79 KiB
79 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | SQ_CYCLES | SQ_BUSY_CYCLES | SQ_BUSY_CU_CYCLES | SQ_WAVES | SQ_WAVE_CYCLES | GRBM_COUNT | GRBM_GUI_ACTIVE | TA_TA_BUSY_sum | TA_SH_FIFO_BUSY_sum | TA_SH_FIFO_CMD_BUSY_sum | TA_SH_FIFO_ADDR_BUSY_sum | TA_BUFFER_COALESCED_READ_CYCLES_sum | TA_BUFFER_COALESCED_WRITE_CYCLES_sum | TA_ADDR_STALLED_BY_TC_CYCLES_sum | TA_TOTAL_WAVEFRONTS_sum | TA_ADDR_STALLED_BY_TD_CYCLES_sum | TA_DATA_STALLED_BY_TC_CYCLES_sum | TA_FLAT_WAVEFRONTS_sum | TA_FLAT_READ_WAVEFRONTS_sum | TA_FLAT_WRITE_WAVEFRONTS_sum | TA_FLAT_ATOMIC_WAVEFRONTS_sum | TA_FLAT_COALESCEABLE_WAVEFRONTS_sum | TA_SH_FIFO_DATA_BUSY_sum | TA_SH_FIFO_DATA_SFIFO_BUSY_sum | TA_SH_FIFO_DATA_TFIFO_BUSY_sum | TA_SQ_TA_CMD_CYCLES_sum | TA_SP_TA_ADDR_CYCLES_sum | TA_SP_TA_DATA_CYCLES_sum | TA_SH_FIFO_ADDR_STARVED_WHILE_BUSY_CYCLES_sum | TA_SH_FIFO_CMD_STARVED_WHILE_BUSY_CYCLES_sum | TA_SH_FIFO_DATA_STARVED_WHILE_BUSY_CYCLES_sum | TA_TA_SH_FIFO_STARVED_sum | TA_BUFFER_WAVEFRONTS_sum | TA_BUFFER_READ_WAVEFRONTS_sum | TA_BUFFER_WRITE_WAVEFRONTS_sum | TA_BUFFER_ATOMIC_WAVEFRONTS_sum | TA_BUFFER_TOTAL_CYCLES_sum | TA_BUFFER_COALESCABLE_WAVEFRONTS_sum | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBufferAligned.kd | 0 | 0 | 0 | 147071 | 147071 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7f2230404280 | 3046232 | 2959616 | 38449381 | 524288 | 238753320 | 380778 | 380778 | 30852999.0 | 30478278.0 | 28313183.0 | 27565185.0 | 0.0 | 0.0 | 19857447.0 | 524288.0 | 0.0 | 20515113.0 | 524288.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 29700912.0 | 28009036.0 | 29452305.0 | 2097152.0 | 2097152.0 | 4194304.0 | 47.0 | 0.0 | 0.0 | 1254675.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16101851410638 | 16113797745640 | 16113797987402 | 16101999674671 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 147071 | 147071 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7f2230423f80 | 266208 | 166403 | 1409253 | 512 | 1733528 | 33275 | 33275 | 38325.0 | 35129.0 | 32231.0 | 30913.0 | 0.0 | 0.0 | 15119.0 | 4096.0 | 0.0 | 0.0 | 4096.0 | 4096.0 | 0.0 | 0.0 | 4096.0 | 0.0 | 0.0 | 0.0 | 16384.0 | 16384.0 | 0.0 | 0.0 | 0.0 | 0.0 | 1304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4096.0 | 16102005090371 | 16113802798629 | 16113802811909 | 16102005278617 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7f22334cd380 | 0x7f2230423fc0 | 1374336 | 1252892 | 16191606 | 65536 | 82797523 | 171791 | 171791 | 12587106.0 | 12351663.0 | 11701257.0 | 11681359.0 | 0.0 | 0.0 | 11376649.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 262.0 | 0.0 | 0.0 | 45422.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102005568720 | 16113802883750 | 16113802976070 | 16102005848414 |
| 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 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7f22334cd200 | 0x7f2230424000 | 2530944 | 2400503 | 31084681 | 65536 | 224185425 | 316367 | 316367 | 29163404.0 | 29148853.0 | 29414799.0 | 29413967.0 | 0.0 | 0.0 | 20345772.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 1328.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102006144767 | 16113803009831 | 16113803190152 | 16102006527969 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7f22334cd080 | 0x7f2230424040 | 2487336 | 2362056 | 30596334 | 65536 | 212668715 | 310916 | 310916 | 28565559.0 | 28543210.0 | 27698054.0 | 27696046.0 | 0.0 | 0.0 | 21187799.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 1.0 | 0.0 | 0.0 | 832.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102006817133 | 16113803215112 | 16113803395913 | 16102007182804 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7f2230e2df00 | 0x7f2230424080 | 1493936 | 1365691 | 17245858 | 65536 | 82612173 | 186741 | 186741 | 10770243.0 | 10510920.0 | 12582603.0 | 12559189.0 | 0.0 | 0.0 | 11625348.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 261.0 | 0.0 | 0.0 | 21565.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102007472348 | 16113803420553 | 16113803515434 | 16102007739252 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7f2230e2dd80 | 0x7f22304240c0 | 1396000 | 1267187 | 16379583 | 65536 | 88762653 | 174499 | 174499 | 12438558.0 | 12210616.0 | 11594871.0 | 11567472.0 | 0.0 | 0.0 | 10627553.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 115.0 | 0.0 | 0.0 | 39117.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102008025976 | 16113803541674 | 16113803633834 | 16102008328829 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7f2230e2dc00 | 0x7f2230424100 | 1303000 | 1202487 | 15578964 | 65536 | 101784289 | 162874 | 162874 | 14111258.0 | 14043776.0 | 14277164.0 | 14273775.0 | 0.0 | 0.0 | 12243175.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 43.0 | 0.0 | 0.0 | 10478.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102008628772 | 16113803674794 | 16113803767115 | 16102008942985 |
| 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 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7f2230e2da80 | 0x7f2230424140 | 2478760 | 2378170 | 30821838 | 65536 | 225586583 | 309844 | 309844 | 29409443.0 | 29391665.0 | 29437132.0 | 29436300.0 | 0.0 | 0.0 | 20868109.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 832.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102009229299 | 16113803796235 | 16113803975596 | 16102009642720 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7f2230e2d900 | 0x7f2230424180 | 2492280 | 2384358 | 30861888 | 65536 | 224260514 | 311534 | 311534 | 29489322.0 | 29471587.0 | 29031926.0 | 29028006.0 | 0.0 | 0.0 | 20790030.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 3932.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102009929983 | 16113804019597 | 16113804198318 | 16102010341114 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7f2230e2d780 | 0x7f22304241c0 | 1308072 | 1207373 | 15627368 | 65536 | 102962976 | 163508 | 163508 | 14241364.0 | 14221214.0 | 13716119.0 | 13679704.0 | 0.0 | 0.0 | 12151326.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 151.0 | 0.0 | 0.0 | 18176.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102010627338 | 16113804226158 | 16113804319598 | 16102010987760 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7f2230e2d600 | 0x7f2230424200 | 1313224 | 1209065 | 15649507 | 65536 | 91802108 | 164152 | 164152 | 13571608.0 | 13422067.0 | 13923828.0 | 13907148.0 | 0.0 | 0.0 | 11692660.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 6.0 | 0.0 | 0.0 | 15114.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102011274344 | 16113804356719 | 16113804450639 | 16102011630846 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7f22334cd480 | 0x7f2230424240 | 1313320 | 1207850 | 15639827 | 65536 | 97316419 | 164164 | 164164 | 13957484.0 | 13872510.0 | 14137234.0 | 14134573.0 | 0.0 | 0.0 | 12163723.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 44.0 | 0.0 | 0.0 | 16417.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102011928439 | 16113804500719 | 16113804594320 | 16102012282341 |
| 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 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7f22334cd300 | 0x7f2230424280 | 2477152 | 2373469 | 30757921 | 65536 | 228856437 | 309643 | 309643 | 29360560.0 | 29351938.0 | 29235205.0 | 29234373.0 | 0.0 | 0.0 | 20860428.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 832.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102012571045 | 16113804622960 | 16113804801841 | 16102013021835 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7f22334cd180 | 0x7f22304242c0 | 2461712 | 2356479 | 30503613 | 65536 | 221652522 | 307713 | 307713 | 29088061.0 | 29071306.0 | 29205433.0 | 29201551.0 | 0.0 | 0.0 | 20862398.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 3880.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102013309509 | 16113804825681 | 16113805005522 | 16102013725759 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7f22334cd000 | 0x7f2230424300 | 1320600 | 1216284 | 15741214 | 65536 | 85512118 | 165074 | 165074 | 13764169.0 | 13566275.0 | 14186496.0 | 14177064.0 | 0.0 | 0.0 | 11541592.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 119.0 | 0.0 | 0.0 | 30254.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102014012673 | 16113805043923 | 16113805137203 | 16102014383415 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7f2230e2de80 | 0x7f2230424340 | 1310424 | 1206606 | 15604801 | 65536 | 90374134 | 163802 | 163802 | 13316085.0 | 13108102.0 | 13827492.0 | 13801188.0 | 0.0 | 0.0 | 11941351.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 46.0 | 0.0 | 0.0 | 23758.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102014670128 | 16113805175123 | 16113805269204 | 16102015032720 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7f2230e2dd00 | 0x7f2230424380 | 1299424 | 1196663 | 15493054 | 65536 | 90857891 | 162427 | 162427 | 13701151.0 | 13576727.0 | 14188968.0 | 14184192.0 | 0.0 | 0.0 | 12138081.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 125.0 | 0.0 | 0.0 | 3216.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102015327614 | 16113805303764 | 16113805395925 | 16102015639107 |
| 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 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7f2230e2db80 | 0x7f22304243c0 | 2481304 | 2377935 | 30777568 | 65536 | 231161266 | 310162 | 310162 | 29403751.0 | 29391390.0 | 29270771.0 | 29269939.0 | 0.0 | 0.0 | 21125417.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 832.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102015926271 | 16113805426325 | 16113805605206 | 16102016377321 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7f2230e2da00 | 0x7f2230424400 | 2483080 | 2372230 | 30734946 | 65536 | 221613579 | 310384 | 310384 | 29442232.0 | 29425245.0 | 29128614.0 | 29124683.0 | 0.0 | 0.0 | 20790862.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 1.0 | 0.0 | 0.0 | 3790.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102016663684 | 16113805631446 | 16113805809687 | 16102017059415 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7f2230e2d880 | 0x7f2230424440 | 1307400 | 1203106 | 15576425 | 65536 | 99881774 | 163424 | 163424 | 13799031.0 | 13697506.0 | 13533938.0 | 13502018.0 | 0.0 | 0.0 | 11812997.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 79.0 | 0.0 | 0.0 | 53482.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102017346249 | 16113805836087 | 16113805930168 | 16102017655212 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7f2230e2d700 | 0x7f2230424480 | 1306152 | 1204140 | 15561943 | 65536 | 88260575 | 163268 | 163268 | 13317909.0 | 13001434.0 | 13878816.0 | 13807474.0 | 0.0 | 0.0 | 10992169.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 83.0 | 0.0 | 0.0 | 125064.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102017942476 | 16113805968408 | 16113806061849 | 16102018320547 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7f22334cd580 | 0x7f22304244c0 | 1320152 | 1214855 | 15728589 | 65536 | 102624102 | 165018 | 165018 | 14172690.0 | 14089000.0 | 14060980.0 | 14052715.0 | 0.0 | 0.0 | 12103383.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 55.0 | 0.0 | 0.0 | 46170.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102018614871 | 16113806102489 | 16113806194809 | 16102018930854 |
| 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 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7f22334cd400 | 0x7f2230424500 | 2456768 | 2354384 | 30500098 | 65536 | 223713331 | 307095 | 307095 | 29135190.0 | 29125818.0 | 29193315.0 | 29192483.0 | 0.0 | 0.0 | 20829431.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 832.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102019218298 | 16113806220570 | 16113806398971 | 16102019667948 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7f22334cd280 | 0x7f2230424540 | 2451200 | 2347234 | 30422147 | 65536 | 210378989 | 306399 | 306399 | 29066406.0 | 29046484.0 | 28901629.0 | 28897735.0 | 0.0 | 0.0 | 20706561.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 3896.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102019955851 | 16113806425531 | 16113806605692 | 16102020397761 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7f22334cd100 | 0x7f2230424580 | 1297736 | 1197308 | 15502545 | 65536 | 99639228 | 162216 | 162216 | 14060209.0 | 13978432.0 | 13528493.0 | 13494415.0 | 0.0 | 0.0 | 11913721.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 87.0 | 0.0 | 0.0 | 40471.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102020686235 | 16113806634492 | 16113806726813 | 16102021037037 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7f2230e2df80 | 0x7f22304245c0 | 1302488 | 1200308 | 15501324 | 65536 | 96931237 | 162810 | 162810 | 13781327.0 | 13478708.0 | 13046452.0 | 12795072.0 | 0.0 | 0.0 | 11129757.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 199.0 | 0.0 | 0.0 | 207875.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102021323761 | 16113806753053 | 16113806845053 | 16102021677783 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7f2230e2de00 | 0x7f2230424600 | 1301192 | 1197149 | 15487375 | 65536 | 91347029 | 162648 | 162648 | 13626754.0 | 13510644.0 | 14197589.0 | 14193927.0 | 0.0 | 0.0 | 11465000.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 169.0 | 0.0 | 0.0 | 2631.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102021970297 | 16113806878173 | 16113806972094 | 16102022325079 |
| 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 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7f2230e2dc80 | 0x7f2230424640 | 2448600 | 2343973 | 30377462 | 65536 | 222068245 | 306074 | 306074 | 29117113.0 | 29108003.0 | 29231885.0 | 29231053.0 | 0.0 | 0.0 | 20716980.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 832.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102022611992 | 16113806999294 | 16113807179775 | 16102023063502 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7f2230e2db00 | 0x7f2230424680 | 2450176 | 2345080 | 30373678 | 65536 | 219962427 | 306271 | 306271 | 29049037.0 | 29036454.0 | 29049867.0 | 29046541.0 | 0.0 | 0.0 | 20904653.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2989.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102023350246 | 16113807202975 | 16113807383296 | 16102023794296 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7f2230e2d980 | 0x7f22304246c0 | 1302240 | 1198197 | 15495737 | 65536 | 89231682 | 162779 | 162779 | 13384103.0 | 13115663.0 | 13453359.0 | 13387066.0 | 0.0 | 0.0 | 11870755.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 51.0 | 0.0 | 0.0 | 76940.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102024082620 | 16113807407457 | 16113807501537 | 16102024435642 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7f2230e2d800 | 0x7f2230424700 | 1306432 | 1201694 | 15518303 | 65536 | 90626921 | 163303 | 163303 | 13216648.0 | 12660280.0 | 12469421.0 | 12098122.0 | 0.0 | 0.0 | 10862112.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 225.0 | 0.0 | 0.0 | 345271.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102024721876 | 16113807525857 | 16113807620098 | 16102025076928 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7f2230e2d680 | 0x7f2230424740 | 1314584 | 1211321 | 15671092 | 65536 | 95567187 | 164322 | 164322 | 14048098.0 | 13877343.0 | 13443104.0 | 13380384.0 | 0.0 | 0.0 | 11404351.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 135.0 | 0.0 | 0.0 | 77086.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102025369351 | 16113807652578 | 16113807745859 | 16102025718613 |
| 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 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7f22334cd500 | 0x7f2230424780 | 2437896 | 2329784 | 30194741 | 65536 | 221801948 | 304736 | 304736 | 28938573.0 | 28926321.0 | 29163588.0 | 29162756.0 | 0.0 | 0.0 | 20693911.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 832.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102026006377 | 16113807770019 | 16113807949700 | 16102026457397 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7f22334cd380 | 0x7f22304247c0 | 2434016 | 2330918 | 30208929 | 65536 | 213717886 | 304251 | 304251 | 28855131.0 | 28840877.0 | 29041745.0 | 29038809.0 | 0.0 | 0.0 | 20639398.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 1.0 | 0.0 | 0.0 | 3061.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102026744451 | 16113807975620 | 16113808156901 | 16102027191911 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7f22334cd200 | 0x7f2230424800 | 1302072 | 1196898 | 15466876 | 65536 | 83773293 | 162758 | 162758 | 13158007.0 | 12774051.0 | 13310860.0 | 13149672.0 | 0.0 | 0.0 | 10844204.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 189.0 | 0.0 | 0.0 | 133891.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102027478814 | 16113808182181 | 16113808276102 | 16102027833637 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7f22334cd080 | 0x7f2230424840 | 1311160 | 1199819 | 15471964 | 65536 | 91158962 | 163894 | 163894 | 13062383.0 | 12269863.0 | 12712370.0 | 12223847.0 | 0.0 | 0.0 | 9947004.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 572.0 | 0.0 | 0.0 | 759926.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102028122130 | 16113808300422 | 16113808394502 | 16102028479622 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7f2230e2df00 | 0x7f2230424880 | 1304088 | 1201575 | 15541792 | 65536 | 94426567 | 163010 | 163010 | 13962888.0 | 13803335.0 | 13663573.0 | 13619051.0 | 0.0 | 0.0 | 11825385.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 71.0 | 0.0 | 0.0 | 46993.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102028772356 | 16113808427143 | 16113808521383 | 16102029123868 |
| 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 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7f2230e2dd80 | 0x7f22304248c0 | 2451832 | 2346465 | 30391487 | 65536 | 228760422 | 306478 | 306478 | 29022998.0 | 29013472.0 | 28981151.0 | 28980319.0 | 0.0 | 0.0 | 20671799.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 832.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102029410632 | 16113808546823 | 16113808726504 | 16102029854042 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7f2230e2dc00 | 0x7f2230424900 | 2431936 | 2324711 | 30113232 | 65536 | 212726625 | 303991 | 303991 | 28851626.0 | 28836725.0 | 28825132.0 | 28821719.0 | 0.0 | 0.0 | 20723909.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 3269.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102030141075 | 16113808751785 | 16113808930986 | 16102030593605 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7f2230e2da80 | 0x7f2230424940 | 1309328 | 1202282 | 15547538 | 65536 | 81518816 | 163665 | 163665 | 12674684.0 | 12041102.0 | 13343687.0 | 13225607.0 | 0.0 | 0.0 | 11431259.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 146.0 | 0.0 | 0.0 | 184550.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102030880229 | 16113808956426 | 16113809050666 | 16102031248471 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7f2230e2d900 | 0x7f2230424980 | 1312480 | 1204767 | 15533225 | 65536 | 93616973 | 164059 | 164059 | 12932286.0 | 11739034.0 | 11530692.0 | 10826906.0 | 0.0 | 0.0 | 10108383.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 517.0 | 0.0 | 0.0 | 650816.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102031535634 | 16113809075466 | 16113809170667 | 16102031896916 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7f2230e2d780 | 0x7f22304249c0 | 1305744 | 1203748 | 15566019 | 65536 | 90182187 | 163217 | 163217 | 13370308.0 | 12965364.0 | 13732391.0 | 13612656.0 | 0.0 | 0.0 | 11179870.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 259.0 | 0.0 | 0.0 | 188165.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102032190120 | 16113809203147 | 16113809296588 | 16102032541442 |
| 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 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7f2230e2d600 | 0x7f2230424a00 | 2428488 | 2323576 | 30109690 | 65536 | 220858567 | 303560 | 303560 | 28786286.0 | 28775303.0 | 28902371.0 | 28901531.0 | 0.0 | 0.0 | 20397028.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 832.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102032827916 | 16113809320588 | 16113809499309 | 16102033269906 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7f22334cd480 | 0x7f2230424a40 | 2424232 | 2308041 | 29890626 | 65536 | 192572604 | 303028 | 303028 | 28545900.0 | 28519350.0 | 28512692.0 | 28508725.0 | 0.0 | 0.0 | 20281169.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 3868.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102033555910 | 16113809525869 | 16113809704910 | 16102033992140 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7f22334cd300 | 0x7f2230424a80 | 1290976 | 1187310 | 15344797 | 65536 | 92700075 | 161371 | 161371 | 13320836.0 | 12926136.0 | 12692360.0 | 12394534.0 | 0.0 | 0.0 | 10507374.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 170.0 | 0.0 | 0.0 | 445907.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102034280314 | 16113809730830 | 16113809823311 | 16102034643786 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7f22334cd180 | 0x7f2230424ac0 | 1310528 | 1200014 | 15458525 | 65536 | 98590237 | 163815 | 163815 | 12109168.0 | 10184462.0 | 9975003.0 | 9093257.0 | 0.0 | 0.0 | 8250205.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 518.0 | 0.0 | 0.0 | 920768.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102034931429 | 16113809848111 | 16113809941552 | 16102035244462 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7f22334cd000 | 0x7f2230424b00 | 1291816 | 1189753 | 15383747 | 65536 | 89323282 | 161476 | 161476 | 13315548.0 | 12813233.0 | 13125837.0 | 12906320.0 | 0.0 | 0.0 | 10772013.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 264.0 | 0.0 | 0.0 | 211306.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102035537166 | 16113809974192 | 16113810065712 | 16102035883918 |
| 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 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7f2230e2de80 | 0x7f2230424b40 | 2428280 | 2321398 | 30075058 | 65536 | 223093577 | 303534 | 303534 | 28722543.0 | 28713444.0 | 28658318.0 | 28657478.0 | 0.0 | 0.0 | 20115364.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 832.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102036170272 | 16113810106673 | 16113810285394 | 16102036620582 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7f2230e2dd00 | 0x7f2230424b80 | 2435784 | 2330679 | 30193050 | 65536 | 216257415 | 304472 | 304472 | 28826321.0 | 28812153.0 | 28491165.0 | 28487740.0 | 0.0 | 0.0 | 20178350.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 3.0 | 0.0 | 0.0 | 3601.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102036907065 | 16113810310994 | 16113810490195 | 16102037359195 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7f2230e2db80 | 0x7f2230424bc0 | 1316680 | 1209035 | 15603577 | 65536 | 87432104 | 164584 | 164584 | 12888572.0 | 12150037.0 | 12683150.0 | 12368893.0 | 0.0 | 0.0 | 10529727.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 270.0 | 0.0 | 0.0 | 321481.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102037644389 | 16113810515315 | 16113810610356 | 16102038002231 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7f2230e2da00 | 0x7f2230424c00 | 1297472 | 1193029 | 15382008 | 65536 | 97556303 | 162183 | 162183 | 10156674.0 | 7754958.0 | 8059191.0 | 6870254.0 | 0.0 | 0.0 | 5474754.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 423.0 | 0.0 | 0.0 | 1230897.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102038289275 | 16113810635956 | 16113810731796 | 16102038651337 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7f2230e2d880 | 0x7f2230424c40 | 1300688 | 1197612 | 15474832 | 65536 | 94213845 | 162585 | 162585 | 13469345.0 | 13034301.0 | 13066355.0 | 12837861.0 | 0.0 | 0.0 | 10512014.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 108.0 | 0.0 | 0.0 | 240703.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102038943510 | 16113810766196 | 16113810859477 | 16102039298352 |
| 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 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7f2230e2d700 | 0x7f2230424c80 | 2432952 | 2325239 | 30118003 | 65536 | 221044060 | 304118 | 304118 | 28767843.0 | 28755290.0 | 28627405.0 | 28626521.0 | 0.0 | 0.0 | 20373797.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 905.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102039585046 | 16113810884917 | 16113811063958 | 16102040042566 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7f22334cd580 | 0x7f2230424cc0 | 2406936 | 2298653 | 29778824 | 65536 | 214162588 | 300866 | 300866 | 28452090.0 | 28438302.0 | 28733580.0 | 28730479.0 | 0.0 | 0.0 | 20197894.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 2.0 | 0.0 | 0.0 | 3528.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102040330770 | 16113811088758 | 16113811271639 | 16102040783960 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7f22334cd400 | 0x7f2230424d00 | 1320032 | 1204423 | 15527662 | 65536 | 93983733 | 165003 | 165003 | 13306057.0 | 12731038.0 | 11611579.0 | 11083975.0 | 0.0 | 0.0 | 10172109.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 264.0 | 0.0 | 0.0 | 560735.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102041071403 | 16113811296280 | 16113811390680 | 16102041384217 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7f22334cd280 | 0x7f2230424d40 | 1348424 | 1241072 | 15985426 | 65536 | 105085126 | 168552 | 168552 | 9136396.0 | 6748228.0 | 6121005.0 | 4992175.0 | 0.0 | 0.0 | 3694708.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 364.0 | 0.0 | 0.0 | 1162426.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102041670300 | 16113811417080 | 16113811516441 | 16102042029372 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7f22334cd100 | 0x7f2230424d80 | 1304296 | 1199886 | 15496596 | 65536 | 85617214 | 163036 | 163036 | 12915784.0 | 12154181.0 | 12539088.0 | 12264415.0 | 0.0 | 0.0 | 11120099.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 234.0 | 0.0 | 0.0 | 240745.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102042324436 | 16113811549081 | 16113811642842 | 16102042679038 |
| 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 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7f2230e2df80 | 0x7f2230424dc0 | 2405656 | 2298231 | 29744729 | 65536 | 217522497 | 300706 | 300706 | 28478401.0 | 28464868.0 | 28638789.0 | 28637951.0 | 0.0 | 0.0 | 20198456.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 1.0 | 0.0 | 0.0 | 866.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102042966722 | 16113811670522 | 16113811851003 | 16102043407712 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7f2230e2de00 | 0x7f2230424e00 | 2400536 | 2290420 | 29678817 | 65536 | 212799545 | 300066 | 300066 | 28408100.0 | 28394464.0 | 28599169.0 | 28595671.0 | 0.0 | 0.0 | 20012243.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 2.0 | 0.0 | 0.0 | 3469.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102043693506 | 16113811875163 | 16113812055644 | 16102044139556 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7f2230e2dc80 | 0x7f2230424e40 | 1305544 | 1201604 | 15488422 | 65536 | 88419844 | 163192 | 163192 | 13162237.0 | 12340153.0 | 12249194.0 | 11806824.0 | 0.0 | 0.0 | 10237041.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 355.0 | 0.0 | 0.0 | 432492.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102044425919 | 16113812080284 | 16113812175325 | 16102044781791 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7f2230e2db00 | 0x7f2230424e80 | 1410320 | 1304500 | 16794297 | 65536 | 105407242 | 176289 | 176289 | 8300722.0 | 5727060.0 | 6126929.0 | 4964139.0 | 0.0 | 0.0 | 3321969.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 340.0 | 0.0 | 0.0 | 1208828.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102045069965 | 16113812199485 | 16113812303166 | 16102045439247 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7f2230e2d980 | 0x7f2230424ec0 | 1301160 | 1190034 | 15366958 | 65536 | 90575127 | 162644 | 162644 | 13313540.0 | 12638901.0 | 12601066.0 | 12301556.0 | 0.0 | 0.0 | 11011102.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 240.0 | 0.0 | 0.0 | 294104.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102045731620 | 16113812336606 | 16113812429246 | 16102046081013 |
| 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 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7f2230e2d800 | 0x7f2230424f00 | 2394504 | 2291824 | 29700663 | 65536 | 213309165 | 299312 | 299312 | 28327521.0 | 28320118.0 | 28220842.0 | 28219782.0 | 0.0 | 0.0 | 20245395.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 1.0 | 0.0 | 0.0 | 2083.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102046367936 | 16113812454846 | 16113812635488 | 16102046763837 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7f2230e2d680 | 0x7f2230424f40 | 2408528 | 2307871 | 29895965 | 65536 | 220946089 | 301065 | 301065 | 28532609.0 | 28526388.0 | 28566376.0 | 28565544.0 | 0.0 | 0.0 | 20310722.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 832.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102047051121 | 16113812662048 | 16113812843809 | 16102047496101 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7f22334cd500 | 0x7f2230424f80 | 1292216 | 1189756 | 15343239 | 65536 | 94574035 | 161526 | 161526 | 13401689.0 | 12658871.0 | 11023613.0 | 9984148.0 | 0.0 | 0.0 | 9517033.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 624.0 | 0.0 | 0.0 | 919273.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102047782165 | 16113812867329 | 16113812960769 | 16102048147027 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7f22334cd380 | 0x7f2230424fc0 | 1458280 | 1353496 | 17458877 | 65536 | 113806500 | 182284 | 182284 | 7923548.0 | 5378224.0 | 4869101.0 | 3523605.0 | 0.0 | 0.0 | 1918981.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 340.0 | 0.0 | 0.0 | 1316824.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102048434420 | 16113812985090 | 16113813092450 | 16102048820212 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7f22334cd200 | 0x7f2230425000 | 1305320 | 1193555 | 15413632 | 65536 | 95321091 | 163164 | 163164 | 13237985.0 | 12776221.0 | 12404197.0 | 12097592.0 | 0.0 | 0.0 | 10646927.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 215.0 | 0.0 | 0.0 | 322275.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102049124775 | 16113813127010 | 16113813220611 | 16102049485267 |
| 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 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7f22334cd080 | 0x7f2230425040 | 2428184 | 2323319 | 30061143 | 65536 | 219733342 | 303522 | 303522 | 28649713.0 | 28642255.0 | 28490111.0 | 28489091.0 | 0.0 | 0.0 | 20257040.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 1004.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102049771591 | 16113813246371 | 16113813425412 | 16102050222251 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7f2230e2df00 | 0x7f2230425080 | 2405296 | 2298604 | 29759204 | 65536 | 221022592 | 300661 | 300661 | 28424124.0 | 28414319.0 | 28273687.0 | 28272855.0 | 0.0 | 0.0 | 20257250.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 850.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102050511114 | 16113813450052 | 16113813629573 | 16102050961344 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7f2230e2dd80 | 0x7f22304250c0 | 1300408 | 1192114 | 15377962 | 65536 | 92685300 | 162550 | 162550 | 12967006.0 | 11647389.0 | 11626367.0 | 10955949.0 | 0.0 | 0.0 | 9343383.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 518.0 | 0.0 | 0.0 | 821274.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102051248718 | 16113813656294 | 16113813751334 | 16102051608200 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7f2230e2dc00 | 0x7f2230425100 | 1541752 | 1426864 | 18403235 | 65536 | 121770905 | 192718 | 192718 | 6793252.0 | 4595432.0 | 4346928.0 | 3218768.0 | 0.0 | 0.0 | 1434382.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 311.0 | 0.0 | 0.0 | 1135909.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102051894434 | 16113813776934 | 16113813893095 | 16102052276695 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7f2230e2da80 | 0x7f2230425140 | 1288488 | 1188569 | 15355040 | 65536 | 91493384 | 161060 | 161060 | 13146222.0 | 12484028.0 | 13110743.0 | 12891495.0 | 0.0 | 0.0 | 10461095.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 230.0 | 0.0 | 0.0 | 386213.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102052569119 | 16113813938375 | 16113814032296 | 16102052925441 |
| 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 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7f2230e2d900 | 0x7f2230425180 | 2413368 | 2307798 | 29876932 | 65536 | 221491547 | 301670 | 301670 | 28459882.0 | 28453356.0 | 28538594.0 | 28537690.0 | 0.0 | 0.0 | 20068461.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 890.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102053212374 | 16113814058376 | 16113814239497 | 16102053662284 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7f2230e2d780 | 0x7f22304251c0 | 2382672 | 2276773 | 29506679 | 65536 | 203166900 | 297833 | 297833 | 28163304.0 | 28142032.0 | 28279755.0 | 28278855.0 | 0.0 | 0.0 | 20027236.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 1306.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102053948158 | 16113814265577 | 16113814444298 | 16102054404958 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7f2230e2d600 | 0x7f2230425200 | 1310120 | 1195712 | 15434883 | 65536 | 94232435 | 163764 | 163764 | 12719722.0 | 11058763.0 | 10634585.0 | 9708850.0 | 0.0 | 0.0 | 9468868.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 521.0 | 0.0 | 0.0 | 846865.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102054691872 | 16113814469578 | 16113814565259 | 16102055059713 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7f22334cd480 | 0x7f2230425240 | 1612832 | 1503583 | 19375773 | 65536 | 125876334 | 201603 | 201603 | 6615170.0 | 4356279.0 | 3991277.0 | 2835825.0 | 0.0 | 0.0 | 1183648.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 332.0 | 0.0 | 0.0 | 1138858.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102055347587 | 16113814590859 | 16113814712460 | 16102055738438 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7f22334cd300 | 0x7f2230425280 | 1294792 | 1190079 | 15360601 | 65536 | 89583955 | 161848 | 161848 | 12790871.0 | 11996176.0 | 11741759.0 | 11265182.0 | 0.0 | 0.0 | 10262906.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 278.0 | 0.0 | 0.0 | 341474.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102056031722 | 16113814744780 | 16113814839501 | 16102056401324 |
| 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 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7f22334cd180 | 0x7f22304252c0 | 2428120 | 2321235 | 30059266 | 65536 | 220725780 | 303514 | 303514 | 28652667.0 | 28639042.0 | 28648273.0 | 28647425.0 | 0.0 | 0.0 | 20250878.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 840.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102056688957 | 16113814864141 | 16113815043822 | 16102057139067 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7f22334cd000 | 0x7f2230425300 | 2391336 | 2285858 | 29631441 | 65536 | 193261474 | 298916 | 298916 | 28252530.0 | 28214616.0 | 28434111.0 | 28431974.0 | 0.0 | 0.0 | 19878503.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2360.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102057427571 | 16113815067502 | 16113815247183 | 16102057882991 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7f2230e2de80 | 0x7f2230425340 | 1291088 | 1187488 | 15292378 | 65536 | 96597388 | 161385 | 161385 | 12247918.0 | 10536547.0 | 10908261.0 | 10109080.0 | 0.0 | 0.0 | 7880832.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 520.0 | 0.0 | 0.0 | 877221.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102058171264 | 16113815272143 | 16113815367504 | 16102058545296 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7f2230e2dd00 | 0x7f2230425380 | 1689680 | 1578608 | 20338834 | 65536 | 126222812 | 211209 | 211209 | 6180948.0 | 4128187.0 | 4063104.0 | 2908465.0 | 0.0 | 0.0 | 924982.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 290.0 | 0.0 | 0.0 | 1174075.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102058831230 | 16113815392144 | 16113815518225 | 16102059179652 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7f2230e2db80 | 0x7f22304253c0 | 1291784 | 1189995 | 15344493 | 65536 | 91402084 | 161472 | 161472 | 12913954.0 | 12087353.0 | 11997657.0 | 11542248.0 | 0.0 | 0.0 | 10055212.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 272.0 | 0.0 | 0.0 | 615845.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102059472686 | 16113815551025 | 16113815645425 | 16102059828548 |
| 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 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7f2230e2da00 | 0x7f2230425400 | 2406024 | 2300988 | 29798018 | 65536 | 220221221 | 300752 | 300752 | 28506431.0 | 28494850.0 | 28546164.0 | 28545308.0 | 0.0 | 0.0 | 19753277.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 1008.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102060117141 | 16113815677906 | 16113815856147 | 16102060572241 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7f2230e2d880 | 0x7f2230425440 | 2386472 | 2280940 | 29560557 | 65536 | 210367746 | 298308 | 298308 | 28235737.0 | 28225062.0 | 28381366.0 | 28378677.0 | 0.0 | 0.0 | 19937236.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 1.0 | 0.0 | 0.0 | 2387.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102060858575 | 16113815880627 | 16113816059348 | 16102061305775 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7f2230e2d700 | 0x7f2230425480 | 1293120 | 1188527 | 15330121 | 65536 | 98767649 | 161639 | 161639 | 11725464.0 | 9530281.0 | 9400342.0 | 8404271.0 | 0.0 | 0.0 | 6946172.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 459.0 | 0.0 | 0.0 | 1033264.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102061590729 | 16113816083668 | 16113816177269 | 16102061947391 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7f22334cd580 | 0x7f22304254c0 | 1745168 | 1639644 | 21178211 | 65536 | 144325219 | 218145 | 218145 | 6065740.0 | 4008494.0 | 3830865.0 | 2659994.0 | 0.0 | 0.0 | 872239.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 269.0 | 0.0 | 0.0 | 1182404.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102062235164 | 16113816201749 | 16113816332469 | 16102062636885 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7f22334cd400 | 0x7f2230425500 | 1278496 | 1177958 | 15207754 | 65536 | 88806887 | 159811 | 159811 | 12691775.0 | 11677880.0 | 11560714.0 | 10964269.0 | 0.0 | 0.0 | 9579352.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 448.0 | 0.0 | 0.0 | 524744.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102062930239 | 16113816367030 | 16113816460150 | 16102063294221 |
| 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 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7f22334cd280 | 0x7f2230425540 | 2398784 | 2290909 | 29664573 | 65536 | 212176478 | 299847 | 299847 | 28287235.0 | 28278429.0 | 28027278.0 | 28026398.0 | 0.0 | 0.0 | 19715544.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 858.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102063582395 | 16113816486390 | 16113816664471 | 16102064033454 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7f22334cd100 | 0x7f2230425580 | 2383912 | 2274683 | 29458350 | 65536 | 207086923 | 297988 | 297988 | 28111893.0 | 28101449.0 | 28117907.0 | 28116061.0 | 0.0 | 0.0 | 19724487.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 2.0 | 0.0 | 0.0 | 1810.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102064319968 | 16113816688792 | 16113816867833 | 16102064770858 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7f2230e2df80 | 0x7f22304255c0 | 1296016 | 1190377 | 15361510 | 65536 | 99968517 | 162001 | 162001 | 10876217.0 | 8315464.0 | 8403217.0 | 7224365.0 | 0.0 | 0.0 | 6824997.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 473.0 | 0.0 | 0.0 | 1174587.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102065057592 | 16113816892473 | 16113816988473 | 16102065425704 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7f2230e2de00 | 0x7f2230425600 | 1839440 | 1728275 | 22305954 | 65536 | 147658874 | 229929 | 229929 | 5971794.0 | 3943024.0 | 3711406.0 | 2577410.0 | 0.0 | 0.0 | 747559.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 297.0 | 0.0 | 0.0 | 1121630.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102065710797 | 16113817014233 | 16113817152954 | 16102066110728 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7f2230e2dc80 | 0x7f2230425640 | 1282592 | 1178164 | 15203307 | 65536 | 97190720 | 160323 | 160323 | 12972862.0 | 12058139.0 | 11440698.0 | 10799836.0 | 0.0 | 0.0 | 10324428.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 361.0 | 0.0 | 0.0 | 544601.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102066403342 | 16113817186715 | 16113817281595 | 16102066771554 |
| 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 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7f2230e2db00 | 0x7f2230425680 | 2392152 | 2289114 | 29637012 | 65536 | 213912778 | 299018 | 299018 | 28197115.0 | 28184470.0 | 27993876.0 | 27992396.0 | 0.0 | 0.0 | 19708308.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 872.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102067057737 | 16113817307835 | 16113817487676 | 16102067509777 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7f2230e2d980 | 0x7f22304256c0 | 2386536 | 2271193 | 29418399 | 65536 | 203469819 | 298316 | 298316 | 28074131.0 | 28064544.0 | 28239912.0 | 28237016.0 | 0.0 | 0.0 | 19802633.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2996.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102067796581 | 16113817512636 | 16113817694238 | 16102068254611 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7f2230e2d800 | 0x7f2230425700 | 1308096 | 1206510 | 15564360 | 65536 | 101247825 | 163511 | 163511 | 10263186.0 | 7625382.0 | 7476761.0 | 6178146.0 | 0.0 | 0.0 | 5292233.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 445.0 | 0.0 | 0.0 | 1343326.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102068540725 | 16113817720318 | 16113817817278 | 16102068910626 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7f2230e2d680 | 0x7f2230425740 | 1925592 | 1808928 | 23350951 | 65536 | 149680109 | 240698 | 240698 | 5687331.0 | 3799157.0 | 3611213.0 | 2491371.0 | 0.0 | 0.0 | 626550.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 315.0 | 0.0 | 0.0 | 1119615.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102069197060 | 16113817842718 | 16113817987199 | 16102069559382 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7f22334cd500 | 0x7f2230425780 | 1291272 | 1186717 | 15305116 | 65536 | 97661159 | 161408 | 161408 | 12527177.0 | 11163526.0 | 10638972.0 | 9897208.0 | 0.0 | 0.0 | 8914944.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 463.0 | 0.0 | 0.0 | 734918.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102069851665 | 16113818021119 | 16113818117280 | 16102070209878 |
| 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 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7f22334cd380 | 0x7f22304257c0 | 2386488 | 2276096 | 29454492 | 65536 | 196565619 | 298310 | 298310 | 28048260.0 | 28020710.0 | 27971720.0 | 27965827.0 | 0.0 | 0.0 | 19650059.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 3.0 | 0.0 | 0.0 | 7784.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102070496801 | 16113818142880 | 16113818323681 | 16102070955021 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7f22334cd200 | 0x7f2230425800 | 2387192 | 2277174 | 29487193 | 65536 | 198382884 | 298398 | 298398 | 28042936.0 | 28003442.0 | 27882668.0 | 27871447.0 | 0.0 | 0.0 | 19779754.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 1.0 | 0.0 | 0.0 | 8189.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102071241405 | 16113818347361 | 16113818528002 | 16102071695115 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7f22334cd080 | 0x7f2230425840 | 1361680 | 1249733 | 16131817 | 65536 | 98797244 | 170209 | 170209 | 8792796.0 | 6181968.0 | 6028241.0 | 4803692.0 | 0.0 | 0.0 | 4106274.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 265.0 | 0.0 | 0.0 | 1215213.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102071983068 | 16113818552003 | 16113818651043 | 16102072358860 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7f2230e2df00 | 0x7f2230425880 | 2076488 | 1968917 | 25426350 | 65536 | 171932497 | 259560 | 259560 | 4633990.0 | 3350395.0 | 3207709.0 | 2507544.0 | 0.0 | 0.0 | 545883.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 460.0 | 0.0 | 0.0 | 709492.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102072644814 | 16113818674243 | 16113818830244 | 16102073072204 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7f2230e2dd80 | 0x7f22304258c0 | 1294656 | 1188210 | 15322880 | 65536 | 98088607 | 161831 | 161831 | 11463668.0 | 9479600.0 | 9480286.0 | 8479165.0 | 0.0 | 0.0 | 7276965.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 501.0 | 0.0 | 0.0 | 1049207.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102073364568 | 16113818862884 | 16113818958725 | 16102073725140 |
| 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 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7f2230e2dc00 | 0x7f2230425900 | 2364408 | 2260374 | 29241741 | 65536 | 202748371 | 295550 | 295550 | 27901763.0 | 27880928.0 | 27906160.0 | 27896824.0 | 0.0 | 0.0 | 19614019.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 7.0 | 0.0 | 0.0 | 7339.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102074010273 | 16113818986085 | 16113819164646 | 16102074458783 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7f2230e2da80 | 0x7f2230425940 | 2371992 | 2268089 | 29367698 | 65536 | 207600987 | 296498 | 296498 | 27964624.0 | 27955446.0 | 27932845.0 | 27930088.0 | 0.0 | 0.0 | 19352996.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 3.0 | 0.0 | 0.0 | 1945.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102074743817 | 16113819189606 | 16113819369607 | 16102075146608 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7f2230e2d900 | 0x7f2230425980 | 1437176 | 1325739 | 17091817 | 65536 | 105734781 | 179646 | 179646 | 8330682.0 | 5539102.0 | 5129227.0 | 3764403.0 | 0.0 | 0.0 | 2401066.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 199.0 | 0.0 | 0.0 | 1366739.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102075431862 | 16113819393128 | 16113819500808 | 16102075761824 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7f2230e2d780 | 0x7f22304259c0 | 2234376 | 2128228 | 27507685 | 65536 | 194115984 | 279296 | 279296 | 4586730.0 | 3290144.0 | 3160946.0 | 2461192.0 | 0.0 | 0.0 | 553454.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 453.0 | 0.0 | 0.0 | 712565.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102076047998 | 16113819526248 | 16113819697449 | 16102076491208 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7f2230e2d600 | 0x7f2230425a00 | 1293552 | 1192651 | 15364307 | 65536 | 98869369 | 161693 | 161693 | 10076638.0 | 7748886.0 | 7501346.0 | 6141696.0 | 0.0 | 0.0 | 4932433.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 372.0 | 0.0 | 0.0 | 1295878.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102076783712 | 16113819731370 | 16113819826890 | 16102077148374 |
| 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 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7f22334cd480 | 0x7f2230425a40 | 2367464 | 2257276 | 29177573 | 65536 | 199014001 | 295932 | 295932 | 27712847.0 | 27699455.0 | 27685899.0 | 27681128.0 | 0.0 | 0.0 | 19271657.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 5273.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102077436447 | 16113819851530 | 16113820035851 | 16102077882657 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7f22334cd300 | 0x7f2230425a80 | 2369672 | 2266993 | 29339867 | 65536 | 208841088 | 296208 | 296208 | 27942585.0 | 27931766.0 | 27681531.0 | 27677681.0 | 0.0 | 0.0 | 19459432.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 2.0 | 0.0 | 0.0 | 4840.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102078170891 | 16113820059532 | 16113820240813 | 16102078626331 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7f22334cd180 | 0x7f2230425ac0 | 1496016 | 1385138 | 17861131 | 65536 | 113099669 | 187001 | 187001 | 8203768.0 | 5136265.0 | 4762091.0 | 3230323.0 | 0.0 | 0.0 | 1364557.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 185.0 | 0.0 | 0.0 | 1534900.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102078912675 | 16113820265613 | 16113820376973 | 16102079292436 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7f22334cd000 | 0x7f2230425b00 | 2405608 | 2290930 | 29561128 | 65536 | 202446875 | 300700 | 300700 | 4591951.0 | 3321033.0 | 3142841.0 | 2441455.0 | 0.0 | 0.0 | 519982.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 407.0 | 0.0 | 0.0 | 697078.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102079578960 | 16113820400814 | 16113820582095 | 16102080030330 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7f2230e2de80 | 0x7f2230425b40 | 1363000 | 1262559 | 16284629 | 65536 | 107158528 | 170374 | 170374 | 8586798.0 | 5921336.0 | 5677933.0 | 4493142.0 | 0.0 | 0.0 | 2906003.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 307.0 | 0.0 | 0.0 | 1225453.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102080322203 | 16113820614255 | 16113820715375 | 16102080682975 |
| 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 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7f2230e2dd00 | 0x7f2230425b80 | 2385784 | 2252923 | 29130405 | 65536 | 157456246 | 298222 | 298222 | 25198749.0 | 24514077.0 | 27328395.0 | 27281627.0 | 0.0 | 0.0 | 17864709.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 50.0 | 0.0 | 0.0 | 170102.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102080969639 | 16113820739696 | 16113820926417 | 16102081420199 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7f2230e2db80 | 0x7f2230425bc0 | 2364944 | 2255846 | 29137360 | 65536 | 191920300 | 295617 | 295617 | 27480176.0 | 27430824.0 | 27530202.0 | 27507955.0 | 0.0 | 0.0 | 19114211.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 26.0 | 0.0 | 0.0 | 119490.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102081704923 | 16113820950097 | 16113821134738 | 16102082159893 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7f2230e2da00 | 0x7f2230425c00 | 1648808 | 1539133 | 19844856 | 65536 | 132703643 | 206100 | 206100 | 7183956.0 | 4557904.0 | 4283109.0 | 2936201.0 | 0.0 | 0.0 | 930769.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 192.0 | 0.0 | 0.0 | 1370451.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102082446216 | 16113821158098 | 16113821280819 | 16102082848707 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7f2230e2d880 | 0x7f2230425c40 | 2719656 | 2609295 | 33717829 | 65536 | 241591505 | 339956 | 339956 | 4526816.0 | 3213368.0 | 3069097.0 | 2403766.0 | 0.0 | 0.0 | 479124.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 371.0 | 0.0 | 0.0 | 666493.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102083134091 | 16113821305939 | 16113821512820 | 16102083626820 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7f2230e2d700 | 0x7f2230425c80 | 1493992 | 1374923 | 17740176 | 65536 | 99572522 | 186748 | 186748 | 7561106.0 | 4741700.0 | 4445642.0 | 3038937.0 | 0.0 | 0.0 | 1421672.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 203.0 | 0.0 | 0.0 | 1412963.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102083898344 | 16113821561780 | 16113821672501 | 16102084274366 |
| 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 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7f22334cd580 | 0x7f2230425cc0 | 2359368 | 2245050 | 28953299 | 65536 | 182368501 | 294920 | 294920 | 26873803.0 | 26701673.0 | 25209117.0 | 24981103.0 | 0.0 | 0.0 | 18651136.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 204.0 | 0.0 | 0.0 | 295966.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102084559439 | 16113821699861 | 16113821883062 | 16102084959111 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7f22334cd400 | 0x7f2230425d00 | 2379464 | 2268338 | 29253852 | 65536 | 194782297 | 297432 | 297432 | 27177837.0 | 27008126.0 | 25500069.0 | 25275478.0 | 0.0 | 0.0 | 18503298.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 225.0 | 0.0 | 0.0 | 336661.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102085244924 | 16113821907702 | 16113822094904 | 16102085693764 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7f22334cd280 | 0x7f2230425d40 | 1802464 | 1691949 | 21851145 | 65536 | 143136255 | 225307 | 225307 | 6633530.0 | 4049794.0 | 3810407.0 | 2398988.0 | 0.0 | 0.0 | 534055.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 134.0 | 0.0 | 0.0 | 1388618.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102085979538 | 16113822120824 | 16113822255385 | 16102086398449 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7f22334cd100 | 0x7f2230425d80 | 3039880 | 2931280 | 37897803 | 65536 | 278495878 | 379984 | 379984 | 4519076.0 | 3213895.0 | 3101890.0 | 2440413.0 | 0.0 | 0.0 | 506058.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 398.0 | 0.0 | 0.0 | 651121.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102086685712 | 16113822279225 | 16113822511226 | 16102087211941 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7f2230e2df80 | 0x7f2230425dc0 | 1680960 | 1575311 | 20351023 | 65536 | 142350520 | 210119 | 210119 | 6722898.0 | 4352134.0 | 4027532.0 | 2487445.0 | 0.0 | 0.0 | 676518.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 199.0 | 0.0 | 0.0 | 1515055.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102087485444 | 16113822581786 | 16113822708667 | 16102087878096 |
| 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 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7f2230e2de00 | 0x7f2230425e00 | 2446648 | 2326711 | 29932355 | 65536 | 189347691 | 305830 | 305830 | 21615094.0 | 20738774.0 | 20749357.0 | 20134356.0 | 0.0 | 0.0 | 11850580.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 129.0 | 0.0 | 0.0 | 734015.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102088163939 | 16113822734747 | 16113822928829 | 16102088631409 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7f2230e2dc80 | 0x7f2230425e40 | 2484864 | 2344809 | 30211667 | 65536 | 174292089 | 310607 | 310607 | 21459414.0 | 19777707.0 | 18980564.0 | 18190568.0 | 0.0 | 0.0 | 9964078.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 306.0 | 0.0 | 0.0 | 792043.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102088917203 | 16113822954269 | 16113823146750 | 16102089405072 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7f2230e2db00 | 0x7f2230425e80 | 2127312 | 2020207 | 26094778 | 65536 | 182492452 | 265913 | 265913 | 5016248.0 | 3333316.0 | 3127539.0 | 2305490.0 | 0.0 | 0.0 | 518363.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 124.0 | 0.0 | 0.0 | 845906.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102089671406 | 16113823171070 | 16113823331071 | 16102090094407 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7f2230e2d980 | 0x7f2230425ec0 | 3695440 | 3576951 | 46294606 | 65536 | 337934350 | 461929 | 461929 | 4716893.0 | 3227385.0 | 3102863.0 | 2466693.0 | 0.0 | 0.0 | 560976.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 239.0 | 0.0 | 0.0 | 636994.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102090382600 | 16113823355071 | 16113823638753 | 16102090960887 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7f2230e2d800 | 0x7f2230425f00 | 1959888 | 1843114 | 23725978 | 65536 | 144761327 | 244985 | 244985 | 7214250.0 | 4486937.0 | 4159938.0 | 2371224.0 | 0.0 | 0.0 | 390258.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 102.0 | 0.0 | 0.0 | 1806679.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102091232901 | 16113823707873 | 16113823856994 | 16102091653842 |
| 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 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7f2230e2d680 | 0x7f2230425f40 | 2680784 | 2565835 | 33068076 | 65536 | 211914058 | 335097 | 335097 | 19370501.0 | 18228117.0 | 17128126.0 | 16178371.0 | 0.0 | 0.0 | 9339916.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 117.0 | 0.0 | 0.0 | 871861.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102091939316 | 16113823883234 | 16113824092515 | 16102092436245 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7f22334cd500 | 0x7f2230425f80 | 2655024 | 2517903 | 32487770 | 65536 | 195281005 | 331877 | 331877 | 19187494.0 | 16433522.0 | 15184738.0 | 13934835.0 | 0.0 | 0.0 | 7703739.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 334.0 | 0.0 | 0.0 | 1327437.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102092704909 | 16113824154276 | 16113824360517 | 16102093198388 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7f22334cd380 | 0x7f2230425fc0 | 2447064 | 2340712 | 30296013 | 65536 | 224533737 | 305882 | 305882 | 5190672.0 | 3436329.0 | 3214062.0 | 2317915.0 | 0.0 | 0.0 | 469667.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 105.0 | 0.0 | 0.0 | 866526.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102093465922 | 16113824425477 | 16113824611398 | 16102093918062 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7f22334cd200 | 0x7f2230426000 | 4338248 | 4222116 | 54681539 | 65536 | 405581995 | 542280 | 542280 | 4521884.0 | 3156804.0 | 3057710.0 | 2467455.0 | 0.0 | 0.0 | 614352.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 290.0 | 0.0 | 0.0 | 597707.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102094204266 | 16113824637159 | 16113824971721 | 16102094840251 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7f22334cd080 | 0x7f2230426040 | 2184080 | 2070102 | 26723721 | 65536 | 181199710 | 273009 | 273009 | 6668778.0 | 4357676.0 | 4058996.0 | 2389799.0 | 0.0 | 0.0 | 455690.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 208.0 | 0.0 | 0.0 | 1674680.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102095113835 | 16113825014921 | 16113825182602 | 16102095537696 |
| 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 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7f2230e2df00 | 0x7f2230426080 | 2950472 | 2838283 | 36461572 | 65536 | 247052524 | 368808 | 368808 | 18005738.0 | 16663727.0 | 13665999.0 | 12452444.0 | 0.0 | 0.0 | 7015814.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 138.0 | 0.0 | 0.0 | 1181945.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102095825810 | 16113825207562 | 16113825437163 | 16102096347318 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7f2230e2dd80 | 0x7f22304260c0 | 2927992 | 2817368 | 36286382 | 65536 | 251235859 | 365998 | 365998 | 19277161.0 | 15964038.0 | 13515117.0 | 11938537.0 | 0.0 | 0.0 | 6493823.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 214.0 | 0.0 | 0.0 | 1596823.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102096613042 | 16113825471244 | 16113825700205 | 16102097129581 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7f2230e2dc00 | 0x7f2230426100 | 2778888 | 2667230 | 34429322 | 65536 | 241235521 | 347360 | 347360 | 5190772.0 | 3402391.0 | 3164531.0 | 2277538.0 | 0.0 | 0.0 | 442164.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 82.0 | 0.0 | 0.0 | 922065.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102097395085 | 16113825739565 | 16113825951086 | 16102097889744 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7f2230e2da80 | 0x7f2230426140 | 4991984 | 4872937 | 63098004 | 65536 | 470910328 | 623997 | 623997 | 4549542.0 | 3177268.0 | 3095473.0 | 2497185.0 | 0.0 | 0.0 | 671943.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 254.0 | 0.0 | 0.0 | 597306.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102098160888 | 16113825985167 | 16113826370769 | 16102098845033 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7f2230e2d900 | 0x7f2230426180 | 2428544 | 2316640 | 29961817 | 65536 | 215408454 | 303567 | 303567 | 6880662.0 | 4481170.0 | 4094412.0 | 2383974.0 | 0.0 | 0.0 | 464935.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 186.0 | 0.0 | 0.0 | 1705235.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102099117027 | 16113826441649 | 16113826629810 | 16102099567747 |
| 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 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7f2230e2d780 | 0x7f22304261c0 | 3199096 | 3085137 | 39801548 | 65536 | 270163198 | 399886 | 399886 | 16480592.0 | 14938554.0 | 13118996.0 | 11726898.0 | 0.0 | 0.0 | 6100628.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 98.0 | 0.0 | 0.0 | 1388146.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102099853680 | 16113826653971 | 16113826904052 | 16102100343559 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7f2230e2d600 | 0x7f2230426200 | 3129584 | 3021318 | 39111332 | 65536 | 291389074 | 391197 | 391197 | 15178333.0 | 11766900.0 | 9102821.0 | 7274694.0 | 0.0 | 0.0 | 2852371.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 265.0 | 0.0 | 0.0 | 1836877.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102100608743 | 16113826965972 | 16113827214454 | 16102101146692 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7f22334cd480 | 0x7f2230426240 | 3103056 | 2989328 | 38666745 | 65536 | 278800279 | 387881 | 387881 | 5144430.0 | 3378352.0 | 3253413.0 | 2320653.0 | 0.0 | 0.0 | 513966.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 105.0 | 0.0 | 0.0 | 882325.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102101412436 | 16113827280374 | 16113827517496 | 16102101953384 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7f22334cd300 | 0x7f2230426280 | 5758376 | 5638070 | 72933214 | 65536 | 537043617 | 719796 | 719796 | 15201964.0 | 6848726.0 | 5957500.0 | 2155826.0 | 0.0 | 0.0 | 53277.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 3817415.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102102225178 | 16113827581176 | 16113828035259 | 16102102972561 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7f22334cd180 | 0x7f22304262c0 | 2911408 | 2801604 | 36209978 | 65536 | 258652663 | 363925 | 363925 | 7234003.0 | 4510790.0 | 4178168.0 | 2389631.0 | 0.0 | 0.0 | 445127.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 192.0 | 0.0 | 0.0 | 1773228.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102103245605 | 16113828103899 | 16113828330301 | 16102103746994 |
| 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 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7f22334cd000 | 0x7f2230426300 | 3764656 | 3653475 | 47274070 | 65536 | 351123475 | 470581 | 470581 | 14409489.0 | 11754171.0 | 9389113.0 | 7745326.0 | 0.0 | 0.0 | 1863249.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 380.0 | 0.0 | 0.0 | 1635572.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102104015568 | 16113828394461 | 16113828692543 | 16102104601745 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7f2230e2de80 | 0x7f2230426340 | 3791504 | 3680063 | 47563883 | 65536 | 349102787 | 473937 | 473937 | 14126368.0 | 12102790.0 | 10064002.0 | 8843608.0 | 0.0 | 0.0 | 2831121.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 215.0 | 0.0 | 0.0 | 1231152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102104868509 | 16113828755743 | 16113829054625 | 16102105462326 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7f2230e2dd00 | 0x7f2230426380 | 3857288 | 3746624 | 48499853 | 65536 | 356927919 | 482160 | 482160 | 14711071.0 | 6815132.0 | 5931303.0 | 2139461.0 | 0.0 | 0.0 | 79666.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 2.0 | 0.0 | 0.0 | 3791648.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102105727400 | 16113829119105 | 16113829415747 | 16102106310357 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7f2230e2db80 | 0x7f22304263c0 | 7052896 | 6927462 | 89688438 | 65536 | 676998070 | 881611 | 881611 | 14834324.0 | 6712428.0 | 5851082.0 | 2166951.0 | 0.0 | 0.0 | 94014.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 2.0 | 0.0 | 0.0 | 3669959.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102106576891 | 16113829483427 | 16113830040391 | 16102107429242 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7f2230e2da00 | 0x7f2230426400 | 3410208 | 3300821 | 42710911 | 65536 | 313005140 | 426275 | 426275 | 6120846.0 | 3819180.0 | 3516126.0 | 2308640.0 | 0.0 | 0.0 | 318246.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 92.0 | 0.0 | 0.0 | 1222123.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102107699656 | 16113830094791 | 16113830358473 | 16102108250444 |
| 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 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7f2230e2d880 | 0x7f2230426440 | 4404216 | 4297773 | 55551318 | 65536 | 407987985 | 550526 | 550526 | 14142045.0 | 11801815.0 | 9863039.0 | 8437093.0 | 0.0 | 0.0 | 2065303.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 139.0 | 0.0 | 0.0 | 1331404.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102108516508 | 16113830423433 | 16113830773835 | 16102109160994 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7f2230e2d700 | 0x7f2230426480 | 4420608 | 4303495 | 55649106 | 65536 | 405768365 | 552575 | 552575 | 14093693.0 | 11651318.0 | 9818569.0 | 8631080.0 | 0.0 | 0.0 | 2312877.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 201.0 | 0.0 | 0.0 | 1129215.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102109423688 | 16113830838315 | 16113831188237 | 16102110065364 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7f22334cd580 | 0x7f22304264c0 | 4501144 | 4390838 | 56818097 | 65536 | 419574176 | 562642 | 562642 | 15019429.0 | 6849294.0 | 5977011.0 | 2162389.0 | 0.0 | 0.0 | 72316.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 2.0 | 0.0 | 0.0 | 3819446.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102110337468 | 16113831256078 | 16113831603600 | 16102110979034 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7f22334cd400 | 0x7f2230426500 | 8337352 | 8216591 | 106443594 | 65536 | 805183057 | 1042168 | 1042168 | 14905026.0 | 6705770.0 | 5788101.0 | 2155644.0 | 0.0 | 0.0 | 61769.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 3662439.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102111245978 | 16113831665200 | 16113832326964 | 16102112199836 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7f22334cd280 | 0x7f2230426540 | 5785832 | 5658914 | 73235292 | 65536 | 551627288 | 723228 | 723228 | 15183678.0 | 6876573.0 | 5940770.0 | 2135698.0 | 0.0 | 0.0 | 63608.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 3808538.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102112473500 | 16113832398965 | 16113832846007 | 16102113209884 |
| 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 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7f22334cd100 | 0x7f2230426580 | 5799984 | 5683410 | 73546035 | 65536 | 542932574 | 724997 | 724997 | 20858843.0 | 13078547.0 | 6843395.0 | 2971866.0 | 0.0 | 0.0 | 788608.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 97.0 | 0.0 | 0.0 | 3865140.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102113478478 | 16113832910328 | 16113833375610 | 16102114184102 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7f2230e2df80 | 0x7f22304265c0 | 5775736 | 5666680 | 73352151 | 65536 | 555698281 | 721966 | 721966 | 20772732.0 | 13003937.0 | 6862969.0 | 2999382.0 | 0.0 | 0.0 | 765702.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 98.0 | 0.0 | 0.0 | 3860855.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102114451077 | 16113833447771 | 16113833910494 | 16102115156311 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7f2230e2de00 | 0x7f2230426600 | 5830352 | 5702485 | 73707349 | 65536 | 547836705 | 728793 | 728793 | 15223618.0 | 6886173.0 | 5976618.0 | 2170013.0 | 0.0 | 0.0 | 61317.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 3819438.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102115420665 | 16113833950974 | 16113834402976 | 16102116110740 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7f2230e2dc80 | 0x7f2230426640 | 10936424 | 10815497 | 140145980 | 65536 | 1061363875 | 1367052 | 1367052 | 15025390.0 | 6771661.0 | 5838773.0 | 2139267.0 | 0.0 | 0.0 | 56763.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 1.0 | 0.0 | 0.0 | 3696313.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102116376624 | 16113834472417 | 16113835342182 | 16102117532418 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7f2230e2db00 | 0x7f2230426680 | 10980832 | 10854806 | 140614047 | 65536 | 1081328826 | 1372603 | 1372603 | 15293823.0 | 6831566.0 | 5900453.0 | 2164263.0 | 0.0 | 0.0 | 93041.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 3761274.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102117805372 | 16113835418182 | 16113836271948 | 16102118955497 |
| 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 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7f2230e2d980 | 0x7f22304266c0 | 10981560 | 10859851 | 140702741 | 65536 | 1075239635 | 1372694 | 1372694 | 21307310.0 | 13128643.0 | 6798976.0 | 2897254.0 | 0.0 | 0.0 | 755928.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 84.0 | 0.0 | 0.0 | 3896617.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102119217791 | 16113836336588 | 16113837221553 | 16102120415904 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7f2230e2d800 | 0x7f2230426700 | 10984328 | 10848855 | 140516125 | 65536 | 1065824400 | 1373040 | 1373040 | 21203858.0 | 13083153.0 | 6797920.0 | 2914880.0 | 0.0 | 0.0 | 725258.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 101.0 | 0.0 | 0.0 | 3881744.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102120682758 | 16113837286194 | 16113838164759 | 16102121873452 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7f2230e2d680 | 0x7f2230426740 | 10998456 | 10883367 | 141020166 | 65536 | 1082878556 | 1374806 | 1374806 | 15370389.0 | 6866930.0 | 5963961.0 | 2188217.0 | 0.0 | 0.0 | 82876.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 2.0 | 0.0 | 0.0 | 3766433.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102122139226 | 16113838242199 | 16113839102364 | 16102123267211 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7f22334cd500 | 0x7f2230426780 | 21308096 | 21182103 | 274535292 | 65536 | 2123242844 | 2663511 | 2663511 | 14682233.0 | 6603277.0 | 5756170.0 | 2163628.0 | 0.0 | 0.0 | 78709.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 3585347.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102123531955 | 16113839172605 | 16113840871175 | 16102125581870 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7f22334cd380 | 0x7f22304267c0 | 21336672 | 21225821 | 275097254 | 65536 | 2123685599 | 2667083 | 2667083 | 15837561.0 | 6929526.0 | 6005965.0 | 2165470.0 | 0.0 | 0.0 | 85563.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 3844710.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102125806745 | 16113840973735 | 16113842639185 | 16102127793851 |
| 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 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7f22334cd200 | 0x7f2230426800 | 21368912 | 21237647 | 275199055 | 65536 | 2131941379 | 2671113 | 2671113 | 22013749.0 | 13294360.0 | 6744912.0 | 2805138.0 | 0.0 | 0.0 | 666935.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 80.0 | 0.0 | 0.0 | 3942275.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102128012996 | 16113842729586 | 16113844454876 | 16102130082190 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7f22334cd080 | 0x7f2230426840 | 21350976 | 21225361 | 275096142 | 65536 | 2120754153 | 2668871 | 2668871 | 22063919.0 | 13333501.0 | 6706558.0 | 2767258.0 | 0.0 | 0.0 | 776635.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 74.0 | 0.0 | 0.0 | 3936428.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16102130298885 | 16113844543837 | 16113846258567 | 16102132366799 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7f2230e2df00 | 0x7f2230426880 | 21398024 | 21263651 | 275507342 | 65536 | 2130321269 | 2674752 | 2674752 | 15806576.0 | 6930924.0 | 5983925.0 | 2150280.0 | 0.0 | 0.0 | 76932.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 3833330.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102132581965 | 16113846350887 | 16113848025137 | 16102134611070 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 147071 | 147071 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7f2230e2dd80 | 0x7f22304268c0 | 42049168 | 41927992 | 543400621 | 65536 | 4230004783 | 5256145 | 5256145 | 14588176.0 | 6583880.0 | 5745892.0 | 2156940.0 | 0.0 | 0.0 | 97921.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 524288.0 | 0.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 3563136.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16102134828195 | 16113848112978 | 16113851470598 | 16102138535143 |