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",0,0,0,906562,906567,33554432,256,0,0,8,32,6464,0x0,0x7f4385604180,12076040869119418,12076040869166673,12076040869490510,12076040869595163
|
|
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,906562,906567,32768,256,0,0,24,24,12480,0x0,0x7f4385635100,12076040884412370,12076040884512411,12076040884519291,12076040884525019
|
|
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,906562,906567,4194304,256,0,0,24,24,12928,0x7f44911b4900,0x7f4385635140,12076040884570664,12076040884584411,12076040884719290,12076040884722877
|
|
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,906562,906567,4194304,256,0,0,36,24,13632,0x7f44911b4800,0x7f4385635180,12076040884769143,12076040884782489,12076040885029047,12076040885126046
|
|
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,906562,906567,4194304,256,0,0,28,24,14080,0x7f44911b4700,0x7f43856351c0,12076040885152816,12076040885164086,12076040885406643,12076040885502576
|
|
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,906562,906567,4194304,256,0,0,24,24,14528,0x7f44911b4600,0x7f4385635200,12076040885526400,12076040885538322,12076040885663761,12076040885667122
|
|
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,906562,906567,4194304,256,0,0,24,24,14976,0x7f44911b4500,0x7f4385635240,12076040885694863,12076040885706161,12076040885830959,12076040885833972
|
|
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,906562,906567,4194304,256,0,0,24,24,15424,0x7f44911b4400,0x7f4385635280,12076040885887982,12076040885903919,12076040886027758,12076040886031048
|
|
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,906562,906567,4194304,256,0,0,28,24,16128,0x7f44911b4300,0x7f43856352c0,12076040886060503,12076040886073517,12076040886320235,12076040886418057
|
|
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,906562,906567,4194304,256,0,0,28,24,16832,0x7f44911b4a00,0x7f4385635300,12076040886439948,12076040886451754,12076040886700231,12076040886796511
|
|
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,906562,906567,4194304,256,0,0,24,24,17536,0x7f44911b4900,0x7f4385635340,12076040886818602,12076040886830310,12076040886954949,12076040886958472
|
|
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,906562,906567,4194304,256,0,0,24,24,18240,0x7f44911b4800,0x7f4385635380,12076040886984310,12076040886996229,12076040887120868,12076040887124610
|
|
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,906562,906567,4194304,256,0,0,24,24,18944,0x7f44911b4700,0x7f43856353c0,12076040887165056,12076040887176547,12076040887300706,12076040887303924
|
|
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,906562,906567,4194304,256,0,0,28,24,19904,0x7f44911b4600,0x7f4385635400,12076040887332156,12076040887344065,12076040887591583,12076040887663462
|
|
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,906562,906567,4194304,256,0,0,28,24,20608,0x7f44911b4500,0x7f4385635440,12076040887685052,12076040887696062,12076040887941980,12076040888016949
|
|
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,906562,906567,4194304,256,0,0,24,24,21312,0x7f44911b4400,0x7f4385635480,12076040888039501,12076040888051579,12076040888176218,12076040888179651
|
|
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,906562,906567,4194304,256,0,0,24,24,22016,0x7f44911b4300,0x7f43856354c0,12076040888207122,12076040888219257,12076040888344216,12076040888347543
|
|
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,906562,906567,4194304,256,0,0,24,24,22720,0x7f44911b4a00,0x7f4385635500,12076040888386796,12076040888399736,12076040888523895,12076040888527227
|
|
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,906562,906567,4194304,256,0,0,28,24,23680,0x7f44911b4900,0x7f4385635540,12076040888555540,12076040888569014,12076040888851572,12076040888892205
|
|
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,906562,906567,4194304,256,0,0,28,24,24384,0x7f44911b4800,0x7f4385635580,12076040888914547,12076040888928531,12076040889176049,12076040889272913
|
|
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,906562,906567,4194304,256,0,0,24,24,25088,0x7f44911b4700,0x7f43856355c0,12076040889294994,12076040889306927,12076040889432206,12076040889435515
|
|
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,906562,906567,4194304,256,0,0,24,24,25792,0x7f44911b4600,0x7f4385635600,12076040889462275,12076040889473486,12076040889598605,12076040889602065
|
|
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,906562,906567,4194304,256,0,0,24,24,26496,0x7f44911b4500,0x7f4385635640,12076040889639895,12076040889653324,12076040889777323,12076040889780606
|
|
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,906562,906567,4194304,256,0,0,28,24,27712,0x7f44911b4400,0x7f4385635680,12076040889808258,12076040889821163,12076040890070280,12076040890138482
|
|
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,906562,906567,4194304,256,0,0,28,24,28416,0x7f44911b4300,0x7f43856356c0,12076040890162336,12076040890175079,12076040890420677,12076040890487680
|
|
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,906562,906567,4194304,256,0,0,24,24,29120,0x7f44911b4a00,0x7f4385635700,12076040890511625,12076040890525156,12076040890649475,12076040890652547
|
|
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,906562,906567,4194304,256,0,0,24,24,30080,0x7f44911b4900,0x7f4385635740,12076040890678355,12076040890690595,12076040890816034,12076040890819287
|
|
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,906562,906567,4194304,256,0,0,24,24,30784,0x7f44911b4800,0x7f4385635780,12076040890856486,12076040890869793,12076040890994272,12076040890997819
|
|
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,906562,906567,4194304,256,0,0,28,24,32000,0x7f44911b4700,0x7f43856357c0,12076040891026482,12076040891038432,12076040891283709,12076040891336578
|
|
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,906562,906567,4194304,256,0,0,28,24,32960,0x7f44911b4600,0x7f4385635800,12076040891359631,12076040891372188,12076040891618586,12076040891695465
|
|
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,906562,906567,4194304,256,0,0,24,24,33920,0x7f44911b4500,0x7f4385635840,12076040891717546,12076040891728985,12076040891854104,12076040891857637
|
|
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,906562,906567,4194304,256,0,0,24,24,34880,0x7f44911b4400,0x7f4385635880,12076040891883875,12076040891895384,12076040892021143,12076040892024747
|
|
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,906562,906567,4194304,256,0,0,24,24,35840,0x7f44911b4300,0x7f43856358c0,12076040892062477,12076040892074902,12076040892199861,12076040892203489
|
|
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,906562,906567,4194304,256,0,0,28,24,37312,0x7f44911b4a00,0x7f4385635900,12076040892229728,12076040892241621,12076040892488978,12076040892542319
|
|
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,906562,906567,4194304,256,0,0,28,24,38272,0x7f44911b4900,0x7f4385635940,12076040892564119,12076040892578737,12076040892822895,12076040892900475
|
|
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,906562,906567,4194304,256,0,0,24,24,39232,0x7f44911b4800,0x7f4385635980,12076040892922295,12076040892934254,12076040893059533,12076040893063457
|
|
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,906562,906567,4194304,256,0,0,24,24,40192,0x7f44911b4700,0x7f43856359c0,12076040893091219,12076040893102413,12076040893228331,12076040893231860
|
|
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,906562,906567,4194304,256,0,0,24,24,41152,0x7f44911b4600,0x7f4385635a00,12076040893268869,12076040893281451,12076040893405770,12076040893409060
|
|
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,906562,906567,4194304,256,0,0,28,24,42624,0x7f44911b4500,0x7f4385635a40,12076040893436911,12076040893451049,12076040893696647,12076040893718805
|
|
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,906562,906567,4194304,256,0,0,28,24,43584,0x7f44911b4400,0x7f4385635a80,12076040893740255,12076040893753127,12076040893995844,12076040894043769
|
|
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,906562,906567,4194304,256,0,0,24,24,44544,0x7f44911b4300,0x7f4385635ac0,12076040894066411,12076040894079044,12076040894203682,12076040894206872
|
|
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,906562,906567,4194304,256,0,0,24,24,45760,0x7f44911b4a00,0x7f4385635b00,12076040894234744,12076040894247842,12076040894374081,12076040894377429
|
|
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,906562,906567,4194304,256,0,0,24,24,46720,0x7f44911b4900,0x7f4385635b40,12076040894414649,12076040894428480,12076040894553119,12076040894556622
|
|
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,906562,906567,4194304,256,0,0,28,24,48448,0x7f44911b4800,0x7f4385635b80,12076040894584514,12076040894597599,12076040894861276,12076040894886746
|
|
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,906562,906567,4194304,256,0,0,28,24,49408,0x7f44911b4700,0x7f4385635bc0,12076040894910330,12076040894923036,12076040895167834,12076040895195379
|
|
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,906562,906567,4194304,256,0,0,24,24,50368,0x7f44911b4600,0x7f4385635c00,12076040895216318,12076040895230073,12076040895353432,12076040895357060
|
|
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,906562,906567,4194304,256,0,0,24,24,51584,0x7f44911b4500,0x7f4385635c40,12076040895384922,12076040895398072,12076040895523830,12076040895527346
|
|
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,906562,906567,4194304,256,0,0,24,24,52544,0x7f44911b4400,0x7f4385635c80,12076040895564305,12076040895577430,12076040895701909,12076040895705387
|
|
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,906562,906567,4194304,256,0,0,28,24,54272,0x7f44911b4300,0x7f4385635cc0,12076040895733089,12076040895746068,12076040895996466,12076040896022336
|
|
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,906562,906567,4194304,256,0,0,28,24,55488,0x7f44911b4a00,0x7f4385635d00,12076040896045019,12076040896057905,12076040896303023,12076040896327784
|
|
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,906562,906567,4194304,256,0,0,24,24,56704,0x7f44911b4900,0x7f4385635d40,12076040896349284,12076040896361903,12076040896486702,12076040896490116
|
|
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,906562,906567,4194304,256,0,0,24,24,58176,0x7f44911b4800,0x7f4385635d80,12076040896518999,12076040896531501,12076040896660460,12076040896663648
|
|
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,906562,906567,4194304,256,0,0,24,24,59392,0x7f44911b4700,0x7f4385635dc0,12076040896701258,12076040896712619,12076040896838058,12076040896841168
|
|
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,906562,906567,4194304,256,0,0,28,24,61376,0x7f44911b4600,0x7f4385635e00,12076040896867928,12076040896881098,12076040897134056,12076040897162826
|
|
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,906562,906567,4194304,256,0,0,28,24,62592,0x7f44911b4500,0x7f4385635e40,12076040897185398,12076040897198375,12076040897443653,12076040897467492
|
|
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,906562,906567,4194304,256,0,0,24,24,63808,0x7f44911b4400,0x7f4385635e80,12076040897490295,12076040897503812,12076040897628771,12076040897631958
|
|
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,906562,906567,4194304,256,0,0,24,24,65280,0x7f44911b4300,0x7f4385635ec0,12076040897658587,12076040897671651,12076040897802049,12076040897805220
|
|
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,906562,906567,4194304,256,0,0,24,24,66496,0x7f44911b4a00,0x7f4385635f00,12076040897842008,12076040897854369,12076040897979328,12076040897982860
|
|
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,906562,906567,4194304,256,0,0,28,24,68480,0x7f44911b4900,0x7f4385635f40,12076040898014639,12076040898026847,12076040898286045,12076040898310509
|
|
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,906562,906567,4194304,256,0,0,28,24,69696,0x7f44911b4800,0x7f4385635f80,12076040898335095,12076040898348604,12076040898593562,12076040898616347
|
|
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,906562,906567,4194304,256,0,0,24,24,70912,0x7f44911b4700,0x7f4385635fc0,12076040898639160,12076040898650202,12076040898775321,12076040898778509
|
|
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,906562,906567,4194304,256,0,0,24,24,72384,0x7f44911b4600,0x7f4385636000,12076040898804727,12076040898817880,12076040898956119,12076040898959475
|
|
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,906562,906567,4194304,256,0,0,24,24,73600,0x7f44911b4500,0x7f4385636040,12076040898996764,12076040899014038,12076040899138357,12076040899141944
|
|
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,906562,906567,4194304,256,0,0,28,24,75840,0x7f44911b4400,0x7f4385636080,12076040899170908,12076040899184117,12076040899442354,12076040899465385
|
|
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,906562,906567,4194304,256,0,0,28,24,77056,0x7f44911b4300,0x7f43856360c0,12076040899488999,12076040899502514,12076040899752592,12076040899779930
|
|
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,906562,906567,4194304,256,0,0,24,24,78272,0x7f44911b4a00,0x7f4385636100,12076040899801159,12076040899813711,12076040899938670,12076040899941971
|
|
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,906562,906567,4194304,256,0,0,24,24,80000,0x7f44911b4900,0x7f4385636140,12076040899971085,12076040899982509,12076040900124908,12076040900128107
|
|
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,906562,906567,4194304,256,0,0,24,24,81216,0x7f44911b4800,0x7f4385636180,12076040900165897,12076040900177868,12076040900302986,12076040900306468
|
|
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,906562,906567,4194304,256,0,0,28,24,83456,0x7f44911b4700,0x7f43856361c0,12076040900334120,12076040900349706,12076040900601544,12076040900625621
|
|
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,906562,906567,4194304,256,0,0,28,24,84928,0x7f44911b4600,0x7f4385636200,12076040900647021,12076040900659783,12076040900906981,12076040900929396
|
|
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,906562,906567,4194304,256,0,0,24,24,86400,0x7f44911b4500,0x7f4385636240,12076040900951056,12076040900963780,12076040901088899,12076040901092529
|
|
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,906562,906567,4194304,256,0,0,24,24,88128,0x7f44911b4400,0x7f4385636280,12076040901120161,12076040901133539,12076040901285217,12076040901288463
|
|
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,906562,906567,4194304,256,0,0,24,24,89600,0x7f44911b4300,0x7f43856362c0,12076040901338917,12076040901352417,12076040901478016,12076040901481352
|
|
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,906562,906567,4194304,256,0,0,28,24,92096,0x7f44911b4a00,0x7f4385636300,12076040901508893,12076040901521375,12076040901775293,12076040901794464
|
|
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,906562,906567,4194304,256,0,0,28,24,93568,0x7f44911b4900,0x7f4385636340,12076040901817026,12076040901829212,12076040902075130,12076040902105983
|
|
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,906562,906567,4194304,256,0,0,24,24,95040,0x7f44911b4800,0x7f4385636380,12076040902132842,12076040902148250,12076040902274328,12076040902277872
|
|
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,906562,906567,4194304,256,0,0,24,24,96768,0x7f44911b4700,0x7f43856363c0,12076040902305433,12076040902320248,12076040902478167,12076040902481390
|
|
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,906562,906567,4194304,256,0,0,24,24,98240,0x7f44911b4600,0x7f4385636400,12076040902518509,12076040902531286,12076040902656245,12076040902659461
|
|
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,906562,906567,4194304,256,0,0,28,24,100736,0x7f44911b4500,0x7f4385636440,12076040902687113,12076040902699604,12076040902963442,12076040902986118
|
|
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,906562,906567,4194304,256,0,0,28,24,102208,0x7f44911b4400,0x7f4385636480,12076040903012618,12076040903025841,12076040903271279,12076040903301514
|
|
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,906562,906567,4194304,256,0,0,24,24,103680,0x7f44911b4300,0x7f43856364c0,12076040903323145,12076040903336239,12076040903461517,12076040903464748
|
|
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,906562,906567,4194304,256,0,0,24,24,105664,0x7f44911b4a00,0x7f4385636500,12076040903493411,12076040903506157,12076040903671436,12076040903674588
|
|
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,906562,906567,4194304,256,0,0,24,24,107136,0x7f44911b4900,0x7f4385636540,12076040903710775,12076040903723595,12076040903849194,12076040903852388
|
|
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,906562,906567,4194304,256,0,0,28,24,109888,0x7f44911b4800,0x7f4385636580,12076040903878176,12076040903890954,12076040904144551,12076040904171521
|
|
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,906562,906567,4194304,256,0,0,28,24,111360,0x7f44911b4700,0x7f43856365c0,12076040904193452,12076040904206791,12076040904452068,12076040904475817
|
|
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,906562,906567,4194304,256,0,0,24,24,112832,0x7f44911b4600,0x7f4385636600,12076040904497006,12076040904510468,12076040904635587,12076040904638810
|
|
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,906562,906567,4194304,256,0,0,24,24,114816,0x7f44911b4500,0x7f4385636640,12076040904665469,12076040904677026,12076040904849185,12076040904852507
|
|
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,906562,906567,4194304,256,0,0,24,24,116288,0x7f44911b4400,0x7f4385636680,12076040904889476,12076040904901984,12076040905028543,12076040905032241
|
|
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,906562,906567,4194304,256,0,0,28,24,119040,0x7f44911b4300,0x7f43856366c0,12076040905060493,12076040905073663,12076040905333340,12076040905356093
|
|
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,906562,906567,4194304,256,0,0,28,24,120768,0x7f44911b4a00,0x7f4385636700,12076040905377883,12076040905390460,12076040905635258,12076040905661731
|
|
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,906562,906567,4194304,256,0,0,24,24,122496,0x7f44911b4900,0x7f4385636740,12076040905684834,12076040905697497,12076040905823096,12076040905826467
|
|
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,906562,906567,4194304,256,0,0,24,24,124736,0x7f44911b4800,0x7f4385636780,12076040905852545,12076040905863895,12076040906045654,12076040906048930
|
|
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,906562,906567,4194304,256,0,0,24,24,126464,0x7f44911b4700,0x7f43856367c0,12076040906087642,12076040906098613,12076040906225812,12076040906229125
|
|
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,906562,906567,4194304,256,0,0,20,24,127936,0x7f44911b4600,0x7f4385636800,12076040906256666,12076040906269652,12076040906532049,12076040906558868
|
|
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,906562,906567,4194304,256,0,0,28,24,129664,0x7f44911b4500,0x7f4385636840,12076040906580749,12076040906593329,12076040906838926,12076040906861541
|
|
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,906562,906567,4194304,256,0,0,24,24,131392,0x7f44911b4400,0x7f4385636880,12076040906882419,12076040906895246,12076040907021165,12076040907024483
|
|
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,906562,906567,4194304,256,0,0,24,24,133632,0x7f44911b4300,0x7f43856368c0,12076040907054780,12076040907066284,12076040907257163,12076040907260382
|
|
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,906562,906567,4194304,256,0,0,24,24,135360,0x7f44911b4a00,0x7f4385636900,12076040907296870,12076040907308202,12076040907435241,12076040907438523
|
|
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,906562,906567,4194304,256,0,0,20,24,136832,0x7f44911b4900,0x7f4385636940,12076040907464942,12076040907477641,12076040907759398,12076040907780278
|
|
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,906562,906567,4194304,256,0,0,28,24,138560,0x7f44911b4800,0x7f4385636980,12076040907801728,12076040907814277,12076040908062595,12076040908090154
|
|
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,906562,906567,4194304,256,0,0,24,24,140288,0x7f44911b4700,0x7f43856369c0,12076040908111383,12076040908124675,12076040908250273,12076040908254119
|
|
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,906562,906567,4194304,256,0,0,24,24,142784,0x7f44911b4600,0x7f4385636a00,12076040908280848,12076040908295233,12076040908504031,12076040908530222
|
|
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,906562,906567,4194304,256,0,0,24,24,144768,0x7f44911b4500,0x7f4385636a40,12076040908561099,12076040908573471,12076040908700829,12076040908704415
|
|
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,906562,906567,4194304,256,0,0,20,24,145728,0x7f44911b4400,0x7f4385636a80,12076040908730754,12076040908743229,12076040909049306,12076040909076838
|
|
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,906562,906567,4194304,256,0,0,28,24,147712,0x7f44911b4300,0x7f4385636ac0,12076040909100472,12076040909113786,12076040909365943,12076040909392985
|
|
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,906562,906567,4194304,256,0,0,24,24,149696,0x7f44911b4a00,0x7f4385636b00,12076040909414545,12076040909427383,12076040909554102,12076040909557461
|
|
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,906562,906567,4194304,256,0,0,24,24,152192,0x7f44911b4900,0x7f4385636b40,12076040909584702,12076040909596981,12076040909824339,12076040909846889
|
|
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,906562,906567,4194304,256,0,0,24,24,154176,0x7f44911b4800,0x7f4385636b80,12076040909878057,12076040909890898,12076040910018257,12076040910021563
|
|
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,906562,906567,4194304,256,0,0,20,24,155648,0x7f44911b4700,0x7f4385636bc0,12076040910050507,12076040910062737,12076040910391054,12076040910414714
|
|
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,906562,906567,4194304,256,0,0,28,24,157632,0x7f44911b4600,0x7f4385636c00,12076040910436505,12076040910449133,12076040910702251,12076040910724830
|
|
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,906562,906567,4194304,256,0,0,24,24,159616,0x7f44911b4500,0x7f4385636c40,12076040910746521,12076040910759050,12076040910886889,12076040910890208
|
|
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,906562,906567,4194304,256,0,0,24,24,162368,0x7f44911b4400,0x7f4385636c80,12076040910917839,12076040910930249,12076040911173927,12076040911201496
|
|
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,906562,906567,4194304,256,0,0,24,24,164608,0x7f44911b4300,0x7f4385636cc0,12076040911233526,12076040911246406,12076040911375365,12076040911378896
|
|
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,906562,906567,4194304,256,0,0,20,24,166336,0x7f44911b4a00,0x7f4385636d00,12076040911405596,12076040911418404,12076040911791841,12076040911818974
|
|
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,906562,906567,4194304,256,0,0,28,24,168576,0x7f44911b4900,0x7f4385636d40,12076040911839933,12076040911852320,12076040912113758,12076040912147454
|
|
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,906562,906567,4194304,256,0,0,24,24,170816,0x7f44911b4800,0x7f4385636d80,12076040912167962,12076040912180637,12076040912311036,12076040912314635
|
|
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,906562,906567,4194304,256,0,0,24,24,174080,0x7f44911b4700,0x7f4385636dc0,12076040912341254,12076040912356156,12076040912634873,12076040912661520
|
|
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,906562,906567,4194304,256,0,0,24,24,176576,0x7f44911b4600,0x7f4385636e00,12076040912693279,12076040912706073,12076040912840471,12076040912844009
|
|
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,906562,906567,4194304,256,0,0,20,24,177792,0x7f44911b4500,0x7f4385636e40,12076040912870528,12076040912882551,12076040913304627,12076040913332527
|
|
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,906562,906567,4194304,256,0,0,28,24,180288,0x7f44911b4400,0x7f4385636e80,12076040913358355,12076040913369746,12076040913628144,12076040913654766
|
|
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,906562,906567,4194304,256,0,0,24,24,182784,0x7f44911b4300,0x7f4385636ec0,12076040913678079,12076040913688944,12076040913824782,12076040913828228
|
|
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,906562,906567,4194304,256,0,0,24,24,186304,0x7f44911b4a00,0x7f4385636f00,12076040913855539,12076040913868462,12076040914182379,12076040914212312
|
|
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,906562,906567,4194304,256,0,0,24,24,189312,0x7f44911b4900,0x7f4385636f40,12076040914244091,12076040914257098,12076040914408777,12076040914412333
|
|
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,906562,906567,4194304,256,0,0,20,24,190784,0x7f44911b4800,0x7f4385636f80,12076040914437951,12076040914450057,12076040914965572,12076040914992081
|
|
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,906562,906567,4194304,256,0,0,28,24,193792,0x7f44911b4700,0x7f4385636fc0,12076040915020233,12076040915032931,12076040915331648,12076040915358712
|
|
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,906562,906567,4194304,256,0,0,24,24,196800,0x7f44911b4600,0x7f4385637000,12076040915385592,12076040915397408,12076040915590846,12076040915616962
|
|
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,906562,906567,4194304,256,0,0,24,24,201088,0x7f44911b4500,0x7f4385637040,12076040915643932,12076040915656925,12076040916042682,12076040916070725
|
|
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,906562,906567,4194304,256,0,0,24,24,204608,0x7f44911b4400,0x7f4385637080,12076040916105660,12076040916119161,12076040916294840,12076040916298288
|
|
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,906562,906567,4194304,256,0,0,20,24,206080,0x7f44911b4300,0x7f43856370c0,12076040916325048,12076040916337559,12076040916945874,12076040916972932
|
|
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,906562,906567,4194304,256,0,0,28,24,209600,0x7f44911b4a00,0x7f4385637100,12076040916993791,12076040917006193,12076040917333710,12076040917364159
|
|
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,906562,906567,4194304,256,0,0,24,24,213120,0x7f44911b4900,0x7f4385637140,12076040917386911,12076040917399309,12076040917577228,12076040917581012
|
|
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,906562,906567,4194304,256,0,0,24,24,218176,0x7f44911b4800,0x7f4385637180,12076040917607802,12076040917618667,12076040918074343,12076040918102491
|
|
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,906562,906567,4194304,256,0,0,24,24,222208,0x7f44911b4700,0x7f43856371c0,12076040918135282,12076040918147463,12076040918346661,12076040918375118
|
|
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,906562,906567,4194304,256,0,0,20,24,223936,0x7f44911b4600,0x7f4385637200,12076040918397139,12076040918409860,12076040919110174,12076040919139408
|
|
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,906562,906567,4194304,256,0,0,28,24,227968,0x7f44911b4500,0x7f4385637240,12076040919163864,12076040919176253,12076040919547450,12076040919573946
|
|
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,906562,906567,4194304,256,0,0,24,24,232000,0x7f44911b4400,0x7f4385637280,12076040919597710,12076040919610169,12076040919811607,12076040919837806
|
|
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,906562,906567,4194304,256,0,0,24,24,237824,0x7f44911b4300,0x7f43856372c0,12076040919859006,12076040919871447,12076040920396722,12076040920430758
|
|
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,906562,906567,4194304,256,0,0,24,24,242368,0x7f44911b4a00,0x7f4385637300,12076040920463549,12076040920477041,12076040920701839,12076040920728411
|
|
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,906562,906567,4194304,256,0,0,20,24,243584,0x7f44911b4900,0x7f4385637340,12076040920752136,12076040920763599,12076040921560551,12076040921587959
|
|
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,906562,906567,4194304,256,0,0,28,24,248128,0x7f44911b4800,0x7f4385637380,12076040921611443,12076040921622151,12076040922064547,12076040922092276
|
|
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,906562,906567,4194304,256,0,0,24,24,252672,0x7f44911b4700,0x7f43856373c0,12076040922115710,12076040922127266,12076040922353184,12076040922379630
|
|
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,906562,906567,4194304,256,0,0,24,24,259264,0x7f44911b4600,0x7f4385637400,12076040922402262,12076040922415263,12076040923011738,12076040923040108
|
|
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,906562,906567,4194304,256,0,0,24,24,264832,0x7f44911b4500,0x7f4385637440,12076040923072548,12076040923084857,12076040923353495,12076040923380090
|
|
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,906562,906567,4194304,256,0,0,20,24,266304,0x7f44911b4400,0x7f4385637480,12076040923402371,12076040923415094,12076040924397965,12076040924426063
|
|
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,906562,906567,4194304,256,0,0,28,24,271872,0x7f44911b4300,0x7f43856374c0,12076040924448305,12076040924460685,12076040924990120,12076040925017703
|
|
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,906562,906567,4194304,256,0,0,24,24,277440,0x7f44911b4a00,0x7f4385637500,12076040925039894,12076040925052519,12076040925322277,12076040925349229
|
|
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,906562,906567,4194304,256,0,0,12,24,279936,0x7f44911b4900,0x7f4385637540,12076040925372062,12076040925385476,12076040926122109,12076040926150077
|
|
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,906562,906567,4194304,256,0,0,24,24,286528,0x7f44911b4800,0x7f4385637580,12076040926182858,12076040926195389,12076040926510426,12076040926537297
|
|
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,906562,906567,4194304,256,0,0,20,24,288000,0x7f44911b4700,0x7f43856375c0,12076040926560099,12076040926571225,12076040927740815,12076040927768826
|
|
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,906562,906567,4194304,256,0,0,32,24,294592,0x7f44911b4600,0x7f4385637600,12076040927793151,12076040927806094,12076040928414248,12076040928448208
|
|
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,906562,906567,4194304,256,0,0,24,24,301184,0x7f44911b4500,0x7f4385637640,12076040928472724,12076040928485448,12076040928831684,12076040928859453
|
|
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,906562,906567,4194304,256,0,0,12,24,304960,0x7f44911b4400,0x7f4385637680,12076040928882766,12076040928896164,12076040929772476,12076040929802485
|
|
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,906562,906567,4194304,256,0,0,24,24,313600,0x7f44911b4300,0x7f43856376c0,12076040929836609,12076040929849275,12076040930258871,12076040930288569
|
|
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,906562,906567,4194304,256,0,0,20,24,314816,0x7f44911b4a00,0x7f4385637700,12076040930310680,12076040930323511,12076040931870697,12076040931942092
|
|
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,906562,906567,4194304,256,0,0,20,24,317568,0x7f44911b4900,0x7f4385637740,12076040931965164,12076040931978532,12076040932770526,12076040932848656
|
|
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,906562,906567,4194304,256,0,0,12,24,320320,0x7f44911b4800,0x7f4385637780,12076040932868503,12076040932880124,12076040933317401,12076040933387979
|
|
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,906562,906567,4194304,256,0,0,12,24,324096,0x7f44911b4700,0x7f43856377c0,12076040933414168,12076040933425720,12076040934583791,12076040934655424
|
|
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,906562,906567,4194304,256,0,0,12,24,328896,0x7f44911b4600,0x7f4385637800,12076040934686813,12076040934700590,12076040935485384,12076040935557801
|
|
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,906562,906567,4194304,256,0,0,20,24,330112,0x7f44911b4500,0x7f4385637840,12076040935581255,12076040935592743,12076040938641680,12076040938716071
|
|
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,906562,906567,4194304,256,0,0,20,24,332864,0x7f44911b4400,0x7f4385637880,12076040938738362,12076040938749839,12076040940289507,12076040940361729
|
|
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,906562,906567,4194304,256,0,0,12,24,335616,0x7f44911b4300,0x7f43856378c0,12076040940385143,12076040940396866,12076040941187420,12076040941259428
|
|
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,906562,906567,4194304,256,0,0,12,24,339392,0x7f44911b4a00,0x7f4385637900,12076040941281468,12076040941294299,12076040943575882,12076040943647055
|
|
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,906562,906567,4194304,256,0,0,12,24,344192,0x7f44911b4900,0x7f4385637940,12076040943679275,12076040943693321,12076040945227229,12076040945299255
|
|
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,906562,906567,4194304,256,0,0,20,24,345408,0x7f44911b4800,0x7f4385637980,12076040945321146,12076040945334268,12076040951386701,12076040951458392
|
|
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,906562,906567,4194304,256,0,0,20,24,348160,0x7f44911b4700,0x7f43856379c0,12076040951482196,12076040951494220,12076040954535317,12076040954607204
|
|
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,906562,906567,4194304,256,0,0,12,24,350912,0x7f44911b4600,0x7f4385637a00,12076040954630918,12076040954642036,12076040956181064,12076040956253383
|
|
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,906562,906567,4194304,256,0,0,12,24,0,0x7f44911b4500,0x7f4385637a40,12076040956274633,12076040956288263,12076040960813188,12076040960885011
|