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,881008,881013,4194304,256,0,0,28,24,20608,0x7f17769fb500,0x7f1646a35440,12075541631634019,12075541631645043,12075541631888721,12075541631956078
|
|
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,881008,881013,4194304,256,0,0,24,24,21312,0x7f17769fb400,0x7f1646a35480,12075541631977157,12075541631989680,12075541632114479,12075541632117588
|
|
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,881008,881013,4194304,256,0,0,24,24,22016,0x7f17769fb300,0x7f1646a354c0,12075541632143717,12075541632155439,12075541632280877,12075541632283747
|
|
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,881008,881013,4194304,256,0,0,24,24,22720,0x7f17769fba00,0x7f1646a35500,12075541632321487,12075541632334637,12075541632459116,12075541632461948
|
|
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,881008,881013,4194304,256,0,0,28,24,23680,0x7f17769fb900,0x7f1646a35540,12075541632488608,12075541632503755,12075541632752553,12075541632794316
|
|
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,881008,881013,4194304,256,0,0,28,24,24384,0x7f17769fb800,0x7f1646a35580,12075541632814062,12075541632825833,12075541633073190,12075541633139457
|
|
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,881008,881013,4194304,256,0,0,24,24,25088,0x7f17769fb700,0x7f1646a355c0,12075541633160186,12075541633173029,12075541633297828,12075541633300466
|
|
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,881008,881013,4194304,256,0,0,24,24,25792,0x7f17769fb600,0x7f1646a35600,12075541633325653,12075541633337508,12075541633462627,12075541633465313
|
|
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,881008,881013,4194304,256,0,0,24,24,26496,0x7f17769fb500,0x7f1646a35640,12075541633502091,12075541633513826,12075541633638145,12075541633640969
|
|
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,881008,881013,4194304,256,0,0,28,24,27712,0x7f17769fb400,0x7f1646a35680,12075541633668621,12075541633682305,12075541633934302,12075541633974890
|
|
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,881008,881013,4194304,256,0,0,28,24,28416,0x7f17769fb300,0x7f1646a356c0,12075541633996540,12075541634014942,12075541634258619,12075541634326573
|
|
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,881008,881013,4194304,256,0,0,24,24,29120,0x7f17769fba00,0x7f1646a35700,12075541634347923,12075541634361339,12075541634485977,12075541634488584
|
|
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,881008,881013,4194304,256,0,0,24,24,30080,0x7f17769fb900,0x7f1646a35740,12075541634514523,12075541634527737,12075541634653496,12075541634656336
|
|
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,881008,881013,4194304,256,0,0,24,24,30784,0x7f17769fb800,0x7f1646a35780,12075541634692774,12075541634706295,12075541634831094,12075541634833936
|
|
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,881008,881013,4194304,256,0,0,28,24,32000,0x7f17769fb700,0x7f1646a357c0,12075541634859373,12075541634871414,12075541635118452,12075541635196941
|
|
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,881008,881013,4194304,256,0,0,28,24,32960,0x7f17769fb600,0x7f1646a35800,12075541635219262,12075541635231251,12075541635476368,12075541635553443
|
|
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,881008,881013,4194304,256,0,0,24,24,33920,0x7f17769fb500,0x7f1646a35840,12075541635574553,12075541635585647,12075541635710286,12075541635713180
|
|
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,881008,881013,4194304,256,0,0,24,24,34880,0x7f17769fb400,0x7f1646a35880,12075541635738948,12075541635750766,12075541635876045,12075541635879249
|
|
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,881008,881013,4194304,256,0,0,24,24,35840,0x7f17769fb300,0x7f1646a358c0,12075541635915196,12075541635932044,12075541636056523,12075541636059414
|
|
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,881008,881013,4194304,256,0,0,28,24,37312,0x7f17769fba00,0x7f1646a35900,12075541636086274,12075541636098283,12075541636346440,12075541636423030
|
|
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,881008,881013,4194304,256,0,0,28,24,38272,0x7f17769fb900,0x7f1646a35940,12075541636444249,12075541636462119,12075541636707717,12075541636784331
|
|
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,881008,881013,4194304,256,0,0,24,24,39232,0x7f17769fb800,0x7f1646a35980,12075541636805861,12075541636817956,12075541636942755,12075541636945971
|
|
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,881008,881013,4194304,256,0,0,24,24,40192,0x7f17769fb700,0x7f1646a359c0,12075541636973693,12075541636985795,12075541637111873,12075541637115016
|
|
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,881008,881013,4194304,256,0,0,24,24,41152,0x7f17769fb600,0x7f1646a35a00,12075541637152986,12075541637168033,12075541637293152,12075541637295882
|
|
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,881008,881013,4194304,256,0,0,28,24,42624,0x7f17769fb500,0x7f1646a35a40,12075541637323383,12075541637335551,12075541637581629,12075541637637226
|
|
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,881008,881013,4194304,256,0,0,28,24,43584,0x7f17769fb400,0x7f1646a35a80,12075541637658065,12075541637669148,12075541637913466,12075541637938636
|
|
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,881008,881013,4194304,256,0,0,24,24,44544,0x7f17769fb300,0x7f1646a35ac0,12075541637958313,12075541637970586,12075541638095385,12075541638098353
|
|
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,881008,881013,4194304,256,0,0,24,24,45760,0x7f17769fba00,0x7f1646a35b00,12075541638126185,12075541638139704,12075541638265783,12075541638268670
|
|
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,881008,881013,4194304,256,0,0,24,24,46720,0x7f17769fb900,0x7f1646a35b40,12075541638305147,12075541638318102,12075541638443061,12075541638445618
|
|
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,881008,881013,4194304,256,0,0,28,24,48448,0x7f17769fb800,0x7f1646a35b80,12075541638470334,12075541638482581,12075541638744979,12075541638769200
|
|
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,881008,881013,4194304,256,0,0,28,24,49408,0x7f17769fb700,0x7f1646a35bc0,12075541638793024,12075541638806098,12075541639049296,12075541639073105
|
|
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,881008,881013,4194304,256,0,0,24,24,50368,0x7f17769fb600,0x7f1646a35c00,12075541639093222,12075541639107055,12075541639231694,12075541639234164
|
|
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,881008,881013,4194304,256,0,0,24,24,51584,0x7f17769fb500,0x7f1646a35c40,12075541639260152,12075541639273614,12075541639400013,12075541639402747
|
|
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,881008,881013,4194304,256,0,0,24,24,52544,0x7f17769fb400,0x7f1646a35c80,12075541639438894,12075541639451692,12075541639576171,12075541639579015
|
|
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,881008,881013,4194304,256,0,0,28,24,54272,0x7f17769fb300,0x7f1646a35cc0,12075541639605053,12075541639617451,12075541639877128,12075541639904209
|
|
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,881008,881013,4194304,256,0,0,28,24,55488,0x7f17769fba00,0x7f1646a35d00,12075541639924347,12075541639937288,12075541640183846,12075541640214536
|
|
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,881008,881013,4194304,256,0,0,24,24,56704,0x7f17769fb900,0x7f1646a35d40,12075541640234773,12075541640248485,12075541640373124,12075541640375545
|
|
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,881008,881013,4194304,256,0,0,24,24,58176,0x7f17769fb800,0x7f1646a35d80,12075541640402425,12075541640415523,12075541640543362,12075541640546132
|
|
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,881008,881013,4194304,256,0,0,24,24,59392,0x7f17769fb700,0x7f1646a35dc0,12075541640581668,12075541640594082,12075541640718881,12075541640721769
|
|
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,881008,881013,4194304,256,0,0,28,24,61376,0x7f17769fb600,0x7f1646a35e00,12075541640747757,12075541640760640,12075541641012318,12075541641036313
|
|
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,881008,881013,4194304,256,0,0,28,24,62592,0x7f17769fb500,0x7f1646a35e40,12075541641057563,12075541641069437,12075541641316155,12075541641338405
|
|
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,881008,881013,4194304,256,0,0,24,24,63808,0x7f17769fb400,0x7f1646a35e80,12075541641358893,12075541641370555,12075541641495674,12075541641498362
|
|
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,881008,881013,4194304,256,0,0,24,24,65280,0x7f17769fb300,0x7f1646a35ec0,12075541641524300,12075541641538553,12075541641667992,12075541641670842
|
|
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,881008,881013,4194304,256,0,0,24,24,66496,0x7f17769fba00,0x7f1646a35f00,12075541641707300,12075541641719992,12075541641845110,12075541641847881
|
|
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,881008,881013,4194304,256,0,0,28,24,68480,0x7f17769fb900,0x7f1646a35f40,12075541641873900,12075541641887350,12075541642150868,12075541642179037
|
|
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,881008,881013,4194304,256,0,0,28,24,69696,0x7f17769fb800,0x7f1646a35f80,12075541642201589,12075541642213267,12075541642462065,12075541642489834
|
|
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,881008,881013,4194304,256,0,0,24,24,70912,0x7f17769fb700,0x7f1646a35fc0,12075541642509260,12075541642520944,12075541642646383,12075541642648990
|
|
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,881008,881013,4194304,256,0,0,24,24,72384,0x7f17769fb600,0x7f1646a36000,12075541642674838,12075541642688303,12075541642824621,12075541642827462
|
|
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,881008,881013,4194304,256,0,0,24,24,73600,0x7f17769fb500,0x7f1646a36040,12075541642863529,12075541642877421,12075541643001740,12075541643005282
|
|
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,881008,881013,4194304,256,0,0,28,24,75840,0x7f17769fb400,0x7f1646a36080,12075541643031180,12075541643044459,12075541643306057,12075541643330076
|
|
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,881008,881013,4194304,256,0,0,28,24,77056,0x7f17769fb300,0x7f1646a360c0,12075541643350945,12075541643364137,12075541643611654,12075541643633510
|
|
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,881008,881013,4194304,256,0,0,24,24,78272,0x7f17769fba00,0x7f1646a36100,12075541643653287,12075541643665894,12075541643790373,12075541643793327
|
|
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,881008,881013,4194304,256,0,0,24,24,80000,0x7f17769fb900,0x7f1646a36140,12075541643821950,12075541643834692,12075541643978051,12075541643981026
|
|
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,881008,881013,4194304,256,0,0,24,24,81216,0x7f17769fb800,0x7f1646a36180,12075541644023735,12075541644035330,12075541644160289,12075541644163344
|
|
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,881008,881013,4194304,256,0,0,28,24,83456,0x7f17769fb700,0x7f1646a361c0,12075541644189573,12075541644202529,12075541644458367,12075541644485042
|
|
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,881008,881013,4194304,256,0,0,28,24,84928,0x7f17769fb600,0x7f1646a36200,12075541644505280,12075541644518366,12075541644763004,12075541644788536
|
|
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,881008,881013,4194304,256,0,0,24,24,86400,0x7f17769fb500,0x7f1646a36240,12075541644808473,12075541644821243,12075541644947002,12075541644949856
|
|
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,881008,881013,4194304,256,0,0,24,24,88128,0x7f17769fb400,0x7f1646a36280,12075541644975845,12075541644988762,12075541645139160,12075541645142314
|
|
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,881008,881013,4194304,256,0,0,24,24,89600,0x7f17769fb300,0x7f1646a362c0,12075541645195803,12075541645207640,12075541645333239,12075541645336094
|
|
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,881008,881013,4194304,256,0,0,28,24,92096,0x7f17769fba00,0x7f1646a36300,12075541645362263,12075541645375638,12075541645630676,12075541645654656
|
|
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,881008,881013,4194304,256,0,0,28,24,93568,0x7f17769fb900,0x7f1646a36340,12075541645677028,12075541645691155,12075541645936433,12075541645962729
|
|
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,881008,881013,4194304,256,0,0,24,24,95040,0x7f17769fb800,0x7f1646a36380,12075541645983076,12075541645994513,12075541646119951,12075541646122646
|
|
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,881008,881013,4194304,256,0,0,24,24,96768,0x7f17769fb700,0x7f1646a363c0,12075541646149095,12075541646160911,12075541646318190,12075541646321235
|
|
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,881008,881013,4194304,256,0,0,24,24,98240,0x7f17769fb600,0x7f1646a36400,12075541646357592,12075541646371149,12075541646496428,12075541646499095
|
|
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,881008,881013,4194304,256,0,0,28,24,100736,0x7f17769fb500,0x7f1646a36440,12075541646525735,12075541646538188,12075541646795625,12075541646817798
|
|
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,881008,881013,4194304,256,0,0,28,24,102208,0x7f17769fb400,0x7f1646a36480,12075541646838015,12075541646850985,12075541647096583,12075541647123636
|
|
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,881008,881013,4194304,256,0,0,24,24,103680,0x7f17769fb300,0x7f1646a364c0,12075541647143573,12075541647156902,12075541647282981,12075541647285828
|
|
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,881008,881013,4194304,256,0,0,24,24,105664,0x7f17769fba00,0x7f1646a36500,12075541647313840,12075541647326980,12075541647490979,12075541647493874
|
|
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,881008,881013,4194304,256,0,0,24,24,107136,0x7f17769fb900,0x7f1646a36540,12075541647530152,12075541647543458,12075541647669217,12075541647672186
|
|
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,881008,881013,4194304,256,0,0,28,24,109888,0x7f17769fb800,0x7f1646a36580,12075541647697893,12075541647710337,12075541647964575,12075541647990507
|
|
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,881008,881013,4194304,256,0,0,28,24,111360,0x7f17769fb700,0x7f1646a365c0,12075541648015363,12075541648028894,12075541648273532,12075541648299552
|
|
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,881008,881013,4194304,256,0,0,24,24,112832,0x7f17769fb600,0x7f1646a36600,12075541648320991,12075541648333851,12075541648460090,12075541648462865
|
|
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,881008,881013,4194304,256,0,0,24,24,114816,0x7f17769fb500,0x7f1646a36640,12075541648489835,12075541648502970,12075541648674968,12075541648677955
|
|
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,881008,881013,4194304,256,0,0,24,24,116288,0x7f17769fb400,0x7f1646a36680,12075541648714513,12075541648727448,12075541648853207,12075541648856276
|
|
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,881008,881013,4194304,256,0,0,28,24,119040,0x7f17769fb300,0x7f1646a366c0,12075541648883356,12075541648896406,12075541649153044,12075541649176601
|
|
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,881008,881013,4194304,256,0,0,28,24,120768,0x7f17769fba00,0x7f1646a36700,12075541649198723,12075541649211923,12075541649458161,12075541649480777
|
|
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,881008,881013,4194304,256,0,0,24,24,122496,0x7f17769fb900,0x7f1646a36740,12075541649502367,12075541649515280,12075541649641039,12075541649643880
|
|
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,881008,881013,4194304,256,0,0,24,24,124736,0x7f17769fb800,0x7f1646a36780,12075541649670369,12075541649683439,12075541649865037,12075541649868097
|
|
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,881008,881013,4194304,256,0,0,24,24,126464,0x7f17769fb700,0x7f1646a367c0,12075541649904975,12075541649918637,12075541650044716,12075541650048021
|
|
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,881008,881013,4194304,256,0,0,20,24,127936,0x7f17769fb600,0x7f1646a36800,12075541650074911,12075541650087435,12075541650351273,12075541650377513
|
|
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,881008,881013,4194304,256,0,0,28,24,129664,0x7f17769fb500,0x7f1646a36840,12075541650398883,12075541650411752,12075541650657190,12075541650682981
|
|
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,881008,881013,4194304,256,0,0,24,24,131392,0x7f17769fb400,0x7f1646a36880,12075541650702948,12075541650715750,12075541650841988,12075541650844752
|
|
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,881008,881013,4194304,256,0,0,24,24,133632,0x7f17769fb300,0x7f1646a368c0,12075541650873555,12075541650886468,12075541651077186,12075541651081572
|
|
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,881008,881013,4194304,256,0,0,24,24,135360,0x7f17769fba00,0x7f1646a36900,12075541651117619,12075541651130306,12075541651256225,12075541651259332
|
|
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,881008,881013,4194304,256,0,0,20,24,136832,0x7f17769fb900,0x7f1646a36940,12075541651285471,12075541651298624,12075541651581022,12075541651603231
|
|
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,881008,881013,4194304,256,0,0,28,24,138560,0x7f17769fb800,0x7f1646a36980,12075541651624300,12075541651637021,12075541651885659,12075541651907607
|
|
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,881008,881013,4194304,256,0,0,24,24,140288,0x7f17769fb700,0x7f1646a369c0,12075541651927163,12075541651940058,12075541652065977,12075541652069117
|
|
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,881008,881013,4194304,256,0,0,24,24,142784,0x7f17769fb600,0x7f1646a36a00,12075541652095216,12075541652108537,12075541652318775,12075541652344950
|
|
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,881008,881013,4194304,256,0,0,24,24,144768,0x7f17769fb500,0x7f1646a36a40,12075541652375717,12075541652389174,12075541652516373,12075541652519424
|
|
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,881008,881013,4194304,256,0,0,20,24,145728,0x7f17769fb400,0x7f1646a36a80,12075541652545963,12075541652558613,12075541652864530,12075541652886967
|
|
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,881008,881013,4194304,256,0,0,28,24,147712,0x7f17769fb300,0x7f1646a36ac0,12075541652909509,12075541652922449,12075541653171887,12075541653198927
|
|
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,881008,881013,4194304,256,0,0,24,24,149696,0x7f17769fba00,0x7f1646a36b00,12075541653218844,12075541653231407,12075541653359885,12075541653362731
|
|
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,881008,881013,4194304,256,0,0,24,24,152192,0x7f17769fb900,0x7f1646a36b40,12075541653389200,12075541653402125,12075541653629003,12075541653652440
|
|
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,881008,881013,4194304,256,0,0,24,24,154176,0x7f17769fb800,0x7f1646a36b80,12075541653683317,12075541653697002,12075541653823081,12075541653826052
|
|
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,881008,881013,4194304,256,0,0,20,24,155648,0x7f17769fb700,0x7f1646a36bc0,12075541653851890,12075541653864681,12075541654193638,12075541654219794
|
|
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,881008,881013,4194304,256,0,0,28,24,157632,0x7f17769fb600,0x7f1646a36c00,12075541654240242,12075541654253157,12075541654506755,12075541654529259
|
|
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,881008,881013,4194304,256,0,0,24,24,159616,0x7f17769fb500,0x7f1646a36c40,12075541654549397,12075541654562435,12075541654690433,12075541654693564
|
|
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,881008,881013,4194304,256,0,0,24,24,162368,0x7f17769fb400,0x7f1646a36c80,12075541654722047,12075541654734913,12075541654979551,12075541655006777
|
|
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,881008,881013,4194304,256,0,0,24,24,164608,0x7f17769fb300,0x7f1646a36cc0,12075541655038365,12075541655051390,12075541655180189,12075541655183004
|
|
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,881008,881013,4194304,256,0,0,20,24,166336,0x7f17769fba00,0x7f1646a36d00,12075541655210415,12075541655223228,12075541655597305,12075541655624224
|
|
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,881008,881013,4194304,256,0,0,28,24,168576,0x7f17769fb900,0x7f1646a36d40,12075541655644412,12075541655657145,12075541655914422,12075541655940342
|
|
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,881008,881013,4194304,256,0,0,24,24,170816,0x7f17769fb800,0x7f1646a36d80,12075541655960259,12075541655972022,12075541656101780,12075541656104917
|
|
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,881008,881013,4194304,256,0,0,24,24,174080,0x7f17769fb700,0x7f1646a36dc0,12075541656131306,12075541656142900,12075541656420978,12075541656448867
|
|
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,881008,881013,4194304,256,0,0,24,24,176576,0x7f17769fb600,0x7f1646a36e00,12075541656479403,12075541656491217,12075541656625456,12075541656628290
|
|
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,881008,881013,4194304,256,0,0,20,24,177792,0x7f17769fb500,0x7f1646a36e40,12075541656654940,12075541656667855,12075541657089611,12075541657116377
|
|
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,881008,881013,4194304,256,0,0,28,24,180288,0x7f17769fb400,0x7f1646a36e80,12075541657144670,12075541657157611,12075541657415369,12075541657441040
|
|
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,881008,881013,4194304,256,0,0,24,24,182784,0x7f17769fb300,0x7f1646a36ec0,12075541657463392,12075541657474728,12075541657610087,12075541657612890
|
|
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,881008,881013,4194304,256,0,0,24,24,186304,0x7f17769fba00,0x7f1646a36f00,12075541657638467,12075541657652006,12075541657965764,12075541657991554
|
|
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,881008,881013,4194304,256,0,0,24,24,189312,0x7f17769fb900,0x7f1646a36f40,12075541658031217,12075541658043043,12075541658194241,12075541658197286
|
|
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,881008,881013,4194304,256,0,0,20,24,190784,0x7f17769fb800,0x7f1646a36f80,12075541658226620,12075541658238401,12075541658772956,12075541658795818
|
|
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,881008,881013,4194304,256,0,0,28,24,193792,0x7f17769fb700,0x7f1646a36fc0,12075541658820184,12075541658833436,12075541659130873,12075541659157090
|
|
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,881008,881013,4194304,256,0,0,24,24,196800,0x7f17769fb600,0x7f1646a37000,12075541659186354,12075541659198232,12075541659351191,12075541659354296
|
|
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,881008,881013,4194304,256,0,0,24,24,201088,0x7f17769fb500,0x7f1646a37040,12075541659382018,12075541659395190,12075541659779827,12075541659805615
|
|
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,881008,881013,4194304,256,0,0,24,24,204608,0x7f17769fb400,0x7f1646a37080,12075541659835931,12075541659848786,12075541660025105,12075541660028098
|
|
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,881008,881013,4194304,256,0,0,20,24,206080,0x7f17769fb300,0x7f1646a370c0,12075541660054738,12075541660068144,12075541660677259,12075541660704275
|
|
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,881008,881013,4194304,256,0,0,28,24,209600,0x7f17769fba00,0x7f1646a37100,12075541660724743,12075541660737738,12075541661066535,12075541661093478
|
|
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,881008,881013,4194304,256,0,0,24,24,213120,0x7f17769fb900,0x7f1646a37140,12075541661118705,12075541661129895,12075541661307813,12075541661310842
|
|
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,881008,881013,4194304,256,0,0,24,24,218176,0x7f17769fb800,0x7f1646a37180,12075541661340798,12075541661353093,12075541661808289,12075541661834185
|
|
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,881008,881013,4194304,256,0,0,24,24,222208,0x7f17769fb700,0x7f1646a371c0,12075541661865343,12075541661877888,12075541662076606,12075541662109306
|
|
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,881008,881013,4194304,256,0,0,20,24,223936,0x7f17769fb600,0x7f1646a37200,12075541662127690,12075541662141085,12075541662850519,12075541662878456
|
|
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,881008,881013,4194304,256,0,0,28,24,227968,0x7f17769fb500,0x7f1646a37240,12075541662902601,12075541662914038,12075541663286515,12075541663318764
|
|
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,881008,881013,4194304,256,0,0,24,24,232000,0x7f17769fb400,0x7f1646a37280,12075541663341867,12075541663353394,12075541663555633,12075541663581142
|
|
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,881008,881013,4194304,256,0,0,24,24,237824,0x7f17769fb300,0x7f1646a372c0,12075541663601439,12075541663614352,12075541664139307,12075541664166580
|
|
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,881008,881013,4194304,256,0,0,24,24,242368,0x7f17769fba00,0x7f1646a37300,12075541664197958,12075541664210827,12075541664433865,12075541664459524
|
|
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,881008,881013,4194304,256,0,0,20,24,243584,0x7f17769fb900,0x7f1646a37340,12075541664482787,12075541664494344,12075541665291937,12075541665319182
|
|
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,881008,881013,4194304,256,0,0,28,24,248128,0x7f17769fb800,0x7f1646a37380,12075541665345481,12075541665358176,12075541665776892,12075541665802610
|
|
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,881008,881013,4194304,256,0,0,24,24,252672,0x7f17769fb700,0x7f1646a373c0,12075541665828659,12075541665841852,12075541666065530,12075541666095134
|
|
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,881008,881013,4194304,256,0,0,24,24,259264,0x7f17769fb600,0x7f1646a37400,12075541666118357,12075541666129689,12075541666725364,12075541666751454
|
|
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,881008,881013,4194304,256,0,0,24,24,264832,0x7f17769fb500,0x7f1646a37440,12075541666782922,12075541666794163,12075541667062321,12075541667089432
|
|
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,881008,881013,4194304,256,0,0,20,24,266304,0x7f17769fb400,0x7f1646a37480,12075541667111242,12075541667122800,12075541668107111,12075541668134514
|
|
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,881008,881013,4194304,256,0,0,28,24,271872,0x7f17769fb300,0x7f1646a374c0,12075541668158258,12075541668169191,12075541668683266,12075541668710304
|
|
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,881008,881013,4194304,256,0,0,24,24,277440,0x7f17769fba00,0x7f1646a37500,12075541668736382,12075541668748225,12075541669019583,12075541669047420
|
|
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,881008,881013,4194304,256,0,0,12,24,279936,0x7f17769fb900,0x7f1646a37540,12075541669071305,12075541669082622,12075541669820056,12075541669846395
|
|
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,881008,881013,4194304,256,0,0,24,24,286528,0x7f17769fb800,0x7f1646a37580,12075541669877834,12075541669889655,12075541670206132,12075541670238454
|
|
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,881008,881013,4194304,256,0,0,20,24,288000,0x7f17769fb700,0x7f1646a375c0,12075541670260976,12075541670273171,12075541671444681,12075541671472137
|
|
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,881008,881013,4194304,256,0,0,32,24,294592,0x7f17769fb600,0x7f1646a37600,12075541671494989,12075541671506920,12075541672116035,12075541672144677
|
|
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,881008,881013,4194304,256,0,0,24,24,301184,0x7f17769fb500,0x7f1646a37640,12075541672170484,12075541672183074,12075541672501471,12075541672530013
|
|
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,881008,881013,4194304,256,0,0,12,24,304960,0x7f17769fb400,0x7f1646a37680,12075541672555841,12075541672568990,12075541673445782,12075541673475149
|
|
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,881008,881013,4194304,256,0,0,24,24,313600,0x7f17769fb300,0x7f1646a376c0,12075541673506528,12075541673519542,12075541673929298,12075541673956654
|
|
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,881008,881013,4194304,256,0,0,20,24,314816,0x7f17769fba00,0x7f1646a37700,12075541673978585,12075541673991058,12075541675539203,12075541675611730
|
|
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,881008,881013,4194304,256,0,0,20,24,317568,0x7f17769fb900,0x7f1646a37740,12075541675633831,12075541675647804,12075541676440598,12075541676515039
|
|
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,881008,881013,4194304,256,0,0,12,24,320320,0x7f17769fb800,0x7f1646a37780,12075541676535026,12075541676547476,12075541676961553,12075541677033111
|
|
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,881008,881013,4194304,256,0,0,12,24,324096,0x7f17769fb700,0x7f1646a377c0,12075541677061735,12075541677073392,12075541678231623,12075541678301950
|
|
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,881008,881013,4194304,256,0,0,12,24,328896,0x7f17769fb600,0x7f1646a37800,12075541678336273,12075541678347942,12075541679135135,12075541679205318
|
|
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,881008,881013,4194304,256,0,0,20,24,330112,0x7f17769fb500,0x7f1646a37840,12075541679227710,12075541679239615,12075541682289670,12075541682360743
|
|
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,881008,881013,4194304,256,0,0,20,24,332864,0x7f17769fb400,0x7f1646a37880,12075541682382393,12075541682395109,12075541683935417,12075541684008715
|
|
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,881008,881013,4194304,256,0,0,12,24,335616,0x7f17769fb300,0x7f1646a378c0,12075541684030356,12075541684043736,12075541684832370,12075541684902466
|
|
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,881008,881013,4194304,256,0,0,12,24,339392,0x7f17769fba00,0x7f1646a37900,12075541684923115,12075541684936369,12075541687216511,12075541687289623
|
|
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,881008,881013,4194304,256,0,0,12,24,344192,0x7f17769fb900,0x7f1646a37940,12075541687325830,12075541687339230,12075541688874417,12075541688944719
|
|
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,881008,881013,4194304,256,0,0,20,24,345408,0x7f17769fb800,0x7f1646a37980,12075541688972120,12075541688984497,12075541695038688,12075541695111209
|
|
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,881008,881013,4194304,256,0,0,20,24,348160,0x7f17769fb700,0x7f1646a379c0,12075541695138439,12075541695150367,12075541698192263,12075541698265180
|
|
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,881008,881013,4194304,256,0,0,12,24,350912,0x7f17769fb600,0x7f1646a37a00,12075541698295206,12075541698307942,12075541699846809,12075541699917141
|
|
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,881008,881013,4194304,256,0,0,12,24,0,0x7f17769fb500,0x7f1646a37a40,12075541699941826,12075541699955449,12075541704482132,12075541704556613
|