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 | 145593 | 145593 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7fc075e04280 | 3086600 | 2999136 | 38943805 | 524288 | 242505422 | 385824 | 385824 | 31218489.0 | 30844323.0 | 28229379.0 | 27478990.0 | 0.0 | 0.0 | 19970745.0 | 524288.0 | 0.0 | 20911587.0 | 524288.0 | 0.0 | 524288.0 | 0.0 | 0.0 | 29781861.0 | 28088624.0 | 29252073.0 | 2097152.0 | 2097152.0 | 4194304.0 | 77.0 | 0.0 | 0.0 | 1245507.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062052903004 | 16074044451735 | 16074044692537 | 16062204068440 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 145593 | 145593 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7fc075e23f80 | 273568 | 158617 | 1465257 | 512 | 1782234 | 34195 | 34195 | 35277.0 | 30729.0 | 37671.0 | 36325.0 | 0.0 | 0.0 | 16621.0 | 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 | 1341.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4096.0 | 16062209486770 | 16074049489845 | 16074049503445 | 16062209674865 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7fc078d53380 | 0x7fc075e23fc0 | 1410112 | 1280712 | 16509767 | 65536 | 80439646 | 176263 | 176263 | 11638605.0 | 11329706.0 | 12043703.0 | 12011243.0 | 0.0 | 0.0 | 9081557.0 | 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 | 160.0 | 0.0 | 0.0 | 43360.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062209964069 | 16074049569366 | 16074049661366 | 16062210260012 |
| 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 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7fc078d53200 | 0x7fc075e24000 | 2465224 | 2356825 | 30518538 | 65536 | 211755797 | 308152 | 308152 | 29166999.0 | 29157849.0 | 28582824.0 | 28581512.0 | 0.0 | 0.0 | 21263820.0 | 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 | 1256.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062210553536 | 16074049694966 | 16074049872727 | 16062210999186 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7fc078d53080 | 0x7fc075e24040 | 2504616 | 2384849 | 30868378 | 65536 | 225602488 | 313076 | 313076 | 28806289.0 | 28786937.0 | 28707646.0 | 28706334.0 | 0.0 | 0.0 | 19628958.0 | 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 | 7712.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062211286950 | 16074049899128 | 16074050078329 | 16062211639412 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7fc0765fbf00 | 0x7fc075e24080 | 1338232 | 1224173 | 15830544 | 65536 | 74712758 | 167278 | 167278 | 12740734.0 | 12354003.0 | 13564072.0 | 13545845.0 | 0.0 | 0.0 | 10150071.0 | 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 | 144.0 | 0.0 | 0.0 | 54019.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062211928455 | 16074050111769 | 16074050205689 | 16062212268908 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7fc0765fbd80 | 0x7fc075e240c0 | 1324736 | 1212612 | 15688938 | 65536 | 76319346 | 165591 | 165591 | 13166412.0 | 12810973.0 | 12332249.0 | 12292540.0 | 0.0 | 0.0 | 9073137.0 | 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 | 22.0 | 0.0 | 0.0 | 39059.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062212555461 | 16074050230970 | 16074050323450 | 16062212891884 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7fc0765fbc00 | 0x7fc075e24100 | 1378432 | 1257670 | 16256501 | 65536 | 92654692 | 172303 | 172303 | 12734557.0 | 12607463.0 | 13525771.0 | 13508211.0 | 0.0 | 0.0 | 12079312.0 | 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 | 3.0 | 0.0 | 0.0 | 19309.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062213189657 | 16074050363290 | 16074050455771 | 16062213456421 |
| 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 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7fc0765fba80 | 0x7fc075e24140 | 2483944 | 2369767 | 30708830 | 65536 | 225344651 | 310492 | 310492 | 29326988.0 | 29318628.0 | 29227084.0 | 29226252.0 | 0.0 | 0.0 | 20889569.0 | 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 | 16062213744515 | 16074050487451 | 16074050667612 | 16062214191105 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7fc0765fb900 | 0x7fc075e24180 | 2478680 | 2358245 | 30546883 | 65536 | 213125784 | 309834 | 309834 | 28485049.0 | 28450355.0 | 29227563.0 | 29223659.0 | 0.0 | 0.0 | 20936534.0 | 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 | 3960.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062214477419 | 16074050699452 | 16074050880094 | 16062214827421 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7fc0765fb780 | 0x7fc075e241c0 | 1459704 | 1339066 | 17027934 | 65536 | 86474075 | 182462 | 182462 | 12246372.0 | 11941713.0 | 13244357.0 | 13187380.0 | 0.0 | 0.0 | 11016992.0 | 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 | 23.0 | 0.0 | 0.0 | 39858.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062215116095 | 16074050924094 | 16074051017694 | 16062215391479 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7fc0765fb600 | 0x7fc075e24200 | 1404632 | 1285827 | 16573639 | 65536 | 94803155 | 175578 | 175578 | 13090393.0 | 12932412.0 | 14298703.0 | 14294187.0 | 0.0 | 0.0 | 11855344.0 | 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 | 78.0 | 0.0 | 0.0 | 2773.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062215679772 | 16074051046495 | 16074051139455 | 16062215959256 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7fc078d53480 | 0x7fc075e24240 | 1412400 | 1287954 | 16578009 | 65536 | 93196930 | 176549 | 176549 | 12380890.0 | 12191288.0 | 13526675.0 | 13506230.0 | 0.0 | 0.0 | 12205701.0 | 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 | 30.0 | 0.0 | 0.0 | 24321.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062216259429 | 16074051172095 | 16074051265536 | 16062216538233 |
| 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 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7fc078d53300 | 0x7fc075e24280 | 2468864 | 2360960 | 30586810 | 65536 | 224691466 | 308607 | 308607 | 29187955.0 | 29183978.0 | 29354548.0 | 29353716.0 | 0.0 | 0.0 | 20998739.0 | 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 | 16062216828917 | 16074051297696 | 16074051478177 | 16062217251337 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7fc078d53180 | 0x7fc075e242c0 | 2489776 | 2378249 | 30786745 | 65536 | 217508484 | 311221 | 311221 | 29325828.0 | 29301211.0 | 29137604.0 | 29133636.0 | 0.0 | 0.0 | 20795123.0 | 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 | 3956.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062217539101 | 16074051506337 | 16074051688898 | 16062217972681 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7fc078d53000 | 0x7fc075e24300 | 1324480 | 1220435 | 15779725 | 65536 | 93601650 | 165559 | 165559 | 13952721.0 | 13769150.0 | 13437174.0 | 13391484.0 | 0.0 | 0.0 | 11384461.0 | 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 | 94.0 | 0.0 | 0.0 | 24402.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062218260325 | 16074051717859 | 16074051811139 | 16062218597377 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7fc0765fbe80 | 0x7fc075e24340 | 1310096 | 1205217 | 15574441 | 65536 | 85271474 | 163761 | 163761 | 13453501.0 | 13231524.0 | 13144720.0 | 13082105.0 | 0.0 | 0.0 | 11418175.0 | 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 | 84.0 | 0.0 | 0.0 | 38591.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062218882861 | 16074051840579 | 16074051934340 | 16062219240463 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7fc0765fbd00 | 0x7fc075e24380 | 1312600 | 1208276 | 15643339 | 65536 | 101918899 | 164074 | 164074 | 14061610.0 | 14007311.0 | 14159621.0 | 14157141.0 | 0.0 | 0.0 | 11572720.0 | 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 | 8876.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062219535097 | 16074051967620 | 16074052060741 | 16062219843630 |
| 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 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7fc0765fbb80 | 0x7fc075e243c0 | 2472776 | 2366426 | 30648554 | 65536 | 227475074 | 309096 | 309096 | 29225657.0 | 29204498.0 | 29168588.0 | 29167756.0 | 0.0 | 0.0 | 21016124.0 | 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 | 16062220130923 | 16074052095941 | 16074052274662 | 16062220574694 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7fc0765fba00 | 0x7fc075e24400 | 2455744 | 2344759 | 30363082 | 65536 | 213240298 | 306967 | 306967 | 29019785.0 | 29000482.0 | 29007086.0 | 29003158.0 | 0.0 | 0.0 | 20887234.0 | 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 | 3877.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062220860987 | 16074052301542 | 16074052481383 | 16062221254529 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7fc0765fb880 | 0x7fc075e24440 | 1317288 | 1211982 | 15691234 | 65536 | 95735560 | 164660 | 164660 | 13813944.0 | 13717681.0 | 13419589.0 | 13378641.0 | 0.0 | 0.0 | 12029643.0 | 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 | 3.0 | 0.0 | 0.0 | 41444.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062221541112 | 16074052508583 | 16074052602664 | 16062221849385 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7fc0765fb700 | 0x7fc075e24480 | 1307024 | 1202268 | 15564041 | 65536 | 94166245 | 163377 | 163377 | 13944045.0 | 13740024.0 | 13878039.0 | 13826544.0 | 0.0 | 0.0 | 11368977.0 | 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 | 103.0 | 0.0 | 0.0 | 22830.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062222136469 | 16074052630504 | 16074052723945 | 16062222447082 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7fc078d53580 | 0x7fc075e244c0 | 1303056 | 1196493 | 15490810 | 65536 | 94126137 | 162881 | 162881 | 13794584.0 | 13698311.0 | 13710339.0 | 13688090.0 | 0.0 | 0.0 | 11908710.0 | 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 | 31.0 | 0.0 | 0.0 | 41082.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062222741446 | 16074052757385 | 16074052849706 | 16062223096488 |
| 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 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7fc078d53400 | 0x7fc075e24500 | 2438568 | 2336983 | 30286058 | 65536 | 219002598 | 304820 | 304820 | 28901883.0 | 28890224.0 | 29137192.0 | 29136360.0 | 0.0 | 0.0 | 20914314.0 | 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 | 16062223383221 | 16074052882186 | 16074053061387 | 16062223820942 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7fc078d53280 | 0x7fc075e24540 | 2452352 | 2347865 | 30405126 | 65536 | 214754524 | 306543 | 306543 | 28935804.0 | 28916481.0 | 29325947.0 | 29322069.0 | 0.0 | 0.0 | 20619853.0 | 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 | 3893.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062224107575 | 16074053085547 | 16074053267788 | 16062224546786 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7fc078d53100 | 0x7fc075e24580 | 1295424 | 1192412 | 15421107 | 65536 | 82256179 | 161927 | 161927 | 13300466.0 | 12954325.0 | 13386466.0 | 13340053.0 | 0.0 | 0.0 | 11895275.0 | 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 | 28.0 | 0.0 | 0.0 | 37287.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062224834439 | 16074053315628 | 16074053407789 | 16062225187441 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7fc0765fbf80 | 0x7fc075e245c0 | 1308856 | 1202020 | 15512619 | 65536 | 79508224 | 163606 | 163606 | 12846849.0 | 12222113.0 | 13110026.0 | 12891115.0 | 0.0 | 0.0 | 11325471.0 | 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 | 158.0 | 0.0 | 0.0 | 208331.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062225473735 | 16074053435149 | 16074053526990 | 16062225824227 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7fc0765fbe00 | 0x7fc075e24600 | 1298504 | 1195739 | 15487695 | 65536 | 104620319 | 162312 | 162312 | 14110750.0 | 14089456.0 | 14030549.0 | 14026680.0 | 0.0 | 0.0 | 11867895.0 | 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 | 131.0 | 0.0 | 0.0 | 24248.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062226116871 | 16074053559790 | 16074053652750 | 16062226464613 |
| 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 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7fc0765fbc80 | 0x7fc075e24640 | 2440928 | 2329782 | 30190480 | 65536 | 220918207 | 305115 | 305115 | 28884441.0 | 28875916.0 | 28785475.0 | 28784643.0 | 0.0 | 0.0 | 20526678.0 | 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 | 16062226749667 | 16074053681231 | 16074053861232 | 16062227191287 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7fc0765fbb00 | 0x7fc075e24680 | 2452736 | 2347982 | 30423742 | 65536 | 219398832 | 306591 | 306591 | 29078342.0 | 29065081.0 | 29270081.0 | 29267042.0 | 0.0 | 0.0 | 20696480.0 | 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 | 3151.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062227477211 | 16074053888112 | 16074054068913 | 16062227916501 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7fc0765fb980 | 0x7fc075e246c0 | 1304024 | 1200050 | 15522000 | 65536 | 91490601 | 163002 | 163002 | 13601764.0 | 13404293.0 | 13600264.0 | 13550885.0 | 0.0 | 0.0 | 11945831.0 | 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 | 26.0 | 0.0 | 0.0 | 81653.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062228202854 | 16074054111153 | 16074054205554 | 16062228554407 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7fc0765fb800 | 0x7fc075e24700 | 1312504 | 1206297 | 15576144 | 65536 | 89287626 | 164062 | 164062 | 13251389.0 | 12673053.0 | 12762248.0 | 12488739.0 | 0.0 | 0.0 | 10491508.0 | 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 | 312768.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062228840860 | 16074054233714 | 16074054327795 | 16062229197382 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7fc0765fb680 | 0x7fc075e24740 | 1311064 | 1204491 | 15591864 | 65536 | 95480708 | 163882 | 163882 | 13623866.0 | 13454386.0 | 13247780.0 | 13175788.0 | 0.0 | 0.0 | 11783855.0 | 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 | 40.0 | 0.0 | 0.0 | 47774.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062229488486 | 16074054361555 | 16074054455475 | 16062229836348 |
| 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 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7fc078d53500 | 0x7fc075e24780 | 2452712 | 2347867 | 30433002 | 65536 | 223604694 | 306588 | 306588 | 29138934.0 | 29120728.0 | 28987577.0 | 28986745.0 | 0.0 | 0.0 | 20721932.0 | 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 | 16062230123602 | 16074054485396 | 16074054664597 | 16062230586462 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7fc078d53380 | 0x7fc075e247c0 | 2470080 | 2363357 | 30624692 | 65536 | 219654449 | 308759 | 308759 | 29234265.0 | 29221095.0 | 28713600.0 | 28710392.0 | 0.0 | 0.0 | 20496417.0 | 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 | 3096.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062230872655 | 16074054689717 | 16074054870038 | 16062231323615 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7fc078d53200 | 0x7fc075e24800 | 1300224 | 1194025 | 15446006 | 65536 | 93675353 | 162527 | 162527 | 13416354.0 | 13147859.0 | 13645643.0 | 13546091.0 | 0.0 | 0.0 | 11622648.0 | 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 | 136295.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062231612489 | 16074054894038 | 16074054986999 | 16062231976611 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7fc078d53080 | 0x7fc075e24840 | 1304400 | 1197914 | 15458610 | 65536 | 86345322 | 163049 | 163049 | 12818750.0 | 11696813.0 | 11993200.0 | 11274828.0 | 0.0 | 0.0 | 10110386.0 | 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 | 652.0 | 0.0 | 0.0 | 563149.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062232262724 | 16074055010839 | 16074055105079 | 16062232615947 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7fc0765fbf00 | 0x7fc075e24880 | 1310640 | 1207300 | 15609406 | 65536 | 99159696 | 163829 | 163829 | 13636119.0 | 13524458.0 | 13327585.0 | 13248834.0 | 0.0 | 0.0 | 11998889.0 | 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 | 35.0 | 0.0 | 0.0 | 190781.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062232907580 | 16074055137560 | 16074055231320 | 16062233257492 |
| 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 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7fc0765fbd80 | 0x7fc075e248c0 | 2448880 | 2344373 | 30371327 | 65536 | 229664054 | 306109 | 306109 | 29004198.0 | 28997426.0 | 28639375.0 | 28638543.0 | 0.0 | 0.0 | 20683921.0 | 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 | 16062233543946 | 16074055255800 | 16074055435321 | 16062233981886 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7fc0765fbc00 | 0x7fc075e24900 | 2458656 | 2346882 | 30410755 | 65536 | 219595025 | 307331 | 307331 | 29125889.0 | 29109731.0 | 28854903.0 | 28851671.0 | 0.0 | 0.0 | 20442742.0 | 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 | 3254.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062234269020 | 16074055459321 | 16074055640923 | 16062234715090 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7fc0765fba80 | 0x7fc075e24940 | 1306952 | 1202357 | 15535375 | 65536 | 93853916 | 163368 | 163368 | 13503963.0 | 13188942.0 | 13327999.0 | 13216448.0 | 0.0 | 0.0 | 11429648.0 | 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 | 117.0 | 0.0 | 0.0 | 128480.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062235000424 | 16074055665883 | 16074055759323 | 16062235361806 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7fc0765fb900 | 0x7fc075e24980 | 1298408 | 1196351 | 15423616 | 65536 | 94469258 | 162300 | 162300 | 12923321.0 | 11798380.0 | 11798800.0 | 11178796.0 | 0.0 | 0.0 | 10029593.0 | 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 | 542.0 | 0.0 | 0.0 | 638086.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062235647349 | 16074055790523 | 16074055885564 | 16062236013211 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7fc0765fb780 | 0x7fc075e249c0 | 1306880 | 1198945 | 15508545 | 65536 | 93623443 | 163359 | 163359 | 13736551.0 | 13393856.0 | 13055152.0 | 12829285.0 | 0.0 | 0.0 | 11676767.0 | 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 | 173.0 | 0.0 | 0.0 | 149642.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062236303945 | 16074055918044 | 16074056011005 | 16062236654657 |
| 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 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7fc0765fb600 | 0x7fc075e24a00 | 2447376 | 2341715 | 30330205 | 65536 | 218390594 | 305921 | 305921 | 28956455.0 | 28947493.0 | 28953711.0 | 28952879.0 | 0.0 | 0.0 | 20273764.0 | 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 | 16062236940561 | 16074056037405 | 16074056215966 | 16062237388001 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7fc078d53480 | 0x7fc075e24a40 | 2433592 | 2325500 | 30088083 | 65536 | 215706872 | 304198 | 304198 | 28707874.0 | 28691498.0 | 28526795.0 | 28522956.0 | 0.0 | 0.0 | 20177836.0 | 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 | 3415.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062237673124 | 16074056240606 | 16074056421887 | 16062238108775 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7fc078d53300 | 0x7fc075e24a80 | 1309128 | 1193440 | 15401343 | 65536 | 84662898 | 163640 | 163640 | 13063037.0 | 12440728.0 | 12300113.0 | 11938524.0 | 0.0 | 0.0 | 10956752.0 | 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 | 239789.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062238396108 | 16074056446687 | 16074056539328 | 16062238754450 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7fc078d53180 | 0x7fc075e24ac0 | 1292288 | 1187985 | 15301349 | 65536 | 97897629 | 161535 | 161535 | 12104332.0 | 10219338.0 | 9804289.0 | 8906985.0 | 0.0 | 0.0 | 8055096.0 | 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 | 893387.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062239040034 | 16074056564768 | 16074056658049 | 16062239400416 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7fc078d53000 | 0x7fc075e24b00 | 1290616 | 1188154 | 15364208 | 65536 | 87925036 | 161326 | 161326 | 13072107.0 | 12567884.0 | 12749451.0 | 12485593.0 | 0.0 | 0.0 | 11126063.0 | 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 | 212.0 | 0.0 | 0.0 | 228628.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062239693380 | 16074056691329 | 16074056783490 | 16062240048832 |
| 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 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7fc0765fbe80 | 0x7fc075e24b40 | 2417136 | 2309987 | 29932698 | 65536 | 207656524 | 302141 | 302141 | 28565605.0 | 28557104.0 | 28705551.0 | 28704711.0 | 0.0 | 0.0 | 20390639.0 | 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 | 865.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062240335185 | 16074056809570 | 16074056989571 | 16062240779816 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7fc0765fbd00 | 0x7fc075e24b80 | 2411424 | 2307415 | 29881821 | 65536 | 208989618 | 301427 | 301427 | 28472216.0 | 28458837.0 | 28448975.0 | 28445315.0 | 0.0 | 0.0 | 20107407.0 | 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 | 3956.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062241065619 | 16074057013251 | 16074057194692 | 16062241510469 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7fc0765fbb80 | 0x7fc075e24bc0 | 1299584 | 1194733 | 15422550 | 65536 | 89302706 | 162447 | 162447 | 13183254.0 | 12681457.0 | 13005830.0 | 12765537.0 | 0.0 | 0.0 | 11045082.0 | 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 | 369.0 | 0.0 | 0.0 | 218762.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062241795603 | 16074057219812 | 16074057314373 | 16062242152485 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7fc0765fba00 | 0x7fc075e24c00 | 1320248 | 1211411 | 15628674 | 65536 | 101594836 | 165030 | 165030 | 10560405.0 | 8233254.0 | 7783213.0 | 6542477.0 | 0.0 | 0.0 | 5451114.0 | 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 | 470.0 | 0.0 | 0.0 | 1202524.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062242438969 | 16074057339973 | 16074057435174 | 16062242804681 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7fc0765fb880 | 0x7fc075e24c40 | 1294808 | 1188956 | 15376404 | 65536 | 94100979 | 161850 | 161850 | 13731373.0 | 13370644.0 | 13095493.0 | 12887114.0 | 0.0 | 0.0 | 11080419.0 | 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 | 198.0 | 0.0 | 0.0 | 208598.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062243097014 | 16074057467494 | 16074057560294 | 16062243444386 |
| 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 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7fc0765fb700 | 0x7fc075e24c80 | 2421696 | 2304908 | 29851660 | 65536 | 208569222 | 302711 | 302711 | 28442448.0 | 28421706.0 | 28605506.0 | 28604613.0 | 0.0 | 0.0 | 20331351.0 | 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 | 864.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062243731120 | 16074057584774 | 16074057765096 | 16062244168070 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7fc078d53580 | 0x7fc075e24cc0 | 2415016 | 2308415 | 29921388 | 65536 | 214624235 | 301876 | 301876 | 28536941.0 | 28520947.0 | 28616419.0 | 28612817.0 | 0.0 | 0.0 | 20060559.0 | 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 | 3584.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062244454164 | 16074057789096 | 16074057970537 | 16062244898774 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7fc078d53400 | 0x7fc075e24d00 | 1301088 | 1195501 | 15421799 | 65536 | 81940964 | 162635 | 162635 | 12522203.0 | 11684207.0 | 12387142.0 | 11978666.0 | 0.0 | 0.0 | 10390758.0 | 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 | 325.0 | 0.0 | 0.0 | 384395.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062245186898 | 16074057993257 | 16074058087017 | 16062245538670 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7fc078d53280 | 0x7fc075e24d40 | 1350200 | 1243619 | 16027330 | 65536 | 103458068 | 168774 | 168774 | 8910324.0 | 6491674.0 | 6144999.0 | 5004836.0 | 0.0 | 0.0 | 4341318.0 | 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 | 1128561.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062245823634 | 16074058123178 | 16074058223018 | 16062246194885 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7fc078d53100 | 0x7fc075e24d80 | 1296160 | 1195206 | 15441467 | 65536 | 90757957 | 162019 | 162019 | 13297029.0 | 12799375.0 | 12163468.0 | 11799885.0 | 0.0 | 0.0 | 11166488.0 | 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 | 253.0 | 0.0 | 0.0 | 348487.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062246488069 | 16074058255179 | 16074058349739 | 16062246844071 |
| 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 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7fc0765fbf80 | 0x7fc075e24dc0 | 2410488 | 2302332 | 29828744 | 65536 | 221303140 | 301310 | 301310 | 28510438.0 | 28499614.0 | 28671249.0 | 28670377.0 | 0.0 | 0.0 | 20036703.0 | 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 | 956.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062247131965 | 16074058378859 | 16074058558060 | 16062247575625 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7fc0765fbe00 | 0x7fc075e24e00 | 2399000 | 2292113 | 29695050 | 65536 | 209238392 | 299874 | 299874 | 28405760.0 | 28391273.0 | 28415173.0 | 28411207.0 | 0.0 | 0.0 | 20020519.0 | 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 | 3012.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062247861339 | 16074058581901 | 16074058762862 | 16062248303379 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7fc0765fbc80 | 0x7fc075e24e40 | 1301600 | 1198328 | 15438743 | 65536 | 87824742 | 162699 | 162699 | 12844778.0 | 11983556.0 | 12307784.0 | 11904401.0 | 0.0 | 0.0 | 10594758.0 | 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 | 408.0 | 0.0 | 0.0 | 484650.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062248589022 | 16074058787982 | 16074058882382 | 16062248959664 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7fc0765fbb00 | 0x7fc075e24e80 | 1418896 | 1310068 | 16915272 | 65536 | 97028573 | 177361 | 177361 | 8197508.0 | 5593471.0 | 5297827.0 | 4048631.0 | 0.0 | 0.0 | 3010604.0 | 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 | 377.0 | 0.0 | 0.0 | 1186281.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062249247938 | 16074058907822 | 16074059011663 | 16062249618090 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7fc0765fb980 | 0x7fc075e24ec0 | 1281608 | 1179295 | 15232926 | 65536 | 80835240 | 160200 | 160200 | 12473991.0 | 11606963.0 | 12435529.0 | 12113800.0 | 0.0 | 0.0 | 10653181.0 | 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 | 327.0 | 0.0 | 0.0 | 494596.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062249910903 | 16074059044783 | 16074059137104 | 16062250261685 |
| 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 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7fc0765fb800 | 0x7fc075e24f00 | 2413816 | 2302526 | 29826053 | 65536 | 207431712 | 301726 | 301726 | 28376250.0 | 28371510.0 | 28384202.0 | 28383158.0 | 0.0 | 0.0 | 20323502.0 | 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 | 1044.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062250547219 | 16074059162864 | 16074059341905 | 16062250990429 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7fc0765fb680 | 0x7fc075e24f40 | 2405208 | 2292949 | 29710183 | 65536 | 212727465 | 300650 | 300650 | 28328982.0 | 28320648.0 | 28432790.0 | 28431942.0 | 0.0 | 0.0 | 20111241.0 | 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 | 16062251277153 | 16074059368945 | 16074059549106 | 16062251719683 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7fc078d53500 | 0x7fc075e24f80 | 1291472 | 1188104 | 15326124 | 65536 | 90651072 | 161433 | 161433 | 12939778.0 | 11982917.0 | 11920423.0 | 11196778.0 | 0.0 | 0.0 | 10128438.0 | 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 | 565.0 | 0.0 | 0.0 | 514127.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062252006236 | 16074059573267 | 16074059666867 | 16062252360318 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7fc078d53380 | 0x7fc075e24fc0 | 1467160 | 1355639 | 17509545 | 65536 | 103075912 | 183394 | 183394 | 7595497.0 | 5027554.0 | 4663953.0 | 3309636.0 | 0.0 | 0.0 | 1956303.0 | 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 | 363.0 | 0.0 | 0.0 | 1338642.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062252647982 | 16074059694227 | 16074059800788 | 16062253015964 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7fc078d53200 | 0x7fc075e25000 | 1292320 | 1187422 | 15340300 | 65536 | 100929115 | 161539 | 161539 | 13476908.0 | 13116638.0 | 12686877.0 | 12388988.0 | 0.0 | 0.0 | 10505932.0 | 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 | 229.0 | 0.0 | 0.0 | 254349.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062253320037 | 16074059834548 | 16074059927669 | 16062253669449 |
| 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 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7fc078d53080 | 0x7fc075e25040 | 2409840 | 2304128 | 29847680 | 65536 | 210307169 | 301229 | 301229 | 28406112.0 | 28398145.0 | 28404482.0 | 28403373.0 | 0.0 | 0.0 | 20255391.0 | 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 | 1088.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062253956603 | 16074059953269 | 16074060133590 | 16062254409113 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7fc0765fbf00 | 0x7fc075e25080 | 2411264 | 2299352 | 29791818 | 65536 | 211257780 | 301407 | 301407 | 28392885.0 | 28382873.0 | 28192579.0 | 28191716.0 | 0.0 | 0.0 | 20048761.0 | 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 | 896.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062254694836 | 16074060158870 | 16074060338871 | 16062255140876 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7fc0765fbd80 | 0x7fc075e250c0 | 1303864 | 1198696 | 15473329 | 65536 | 88882582 | 162982 | 162982 | 12524116.0 | 11093759.0 | 11446406.0 | 10766551.0 | 0.0 | 0.0 | 9404827.0 | 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 | 523.0 | 0.0 | 0.0 | 755317.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062255426510 | 16074060364951 | 16074060460312 | 16062255786812 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7fc0765fbc00 | 0x7fc075e25100 | 1540208 | 1429946 | 18421472 | 65536 | 113848494 | 192525 | 192525 | 6690065.0 | 4459354.0 | 4028918.0 | 2891316.0 | 0.0 | 0.0 | 1505048.0 | 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 | 273.0 | 0.0 | 0.0 | 1138288.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062256072446 | 16074060485752 | 16074060601593 | 16062256448937 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7fc0765fba80 | 0x7fc075e25140 | 1291856 | 1188991 | 15364519 | 65536 | 96735499 | 161481 | 161481 | 13535007.0 | 13030632.0 | 11728151.0 | 11278706.0 | 0.0 | 0.0 | 10799407.0 | 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 | 294.0 | 0.0 | 0.0 | 400881.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062256741401 | 16074060648793 | 16074060742394 | 16062257091593 |
| 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 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7fc0765fb900 | 0x7fc075e25180 | 2406408 | 2301659 | 29802887 | 65536 | 214928306 | 300800 | 300800 | 28371454.0 | 28360263.0 | 28429818.0 | 28428950.0 | 0.0 | 0.0 | 20117997.0 | 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 | 864.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062257377157 | 16074060765914 | 16074060945435 | 16062257827647 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7fc0765fb780 | 0x7fc075e251c0 | 2395576 | 2290070 | 29654181 | 65536 | 211174817 | 299446 | 299446 | 28240164.0 | 28229126.0 | 28505290.0 | 28504418.0 | 0.0 | 0.0 | 19830342.0 | 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 | 889.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062258114811 | 16074060969115 | 16074061150076 | 16062258568650 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7fc0765fb600 | 0x7fc075e25200 | 1309792 | 1200756 | 15474716 | 65536 | 89905163 | 163723 | 163723 | 12318007.0 | 10570286.0 | 11009182.0 | 10178570.0 | 0.0 | 0.0 | 9356858.0 | 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 | 516.0 | 0.0 | 0.0 | 861107.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062258854924 | 16074061176796 | 16074061273437 | 16062259215396 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7fc078d53480 | 0x7fc075e25240 | 1629296 | 1510940 | 19503314 | 65536 | 115628449 | 203661 | 203661 | 6612157.0 | 4321375.0 | 4173477.0 | 3042354.0 | 0.0 | 0.0 | 1467847.0 | 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 | 309.0 | 0.0 | 0.0 | 1145126.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062259501850 | 16074061299517 | 16074061419998 | 16062259883561 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7fc078d53300 | 0x7fc075e25280 | 1297272 | 1190581 | 15365417 | 65536 | 93876561 | 162158 | 162158 | 12845139.0 | 12250827.0 | 12559270.0 | 12254131.0 | 0.0 | 0.0 | 10511104.0 | 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 | 285.0 | 0.0 | 0.0 | 379442.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062260175525 | 16074061452478 | 16074061546239 | 16062260528067 |
| 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 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7fc078d53180 | 0x7fc075e252c0 | 2411680 | 2305997 | 29861766 | 65536 | 216304407 | 301459 | 301459 | 28421969.0 | 28413955.0 | 28621664.0 | 28620824.0 | 0.0 | 0.0 | 20026732.0 | 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 | 852.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062260814611 | 16074061572159 | 16074061752320 | 16062261258981 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7fc078d53000 | 0x7fc075e25300 | 2383080 | 2281876 | 29570850 | 65536 | 202476652 | 297884 | 297884 | 28175658.0 | 28159157.0 | 28301859.0 | 28299953.0 | 0.0 | 0.0 | 19991759.0 | 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 | 2373.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062261546674 | 16074061778560 | 16074061957121 | 16062261985175 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7fc0765fbe80 | 0x7fc075e25340 | 1298032 | 1194184 | 15414886 | 65536 | 94215803 | 162253 | 162253 | 12009798.0 | 10133803.0 | 10589541.0 | 9741363.0 | 0.0 | 0.0 | 8744482.0 | 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 | 498.0 | 0.0 | 0.0 | 838259.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062262270888 | 16074061984961 | 16074062080482 | 16062262632280 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7fc0765fbd00 | 0x7fc075e25380 | 1689768 | 1577672 | 20358212 | 65536 | 135066338 | 211220 | 211220 | 6503124.0 | 4323491.0 | 3926604.0 | 2765705.0 | 0.0 | 0.0 | 909179.0 | 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 | 291.0 | 0.0 | 0.0 | 1155848.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062262917434 | 16074062105282 | 16074062232163 | 16062263317165 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7fc0765fbb80 | 0x7fc075e253c0 | 1294976 | 1192448 | 15388126 | 65536 | 86256402 | 161871 | 161871 | 12671593.0 | 11587955.0 | 11635875.0 | 11071499.0 | 0.0 | 0.0 | 9829719.0 | 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 | 545007.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062263611279 | 16074062265603 | 16074062360004 | 16062263961131 |
| 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 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7fc0765fba00 | 0x7fc075e25400 | 2385080 | 2280621 | 29540142 | 65536 | 212931979 | 298134 | 298134 | 28185759.0 | 28175984.0 | 28047227.0 | 28046046.0 | 0.0 | 0.0 | 20048265.0 | 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 | 856.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062264247185 | 16074062385924 | 16074062566245 | 16062264687635 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7fc0765fb880 | 0x7fc075e25440 | 2392808 | 2282866 | 29560537 | 65536 | 210458321 | 299100 | 299100 | 28181391.0 | 28169833.0 | 28379204.0 | 28376731.0 | 0.0 | 0.0 | 19814534.0 | 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 | 2110.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062264973628 | 16074062590885 | 16074062770566 | 16062265409679 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7fc0765fb700 | 0x7fc075e25480 | 1298288 | 1193247 | 15385209 | 65536 | 97168445 | 162285 | 162285 | 11709936.0 | 9393046.0 | 9164071.0 | 8132496.0 | 0.0 | 0.0 | 7866368.0 | 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 | 474.0 | 0.0 | 0.0 | 1007037.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062265694562 | 16074062795206 | 16074062889927 | 16062266045335 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7fc078d53580 | 0x7fc075e254c0 | 1758712 | 1641870 | 21196105 | 65536 | 130335973 | 219838 | 219838 | 5958709.0 | 3916600.0 | 3815788.0 | 2667664.0 | 0.0 | 0.0 | 785082.0 | 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 | 304.0 | 0.0 | 0.0 | 1154673.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062266331788 | 16074062914887 | 16074063045288 | 16062266738929 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7fc078d53400 | 0x7fc075e25500 | 1291808 | 1185309 | 15281443 | 65536 | 88396317 | 161475 | 161475 | 12636069.0 | 11518784.0 | 11585719.0 | 10993708.0 | 0.0 | 0.0 | 9514848.0 | 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 | 419.0 | 0.0 | 0.0 | 562567.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062267027533 | 16074063077768 | 16074063170728 | 16062267382225 |
| 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 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7fc078d53280 | 0x7fc075e25540 | 2396944 | 2292751 | 29666351 | 65536 | 215906880 | 299617 | 299617 | 28184659.0 | 28174760.0 | 28181295.0 | 28180423.0 | 0.0 | 0.0 | 19856698.0 | 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 | 848.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062267669839 | 16074063196969 | 16074063377130 | 16062268110159 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7fc078d53100 | 0x7fc075e25580 | 2400464 | 2288659 | 29629617 | 65536 | 213380796 | 300057 | 300057 | 28234327.0 | 28223690.0 | 28068548.0 | 28066732.0 | 0.0 | 0.0 | 19841901.0 | 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 | 2204.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062268395623 | 16074063401610 | 16074063581291 | 16062268844193 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7fc0765fbf80 | 0x7fc075e255c0 | 1303968 | 1200698 | 15493319 | 65536 | 98049563 | 162995 | 162995 | 11026576.0 | 8537726.0 | 8550682.0 | 7423058.0 | 0.0 | 0.0 | 6404608.0 | 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 | 540.0 | 0.0 | 0.0 | 1164972.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062269130366 | 16074063606411 | 16074063702092 | 16062269489448 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7fc0765fbe00 | 0x7fc075e25600 | 1842968 | 1732163 | 22387466 | 65536 | 147360593 | 230370 | 230370 | 5778294.0 | 3841417.0 | 3596710.0 | 2502426.0 | 0.0 | 0.0 | 863884.0 | 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 | 1107702.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062269776332 | 16074063727052 | 16074063865453 | 16062270177133 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7fc0765fbc80 | 0x7fc075e25640 | 1297328 | 1187950 | 15309922 | 65536 | 87241452 | 162165 | 162165 | 12375085.0 | 11049110.0 | 11439268.0 | 10832406.0 | 0.0 | 0.0 | 10463544.0 | 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 | 351.0 | 0.0 | 0.0 | 652638.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062270469487 | 16074063898573 | 16074063992973 | 16062270827319 |
| 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 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7fc0765fbb00 | 0x7fc075e25680 | 2388080 | 2282004 | 29562901 | 65536 | 199962724 | 298509 | 298509 | 28090564.0 | 28083526.0 | 27913004.0 | 27911976.0 | 0.0 | 0.0 | 19735521.0 | 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 | 1592.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062271114052 | 16074064016974 | 16074064196175 | 16062271562212 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7fc0765fb980 | 0x7fc075e256c0 | 2387264 | 2283422 | 29562135 | 65536 | 209053308 | 298407 | 298407 | 28087934.0 | 28075074.0 | 27992681.0 | 27989511.0 | 0.0 | 0.0 | 19817235.0 | 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 | 2981.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062271848486 | 16074064219855 | 16074064400176 | 16062272295126 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7fc0765fb800 | 0x7fc075e25700 | 1305936 | 1202774 | 15523372 | 65536 | 97270409 | 163241 | 163241 | 10009229.0 | 7349641.0 | 6959202.0 | 5570524.0 | 0.0 | 0.0 | 5065959.0 | 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 | 1264891.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062272581310 | 16074064423696 | 16074064520497 | 16062272944172 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7fc0765fb680 | 0x7fc075e25740 | 1919312 | 1811367 | 23417126 | 65536 | 159243718 | 239913 | 239913 | 5661097.0 | 3763950.0 | 3589980.0 | 2503661.0 | 0.0 | 0.0 | 620386.0 | 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 | 323.0 | 0.0 | 0.0 | 1108650.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062273230445 | 16074064548337 | 16074064693458 | 16062273636066 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7fc078d53500 | 0x7fc075e25780 | 1292952 | 1190544 | 15355419 | 65536 | 97508464 | 161618 | 161618 | 12457170.0 | 10921186.0 | 10690287.0 | 9991690.0 | 0.0 | 0.0 | 9004002.0 | 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 | 492.0 | 0.0 | 0.0 | 722216.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062273927900 | 16074064727058 | 16074064822579 | 16062274279152 |
| 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 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7fc078d53380 | 0x7fc075e257c0 | 2397048 | 2283912 | 29541817 | 65536 | 194147383 | 299630 | 299630 | 28123827.0 | 28108648.0 | 28050943.0 | 28044887.0 | 0.0 | 0.0 | 19714047.0 | 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 | 5686.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062274568146 | 16074064848499 | 16074065029300 | 16062275013326 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7fc078d53200 | 0x7fc075e25800 | 2387088 | 2278510 | 29501019 | 65536 | 188832879 | 298385 | 298385 | 27940763.0 | 27876114.0 | 27940265.0 | 27935133.0 | 0.0 | 0.0 | 19620907.0 | 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 | 9002.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062275299179 | 16074065054580 | 16074065234901 | 16062275743150 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7fc078d53080 | 0x7fc075e25840 | 1366816 | 1264500 | 16317186 | 65536 | 105097383 | 170851 | 170851 | 9221584.0 | 6715364.0 | 6150253.0 | 4941597.0 | 0.0 | 0.0 | 3830521.0 | 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 | 375.0 | 0.0 | 0.0 | 1210606.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062276029263 | 16074065258421 | 16074065358102 | 16062276397855 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7fc0765fbf00 | 0x7fc075e25880 | 2074944 | 1965989 | 25371301 | 65536 | 170805714 | 259367 | 259367 | 4586769.0 | 3295628.0 | 3131579.0 | 2432813.0 | 0.0 | 0.0 | 595428.0 | 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 | 440.0 | 0.0 | 0.0 | 697532.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062276685539 | 16074065385622 | 16074065541783 | 16062277102849 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7fc0765fbd80 | 0x7fc075e258c0 | 1289568 | 1187596 | 15302122 | 65536 | 97882491 | 161195 | 161195 | 11288497.0 | 9286856.0 | 9084124.0 | 8031059.0 | 0.0 | 0.0 | 7207790.0 | 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 | 475.0 | 0.0 | 0.0 | 1016003.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062277396263 | 16074065576983 | 16074065672024 | 16062277748095 |
| 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 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7fc0765fbc00 | 0x7fc075e25900 | 2366072 | 2257109 | 29203601 | 65536 | 195351670 | 295758 | 295758 | 27810924.0 | 27775616.0 | 27808255.0 | 27800305.0 | 0.0 | 0.0 | 19458902.0 | 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 | 6.0 | 0.0 | 0.0 | 7740.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062278033499 | 16074065697944 | 16074065878105 | 16062278492419 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7fc0765fba80 | 0x7fc075e25940 | 2365256 | 2258448 | 29247345 | 65536 | 202711509 | 295656 | 295656 | 27821495.0 | 27808859.0 | 27879002.0 | 27876213.0 | 0.0 | 0.0 | 19635300.0 | 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 | 6.0 | 0.0 | 0.0 | 3720.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062278779162 | 16074065905305 | 16074066085626 | 16062279225542 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7fc0765fb900 | 0x7fc075e25980 | 1439128 | 1325508 | 17096595 | 65536 | 102045165 | 179890 | 179890 | 8078387.0 | 5252680.0 | 4912302.0 | 3524791.0 | 0.0 | 0.0 | 2218619.0 | 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 | 205.0 | 0.0 | 0.0 | 1374569.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062279512006 | 16074066112666 | 16074066220027 | 16062279884548 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7fc0765fb780 | 0x7fc075e259c0 | 2243160 | 2129508 | 27530462 | 65536 | 186617394 | 280394 | 280394 | 4545190.0 | 3271586.0 | 3129136.0 | 2436059.0 | 0.0 | 0.0 | 564633.0 | 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 | 519.0 | 0.0 | 0.0 | 700457.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062280170681 | 16074066244827 | 16074066415868 | 16062280606172 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7fc0765fb600 | 0x7fc075e25a00 | 1313336 | 1211145 | 15617360 | 65536 | 100684086 | 164166 | 164166 | 10209635.0 | 7893938.0 | 7508352.0 | 6171443.0 | 0.0 | 0.0 | 4441307.0 | 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 | 339.0 | 0.0 | 0.0 | 1322063.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062280898935 | 16074066450268 | 16074066546269 | 16062281261077 |
| 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 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7fc078d53480 | 0x7fc075e25a40 | 2372456 | 2262264 | 29270775 | 65536 | 206167676 | 296556 | 296556 | 27640278.0 | 27624345.0 | 27678930.0 | 27674976.0 | 0.0 | 0.0 | 19334060.0 | 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 | 3789.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062281548551 | 16074066570109 | 16074066750270 | 16062281989071 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7fc078d53300 | 0x7fc075e25a80 | 2373328 | 2264112 | 29289976 | 65536 | 201533900 | 296665 | 296665 | 27802833.0 | 27780700.0 | 27698358.0 | 27693487.0 | 0.0 | 0.0 | 19419943.0 | 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 | 5.0 | 0.0 | 0.0 | 4303.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062282276865 | 16074066774430 | 16074066957152 | 16062282724075 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7fc078d53180 | 0x7fc075e25ac0 | 1493592 | 1386091 | 17873201 | 65536 | 110977863 | 186698 | 186698 | 8153191.0 | 5135069.0 | 4636981.0 | 3122686.0 | 0.0 | 0.0 | 1298829.0 | 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 | 174.0 | 0.0 | 0.0 | 1534938.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062283010698 | 16074066982112 | 16074067094112 | 16062283383230 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7fc078d53000 | 0x7fc075e25b00 | 2403704 | 2289985 | 29558936 | 65536 | 205889219 | 300462 | 300462 | 4525207.0 | 3264356.0 | 3136017.0 | 2433487.0 | 0.0 | 0.0 | 531585.0 | 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 | 482.0 | 0.0 | 0.0 | 682285.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062283669494 | 16074067118593 | 16074067299714 | 16062284112044 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7fc0765fbe80 | 0x7fc075e25b40 | 1370744 | 1266780 | 16330254 | 65536 | 103786859 | 171342 | 171342 | 8508036.0 | 5794989.0 | 5585074.0 | 4409160.0 | 0.0 | 0.0 | 2838780.0 | 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 | 337.0 | 0.0 | 0.0 | 1200122.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062284403858 | 16074067332194 | 16074067433954 | 16062284764560 |
| 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 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7fc0765fbd00 | 0x7fc075e25b80 | 2422688 | 2285133 | 29482657 | 65536 | 148904523 | 302835 | 302835 | 25055134.0 | 24219385.0 | 25800658.0 | 25618208.0 | 0.0 | 0.0 | 19201399.0 | 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 | 75.0 | 0.0 | 0.0 | 174964.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062285049903 | 16074067459235 | 16074067644836 | 16062285499913 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7fc0765fbb80 | 0x7fc075e25bc0 | 2384992 | 2263488 | 29230449 | 65536 | 176410680 | 298123 | 298123 | 27621218.0 | 27549102.0 | 27065966.0 | 26995586.0 | 0.0 | 0.0 | 19372525.0 | 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 | 21410.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062285785987 | 16074067668676 | 16074067855077 | 16062286190098 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7fc0765fba00 | 0x7fc075e25c00 | 1660192 | 1541896 | 19883839 | 65536 | 111179830 | 207523 | 207523 | 7010019.0 | 4369272.0 | 4189683.0 | 2818037.0 | 0.0 | 0.0 | 1434877.0 | 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 | 213.0 | 0.0 | 0.0 | 1363645.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062286476462 | 16074067878757 | 16074068001318 | 16062286873193 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7fc0765fb880 | 0x7fc075e25c40 | 2726128 | 2610926 | 33780239 | 65536 | 241147007 | 340765 | 340765 | 4555476.0 | 3230310.0 | 3084012.0 | 2419935.0 | 0.0 | 0.0 | 495131.0 | 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 | 359.0 | 0.0 | 0.0 | 663410.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062287158567 | 16074068026598 | 16074068233319 | 16062287649946 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7fc0765fb700 | 0x7fc075e25c80 | 1479888 | 1372472 | 17692864 | 65536 | 116346902 | 184985 | 184985 | 7825249.0 | 4983734.0 | 4540688.0 | 3147252.0 | 0.0 | 0.0 | 1382149.0 | 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 | 268.0 | 0.0 | 0.0 | 1411095.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062287923390 | 16074068279400 | 16074068390280 | 16062288292371 |
| 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 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7fc078d53580 | 0x7fc075e25cc0 | 2379120 | 2245711 | 28986726 | 65536 | 173433916 | 297389 | 297389 | 26503063.0 | 26125324.0 | 23390649.0 | 23011286.0 | 0.0 | 0.0 | 18877117.0 | 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 | 28.0 | 0.0 | 0.0 | 223085.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062288577655 | 16074068416520 | 16074068600522 | 16062289041325 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7fc078d53400 | 0x7fc075e25d00 | 2402296 | 2273397 | 29352809 | 65536 | 155112790 | 300286 | 300286 | 25235366.0 | 24398486.0 | 22690889.0 | 22171085.0 | 0.0 | 0.0 | 18146607.0 | 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 | 88.0 | 0.0 | 0.0 | 215594.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062289327318 | 16074068624682 | 16074068813483 | 16062289781548 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7fc078d53280 | 0x7fc075e25d40 | 1807560 | 1698018 | 21890679 | 65536 | 136810397 | 225944 | 225944 | 6760320.0 | 4132757.0 | 3750306.0 | 2344587.0 | 0.0 | 0.0 | 481895.0 | 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 | 132.0 | 0.0 | 0.0 | 1404783.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062290068452 | 16074068837483 | 16074068971564 | 16062290434454 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7fc078d53100 | 0x7fc075e25d80 | 3052600 | 2937631 | 37917259 | 65536 | 257817742 | 381574 | 381574 | 4538470.0 | 3201955.0 | 3051884.0 | 2399165.0 | 0.0 | 0.0 | 545502.0 | 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 | 333.0 | 0.0 | 0.0 | 655211.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062290720538 | 16074068997004 | 16074069229325 | 16062291241296 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7fc0765fbf80 | 0x7fc075e25dc0 | 1691560 | 1579406 | 20399511 | 65536 | 128314154 | 211444 | 211444 | 6723038.0 | 4312098.0 | 3916024.0 | 2407008.0 | 0.0 | 0.0 | 624793.0 | 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 | 177.0 | 0.0 | 0.0 | 1549325.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062291515050 | 16074069275406 | 16074069401806 | 16062291901561 |
| 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 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7fc0765fbe00 | 0x7fc075e25e00 | 2453600 | 2334428 | 30059283 | 65536 | 189754871 | 306699 | 306699 | 21705344.0 | 20841464.0 | 19667575.0 | 18957322.0 | 0.0 | 0.0 | 12294128.0 | 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 | 181.0 | 0.0 | 0.0 | 718482.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062292187145 | 16074069426447 | 16074069616528 | 16062292662894 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7fc0765fbc80 | 0x7fc075e25e40 | 2482768 | 2351077 | 30247880 | 65536 | 184534742 | 310345 | 310345 | 22402763.0 | 20919247.0 | 19424326.0 | 18660378.0 | 0.0 | 0.0 | 10485588.0 | 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 | 323.0 | 0.0 | 0.0 | 755474.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062292930319 | 16074069643568 | 16074069837009 | 16062293408158 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7fc0765fbb00 | 0x7fc075e25e80 | 2139000 | 2018549 | 26060362 | 65536 | 177103245 | 267374 | 267374 | 5081737.0 | 3357559.0 | 3137589.0 | 2288796.0 | 0.0 | 0.0 | 549815.0 | 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 | 99.0 | 0.0 | 0.0 | 890214.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062293671082 | 16074069862609 | 16074070022930 | 16062294101503 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7fc0765fb980 | 0x7fc075e25ec0 | 3692016 | 3578524 | 46312065 | 65536 | 340832283 | 461501 | 461501 | 4707899.0 | 3201680.0 | 3034197.0 | 2392502.0 | 0.0 | 0.0 | 581973.0 | 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 | 263.0 | 0.0 | 0.0 | 636005.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062294389676 | 16074070049170 | 16074070332852 | 16062294964853 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7fc0765fb800 | 0x7fc075e25f00 | 1953336 | 1840819 | 23756158 | 65536 | 161679758 | 244166 | 244166 | 7273033.0 | 4515253.0 | 4105775.0 | 2308896.0 | 0.0 | 0.0 | 441440.0 | 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 | 64.0 | 0.0 | 0.0 | 1778360.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062295236667 | 16074070409653 | 16074070559254 | 16062295649748 |
| 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 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7fc0765fb680 | 0x7fc075e25f40 | 2679968 | 2565013 | 33048074 | 65536 | 210370741 | 334995 | 334995 | 19171305.0 | 18019159.0 | 16688048.0 | 15712266.0 | 0.0 | 0.0 | 10076968.0 | 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 | 102.0 | 0.0 | 0.0 | 998542.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062295935112 | 16074070584214 | 16074070792855 | 16062296425311 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7fc078d53500 | 0x7fc075e25f80 | 2648040 | 2530812 | 32622896 | 65536 | 221861211 | 331004 | 331004 | 20714547.0 | 18301386.0 | 14194230.0 | 12835439.0 | 0.0 | 0.0 | 7517456.0 | 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 | 375.0 | 0.0 | 0.0 | 1279893.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062296691835 | 16074070856535 | 16074071065017 | 16062297185604 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7fc078d53380 | 0x7fc075e25fc0 | 2459608 | 2346659 | 30273219 | 65536 | 196414811 | 307450 | 307450 | 5130991.0 | 3384074.0 | 3183717.0 | 2272479.0 | 0.0 | 0.0 | 480682.0 | 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 | 128.0 | 0.0 | 0.0 | 854035.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062297453428 | 16074071126617 | 16074071312538 | 16062297904368 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7fc078d53200 | 0x7fc075e26000 | 4346064 | 4226939 | 54727364 | 65536 | 406655615 | 543257 | 543257 | 4586166.0 | 3223001.0 | 3008019.0 | 2408860.0 | 0.0 | 0.0 | 614159.0 | 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 | 224.0 | 0.0 | 0.0 | 593116.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062298192761 | 16074071336858 | 16074071671420 | 16062298768158 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7fc078d53080 | 0x7fc075e26040 | 2182456 | 2073437 | 26764405 | 65536 | 185220062 | 272806 | 272806 | 6735476.0 | 4410392.0 | 4043830.0 | 2369973.0 | 0.0 | 0.0 | 498008.0 | 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 | 1667668.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062299044982 | 16074071737501 | 16074071905182 | 16062299463753 |
| 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 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7fc0765fbf00 | 0x7fc075e26080 | 2943936 | 2816753 | 36266531 | 65536 | 237867322 | 367991 | 367991 | 17208921.0 | 15807715.0 | 14559286.0 | 13371205.0 | 0.0 | 0.0 | 7165912.0 | 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 | 132.0 | 0.0 | 0.0 | 1184260.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062299748327 | 16074071929662 | 16074072157983 | 16062300267305 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7fc0765fbd80 | 0x7fc075e260c0 | 2935784 | 2820994 | 36290137 | 65536 | 253828025 | 366972 | 366972 | 19279749.0 | 15994844.0 | 13177685.0 | 11559728.0 | 0.0 | 0.0 | 6468850.0 | 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 | 218.0 | 0.0 | 0.0 | 1599651.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062300536889 | 16074072216544 | 16074072445665 | 16062301050798 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7fc0765fbc00 | 0x7fc075e26100 | 2778376 | 2669269 | 34503938 | 65536 | 246740341 | 347296 | 347296 | 5242753.0 | 3461098.0 | 3171743.0 | 2270769.0 | 0.0 | 0.0 | 458416.0 | 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 | 112.0 | 0.0 | 0.0 | 898593.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062301320582 | 16074072505825 | 16074072717187 | 16062301817731 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7fc0765fba80 | 0x7fc075e26140 | 5251640 | 5101501 | 65541697 | 65536 | 386213685 | 656454 | 656454 | 4817317.0 | 3335744.0 | 3032420.0 | 2436882.0 | 0.0 | 0.0 | 652536.0 | 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 | 222.0 | 0.0 | 0.0 | 595186.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062302093565 | 16074072776227 | 16074073161989 | 16062302686482 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7fc0765fb900 | 0x7fc075e26180 | 2433144 | 2318372 | 29928326 | 65536 | 203010694 | 304142 | 304142 | 6809355.0 | 4415319.0 | 4064760.0 | 2354013.0 | 0.0 | 0.0 | 492823.0 | 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 | 202.0 | 0.0 | 0.0 | 1716925.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062302932926 | 16074073204070 | 16074073391111 | 16062303472154 |
| 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 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7fc0765fb780 | 0x7fc075e261c0 | 3457936 | 3324197 | 42783699 | 65536 | 267200046 | 432241 | 432241 | 15480159.0 | 13921885.0 | 12973702.0 | 11607249.0 | 0.0 | 0.0 | 5346425.0 | 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 | 1369462.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062303756588 | 16074073416551 | 16074073665832 | 16062304164399 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7fc0765fb600 | 0x7fc075e26200 | 3243320 | 3077611 | 39713445 | 65536 | 225981051 | 405414 | 405414 | 16190810.0 | 12420143.0 | 8939421.0 | 7122115.0 | 0.0 | 0.0 | 2043121.0 | 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 | 271.0 | 0.0 | 0.0 | 1822383.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062304452302 | 16074073700713 | 16074073949834 | 16062304884933 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7fc078d53480 | 0x7fc075e26240 | 3395752 | 3234675 | 41552929 | 65536 | 246111200 | 424468 | 424468 | 4953063.0 | 3384732.0 | 3229743.0 | 2319191.0 | 0.0 | 0.0 | 447370.0 | 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 | 109.0 | 0.0 | 0.0 | 895682.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062305173496 | 16074073984714 | 16074074221676 | 16062305589787 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7fc078d53300 | 0x7fc075e26280 | 5759352 | 5639840 | 72946396 | 65536 | 534220595 | 719918 | 719918 | 15203739.0 | 6849840.0 | 5940179.0 | 2131829.0 | 0.0 | 0.0 | 106004.0 | 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 | 4.0 | 0.0 | 0.0 | 3815923.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062305879371 | 16074074257516 | 16074074712399 | 16062306622674 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7fc078d53180 | 0x7fc075e262c0 | 2913704 | 2802396 | 36218458 | 65536 | 255249261 | 364212 | 364212 | 7140036.0 | 4465077.0 | 4111146.0 | 2355318.0 | 0.0 | 0.0 | 448388.0 | 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 | 162.0 | 0.0 | 0.0 | 1781065.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062306896658 | 16074074781359 | 16074075006961 | 16062307436676 |
| 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 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7fc078d53000 | 0x7fc075e26300 | 3747792 | 3640079 | 47127425 | 65536 | 349720865 | 468473 | 468473 | 14498059.0 | 11721237.0 | 9215039.0 | 7616303.0 | 0.0 | 0.0 | 1912125.0 | 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 | 361.0 | 0.0 | 0.0 | 1657163.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062307704880 | 16074075065521 | 16074075365043 | 16062308326336 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7fc0765fbe80 | 0x7fc075e26340 | 3770912 | 3663271 | 47363193 | 65536 | 347586066 | 471363 | 471363 | 13836964.0 | 11940376.0 | 9867619.0 | 8628268.0 | 0.0 | 0.0 | 2591567.0 | 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 | 1225996.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062308592941 | 16074075423603 | 16074075722005 | 16062309215027 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7fc0765fbd00 | 0x7fc075e26380 | 3862856 | 3754082 | 48563813 | 65536 | 359417791 | 482856 | 482856 | 14714593.0 | 6815297.0 | 5929637.0 | 2139164.0 | 0.0 | 0.0 | 84862.0 | 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 | 3791241.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062309481801 | 16074075782805 | 16074076079607 | 16062310116447 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7fc0765fbb80 | 0x7fc075e263c0 | 7050168 | 6929271 | 89691906 | 65536 | 675855954 | 881270 | 881270 | 14824130.0 | 6715913.0 | 5820546.0 | 2144102.0 | 0.0 | 0.0 | 93951.0 | 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 | 3685350.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062310370211 | 16074076138488 | 16074076696411 | 16062311214302 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7fc0765fba00 | 0x7fc075e26400 | 3423624 | 3309238 | 42766965 | 65536 | 306849347 | 427952 | 427952 | 6096381.0 | 3827708.0 | 3476413.0 | 2265019.0 | 0.0 | 0.0 | 309060.0 | 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 | 94.0 | 0.0 | 0.0 | 1225152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062311476547 | 16074076762971 | 16074077027133 | 16062312017715 |
| 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 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7fc0765fb880 | 0x7fc075e26440 | 4398440 | 4289443 | 55515245 | 65536 | 408617356 | 549804 | 549804 | 14071336.0 | 11741197.0 | 9755978.0 | 8396203.0 | 0.0 | 0.0 | 2197714.0 | 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 | 166.0 | 0.0 | 0.0 | 1342967.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062312272009 | 16074077087133 | 16074077438015 | 16062312888015 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7fc0765fb700 | 0x7fc075e26480 | 4407928 | 4300809 | 55666361 | 65536 | 414022753 | 550990 | 550990 | 13687519.0 | 11394080.0 | 9891600.0 | 8714155.0 | 0.0 | 0.0 | 2482442.0 | 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 | 1135516.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062313159849 | 16074077498016 | 16074077848578 | 16062313780046 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7fc078d53580 | 0x7fc075e264c0 | 4509480 | 4393891 | 56852082 | 65536 | 411624261 | 563684 | 563684 | 15032838.0 | 6857246.0 | 5960278.0 | 2136812.0 | 0.0 | 0.0 | 74428.0 | 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 | 3820167.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062314051240 | 16074077885378 | 16074078232420 | 16062314704905 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7fc078d53400 | 0x7fc075e26500 | 8340104 | 8226145 | 106540703 | 65536 | 803033025 | 1042512 | 1042512 | 14723012.0 | 6658731.0 | 5796156.0 | 2142772.0 | 0.0 | 0.0 | 72259.0 | 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 | 3635235.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062314971939 | 16074078298501 | 16074078958825 | 16062315913538 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7fc078d53280 | 0x7fc075e26540 | 5769432 | 5658598 | 73268767 | 65536 | 550955074 | 721178 | 721178 | 15143177.0 | 6853537.0 | 5936149.0 | 2138223.0 | 0.0 | 0.0 | 84547.0 | 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 | 3810649.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062316191942 | 16074079033225 | 16074079479628 | 16062316901546 |
| 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 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7fc078d53100 | 0x7fc075e26580 | 5790032 | 5674375 | 73459433 | 65536 | 540737989 | 723753 | 723753 | 20866568.0 | 13109639.0 | 6822377.0 | 2952491.0 | 0.0 | 0.0 | 868390.0 | 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 | 103.0 | 0.0 | 0.0 | 3866101.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062317169200 | 16074079544428 | 16074080009071 | 16062317929384 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7fc0765fbf80 | 0x7fc075e265c0 | 5782200 | 5663434 | 73311878 | 65536 | 545142830 | 722774 | 722774 | 20808019.0 | 13013260.0 | 6800880.0 | 2940219.0 | 0.0 | 0.0 | 783396.0 | 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 | 96.0 | 0.0 | 0.0 | 3856855.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062318197908 | 16074080074192 | 16074080536914 | 16062318952351 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7fc0765fbe00 | 0x7fc075e26600 | 5804144 | 5693671 | 73721248 | 65536 | 553645457 | 725517 | 725517 | 15147944.0 | 6856691.0 | 5934484.0 | 2138830.0 | 0.0 | 0.0 | 74795.0 | 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 | 3808732.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062319219995 | 16074080612115 | 16074081063958 | 16062319963488 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7fc0765fbc80 | 0x7fc075e26640 | 10939272 | 10816062 | 140126834 | 65536 | 1063621976 | 1367408 | 1367408 | 14832823.0 | 6703186.0 | 5839659.0 | 2142023.0 | 0.0 | 0.0 | 104593.0 | 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 | 3698552.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062320231783 | 16074081128438 | 16074081998043 | 16062321386957 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7fc0765fbb00 | 0x7fc075e26680 | 10966264 | 10847842 | 140545112 | 65536 | 1076662540 | 1370782 | 1370782 | 15227797.0 | 6825233.0 | 5884605.0 | 2135516.0 | 0.0 | 0.0 | 85448.0 | 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 | 3767874.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062321661291 | 16074082066844 | 16074082919809 | 16062322793916 |
| 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 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7fc0765fb980 | 0x7fc075e266c0 | 11002344 | 10862148 | 140751434 | 65536 | 1074762656 | 1375292 | 1375292 | 21340963.0 | 13157044.0 | 6813690.0 | 2907729.0 | 0.0 | 0.0 | 701756.0 | 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 | 90.0 | 0.0 | 0.0 | 3901670.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062323057040 | 16074082993569 | 16074083878375 | 16062324222804 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7fc0765fb800 | 0x7fc075e26700 | 10981256 | 10858846 | 140590862 | 65536 | 1059250530 | 1372656 | 1372656 | 21210036.0 | 13057841.0 | 6772328.0 | 2887646.0 | 0.0 | 0.0 | 670880.0 | 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 | 3881853.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062324491768 | 16074083944935 | 16074084824621 | 16062325650192 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7fc0765fb680 | 0x7fc075e26740 | 11010504 | 10886835 | 141022321 | 65536 | 1076109790 | 1376312 | 1376312 | 15223473.0 | 6814236.0 | 5901577.0 | 2146253.0 | 0.0 | 0.0 | 69124.0 | 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 | 3756797.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062325918476 | 16074084897581 | 16074085757906 | 16062327072951 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7fc078d53500 | 0x7fc075e26780 | 21302032 | 21185828 | 274551863 | 65536 | 2122072440 | 2662753 | 2662753 | 14632844.0 | 6580338.0 | 5725169.0 | 2137888.0 | 0.0 | 0.0 | 97531.0 | 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 | 3582456.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062327334055 | 16074085823667 | 16074087520957 | 16062329340401 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7fc078d53380 | 0x7fc075e267c0 | 21356928 | 21227121 | 275073480 | 65536 | 2128980457 | 2669615 | 2669615 | 15820293.0 | 6928556.0 | 5992572.0 | 2140244.0 | 0.0 | 0.0 | 79034.0 | 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 | 3826011.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062329593135 | 16074087624318 | 16074089289608 | 16062331574551 |
| 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 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7fc078d53200 | 0x7fc075e26800 | 21361384 | 21241610 | 275249396 | 65536 | 2119677078 | 2670172 | 2670172 | 22060503.0 | 13320733.0 | 6719084.0 | 2777787.0 | 0.0 | 0.0 | 679505.0 | 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 | 75.0 | 0.0 | 0.0 | 3939982.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062331791486 | 16074089389128 | 16074091114099 | 16062333853680 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7fc078d53080 | 0x7fc075e26840 | 21382912 | 21238194 | 275188163 | 65536 | 2117674060 | 2672863 | 2672863 | 22081011.0 | 13307722.0 | 6725493.0 | 2789999.0 | 0.0 | 0.0 | 688617.0 | 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 | 106.0 | 0.0 | 0.0 | 3937880.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 16062334085785 | 16074091204019 | 16074092919390 | 16062336181189 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7fc0765fbf00 | 0x7fc075e26880 | 21401512 | 21267965 | 275539403 | 65536 | 2115533646 | 2675188 | 2675188 | 15893170.0 | 6954678.0 | 5959077.0 | 2132744.0 | 0.0 | 0.0 | 73317.0 | 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 | 3835899.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062336391514 | 16074093006910 | 16074094681001 | 16062338410849 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 145593 | 145593 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7fc0765fbd80 | 0x7fc075e268c0 | 42062464 | 41928568 | 543397042 | 65536 | 4223391203 | 5257807 | 5257807 | 14553106.0 | 6578315.0 | 5729123.0 | 2148818.0 | 0.0 | 0.0 | 101825.0 | 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 | 3576754.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 16062338626925 | 16074094769961 | 16074098127102 | 16062342339862 |