38 KiB
38 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | SQ_INSTS_LDS | SQ_INST_LEVEL_LDS | SQ_ACCUM_PREV_HIRES | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBufferAligned.kd | 0 | 0 | 0 | 170915 | 170915 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7f1581204280 | 0 | 0 | 0 | 16705461014066 | 16704748417215 | 16705608304127 | 16705608417536 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 170915 | 170915 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7f1581223f80 | 0 | 0 | 0 | 16705613583716 | 16705608304127 | 16705613726176 | 16705613730821 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7f1584138380 | 0x7f1581223fc0 | 0 | 0 | 0 | 16705613765250 | 16705613726176 | 16705614091454 | 16705614093829 |
| 5 | 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 | 8 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7f1584138200 | 0x7f1581224000 | 0 | 0 | 0 | 16705614130708 | 16705614091454 | 16705614507772 | 16705614509885 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7f1584138080 | 0x7f1581224040 | 0 | 0 | 0 | 16705614542874 | 16705614507772 | 16705614902490 | 16705614904772 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7f1581b09f00 | 0x7f1581224080 | 0 | 0 | 0 | 16705614938141 | 16705614902490 | 16705615206968 | 16705615209052 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7f1581b09d80 | 0x7f15812240c0 | 0 | 0 | 0 | 16705615242121 | 16705615206968 | 16705615512566 | 16705615514692 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7f1581b09c00 | 0x7f1581224100 | 0 | 0 | 0 | 16705615558571 | 16705615512566 | 16705615811764 | 16705615813843 |
| 10 | 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 | 23 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7f1581b09a80 | 0x7f1581224140 | 0 | 0 | 0 | 16705615845311 | 16705615811764 | 16705616202002 | 16705616204140 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7f1581b09900 | 0x7f1581224180 | 0 | 0 | 0 | 16705616236459 | 16705616202002 | 16705616590320 | 16705616592667 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7f1581b09780 | 0x7f15812241c0 | 0 | 0 | 0 | 16705616623716 | 16705616590320 | 16705616910318 | 16705616912506 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7f1581b09600 | 0x7f1581224200 | 0 | 0 | 0 | 16705616945745 | 16705616910318 | 16705617211277 | 16705617213407 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7f1584138480 | 0x7f1581224240 | 0 | 0 | 0 | 16705617254475 | 16705617211277 | 16705617514315 | 16705617516517 |
| 15 | 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 | 38 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7f1584138300 | 0x7f1581224280 | 0 | 0 | 0 | 16705617549056 | 16705617514315 | 16705617905033 | 16705617907234 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7f1584138180 | 0x7f15812242c0 | 0 | 0 | 0 | 16705617938523 | 16705617905033 | 16705618318151 | 16705618320420 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7f1584138000 | 0x7f1581224300 | 0 | 0 | 0 | 16705618354059 | 16705618318151 | 16705618629189 | 16705618631510 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7f1581b09e80 | 0x7f1581224340 | 0 | 0 | 0 | 16705618664899 | 16705618629189 | 16705618933187 | 16705618935370 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7f1581b09d00 | 0x7f1581224380 | 0 | 0 | 0 | 16705618976219 | 16705618933187 | 16705619215586 | 16705619217171 |
| 20 | 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 | 53 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7f1581b09b80 | 0x7f15812243c0 | 0 | 0 | 0 | 16705619250130 | 16705619215586 | 16705619577504 | 16705619579089 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7f1581b09a00 | 0x7f1581224400 | 0 | 0 | 0 | 16705619611028 | 16705619577504 | 16705619939422 | 16705619941087 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7f1581b09880 | 0x7f1581224440 | 0 | 0 | 0 | 16705619972946 | 16705619939422 | 16705620219740 | 16705620221148 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7f1581b09700 | 0x7f1581224480 | 0 | 0 | 0 | 16705620253457 | 16705620219740 | 16705620498298 | 16705620499869 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7f1584138580 | 0x7f15812244c0 | 0 | 0 | 0 | 16705620539347 | 16705620498298 | 16705620781017 | 16705620782589 |
| 25 | 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 | 68 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7f1584138400 | 0x7f1581224500 | 0 | 0 | 0 | 16705620814888 | 16705620781017 | 16705621147575 | 16705621149197 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7f1584138280 | 0x7f1581224540 | 0 | 0 | 0 | 16705621181846 | 16705621147575 | 16705621514933 | 16705621516545 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7f1584138100 | 0x7f1581224580 | 0 | 0 | 0 | 16705621548714 | 16705621514933 | 16705621791891 | 16705621793446 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7f1581b09f80 | 0x7f15812245c0 | 0 | 0 | 0 | 16705621824935 | 16705621791891 | 16705622069010 | 16705622070507 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7f1581b09e00 | 0x7f1581224600 | 0 | 0 | 0 | 16705622110246 | 16705622069010 | 16705622349648 | 16705622351238 |
| 30 | 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 | 83 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7f1581b09c80 | 0x7f1581224640 | 0 | 0 | 0 | 16705622382937 | 16705622349648 | 16705622716206 | 16705622717856 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7f1581b09b00 | 0x7f1581224680 | 0 | 0 | 0 | 16705622749895 | 16705622716206 | 16705623080364 | 16705623082014 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7f1581b09980 | 0x7f15812246c0 | 0 | 0 | 0 | 16705623113953 | 16705623080364 | 16705623362283 | 16705623363934 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7f1581b09800 | 0x7f1581224700 | 0 | 0 | 0 | 16705623395343 | 16705623362283 | 16705623637321 | 16705623638755 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7f1581b09680 | 0x7f1581224740 | 0 | 0 | 0 | 16705623676674 | 16705623637321 | 16705623915080 | 16705623916616 |
| 35 | 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 | 98 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7f1584138500 | 0x7f1581224780 | 0 | 0 | 0 | 16705623948835 | 16705623915080 | 16705624282598 | 16705624284174 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7f1584138380 | 0x7f15812247c0 | 0 | 0 | 0 | 16705624316053 | 16705624282598 | 16705624644836 | 16705624646502 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7f1584138200 | 0x7f1581224800 | 0 | 0 | 0 | 16705624677771 | 16705624644836 | 16705624922914 | 16705624924563 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7f1584138080 | 0x7f1581224840 | 0 | 0 | 0 | 16705624956492 | 16705624922914 | 16705625199072 | 16705625200644 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7f1581b09f00 | 0x7f1581224880 | 0 | 0 | 0 | 16705625240123 | 16705625199072 | 16705625478271 | 16705625479755 |
| 40 | 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 | 113 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7f1581b09d80 | 0x7f15812248c0 | 0 | 0 | 0 | 16705625511394 | 16705625478271 | 16705625841789 | 16705625843443 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7f1581b09c00 | 0x7f1581224900 | 0 | 0 | 0 | 16705625874812 | 16705625841789 | 16705626216987 | 16705626218581 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7f1581b09a80 | 0x7f1581224940 | 0 | 0 | 0 | 16705626252310 | 16705626216987 | 16705626501465 | 16705626503051 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7f1581b09900 | 0x7f1581224980 | 0 | 0 | 0 | 16705626534850 | 16705626501465 | 16705626780184 | 16705626781762 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7f1581b09780 | 0x7f15812249c0 | 0 | 0 | 0 | 16705626820811 | 16705626780184 | 16705627063222 | 16705627064683 |
| 45 | 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 | 128 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7f1581b09600 | 0x7f1581224a00 | 0 | 0 | 0 | 16705627096992 | 16705627063222 | 16705627426260 | 16705627427841 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7f1584138480 | 0x7f1581224a40 | 0 | 0 | 0 | 16705627460410 | 16705627426260 | 16705627789778 | 16705627791399 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7f1584138300 | 0x7f1581224a80 | 0 | 0 | 0 | 16705627823198 | 16705627789778 | 16705628070737 | 16705628072250 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7f1584138180 | 0x7f1581224ac0 | 0 | 0 | 0 | 16705628104449 | 16705628070737 | 16705628348975 | 16705628350641 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7f1584138000 | 0x7f1581224b00 | 0 | 0 | 0 | 16705628390690 | 16705628348975 | 16705628625933 | 16705628627472 |
| 50 | 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 | 143 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7f1581b09e80 | 0x7f1581224b40 | 0 | 0 | 0 | 16705628658741 | 16705628625933 | 16705628989611 | 16705628991380 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7f1581b09d00 | 0x7f1581224b80 | 0 | 0 | 0 | 16705629023279 | 16705628989611 | 16705629356329 | 16705629357898 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7f1581b09b80 | 0x7f1581224bc0 | 0 | 0 | 0 | 16705629389227 | 16705629356329 | 16705629633768 | 16705629635259 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7f1581b09a00 | 0x7f1581224c00 | 0 | 0 | 0 | 16705629668108 | 16705629633768 | 16705629914086 | 16705629915740 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7f1581b09880 | 0x7f1581224c40 | 0 | 0 | 0 | 16705629953789 | 16705629914086 | 16705630200645 | 16705630202360 |
| 55 | 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 | 158 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7f1581b09700 | 0x7f1581224c80 | 0 | 0 | 0 | 16705630234109 | 16705630200645 | 16705630570403 | 16705630572018 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7f1584138580 | 0x7f1581224cc0 | 0 | 0 | 0 | 16705630604517 | 16705630570403 | 16705630933441 | 16705630935096 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7f1584138400 | 0x7f1581224d00 | 0 | 0 | 0 | 16705630967475 | 16705630933441 | 16705631211199 | 16705631212797 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7f1584138280 | 0x7f1581224d40 | 0 | 0 | 0 | 16705631245236 | 16705631211199 | 16705631491838 | 16705631493288 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7f1584138100 | 0x7f1581224d80 | 0 | 0 | 0 | 16705631533587 | 16705631491838 | 16705631768316 | 16705631769949 |
| 60 | 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 | 173 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7f1581b09f80 | 0x7f1581224dc0 | 0 | 0 | 0 | 16705631801498 | 16705631768316 | 16705632134554 | 16705632136097 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7f1581b09e00 | 0x7f1581224e00 | 0 | 0 | 0 | 16705632168166 | 16705632134554 | 16705632495192 | 16705632496835 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7f1581b09c80 | 0x7f1581224e40 | 0 | 0 | 0 | 16705632527794 | 16705632495192 | 16705632771830 | 16705632773426 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7f1581b09b00 | 0x7f1581224e80 | 0 | 0 | 0 | 16705632805225 | 16705632771830 | 16705633061429 | 16705633062946 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7f1581b09980 | 0x7f1581224ec0 | 0 | 0 | 0 | 16705633101775 | 16705633061429 | 16705633339347 | 16705633341007 |
| 65 | 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 | 188 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7f1581b09800 | 0x7f1581224f00 | 0 | 0 | 0 | 16705633372396 | 16705633339347 | 16705633702705 | 16705633704195 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7f1581b09680 | 0x7f1581224f40 | 0 | 0 | 0 | 16705633735424 | 16705633702705 | 16705634063503 | 16705634064994 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7f1584138500 | 0x7f1581224f80 | 0 | 0 | 0 | 16705634097542 | 16705634063503 | 16705634353582 | 16705634355394 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7f1584138380 | 0x7f1581224fc0 | 0 | 0 | 0 | 16705634386893 | 16705634353582 | 16705634647180 | 16705634648754 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7f1584138200 | 0x7f1581225000 | 0 | 0 | 0 | 16705634687983 | 16705634647180 | 16705634921739 | 16705634923435 |
| 70 | 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 | 203 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7f1584138080 | 0x7f1581225040 | 0 | 0 | 0 | 16705634956294 | 16705634921739 | 16705635288776 | 16705635290333 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7f1581b09f00 | 0x7f1581225080 | 0 | 0 | 0 | 16705635322732 | 16705635288776 | 16705635652294 | 16705635653921 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7f1581b09d80 | 0x7f15812250c0 | 0 | 0 | 0 | 16705635686100 | 16705635652294 | 16705635927653 | 16705635929382 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7f1581b09c00 | 0x7f1581225100 | 0 | 0 | 0 | 16705635961641 | 16705635927653 | 16705636223331 | 16705636224933 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7f1581b09a80 | 0x7f1581225140 | 0 | 0 | 0 | 16705636275471 | 16705636223331 | 16705636510530 | 16705636512303 |
| 75 | 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 | 218 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7f1581b09900 | 0x7f1581225180 | 0 | 0 | 0 | 16705636547462 | 16705636510530 | 16705636880288 | 16705636881941 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7f1581b09780 | 0x7f15812251c0 | 0 | 0 | 0 | 16705636913470 | 16705636880288 | 16705637242526 | 16705637244019 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7f1581b09600 | 0x7f1581225200 | 0 | 0 | 0 | 16705637275078 | 16705637242526 | 16705637518044 | 16705637519600 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7f1584138480 | 0x7f1581225240 | 0 | 0 | 0 | 16705637550909 | 16705637518044 | 16705637819322 | 16705637820900 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7f1584138300 | 0x7f1581225280 | 0 | 0 | 0 | 16705637860129 | 16705637819322 | 16705638111161 | 16705638112911 |
| 80 | 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 | 233 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7f1584138180 | 0x7f15812252c0 | 0 | 0 | 0 | 16705638145569 | 16705638111161 | 16705638482039 | 16705638483688 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7f1584138000 | 0x7f1581225300 | 0 | 0 | 0 | 16705638516367 | 16705638482039 | 16705638843637 | 16705638845166 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7f1581b09e80 | 0x7f1581225340 | 0 | 0 | 0 | 16705638876125 | 16705638843637 | 16705639119315 | 16705639120827 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7f1581b09d00 | 0x7f1581225380 | 0 | 0 | 0 | 16705639152206 | 16705639119315 | 16705639427634 | 16705639429167 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7f1581b09b80 | 0x7f15812253c0 | 0 | 0 | 0 | 16705639468046 | 16705639427634 | 16705639706352 | 16705639707928 |
| 85 | 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 | 248 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7f1581b09a00 | 0x7f1581225400 | 0 | 0 | 0 | 16705639739237 | 16705639706352 | 16705640072430 | 16705640074076 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7f1581b09880 | 0x7f1581225440 | 0 | 0 | 0 | 16705640106385 | 16705640072430 | 16705640442988 | 16705640444684 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7f1581b09700 | 0x7f1581225480 | 0 | 0 | 0 | 16705640475543 | 16705640442988 | 16705640721546 | 16705640723135 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7f1584138580 | 0x7f15812254c0 | 0 | 0 | 0 | 16705640754954 | 16705640721546 | 16705641036425 | 16705641038054 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7f1584138400 | 0x7f1581225500 | 0 | 0 | 0 | 16705641077623 | 16705641036425 | 16705641321543 | 16705641323145 |
| 90 | 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 | 263 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7f1584138280 | 0x7f1581225540 | 0 | 0 | 0 | 16705641355534 | 16705641321543 | 16705641682501 | 16705641684083 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7f1584138100 | 0x7f1581225580 | 0 | 0 | 0 | 16705641715962 | 16705641682501 | 16705642047139 | 16705642048651 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7f1581b09f80 | 0x7f15812255c0 | 0 | 0 | 0 | 16705642088470 | 16705642047139 | 16705642340097 | 16705642341702 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7f1581b09e00 | 0x7f1581225600 | 0 | 0 | 0 | 16705642373881 | 16705642340097 | 16705642662496 | 16705642664061 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7f1581b09c80 | 0x7f1581225640 | 0 | 0 | 0 | 16705642702790 | 16705642662496 | 16705642948094 | 16705642949592 |
| 95 | 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 | 278 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7f1581b09b00 | 0x7f1581225680 | 0 | 0 | 0 | 16705642982481 | 16705642948094 | 16705643310012 | 16705643311670 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7f1581b09980 | 0x7f15812256c0 | 0 | 0 | 0 | 16705643343419 | 16705643310012 | 16705643674490 | 16705643676168 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7f1581b09800 | 0x7f1581225700 | 0 | 0 | 0 | 16705643708237 | 16705643674490 | 16705643955928 | 16705643957589 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7f1581b09680 | 0x7f1581225740 | 0 | 0 | 0 | 16705643989567 | 16705643955928 | 16705644286647 | 16705644288298 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7f1584138500 | 0x7f1581225780 | 0 | 0 | 0 | 16705644327316 | 16705644286647 | 16705644563285 | 16705644564759 |
| 100 | 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 | 293 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7f1584138380 | 0x7f15812257c0 | 0 | 0 | 0 | 16705644598077 | 16705644563285 | 16705644930643 | 16705644932357 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7f1584138200 | 0x7f1581225800 | 0 | 0 | 0 | 16705644966025 | 16705644930643 | 16705645293681 | 16705645295355 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7f1584138080 | 0x7f1581225840 | 0 | 0 | 0 | 16705645326764 | 16705645293681 | 16705645575919 | 16705645577375 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7f1581b09f00 | 0x7f1581225880 | 0 | 0 | 0 | 16705645609904 | 16705645575919 | 16705645913038 | 16705645914684 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7f1581b09d80 | 0x7f15812258c0 | 0 | 0 | 0 | 16705645954183 | 16705645913038 | 16705646202316 | 16705646203785 |
| 105 | 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 | 308 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7f1581b09c00 | 0x7f1581225900 | 0 | 0 | 0 | 16705646235244 | 16705646202316 | 16705646566154 | 16705646567743 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7f1581b09a80 | 0x7f1581225940 | 0 | 0 | 0 | 16705646599482 | 16705646566154 | 16705646926952 | 16705646928371 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7f1581b09900 | 0x7f1581225980 | 0 | 0 | 0 | 16705646960660 | 16705646926952 | 16705647216550 | 16705647218111 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7f1581b09780 | 0x7f15812259c0 | 0 | 0 | 0 | 16705647250470 | 16705647216550 | 16705647573348 | 16705647574770 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7f1581b09600 | 0x7f1581225a00 | 0 | 0 | 0 | 16705647614498 | 16705647573348 | 16705647856387 | 16705647857970 |
| 110 | 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 | 323 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7f1584138480 | 0x7f1581225a40 | 0 | 0 | 0 | 16705647889909 | 16705647856387 | 16705648216545 | 16705648218339 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7f1584138300 | 0x7f1581225a80 | 0 | 0 | 0 | 16705648249878 | 16705648216545 | 16705648576863 | 16705648578207 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7f1584138180 | 0x7f1581225ac0 | 0 | 0 | 0 | 16705648610286 | 16705648576863 | 16705648870941 | 16705648872517 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7f1584138000 | 0x7f1581225b00 | 0 | 0 | 0 | 16705648904166 | 16705648870941 | 16705649236379 | 16705649237945 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7f1581b09e80 | 0x7f1581225b40 | 0 | 0 | 0 | 16705649277154 | 16705649236379 | 16705649522938 | 16705649524456 |
| 115 | 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 | 338 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7f1581b09d00 | 0x7f1581225b80 | 0 | 0 | 0 | 16705649556755 | 16705649522938 | 16705649890136 | 16705649891814 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7f1581b09b80 | 0x7f1581225bc0 | 0 | 0 | 0 | 16705649923533 | 16705649890136 | 16705650255093 | 16705650256942 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7f1581b09a00 | 0x7f1581225c00 | 0 | 0 | 0 | 16705650288611 | 16705650255093 | 16705650567572 | 16705650569171 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7f1581b09880 | 0x7f1581225c40 | 0 | 0 | 0 | 16705650601080 | 16705650567572 | 16705650957810 | 16705651003527 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7f1581b09700 | 0x7f1581225c80 | 0 | 0 | 0 | 16705651023086 | 16705650957810 | 16705651284848 | 16705651286288 |
| 120 | 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 | 353 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7f1584138580 | 0x7f1581225cc0 | 0 | 0 | 0 | 16705651318327 | 16705651284848 | 16705651650446 | 16705651652016 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7f1584138400 | 0x7f1581225d00 | 0 | 0 | 0 | 16705651683975 | 16705651650446 | 16705652017004 | 16705652018544 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7f1584138280 | 0x7f1581225d40 | 0 | 0 | 0 | 16705652050313 | 16705652017004 | 16705652333002 | 16705652334563 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7f1584138100 | 0x7f1581225d80 | 0 | 0 | 0 | 16705652366742 | 16705652333002 | 16705652750280 | 16705652772479 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7f1581b09f80 | 0x7f1581225dc0 | 0 | 0 | 0 | 16705652791468 | 16705652750280 | 16705653069958 | 16705653071509 |
| 125 | 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 | 368 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7f1581b09e00 | 0x7f1581225e00 | 0 | 0 | 0 | 16705653103148 | 16705653069958 | 16705653450276 | 16705653468276 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7f1581b09c80 | 0x7f1581225e40 | 0 | 0 | 0 | 16705653483656 | 16705653450276 | 16705653833794 | 16705653851773 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7f1581b09b00 | 0x7f1581225e80 | 0 | 0 | 0 | 16705653867373 | 16705653833794 | 16705654188672 | 16705654190362 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7f1581b09980 | 0x7f1581225ec0 | 0 | 0 | 0 | 16705654222511 | 16705654188672 | 16705654668669 | 16705654712335 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7f1581b09800 | 0x7f1581225f00 | 0 | 0 | 0 | 16705654732005 | 16705654668669 | 16705655038747 | 16705655040204 |
| 130 | 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 | 383 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7f1581b09680 | 0x7f1581225f40 | 0 | 0 | 0 | 16705655072343 | 16705655038747 | 16705655428825 | 16705655471580 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7f1584138500 | 0x7f1581225f80 | 0 | 0 | 0 | 16705655483290 | 16705655428825 | 16705655848502 | 16705655890756 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7f1584138380 | 0x7f1581225fc0 | 0 | 0 | 0 | 16705655902996 | 16705655848502 | 16705656247220 | 16705656248815 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7f1584138200 | 0x7f1581226000 | 0 | 0 | 0 | 16705656280594 | 16705656247220 | 16705656763697 | 16705656806546 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7f1584138080 | 0x7f1581226040 | 0 | 0 | 0 | 16705656825826 | 16705656763697 | 16705657144975 | 16705657146445 |
| 135 | 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 | 398 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7f1581b09f00 | 0x7f1581226080 | 0 | 0 | 0 | 16705657178134 | 16705657144975 | 16705657557133 | 16705657576841 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7f1581b09d80 | 0x7f15812260c0 | 0 | 0 | 0 | 16705657590051 | 16705657557133 | 16705657982411 | 16705658000557 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7f1581b09c00 | 0x7f1581226100 | 0 | 0 | 0 | 16705658015917 | 16705657982411 | 16705658391048 | 16705658409674 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7f1581b09a80 | 0x7f1581226140 | 0 | 0 | 0 | 16705658424283 | 16705658391048 | 16705658969285 | 16705659012224 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7f1581b09900 | 0x7f1581226180 | 0 | 0 | 0 | 16705659030953 | 16705658969285 | 16705659370243 | 16705659371872 |
| 140 | 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 | 413 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7f1581b09780 | 0x7f15812261c0 | 0 | 0 | 0 | 16705659403231 | 16705659370243 | 16705659804001 | 16705659847066 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7f1581b09600 | 0x7f1581226200 | 0 | 0 | 0 | 16705659860736 | 16705659804001 | 16705660271198 | 16705660313751 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7f1584138480 | 0x7f1581226240 | 0 | 0 | 0 | 16705660324991 | 16705660271198 | 16705660723035 | 16705660765716 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7f1584138300 | 0x7f1581226280 | 0 | 0 | 0 | 16705660776996 | 16705660723035 | 16705661387192 | 16705661429964 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7f1584138180 | 0x7f15812262c0 | 0 | 0 | 0 | 16705661448984 | 16705661387192 | 16705661823509 | 16705661843211 |
| 145 | 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 | 428 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7f1584138000 | 0x7f1581226300 | 0 | 0 | 0 | 16705661856820 | 16705661823509 | 16705662313587 | 16705662357434 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7f1581b09e80 | 0x7f1581226340 | 0 | 0 | 0 | 16705662368954 | 16705662313587 | 16705662834544 | 16705662879177 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7f1581b09d00 | 0x7f1581226380 | 0 | 0 | 0 | 16705662890137 | 16705662834544 | 16705663346061 | 16705663388510 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7f1581b09b80 | 0x7f15812263c0 | 0 | 0 | 0 | 16705663399780 | 16705663346061 | 16705664113417 | 16705664155555 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7f1581b09a00 | 0x7f1581226400 | 0 | 0 | 0 | 16705664174995 | 16705664113417 | 16705664593094 | 16705664634860 |
| 150 | 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 | 443 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7f1581b09880 | 0x7f1581226440 | 0 | 0 | 0 | 16705664645999 | 16705664593094 | 16705665159331 | 16705665201781 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7f1581b09700 | 0x7f1581226480 | 0 | 0 | 0 | 16705665214081 | 16705665159331 | 16705665724288 | 16705665766703 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7f1584138580 | 0x7f15812264c0 | 0 | 0 | 0 | 16705665777872 | 16705665724288 | 16705666295325 | 16705666341184 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7f1584138400 | 0x7f1581226500 | 0 | 0 | 0 | 16705666352533 | 16705666295325 | 16705667173880 | 16705667217895 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7f1584138280 | 0x7f1581226540 | 0 | 0 | 0 | 16705667236994 | 16705667173880 | 16705667835956 | 16705667883413 |
| 155 | 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 | 458 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7f1584138100 | 0x7f1581226580 | 0 | 0 | 0 | 16705667894903 | 16705667835956 | 16705668528112 | 16705668569771 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7f1581b09f80 | 0x7f15812265c0 | 0 | 0 | 0 | 16705668580890 | 16705668528112 | 16705669208108 | 16705669251418 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7f1581b09e00 | 0x7f1581226600 | 0 | 0 | 0 | 16705669262958 | 16705669208108 | 16705669888905 | 16705669909047 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7f1581b09c80 | 0x7f1581226640 | 0 | 0 | 0 | 16705669920926 | 16705669888637 | 16705670980471 | 16705671030870 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7f1581b09b00 | 0x7f1581226680 | 0 | 0 | 0 | 16705671050849 | 16705670980471 | 16705672072943 | 16705672118434 |
| 160 | 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 | 473 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7f1581b09980 | 0x7f15812266c0 | 0 | 0 | 0 | 16705672129754 | 16705672072943 | 16705673187336 | 16705673252977 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7f1581b09800 | 0x7f1581226700 | 0 | 0 | 0 | 16705673264076 | 16705673187336 | 16705674318050 | 16705674388629 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7f1581b09680 | 0x7f1581226740 | 0 | 0 | 0 | 16705674400419 | 16705674318050 | 16705675437883 | 16705675504513 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7f1584138500 | 0x7f1581226780 | 0 | 0 | 0 | 16705675515892 | 16705675437883 | 16705677386351 | 16705677458599 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7f1584138380 | 0x7f15812267c0 | 0 | 0 | 0 | 16705677477468 | 16705677386351 | 16705679308579 | 16705679379225 |
| 165 | 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 | 488 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7f1584138200 | 0x7f1581226800 | 0 | 0 | 0 | 16705679391365 | 16705679308579 | 16705681299927 | 16705681367280 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7f1584138080 | 0x7f1581226840 | 0 | 0 | 0 | 16705681378720 | 16705681299927 | 16705683268555 | 16705683340085 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7f1581b09f00 | 0x7f1581226880 | 0 | 0 | 0 | 16705683351845 | 16705683268555 | 16705685203743 | 16705685270182 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 170915 | 170915 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7f1581b09d80 | 0x7f15812268c0 | 0 | 0 | 0 | 16705685281242 | 16705685203743 | 16705688814922 | 16705688888143 |