101 KiB
101 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | SQ_INSTS_VMEM_WR | SQ_INSTS_VMEM_RD | SQ_INSTS_VMEM | SQ_INSTS_SALU | SQ_INSTS_VSKIPPED | SQ_INSTS_SMEM | SQ_INSTS_FLAT | SQ_INSTS_LDS | GRBM_COUNT | GRBM_GUI_ACTIVE | SQ_INSTS_GDS | SQ_INSTS_EXP_GDS | SQ_INSTS_BRANCH | SQ_INSTS_SENDMSG | SQ_INSTS | SQ_WAVE_CYCLES | SQ_WAIT_ANY | SQ_WAIT_INST_ANY | SQ_ACTIVE_INST_ANY | SQ_CYCLES | SQ_BUSY_CYCLES | SQ_BUSY_CU_CYCLES | SQ_INSTS_VALU | SQ_ACTIVE_INST_VMEM | SQ_ACTIVE_INST_LDS | SQ_ACTIVE_INST_VALU | SQ_ACTIVE_INST_SCA | SQ_ACTIVE_INST_EXP_GDS | SQ_ACTIVE_INST_MISC | SQ_ACTIVE_INST_FLAT | SQ_INST_CYCLES_VMEM_WR | SQ_INST_CYCLES_VMEM_RD | SQ_INST_CYCLES_SMEM | SQ_INST_CYCLES_SALU | SQ_THREAD_CYCLES_VALU | SQ_IFETCH | SQ_LDS_BANK_CONFLICT | SQ_LDS_ADDR_CONFLICT | SQ_LDS_UNALIGNED_STALL | SQ_WAVES | SQ_WAVES_EQ_64 | SQ_WAVES_LT_64 | SQ_WAVES_LT_48 | SQ_WAVES_LT_32 | SQ_WAVES_LT_16 | SQ_ITEMS | SQ_LDS_MEM_VIOLATIONS | SQ_LDS_ATOMIC_RETURN | SQ_LDS_IDX_ACTIVE | SQ_WAVES_RESTORED | SQ_WAVES_SAVED | SQ_INSTS_SMEM_NORM | SQC_TC_INST_REQ | SQC_TC_DATA_READ_REQ | SQC_TC_DATA_WRITE_REQ | SQC_TC_DATA_ATOMIC_REQ | SQC_TC_STALL | SQC_TC_REQ | SQC_DCACHE_REQ_READ_16 | SQC_ICACHE_REQ | SQC_ICACHE_HITS | SQC_ICACHE_MISSES | SQC_ICACHE_MISSES_DUPLICATE | SQC_DCACHE_INPUT_VALID_READYB | SQC_DCACHE_ATOMIC | SQC_DCACHE_REQ_READ_8 | SQC_DCACHE_REQ | SQC_DCACHE_HITS | SQC_DCACHE_MISSES | SQC_DCACHE_MISSES_DUPLICATE | SQC_DCACHE_REQ_READ_1 | SQC_DCACHE_REQ_READ_2 | SQC_DCACHE_REQ_READ_4 | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBuffer.kd | 0 | 0 | 0 | 853819 | 853824 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7f1b60404180 | 1048576 | 0 | 1048576 | 9437184 | 0 | 4194304 | 1048576 | 0 | 506136 | 506136 | 0 | 0 | 3145728 | 524288 | 32505856 | 372897729 | 219252809 | 121139064 | 32505856 | 3988240 | 3782833 | 56584058 | 11534336 | 0 | 0 | 14155776 | 13631488 | 0 | 3670016 | 1048576 | 1048576 | 0 | 4194304 | 9437184 | 905969664 | 6291456 | 0 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 0 | 33554432 | 0 | 0 | 0 | 0 | 0 | 8388608 | 336 | 144 | 0 | 0 | 0 | 480 | 0 | 6291456 | 6289253 | 96 | 2781 | 1912049 | 0 | 0 | 4194304 | 4189858 | 144 | 4302 | 2097152 | 524288 | 1572864 | 12074919163373650 | 12074933586686810 | 12074933587013047 | 12074919407253238 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 853819 | 853824 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7f1b60435100 | 0 | 4096 | 4096 | 512 | 0 | 512 | 4096 | 0 | 28186 | 28186 | 0 | 0 | 512 | 512 | 35328 | 1129873 | 1079015 | 14506 | 36352 | 223152 | 72770 | 1012626 | 26624 | 0 | 0 | 30208 | 1024 | 0 | 1024 | 4096 | 0 | 4096 | 512 | 512 | 1933312 | 8192 | 0 | 0 | 0 | 512 | 512 | 0 | 0 | 0 | 0 | 32768 | 0 | 0 | 0 | 0 | 0 | 1024 | 432 | 48 | 0 | 0 | 0 | 480 | 0 | 8192 | 6651 | 48 | 1493 | 1094 | 0 | 0 | 512 | 0 | 48 | 464 | 0 | 512 | 0 | 12074919421505183 | 12074933601700471 | 12074933601707191 | 12074919421845866 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7f1c6c05c900 | 0x7f1b60435140 | 0 | 524288 | 524288 | 65536 | 0 | 65536 | 524288 | 0 | 219929 | 219929 | 0 | 0 | 65536 | 65536 | 4128768 | 147222780 | 54345681 | 88617259 | 4259840 | 1833112 | 1640220 | 24320186 | 3014656 | 0 | 0 | 3473408 | 131072 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 65536 | 222298112 | 917504 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 384 | 48 | 0 | 0 | 0 | 432 | 0 | 917504 | 914733 | 66 | 5340 | 221761 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 65536 | 0 | 12074919421917469 | 12074933601773270 | 12074933601904149 | 12074919422312564 |
| 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 | 6 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7f1c6c05c800 | 0x7f1b60435180 | 0 | 524288 | 524288 | 917504 | 0 | 65536 | 524288 | 0 | 398435 | 398435 | 0 | 0 | 131072 | 65536 | 6291456 | 235933124 | 55578777 | 173931819 | 6422528 | 3123160 | 2926830 | 43689567 | 4259840 | 0 | 0 | 4718592 | 983040 | 0 | 196608 | 524288 | 0 | 524288 | 65536 | 917504 | 301989888 | 1245184 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 480 | 48 | 0 | 0 | 0 | 528 | 0 | 1245184 | 1240494 | 48 | 7650 | 224551 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 65536 | 0 | 12074919422397381 | 12074933601967829 | 12074933602211026 | 12074919422914422 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7f1c6c05c700 | 0x7f1b604351c0 | 0 | 524288 | 524288 | 65536 | 0 | 65536 | 524288 | 0 | 395697 | 395697 | 0 | 0 | 65536 | 65536 | 4128768 | 266429586 | 105085670 | 156755050 | 4588680 | 3163864 | 2992485 | 44708874 | 3014656 | 0 | 0 | 3802248 | 131072 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 65536 | 243269632 | 983040 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 384 | 48 | 0 | 0 | 0 | 432 | 0 | 983040 | 979878 | 48 | 3335 | 241041 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 65536 | 0 | 12074919422948005 | 12074933602351825 | 12074933602597903 | 12074919423485874 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7f1c6c05c600 | 0x7f1b60435200 | 0 | 524288 | 524288 | 131072 | 0 | 65536 | 524288 | 0 | 220115 | 220115 | 0 | 0 | 65536 | 65536 | 4653056 | 138689867 | 49739293 | 84166446 | 4784128 | 1815192 | 1640038 | 24302570 | 3473408 | 0 | 0 | 3932160 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 251658240 | 1048576 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 432 | 48 | 0 | 0 | 0 | 480 | 0 | 1048576 | 1045669 | 48 | 7702 | 219475 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 65536 | 0 | 12074919423511181 | 12074933602732462 | 12074933602858380 | 12074919423863115 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7f1c6c05c500 | 0x7f1b60435240 | 0 | 524288 | 524288 | 65536 | 0 | 65536 | 524288 | 0 | 222153 | 222153 | 0 | 0 | 65536 | 65536 | 4259840 | 139060765 | 49998686 | 84409023 | 4653056 | 1791704 | 1618848 | 23988002 | 3145728 | 0 | 0 | 3866624 | 131072 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 65536 | 247463936 | 983040 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 432 | 48 | 0 | 0 | 0 | 480 | 0 | 983040 | 980289 | 48 | 7401 | 227435 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 65536 | 0 | 12074919423928747 | 12074933602902060 | 12074933603026859 | 12074919424271965 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7f1c6c05c400 | 0x7f1b60435280 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 217099 | 217099 | 0 | 0 | 65536 | 65536 | 4915200 | 164424727 | 54030135 | 105544928 | 4849664 | 1774808 | 1606316 | 23802910 | 3538944 | 0 | 0 | 3997696 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 255852544 | 1048576 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 432 | 48 | 0 | 0 | 0 | 480 | 0 | 1048576 | 1046068 | 48 | 4985 | 229619 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919424365368 | 12074933603098378 | 12074933603223017 | 12074919424690342 |
| 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 | 16 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7f1c6c05c300 | 0x7f1b604352c0 | 0 | 524288 | 524288 | 917504 | 0 | 131072 | 524288 | 0 | 402313 | 402313 | 0 | 0 | 131072 | 65536 | 8781824 | 362657372 | 119183222 | 234888934 | 8585216 | 3274200 | 3099381 | 46266165 | 6356992 | 0 | 0 | 6815744 | 1048576 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 917504 | 436207616 | 1572864 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 624 | 48 | 0 | 0 | 0 | 672 | 0 | 1572864 | 1569424 | 112 | 7892 | 215296 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074919424753400 | 12074933603266857 | 12074933603522214 | 12074919425256204 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7f1c6c05ca00 | 0x7f1b60435300 | 0 | 524288 | 524288 | 65536 | 0 | 65536 | 524288 | 0 | 387931 | 387931 | 0 | 0 | 65536 | 65536 | 5373952 | 258028668 | 103921883 | 147991247 | 6116906 | 3249688 | 3070471 | 45756925 | 3997696 | 0 | 0 | 5330474 | 131072 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 65536 | 339738624 | 1179648 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 480 | 48 | 0 | 0 | 0 | 528 | 0 | 1179648 | 1177577 | 48 | 3515 | 228653 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074919425296910 | 12074933603652773 | 12074933603898851 | 12074919425800926 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7f1c6c05c900 | 0x7f1b60435340 | 0 | 524288 | 524288 | 131072 | 0 | 131072 | 524288 | 0 | 215097 | 215097 | 0 | 0 | 65536 | 65536 | 5439488 | 159712419 | 51882836 | 102455631 | 5373952 | 1701784 | 1526206 | 22608192 | 3997696 | 0 | 0 | 4456448 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 285212672 | 1114112 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 480 | 48 | 0 | 0 | 0 | 528 | 0 | 1114112 | 1111494 | 48 | 5907 | 198521 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919425825853 | 12074933604035330 | 12074933604159808 | 12074919426175122 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7f1c6c05c800 | 0x7f1b60435380 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 218027 | 218027 | 0 | 0 | 65536 | 65536 | 5570560 | 144925951 | 48120699 | 90513796 | 6291456 | 1749976 | 1578769 | 23339395 | 4194304 | 0 | 0 | 5439488 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 348127232 | 1114112 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 480 | 48 | 0 | 0 | 0 | 528 | 0 | 1114112 | 1111430 | 48 | 4861 | 253255 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919426230875 | 12074933604204288 | 12074933604329087 | 12074919426569294 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7f1c6c05c700 | 0x7f1b604353c0 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 213409 | 213409 | 0 | 0 | 65536 | 65536 | 5439488 | 160394231 | 54116748 | 100903531 | 5373952 | 1718744 | 1547991 | 22952634 | 4063232 | 0 | 0 | 4521984 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 289406976 | 1179648 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 480 | 48 | 0 | 0 | 0 | 528 | 0 | 1179648 | 1177114 | 48 | 4655 | 283051 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919426648151 | 12074933604382206 | 12074933604506685 | 12074919426963346 |
| 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 | 26 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7f1c6c05c600 | 0x7f1b60435400 | 0 | 524288 | 524288 | 917504 | 0 | 131072 | 524288 | 0 | 405723 | 405723 | 0 | 0 | 131072 | 65536 | 10813440 | 242901227 | 111641762 | 120577097 | 10682368 | 3289048 | 3110398 | 46296066 | 8454144 | 0 | 0 | 8912896 | 1048576 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 917504 | 570425344 | 1835008 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 720 | 48 | 0 | 0 | 0 | 768 | 0 | 1835008 | 1831767 | 96 | 7743 | 187665 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074919427032675 | 12074933604548125 | 12074933604792763 | 12074919427553734 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7f1c6c05c500 | 0x7f1b60435440 | 0 | 524288 | 524288 | 65536 | 0 | 65536 | 524288 | 0 | 392321 | 392321 | 0 | 0 | 65536 | 65536 | 5898240 | 319353959 | 111482552 | 200709513 | 7161590 | 3226968 | 3029889 | 45147945 | 4521984 | 0 | 0 | 6375158 | 131072 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 65536 | 406847488 | 1310720 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 528 | 48 | 0 | 0 | 0 | 576 | 0 | 1310720 | 1308551 | 48 | 3445 | 228372 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074919427577909 | 12074933604897402 | 12074933605142679 | 12074919428105910 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7f1c6c05c400 | 0x7f1b60435480 | 0 | 524288 | 524288 | 131072 | 0 | 131072 | 524288 | 0 | 214715 | 214715 | 0 | 0 | 65536 | 65536 | 5963776 | 157679730 | 54029420 | 97752070 | 5898240 | 1744664 | 1577578 | 23355961 | 4521984 | 0 | 0 | 4980736 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 318767104 | 1245184 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 528 | 48 | 0 | 0 | 0 | 576 | 0 | 1245184 | 1242655 | 48 | 4779 | 245972 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919428130776 | 12074933605245558 | 12074933605370517 | 12074919428472882 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7f1c6c05c300 | 0x7f1b604354c0 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 214513 | 214513 | 0 | 0 | 65536 | 65536 | 6619136 | 158227026 | 52095384 | 98267322 | 7864320 | 1820568 | 1651352 | 24498461 | 5242880 | 0 | 0 | 7012352 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 448790528 | 1310720 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 528 | 48 | 0 | 0 | 0 | 576 | 0 | 1310720 | 1308081 | 48 | 5030 | 265630 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919428538243 | 12074933605411797 | 12074933605537236 | 12074919428865331 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7f1c6c05ca00 | 0x7f1b60435500 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 209739 | 209739 | 0 | 0 | 65536 | 65536 | 5963776 | 153890542 | 54689996 | 93302306 | 5898240 | 1705048 | 1524886 | 22624382 | 4587520 | 0 | 0 | 5046272 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 322961408 | 1310720 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 528 | 48 | 0 | 0 | 0 | 576 | 0 | 1310720 | 1308206 | 48 | 4629 | 275437 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919428942344 | 12074933605589395 | 12074933605714194 | 12074919429273510 |
| 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 | 36 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7f1c6c05c900 | 0x7f1b60435540 | 0 | 524288 | 524288 | 917504 | 0 | 131072 | 524288 | 0 | 397441 | 397441 | 0 | 0 | 131072 | 65536 | 12976128 | 356522484 | 116723470 | 227019494 | 12779520 | 3103960 | 2935446 | 43835255 | 10551296 | 0 | 0 | 11010048 | 1048576 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 917504 | 704643072 | 2097152 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 816 | 48 | 0 | 0 | 0 | 864 | 0 | 2097152 | 2092428 | 96 | 9707 | 238440 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074919429338370 | 12074933605755474 | 12074933606001071 | 12074919429857525 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7f1c6c05c800 | 0x7f1b60435580 | 0 | 524288 | 524288 | 65536 | 0 | 65536 | 524288 | 0 | 399763 | 399763 | 0 | 0 | 65536 | 65536 | 6356992 | 264819473 | 110352999 | 146252280 | 8213031 | 3168984 | 2989436 | 44530246 | 5046272 | 0 | 0 | 7426599 | 131072 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 65536 | 473956352 | 1441792 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 576 | 48 | 0 | 0 | 0 | 624 | 0 | 1441792 | 1439338 | 48 | 3649 | 224660 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074919429881259 | 12074933606080271 | 12074933606324589 | 12074919430413608 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7f1c6c05c700 | 0x7f1b604355c0 | 0 | 524288 | 524288 | 131072 | 0 | 131072 | 524288 | 0 | 212177 | 212177 | 0 | 0 | 65536 | 65536 | 6488064 | 161470266 | 56190767 | 98856971 | 6422528 | 1758168 | 1590360 | 23503486 | 5046272 | 0 | 0 | 5505024 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 352321536 | 1376256 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 576 | 48 | 0 | 0 | 0 | 624 | 0 | 1376256 | 1373616 | 48 | 5059 | 292882 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919430437673 | 12074933606425068 | 12074933606550026 | 12074919430771954 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7f1c6c05c600 | 0x7f1b60435600 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 221355 | 221355 | 0 | 0 | 65536 | 65536 | 7667712 | 157703946 | 47758535 | 100508227 | 9437184 | 1813016 | 1627239 | 24166389 | 6291456 | 0 | 0 | 8585216 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 549453824 | 1507328 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 624 | 48 | 0 | 0 | 0 | 672 | 0 | 1507328 | 1504088 | 48 | 5372 | 249609 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919430834090 | 12074933606591306 | 12074933606716905 | 12074919431176436 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7f1c6c05c500 | 0x7f1b60435640 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 216473 | 216473 | 0 | 0 | 65536 | 65536 | 6488064 | 157274503 | 52991599 | 97860376 | 6422528 | 1774040 | 1574325 | 23367499 | 5111808 | 0 | 0 | 5570560 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 356515840 | 1441792 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 576 | 48 | 0 | 0 | 0 | 624 | 0 | 1441792 | 1438284 | 48 | 6002 | 256927 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919431255573 | 12074933606769064 | 12074933606892903 | 12074919431569536 |
| 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 | 46 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7f1c6c05c400 | 0x7f1b60435680 | 0 | 524288 | 524288 | 917504 | 0 | 131072 | 524288 | 0 | 399891 | 399891 | 0 | 0 | 131072 | 65536 | 15073280 | 274228208 | 97658311 | 161693225 | 14876672 | 3284504 | 3099629 | 46176499 | 12648448 | 0 | 0 | 13107200 | 1048576 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 917504 | 838860800 | 2359296 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 912 | 48 | 0 | 0 | 0 | 960 | 0 | 2359296 | 2356226 | 96 | 7761 | 245460 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074919431634998 | 12074933606935623 | 12074933607183781 | 12074919432147330 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7f1c6c05c300 | 0x7f1b604356c0 | 0 | 524288 | 524288 | 65536 | 0 | 65536 | 524288 | 0 | 397641 | 397641 | 0 | 0 | 65536 | 65536 | 6946816 | 252879708 | 105794756 | 137820826 | 9265896 | 3195544 | 3012981 | 44894827 | 5570560 | 0 | 0 | 8479464 | 131072 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 65536 | 541065216 | 1572864 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 624 | 48 | 0 | 0 | 0 | 672 | 0 | 1572864 | 1570445 | 48 | 3578 | 246076 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074919432177436 | 12074933607316899 | 12074933607561057 | 12074919432694206 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7f1c6c05ca00 | 0x7f1b60435700 | 0 | 524288 | 524288 | 131072 | 0 | 131072 | 524288 | 0 | 206219 | 206219 | 0 | 0 | 65536 | 65536 | 7012352 | 169595122 | 55176189 | 107472117 | 6946816 | 1688536 | 1518638 | 22586965 | 5570560 | 0 | 0 | 6029312 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 385875968 | 1507328 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 624 | 48 | 0 | 0 | 0 | 672 | 0 | 1507328 | 1504634 | 48 | 4821 | 257770 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919432717580 | 12074933607691136 | 12074933607814815 | 12074919433048284 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7f1c6c05c900 | 0x7f1b60435740 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 208241 | 208241 | 0 | 0 | 65536 | 65536 | 8716288 | 161517682 | 52462270 | 98045364 | 11010048 | 1734616 | 1562069 | 23126703 | 7340032 | 0 | 0 | 10158080 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 650117120 | 1703936 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 672 | 48 | 0 | 0 | 0 | 720 | 0 | 1703936 | 1701373 | 48 | 5731 | 235637 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919433114948 | 12074933607858654 | 12074933607984253 | 12074919433439161 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7f1c6c05c800 | 0x7f1b60435780 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 207371 | 207371 | 0 | 0 | 65536 | 65536 | 7012352 | 165244784 | 55178208 | 103119760 | 6946816 | 1743256 | 1565283 | 23252327 | 5636096 | 0 | 0 | 6094848 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 390070272 | 1572864 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 576 | 48 | 0 | 0 | 0 | 624 | 0 | 1572864 | 1570347 | 48 | 4948 | 248541 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919433515984 | 12074933608039933 | 12074933608164092 | 12074919433827943 |
| 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 | 56 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7f1c6c05c700 | 0x7f1b604357c0 | 0 | 524288 | 524288 | 917504 | 0 | 131072 | 524288 | 0 | 393345 | 393345 | 0 | 0 | 131072 | 65536 | 17170432 | 261044313 | 101866045 | 142204444 | 16973824 | 3259800 | 3084502 | 46027704 | 14745600 | 0 | 0 | 15204352 | 1048576 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 917504 | 973078528 | 2621440 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1008 | 48 | 0 | 0 | 0 | 1056 | 0 | 2621440 | 2617154 | 48 | 9084 | 229236 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074919433893876 | 12074933608206171 | 12074933608451609 | 12074919434415605 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7f1c6c05c600 | 0x7f1b60435800 | 0 | 524288 | 524288 | 65536 | 0 | 65536 | 524288 | 0 | 397259 | 397259 | 0 | 0 | 65536 | 65536 | 7471104 | 241955348 | 102931987 | 128709550 | 10316719 | 3185496 | 3006452 | 44891564 | 6094848 | 0 | 0 | 9530287 | 131072 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 65536 | 608174080 | 1703936 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 672 | 48 | 0 | 0 | 0 | 720 | 0 | 1703936 | 1701239 | 49 | 3915 | 220526 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074919434440382 | 12074933608537208 | 12074933608785366 | 12074919434958454 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7f1c6c05c500 | 0x7f1b60435840 | 0 | 524288 | 524288 | 131072 | 0 | 131072 | 524288 | 0 | 214825 | 214825 | 0 | 0 | 65536 | 65536 | 7536640 | 160604646 | 48082369 | 105051173 | 7471104 | 1775704 | 1608578 | 23823647 | 6094848 | 0 | 0 | 6553600 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 419430400 | 1638400 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 672 | 48 | 0 | 0 | 0 | 720 | 0 | 1638400 | 1634909 | 48 | 5743 | 249016 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919434983240 | 12074933608895925 | 12074933609020724 | 12074919435323563 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7f1c6c05c400 | 0x7f1b60435880 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 216211 | 216211 | 0 | 0 | 65536 | 65536 | 9764864 | 163619724 | 52374238 | 98662574 | 12582912 | 1760536 | 1591524 | 23486120 | 8388608 | 0 | 0 | 11730944 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 750780416 | 1900544 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 768 | 48 | 0 | 0 | 0 | 816 | 0 | 1900544 | 1896624 | 96 | 5869 | 243403 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919435387472 | 12074933609063603 | 12074933609189042 | 12074919435720661 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7f1c6c05c300 | 0x7f1b604358c0 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 217881 | 217881 | 0 | 0 | 65536 | 65536 | 7536640 | 162191830 | 53631792 | 101088934 | 7471104 | 1731032 | 1569960 | 23305886 | 6160384 | 0 | 0 | 6619136 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 423624704 | 1703936 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 672 | 48 | 0 | 0 | 0 | 720 | 0 | 1703936 | 1701278 | 48 | 4815 | 210326 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919435797303 | 12074933609242002 | 12074933609366640 | 12074919436111277 |
| 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 | 66 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7f1c6c05ca00 | 0x7f1b60435900 | 0 | 524288 | 524288 | 917504 | 0 | 131072 | 524288 | 0 | 395283 | 395283 | 0 | 0 | 131072 | 65536 | 19267584 | 259769762 | 98071023 | 142627763 | 19070976 | 3175512 | 3003535 | 44777905 | 16842752 | 0 | 0 | 17301504 | 1048576 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 917504 | 1107296256 | 2883584 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1104 | 48 | 0 | 0 | 0 | 1152 | 0 | 2883584 | 2877828 | 49 | 10545 | 140721 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074919436175516 | 12074933609408080 | 12074933609697997 | 12074919436685384 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7f1c6c05c900 | 0x7f1b60435940 | 0 | 524288 | 524288 | 65536 | 0 | 65536 | 524288 | 0 | 391577 | 391577 | 0 | 0 | 65536 | 65536 | 7995392 | 289822805 | 109402882 | 169050363 | 11369870 | 3184536 | 3001717 | 44810724 | 6619136 | 0 | 0 | 10583438 | 131072 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 65536 | 675282944 | 1835008 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 720 | 48 | 0 | 0 | 0 | 768 | 0 | 1835008 | 1832469 | 48 | 3713 | 189044 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074919436710190 | 12074933609786157 | 12074933610030314 | 12074919437226730 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7f1c6c05c800 | 0x7f1b60435980 | 0 | 524288 | 524288 | 131072 | 0 | 131072 | 524288 | 0 | 212283 | 212283 | 0 | 0 | 65536 | 65536 | 8060928 | 168804860 | 47242864 | 113566604 | 7995392 | 1825368 | 1632211 | 24182856 | 6619136 | 0 | 0 | 7077888 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 452984832 | 1769472 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 720 | 48 | 0 | 0 | 0 | 768 | 0 | 1769472 | 1763422 | 96 | 9293 | 195393 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919437251035 | 12074933610113834 | 12074933610239112 | 12074919437584775 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7f1c6c05c700 | 0x7f1b604359c0 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 214689 | 214689 | 0 | 0 | 65536 | 65536 | 10813440 | 171816673 | 47857894 | 109803003 | 14155776 | 1825944 | 1642219 | 24218527 | 9437184 | 0 | 0 | 13303808 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 851443712 | 2097152 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 816 | 48 | 0 | 0 | 0 | 864 | 0 | 2097152 | 2090419 | 48 | 9209 | 207915 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919437649405 | 12074933610280072 | 12074933610406311 | 12074919437975150 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7f1c6c05c600 | 0x7f1b60435a00 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 215875 | 215875 | 0 | 0 | 65536 | 65536 | 8060928 | 166712474 | 50611942 | 108105140 | 7995392 | 1712728 | 1535474 | 22722175 | 6684672 | 0 | 0 | 7143424 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 457179136 | 1835008 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 720 | 48 | 0 | 0 | 0 | 768 | 0 | 1835008 | 1831930 | 48 | 5227 | 221583 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919438052845 | 12074933610455910 | 12074933610580549 | 12074919438366738 |
| 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 | 76 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7f1c6c05c500 | 0x7f1b60435a40 | 0 | 524288 | 524288 | 917504 | 0 | 131072 | 524288 | 0 | 399193 | 399193 | 0 | 0 | 131072 | 65536 | 21364736 | 311145308 | 101895180 | 188082000 | 21168128 | 3271256 | 3073771 | 45804726 | 18939904 | 0 | 0 | 19398656 | 1048576 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 917504 | 1241513984 | 3145728 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1200 | 48 | 0 | 0 | 0 | 1248 | 0 | 3145728 | 3138955 | 96 | 11714 | 191400 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074919438423924 | 12074933610624069 | 12074933610871587 | 12074919438944502 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7f1c6c05c400 | 0x7f1b60435a80 | 0 | 524288 | 524288 | 65536 | 0 | 65536 | 524288 | 0 | 399043 | 399043 | 0 | 0 | 65536 | 65536 | 8519680 | 264299483 | 100710155 | 151165147 | 12424808 | 3194392 | 3019879 | 45026630 | 7143424 | 0 | 0 | 11638376 | 131072 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 65536 | 742391808 | 1966080 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 768 | 48 | 0 | 0 | 0 | 816 | 0 | 1966080 | 1962982 | 49 | 4851 | 186182 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074919438971292 | 12074933610925506 | 12074933611172704 | 12074919439497019 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7f1c6c05c300 | 0x7f1b60435ac0 | 0 | 524288 | 524288 | 131072 | 0 | 131072 | 524288 | 0 | 208737 | 208737 | 0 | 0 | 65536 | 65536 | 8585216 | 169548952 | 55185443 | 105843829 | 8519680 | 1745176 | 1565222 | 23176772 | 7143424 | 0 | 0 | 7602176 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 486539264 | 1900544 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 768 | 48 | 0 | 0 | 0 | 816 | 0 | 1900544 | 1895618 | 48 | 7162 | 209075 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919439523598 | 12074933611260543 | 12074933611385662 | 12074919439849103 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7f1c6c05ca00 | 0x7f1b60435b00 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 218251 | 218251 | 0 | 0 | 65536 | 65536 | 11862016 | 166071048 | 49461458 | 100880950 | 15728640 | 1763032 | 1583408 | 23347892 | 10485760 | 0 | 0 | 14876672 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 952107008 | 2293760 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 912 | 48 | 0 | 0 | 0 | 960 | 0 | 2293760 | 2289359 | 48 | 6792 | 209346 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919439912090 | 12074933611427421 | 12074933611553020 | 12074919440247493 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7f1c6c05c900 | 0x7f1b60435b40 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 210377 | 210377 | 0 | 0 | 65536 | 65536 | 8585216 | 165702274 | 49946965 | 107235629 | 8519680 | 1749528 | 1576894 | 23343381 | 7208960 | 0 | 0 | 7667712 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 490733568 | 1966080 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 768 | 48 | 0 | 0 | 0 | 816 | 0 | 1966080 | 1961584 | 96 | 6902 | 198859 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919440324416 | 12074933611603900 | 12074933611728539 | 12074919440631627 |
| 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 | 86 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7f1c6c05c800 | 0x7f1b60435b80 | 0 | 524288 | 524288 | 917504 | 0 | 131072 | 524288 | 0 | 410123 | 410123 | 0 | 0 | 131072 | 65536 | 23461888 | 290558473 | 147932482 | 119360711 | 23265280 | 3316440 | 3142416 | 46756729 | 21037056 | 0 | 0 | 21495808 | 1048576 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 917504 | 1375731712 | 3407872 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1296 | 48 | 0 | 0 | 0 | 1344 | 0 | 3407872 | 3403860 | 48 | 8724 | 189792 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074919440695426 | 12074933611769338 | 12074933612030456 | 12074919441210573 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7f1c6c05c700 | 0x7f1b60435bc0 | 0 | 524288 | 524288 | 65536 | 0 | 65536 | 524288 | 0 | 390105 | 390105 | 0 | 0 | 65536 | 65536 | 9043968 | 343301055 | 106543129 | 223282307 | 13481876 | 3259160 | 3059381 | 45624400 | 7667712 | 0 | 0 | 12695444 | 131072 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 65536 | 809500672 | 2097152 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 816 | 48 | 0 | 0 | 0 | 864 | 0 | 2097152 | 2092687 | 48 | 5971 | 185092 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074919441235459 | 12074933612091415 | 12074933612375093 | 12074919441751649 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7f1c6c05c600 | 0x7f1b60435c00 | 0 | 524288 | 524288 | 131072 | 0 | 131072 | 524288 | 0 | 214843 | 214843 | 0 | 0 | 65536 | 65536 | 9109504 | 170874722 | 49588781 | 112241973 | 9043968 | 1723096 | 1553818 | 22986483 | 7667712 | 0 | 0 | 8126464 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 520093696 | 2031616 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 816 | 48 | 0 | 0 | 0 | 864 | 0 | 2031616 | 2027277 | 96 | 6543 | 213931 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919441776234 | 12074933612429172 | 12074933612553491 | 12074919442108221 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7f1c6c05c500 | 0x7f1b60435c40 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 286937 | 286937 | 0 | 0 | 65536 | 65536 | 12910592 | 160234148 | 47489237 | 95443407 | 17301504 | 1842072 | 1650903 | 24370128 | 11534336 | 0 | 0 | 16449536 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 1052770304 | 2490368 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 960 | 48 | 0 | 0 | 0 | 1008 | 0 | 2490368 | 2482022 | 48 | 10693 | 207452 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919442174374 | 12074933612596531 | 12074933612722290 | 12074919442548950 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7f1c6c05c400 | 0x7f1b60435c80 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 209979 | 209979 | 0 | 0 | 65536 | 65536 | 9109504 | 163962170 | 56560050 | 98358152 | 9043968 | 1716248 | 1537695 | 22835038 | 7733248 | 0 | 0 | 8192000 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 524288000 | 2097152 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 816 | 48 | 0 | 0 | 0 | 864 | 0 | 2097152 | 2089640 | 49 | 12526 | 210840 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919442650268 | 12074933612773649 | 12074933612898608 | 12074919442961978 |
| 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 | 96 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7f1c6c05c300 | 0x7f1b60435cc0 | 0 | 524288 | 524288 | 917504 | 0 | 131072 | 524288 | 0 | 413017 | 413017 | 0 | 0 | 131072 | 65536 | 25559040 | 292208699 | 147555119 | 119291148 | 25362432 | 3313752 | 3105886 | 46233580 | 23134208 | 0 | 0 | 23592960 | 1048576 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 917504 | 1509949440 | 3670016 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1392 | 48 | 0 | 0 | 0 | 1440 | 0 | 3670016 | 3664525 | 96 | 10430 | 187818 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074919443029022 | 12074933612941328 | 12074933613197005 | 12074919443562754 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7f1c6c05ca00 | 0x7f1b60435d00 | 0 | 524288 | 524288 | 65536 | 0 | 65536 | 524288 | 0 | 399795 | 399795 | 0 | 0 | 65536 | 65536 | 9568256 | 294403878 | 96306845 | 183564975 | 14533474 | 3191448 | 3016218 | 44957438 | 8192000 | 0 | 0 | 13747042 | 131072 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 65536 | 876609536 | 2228224 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 864 | 48 | 0 | 0 | 0 | 912 | 0 | 2228224 | 2225081 | 48 | 4606 | 185511 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074919443586709 | 12074933613261965 | 12074933613509482 | 12074919444108478 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7f1c6c05c900 | 0x7f1b60435d40 | 0 | 524288 | 524288 | 131072 | 0 | 131072 | 524288 | 0 | 217377 | 217377 | 0 | 0 | 65536 | 65536 | 9633792 | 159476372 | 51734049 | 98174067 | 9568256 | 1724696 | 1553884 | 22991497 | 8192000 | 0 | 0 | 8650752 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 553648128 | 2162688 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 864 | 48 | 0 | 0 | 0 | 912 | 0 | 2162688 | 2155020 | 48 | 10457 | 197094 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919444131852 | 12074933613570602 | 12074933613695241 | 12074919444470491 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7f1c6c05c800 | 0x7f1b60435d80 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 226395 | 226395 | 0 | 0 | 65536 | 65536 | 13959168 | 174246699 | 42234676 | 113137655 | 18874368 | 1813336 | 1627674 | 23998420 | 12582912 | 0 | 0 | 18022400 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 1153433600 | 2686976 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1056 | 48 | 0 | 0 | 0 | 1104 | 0 | 2686976 | 2673755 | 96 | 17218 | 203957 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919444535502 | 12074933613736040 | 12074933613863879 | 12074919444863191 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7f1c6c05c700 | 0x7f1b60435dc0 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 212265 | 212265 | 0 | 0 | 65536 | 65536 | 9633792 | 157412582 | 53529419 | 94314907 | 9568256 | 1694488 | 1523198 | 22553435 | 8257536 | 0 | 0 | 8716288 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 557842432 | 2228224 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 864 | 48 | 0 | 0 | 0 | 912 | 0 | 2228224 | 2221446 | 48 | 9789 | 247129 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919444939823 | 12074933613915239 | 12074933614040037 | 12074919445257133 |
| 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 | 106 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7f1c6c05c600 | 0x7f1b60435e00 | 0 | 524288 | 524288 | 917504 | 0 | 131072 | 524288 | 0 | 408667 | 408667 | 0 | 0 | 131072 | 65536 | 27721728 | 325405745 | 160810875 | 137004214 | 27590656 | 3332760 | 3142665 | 46707508 | 25362432 | 0 | 0 | 25821184 | 1048576 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 917504 | 1652555776 | 3932160 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1488 | 48 | 0 | 0 | 0 | 1536 | 0 | 3932160 | 3924500 | 49 | 12899 | 176142 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074919445322645 | 12074933614081477 | 12074933614333635 | 12074919445846638 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7f1c6c05c500 | 0x7f1b60435e40 | 0 | 524288 | 524288 | 65536 | 0 | 65536 | 524288 | 0 | 397713 | 397713 | 0 | 0 | 65536 | 65536 | 10092544 | 329512377 | 107221190 | 206709556 | 15583257 | 3200920 | 3004274 | 44836270 | 8716288 | 0 | 0 | 14796825 | 131072 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 65536 | 943718400 | 2359296 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 912 | 48 | 0 | 0 | 0 | 960 | 0 | 2359296 | 2355083 | 96 | 5357 | 184754 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074919445872877 | 12074933614390434 | 12074933614635872 | 12074919446393324 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7f1c6c05c400 | 0x7f1b60435e80 | 0 | 524288 | 524288 | 131072 | 0 | 131072 | 524288 | 0 | 272734 | 272734 | 0 | 0 | 65536 | 65536 | 10158080 | 170999994 | 56399667 | 104507783 | 10092544 | 1751704 | 1582048 | 23409797 | 8716288 | 0 | 0 | 9175040 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 587202560 | 2293760 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 912 | 48 | 0 | 0 | 0 | 960 | 0 | 2293760 | 2284855 | 48 | 12063 | 211451 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919446418822 | 12074933614699391 | 12074933614824990 | 12074919446794360 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7f1c6c05c300 | 0x7f1b60435ec0 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 226323 | 226323 | 0 | 0 | 65536 | 65536 | 15007744 | 181292316 | 40911559 | 119933525 | 20447232 | 1772440 | 1599297 | 23445115 | 13631488 | 0 | 0 | 19595264 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 1254096896 | 2883584 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1104 | 48 | 0 | 0 | 0 | 1152 | 0 | 2883584 | 2871944 | 48 | 14609 | 203256 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919446859691 | 12074933614867070 | 12074933614996669 | 12074919447198280 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7f1c6c05ca00 | 0x7f1b60435f00 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 211017 | 211017 | 0 | 0 | 65536 | 65536 | 10158080 | 161101920 | 47087893 | 103921483 | 10092544 | 1792984 | 1621133 | 24019156 | 8781824 | 0 | 0 | 9240576 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 591396864 | 2359296 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 912 | 48 | 0 | 0 | 0 | 960 | 0 | 2359296 | 2350034 | 96 | 12353 | 215236 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919447275444 | 12074933615049148 | 12074933615174267 | 12074919447585340 |
| 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 | 116 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7f1c6c05c900 | 0x7f1b60435f40 | 0 | 524288 | 524288 | 917504 | 0 | 131072 | 524288 | 0 | 411891 | 411891 | 0 | 0 | 131072 | 65536 | 29818880 | 324870248 | 158763873 | 136418567 | 29687808 | 3265816 | 3082629 | 45796831 | 27459584 | 0 | 0 | 27918336 | 1048576 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 917504 | 1786773504 | 4194304 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1584 | 48 | 0 | 0 | 0 | 1632 | 0 | 4194304 | 4187266 | 48 | 11746 | 201069 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074919447652825 | 12074933615215707 | 12074933615474744 | 12074919448171840 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7f1c6c05c800 | 0x7f1b60435f80 | 0 | 524288 | 524288 | 65536 | 0 | 65536 | 524288 | 0 | 389793 | 389793 | 0 | 0 | 65536 | 65536 | 10616832 | 350837154 | 105231373 | 228970923 | 16630446 | 3241752 | 3024268 | 45096249 | 9240576 | 0 | 0 | 15844014 | 131072 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 65536 | 1010827264 | 2490368 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 960 | 48 | 0 | 0 | 0 | 1008 | 0 | 2490368 | 2486713 | 48 | 4975 | 190405 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074919448198018 | 12074933615536504 | 12074933615782261 | 12074919448715720 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7f1c6c05c700 | 0x7f1b60435fc0 | 0 | 524288 | 524288 | 131072 | 0 | 131072 | 524288 | 0 | 218779 | 218779 | 0 | 0 | 65536 | 65536 | 10682368 | 164523625 | 55596434 | 98310359 | 10616832 | 1671448 | 1503068 | 22189096 | 9240576 | 0 | 0 | 9699328 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 620756992 | 2424832 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 960 | 48 | 0 | 0 | 0 | 1008 | 0 | 2424832 | 2419026 | 48 | 9003 | 210121 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919448739585 | 12074933615838901 | 12074933615964180 | 12074919449077002 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7f1c6c05c600 | 0x7f1b60436000 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 218241 | 218241 | 0 | 0 | 65536 | 65536 | 16056320 | 188523919 | 35785955 | 130717868 | 22020096 | 1808856 | 1626316 | 24040057 | 14680064 | 0 | 0 | 21168128 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 1354760192 | 3080192 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1200 | 48 | 0 | 0 | 0 | 1248 | 0 | 3080192 | 3066856 | 53 | 18981 | 199534 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919449143866 | 12074933616005459 | 12074933616141138 | 12074919449470954 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7f1c6c05c500 | 0x7f1b60436040 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 215715 | 215715 | 0 | 0 | 65536 | 65536 | 10682368 | 161682892 | 55370385 | 95695675 | 10616832 | 1744152 | 1574152 | 23291680 | 9306112 | 0 | 0 | 9764864 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 624951296 | 2490368 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 960 | 48 | 0 | 0 | 0 | 1008 | 0 | 2490368 | 2484272 | 48 | 9883 | 200518 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919449547716 | 12074933616194898 | 12074933616319376 | 12074919449859917 |
| 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 | 126 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7f1c6c05c400 | 0x7f1b60436080 | 0 | 524288 | 524288 | 917504 | 0 | 131072 | 524288 | 0 | 410137 | 410137 | 0 | 0 | 131072 | 65536 | 31981568 | 336745567 | 153338355 | 151622252 | 31784960 | 3306328 | 3130505 | 46577015 | 29556736 | 0 | 0 | 30015488 | 1048576 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 917504 | 1920991232 | 4456448 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1680 | 48 | 0 | 0 | 0 | 1728 | 0 | 4456448 | 4451379 | 48 | 9886 | 195616 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074919449925879 | 12074933616361616 | 12074933616622094 | 12074919450451506 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7f1c6c05c300 | 0x7f1b604360c0 | 0 | 524288 | 524288 | 65536 | 0 | 65536 | 524288 | 0 | 396907 | 396907 | 0 | 0 | 65536 | 65536 | 11141120 | 282303426 | 95568755 | 169040248 | 17689611 | 3234200 | 3036793 | 45225506 | 9764864 | 0 | 0 | 16903179 | 131072 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 65536 | 1077936128 | 2621440 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 1008 | 48 | 0 | 0 | 0 | 1056 | 0 | 2621440 | 2617792 | 48 | 4990 | 256890 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074919450475100 | 12074933616677613 | 12074933616964170 | 12074919450994535 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7f1c6c05ca00 | 0x7f1b60436100 | 0 | 524288 | 524288 | 131072 | 0 | 131072 | 524288 | 0 | 210785 | 210785 | 0 | 0 | 65536 | 65536 | 11206656 | 167191306 | 52133620 | 103916566 | 11141120 | 1762200 | 1584671 | 23467017 | 9764864 | 0 | 0 | 10223616 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 654311424 | 2555904 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1008 | 48 | 0 | 0 | 0 | 1056 | 0 | 2555904 | 2547973 | 96 | 10214 | 228594 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919451024391 | 12074933617024330 | 12074933617150089 | 12074919451356548 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7f1c6c05c900 | 0x7f1b60436140 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 231747 | 231747 | 0 | 0 | 65536 | 65536 | 17170432 | 193084096 | 30811978 | 138679158 | 23592960 | 1860120 | 1694769 | 25108633 | 15728640 | 0 | 0 | 22740992 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 1455423488 | 3276800 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1248 | 48 | 0 | 0 | 0 | 1296 | 0 | 3276800 | 3268755 | 48 | 11907 | 182659 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919451420647 | 12074933617192488 | 12074933617334727 | 12074919451754107 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7f1c6c05c800 | 0x7f1b60436180 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 216593 | 216593 | 0 | 0 | 65536 | 65536 | 11206656 | 169487134 | 50425322 | 107920692 | 11141120 | 1743960 | 1562200 | 23130813 | 9830400 | 0 | 0 | 10289152 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 658505728 | 2621440 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1008 | 48 | 0 | 0 | 0 | 1056 | 0 | 2621440 | 2613136 | 48 | 11264 | 262624 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919451829948 | 12074933617386567 | 12074933617511525 | 12074919452144332 |
| 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 | 136 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7f1c6c05c700 | 0x7f1b604361c0 | 0 | 524288 | 524288 | 917504 | 0 | 131072 | 524288 | 0 | 403947 | 403947 | 0 | 0 | 131072 | 65536 | 34078720 | 286310147 | 140663078 | 111764957 | 33882112 | 3339672 | 3157602 | 46913145 | 31653888 | 0 | 0 | 32112640 | 1048576 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 917504 | 2055208960 | 4718592 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1776 | 48 | 0 | 0 | 0 | 1824 | 0 | 4718592 | 4711842 | 96 | 10334 | 228376 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074919452206718 | 12074933617553445 | 12074933617810403 | 12074919452731403 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7f1c6c05c600 | 0x7f1b60436200 | 0 | 524288 | 524288 | 65536 | 0 | 65536 | 524288 | 0 | 391929 | 391929 | 0 | 0 | 65536 | 65536 | 11665408 | 329049942 | 96024380 | 214271011 | 18742437 | 3189592 | 3012120 | 44915323 | 10289152 | 0 | 0 | 17956005 | 131072 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 65536 | 1145044992 | 2752512 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 1056 | 48 | 0 | 0 | 0 | 1104 | 0 | 2752512 | 2748901 | 48 | 5039 | 224089 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074919452755748 | 12074933617865922 | 12074933618109920 | 12074919453271016 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7f1c6c05c500 | 0x7f1b60436240 | 0 | 524288 | 524288 | 131072 | 0 | 131072 | 524288 | 0 | 214907 | 214907 | 0 | 0 | 65536 | 65536 | 11730944 | 161576362 | 57411421 | 92499533 | 11665408 | 1760856 | 1564034 | 23111736 | 10289152 | 0 | 0 | 10747904 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 687865856 | 2686976 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1056 | 48 | 0 | 0 | 0 | 1104 | 0 | 2686976 | 2678100 | 96 | 11260 | 241330 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919453296062 | 12074933618169759 | 12074933618295038 | 12074919453631906 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7f1c6c05c400 | 0x7f1b60436280 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 241265 | 241265 | 0 | 0 | 65536 | 65536 | 18219008 | 207523897 | 27291760 | 155066313 | 25165824 | 1930712 | 1764236 | 26210414 | 16777216 | 0 | 0 | 24313856 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 1556086784 | 3473408 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1344 | 48 | 0 | 0 | 0 | 1392 | 0 | 3473408 | 3463160 | 48 | 13057 | 150694 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919453695865 | 12074933618335838 | 12074933618485596 | 12074919454033783 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7f1c6c05c300 | 0x7f1b604362c0 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 208187 | 208187 | 0 | 0 | 65536 | 65536 | 11730944 | 168544217 | 47004459 | 109874350 | 11665408 | 1735512 | 1564777 | 23070826 | 10354688 | 0 | 0 | 10813440 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 692060160 | 2752512 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1056 | 48 | 0 | 0 | 0 | 1104 | 0 | 2752512 | 2743573 | 98 | 13753 | 244371 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919454128479 | 12074933618552316 | 12074933618678075 | 12074919454436251 |
| 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 | 146 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7f1c6c05ca00 | 0x7f1b60436300 | 0 | 524288 | 524288 | 917504 | 0 | 131072 | 524288 | 0 | 408385 | 408385 | 0 | 0 | 131072 | 65536 | 36175872 | 290358746 | 124299293 | 130080189 | 35979264 | 3282008 | 3099764 | 45993028 | 33751040 | 0 | 0 | 34209792 | 1048576 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 917504 | 2189426688 | 4980736 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1872 | 48 | 0 | 0 | 0 | 1920 | 0 | 4980736 | 4974117 | 49 | 11575 | 243549 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074919454501382 | 12074933618719674 | 12074933618984312 | 12074919455014165 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7f1c6c05c900 | 0x7f1b60436340 | 0 | 524288 | 524288 | 65536 | 0 | 65536 | 524288 | 0 | 389331 | 389331 | 0 | 0 | 65536 | 65536 | 12189696 | 302523622 | 97215106 | 185512768 | 19792182 | 3208856 | 3025373 | 44995575 | 10813440 | 0 | 0 | 19005750 | 131072 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 65536 | 1212153856 | 2883584 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 1104 | 48 | 0 | 0 | 0 | 1152 | 0 | 2883584 | 2879281 | 96 | 5245 | 250635 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074919455045954 | 12074933619041271 | 12074933619288629 | 12074919455557365 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7f1c6c05c800 | 0x7f1b60436380 | 0 | 524288 | 524288 | 131072 | 0 | 131072 | 524288 | 0 | 217209 | 217209 | 0 | 0 | 65536 | 65536 | 12255232 | 167901995 | 48841310 | 106870989 | 12189696 | 1760280 | 1577834 | 23279021 | 10813440 | 0 | 0 | 11272192 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 721420288 | 2818048 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1104 | 48 | 0 | 0 | 0 | 1152 | 0 | 2818048 | 2809560 | 48 | 11552 | 251185 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919455580758 | 12074933619342869 | 12074933619468627 | 12074919455919959 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7f1c6c05c700 | 0x7f1b604363c0 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 251707 | 251707 | 0 | 0 | 65536 | 65536 | 19202048 | 221890896 | 23824268 | 171327940 | 26738688 | 2015576 | 1850489 | 27461121 | 17825792 | 0 | 0 | 25886720 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 1656750080 | 3670016 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1392 | 48 | 0 | 0 | 0 | 1440 | 0 | 3670016 | 3660271 | 48 | 13621 | 283821 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919455985210 | 12074933619509747 | 12074933619666546 | 12074919456338807 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7f1c6c05c600 | 0x7f1b60436400 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 215953 | 215953 | 0 | 0 | 65536 | 65536 | 12255232 | 166561304 | 54921797 | 99449811 | 12189696 | 1746456 | 1571641 | 23208508 | 10878976 | 0 | 0 | 11337728 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 725614592 | 2883584 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1104 | 48 | 0 | 0 | 0 | 1152 | 0 | 2883584 | 2877044 | 96 | 8829 | 208874 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919456414518 | 12074933619718385 | 12074933619843184 | 12074919456728431 |
| 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 | 156 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7f1c6c05c500 | 0x7f1b60436440 | 0 | 524288 | 524288 | 917504 | 0 | 131072 | 524288 | 0 | 409435 | 409435 | 0 | 0 | 131072 | 65536 | 38273024 | 303537738 | 122547900 | 142913422 | 38076416 | 3362264 | 3166892 | 47046689 | 35848192 | 0 | 0 | 36306944 | 1048576 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 917504 | 2323644416 | 5177344 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1968 | 48 | 0 | 0 | 0 | 2016 | 0 | 5177344 | 5168832 | 48 | 12467 | 208456 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074919456792771 | 12074933619884944 | 12074933620147981 | 12074919457314721 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7f1c6c05c400 | 0x7f1b60436480 | 0 | 524288 | 524288 | 65536 | 0 | 65536 | 524288 | 0 | 401409 | 401409 | 0 | 0 | 65536 | 65536 | 12713984 | 245167640 | 86494609 | 137830308 | 20858262 | 3241624 | 3055332 | 45470624 | 11337728 | 0 | 0 | 20071830 | 131072 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 65536 | 1279262720 | 3014656 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 1152 | 48 | 0 | 0 | 0 | 1200 | 0 | 3014656 | 3009282 | 97 | 6875 | 158950 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074919457339466 | 12074933620209901 | 12074933620455498 | 12074919457863781 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7f1c6c05c300 | 0x7f1b604364c0 | 0 | 524288 | 524288 | 131072 | 0 | 131072 | 524288 | 0 | 219371 | 219371 | 0 | 0 | 65536 | 65536 | 12779520 | 164479197 | 56269354 | 95495859 | 12713984 | 1814360 | 1639095 | 24163299 | 11337728 | 0 | 0 | 11796480 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 754974720 | 2949120 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1152 | 48 | 0 | 0 | 0 | 1200 | 0 | 2949120 | 2934979 | 49 | 18926 | 247438 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919457886673 | 12074933620512778 | 12074933620639337 | 12074919458228889 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7f1c6c05ca00 | 0x7f1b60436500 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 262265 | 262265 | 0 | 0 | 65536 | 65536 | 20250624 | 234212670 | 20117794 | 185783324 | 28311552 | 2138008 | 1953598 | 28960954 | 18874368 | 0 | 0 | 27459584 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 1757413376 | 3866624 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1488 | 48 | 0 | 0 | 0 | 1536 | 0 | 3866624 | 3849843 | 96 | 20996 | 199494 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919458291496 | 12074933620680456 | 12074933620846375 | 12074919458655703 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7f1c6c05c900 | 0x7f1b60436540 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 210043 | 210043 | 0 | 0 | 65536 | 65536 | 12779520 | 171320814 | 54843618 | 103763212 | 12713984 | 1752280 | 1585236 | 23392204 | 11403264 | 0 | 0 | 11862016 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 759169024 | 3014656 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1152 | 48 | 0 | 0 | 0 | 1200 | 0 | 3014656 | 3007028 | 48 | 9745 | 271816 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919458733156 | 12074933620898694 | 12074933621024773 | 12074919459041229 |
| 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 | 166 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7f1c6c05c800 | 0x7f1b60436580 | 0 | 524288 | 524288 | 917504 | 0 | 131072 | 524288 | 0 | 411313 | 411313 | 0 | 0 | 131072 | 65536 | 40370176 | 355276784 | 137561583 | 177541633 | 40173568 | 3300312 | 3114645 | 46249091 | 37945344 | 0 | 0 | 38404096 | 1048576 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 917504 | 2457862144 | 5439488 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 2064 | 48 | 0 | 0 | 0 | 2112 | 0 | 5439488 | 5423789 | 98 | 27602 | 237612 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074919459105298 | 12074933621067653 | 12074933621330530 | 12074919459631977 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7f1c6c05c700 | 0x7f1b604365c0 | 0 | 524288 | 524288 | 65536 | 0 | 65536 | 524288 | 0 | 394995 | 394995 | 0 | 0 | 65536 | 65536 | 13238272 | 244419685 | 92373976 | 130156477 | 21893482 | 3201752 | 3020594 | 44883060 | 11862016 | 0 | 0 | 21107050 | 131072 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 65536 | 1346371584 | 3145728 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 1200 | 48 | 0 | 0 | 0 | 1248 | 0 | 3145728 | 3140604 | 48 | 6412 | 234496 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074919459657885 | 12074933621385890 | 12074933621667327 | 12074919460182039 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7f1c6c05c600 | 0x7f1b60436600 | 0 | 524288 | 524288 | 131072 | 0 | 131072 | 524288 | 0 | 215209 | 215209 | 0 | 0 | 65536 | 65536 | 13303808 | 170672443 | 48476526 | 108957645 | 13238272 | 1759384 | 1587183 | 23464492 | 11862016 | 0 | 0 | 12320768 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 788529152 | 3080192 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1200 | 48 | 0 | 0 | 0 | 1248 | 0 | 3080192 | 3069144 | 60 | 17567 | 203550 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919460206014 | 12074933621727007 | 12074933621852125 | 12074919460544332 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7f1c6c05c500 | 0x7f1b60436640 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 277043 | 277043 | 0 | 0 | 65536 | 65536 | 21299200 | 247716121 | 19167450 | 198664255 | 29884416 | 2238424 | 2049735 | 30456715 | 19922944 | 0 | 0 | 29032448 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 1858076672 | 4063232 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1536 | 48 | 0 | 0 | 0 | 1584 | 0 | 4063232 | 4049266 | 96 | 17641 | 196631 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919460608361 | 12074933621894205 | 12074933622066683 | 12074919460971837 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7f1c6c05c400 | 0x7f1b60436680 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 213849 | 213849 | 0 | 0 | 65536 | 65536 | 13303808 | 172453197 | 45026940 | 114187985 | 13238272 | 1704728 | 1529340 | 22605860 | 11927552 | 0 | 0 | 12386304 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 792723456 | 3145728 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1200 | 48 | 0 | 0 | 0 | 1248 | 0 | 3145728 | 3134023 | 49 | 15635 | 250433 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919461049882 | 12074933622119323 | 12074933622245402 | 12074919461365388 |
| 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 | 176 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7f1c6c05c300 | 0x7f1b604366c0 | 0 | 524288 | 524288 | 917504 | 0 | 131072 | 524288 | 0 | 407675 | 407675 | 0 | 0 | 131072 | 65536 | 42467328 | 335676904 | 101691791 | 191714393 | 42270720 | 3259800 | 3068906 | 45592627 | 40042496 | 0 | 0 | 40501248 | 1048576 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 917504 | 2592079872 | 5701632 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 2160 | 48 | 0 | 0 | 0 | 2208 | 0 | 5701632 | 5691031 | 97 | 14370 | 238749 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074919461428275 | 12074933622288121 | 12074933622541719 | 12074919461926170 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7f1c6c05ca00 | 0x7f1b60436700 | 0 | 524288 | 524288 | 65536 | 0 | 65536 | 524288 | 0 | 399633 | 399633 | 0 | 0 | 65536 | 65536 | 13762560 | 257657618 | 89674939 | 145032431 | 22960005 | 3236184 | 3067851 | 45670850 | 12386304 | 0 | 0 | 22173573 | 131072 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 65536 | 1413480448 | 3276800 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 1248 | 48 | 0 | 0 | 0 | 1296 | 0 | 3276800 | 3272429 | 48 | 6055 | 187245 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074919461964411 | 12074933622592919 | 12074933622841716 | 12074919462477455 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7f1c6c05c900 | 0x7f1b60436740 | 0 | 524288 | 524288 | 131072 | 0 | 131072 | 524288 | 0 | 214475 | 214475 | 0 | 0 | 65536 | 65536 | 13828096 | 164946683 | 47872130 | 103311993 | 13762560 | 1818904 | 1646632 | 24335838 | 12386304 | 0 | 0 | 12845056 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 822083584 | 3211264 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1248 | 48 | 0 | 0 | 0 | 1296 | 0 | 3211264 | 3195458 | 96 | 21976 | 249512 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919462503443 | 12074933622899796 | 12074933623025875 | 12074919462836231 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7f1c6c05c800 | 0x7f1b60436780 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 288993 | 288993 | 0 | 0 | 65536 | 65536 | 22347776 | 259920602 | 19300420 | 209162902 | 31457280 | 2814552 | 2161473 | 32077370 | 20971520 | 0 | 0 | 30605312 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 1958739968 | 4259840 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1632 | 48 | 0 | 0 | 0 | 1680 | 0 | 4259840 | 4240168 | 48 | 23904 | 241993 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919462900571 | 12074933623067954 | 12074933623250033 | 12074919463280717 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7f1c6c05c700 | 0x7f1b604367c0 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 226091 | 226091 | 0 | 0 | 65536 | 65536 | 13828096 | 173357403 | 46538075 | 113056768 | 13762560 | 1817432 | 1642762 | 24253222 | 12451840 | 0 | 0 | 12910592 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 826277888 | 3276800 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1248 | 48 | 0 | 0 | 0 | 1296 | 0 | 3276800 | 3262696 | 96 | 23678 | 233326 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919463383318 | 12074933623302192 | 12074933623428751 | 12074919463704164 |
| 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 | 186 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7f1c6c05c600 | 0x7f1b60436800 | 0 | 524288 | 524288 | 4653056 | 0 | 131072 | 524288 | 0 | 408585 | 408585 | 0 | 0 | 1703936 | 65536 | 51642368 | 376162041 | 141162788 | 184470997 | 50528256 | 3284312 | 3116625 | 46401936 | 42926080 | 0 | 0 | 43450368 | 4784128 | 0 | 1769472 | 524288 | 0 | 524288 | 131072 | 4653056 | 2780823552 | 7733248 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1200 | 48 | 0 | 0 | 0 | 1248 | 0 | 7733248 | 7730609 | 48 | 2883 | 265184 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074919463769856 | 12074933623470511 | 12074933623735308 | 12074919464285986 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7f1c6c05c500 | 0x7f1b60436840 | 0 | 524288 | 524288 | 65536 | 0 | 65536 | 524288 | 0 | 401955 | 401955 | 0 | 0 | 65536 | 65536 | 14286848 | 302781704 | 86104574 | 192661711 | 24012077 | 3165016 | 2977320 | 44390501 | 12910592 | 0 | 0 | 23225645 | 131072 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 65536 | 1480589312 | 3407872 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 1296 | 48 | 0 | 0 | 0 | 1344 | 0 | 3407872 | 3399750 | 96 | 9458 | 242302 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074919464310862 | 12074933623790188 | 12074933624038185 | 12074919464835988 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7f1c6c05c400 | 0x7f1b60436880 | 0 | 524288 | 524288 | 131072 | 0 | 131072 | 524288 | 0 | 217953 | 217953 | 0 | 0 | 65536 | 65536 | 14352384 | 169434239 | 53325733 | 101821658 | 14286848 | 1805656 | 1631681 | 24098429 | 12910592 | 0 | 0 | 13369344 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 855638016 | 3342336 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1296 | 48 | 0 | 0 | 0 | 1344 | 0 | 3342336 | 3329706 | 50 | 19645 | 250063 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919464860243 | 12074933624098025 | 12074933624224264 | 12074919465213079 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7f1c6c05c300 | 0x7f1b604368c0 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 301875 | 301875 | 0 | 0 | 65536 | 65536 | 23396352 | 272522317 | 18103771 | 221388402 | 33030144 | 2435928 | 2264326 | 33574180 | 22020096 | 0 | 0 | 32178176 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 2059403264 | 4456448 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1680 | 48 | 0 | 0 | 0 | 1728 | 0 | 4456448 | 4439910 | 97 | 20380 | 287571 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919465277568 | 12074933624266983 | 12074933624457541 | 12074919465701687 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7f1c6c05ca00 | 0x7f1b60436900 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 222745 | 222745 | 0 | 0 | 65536 | 65536 | 14876672 | 174707228 | 48048574 | 111847518 | 14811136 | 1807512 | 1621421 | 23965048 | 13500416 | 0 | 0 | 13959168 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 893386752 | 3538944 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1344 | 48 | 0 | 0 | 0 | 1392 | 0 | 3538944 | 3524966 | 48 | 26065 | 264729 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919465753062 | 12074933624507621 | 12074933624634980 | 12074919466072546 |
| 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 | 196 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7f1c6c05c900 | 0x7f1b60436940 | 0 | 524288 | 524288 | 5701632 | 0 | 131072 | 524288 | 0 | 437499 | 437499 | 0 | 0 | 2228224 | 65536 | 57933824 | 405577825 | 105788146 | 243494255 | 56295424 | 3878040 | 3336418 | 49650033 | 47120384 | 0 | 0 | 47644672 | 5832704 | 0 | 2293760 | 524288 | 0 | 524288 | 131072 | 5701632 | 3049259008 | 8978432 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1104 | 48 | 0 | 0 | 0 | 1152 | 0 | 8978432 | 8976508 | 48 | 2113 | 260579 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074919466138198 | 12074933624677059 | 12074933624958657 | 12074919466680055 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7f1c6c05c800 | 0x7f1b60436980 | 0 | 524288 | 524288 | 65536 | 0 | 65536 | 524288 | 0 | 392497 | 392497 | 0 | 0 | 65536 | 65536 | 15335424 | 275235946 | 88490989 | 160629867 | 26120537 | 3163992 | 2996527 | 44651913 | 13959168 | 0 | 0 | 25334105 | 131072 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 65536 | 1614807040 | 3670016 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 1392 | 48 | 0 | 0 | 0 | 1440 | 0 | 3670016 | 3665408 | 49 | 5713 | 236583 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074919466705522 | 12074933625018816 | 12074933625266974 | 12074919467223575 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7f1c6c05c700 | 0x7f1b604369c0 | 0 | 524288 | 524288 | 131072 | 0 | 131072 | 524288 | 0 | 217443 | 217443 | 0 | 0 | 65536 | 65536 | 15400960 | 181295613 | 45981934 | 119978255 | 15335424 | 1751448 | 1553398 | 22925512 | 13959168 | 0 | 0 | 14417920 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 922746880 | 3604480 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1392 | 48 | 0 | 0 | 0 | 1440 | 0 | 3604480 | 3589027 | 52 | 20507 | 264130 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919467247629 | 12074933625327293 | 12074933625453692 | 12074919467583444 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7f1c6c05c600 | 0x7f1b60436a00 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 328377 | 328377 | 0 | 0 | 65536 | 65536 | 25493504 | 299518642 | 19704640 | 243638130 | 36175872 | 2645208 | 2481968 | 36886120 | 24117248 | 0 | 0 | 35323904 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 2260729856 | 4849664 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1824 | 48 | 0 | 0 | 0 | 1872 | 0 | 4849664 | 4826576 | 112 | 29374 | 255452 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919467646130 | 12074933625495772 | 12074933625704090 | 12074919468116284 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7f1c6c05c500 | 0x7f1b60436a40 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 217523 | 217523 | 0 | 0 | 65536 | 65536 | 15925248 | 164876103 | 54102284 | 94914107 | 15859712 | 1757144 | 1586748 | 23432945 | 14548992 | 0 | 0 | 15007744 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 960495616 | 3801088 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1440 | 48 | 0 | 0 | 0 | 1488 | 0 | 3801088 | 3790050 | 50 | 16131 | 269256 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919468152782 | 12074933625769049 | 12074933625896888 | 12074919468479188 |
| 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 | 206 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7f1c6c05c400 | 0x7f1b60436a80 | 0 | 524288 | 524288 | 13041664 | 0 | 131072 | 524288 | 0 | 468873 | 468873 | 0 | 0 | 5898240 | 65536 | 76808192 | 436140802 | 112497506 | 252143520 | 71499776 | 3760472 | 3594984 | 53603400 | 51314688 | 0 | 0 | 51838976 | 13172736 | 0 | 5963776 | 524288 | 0 | 524288 | 131072 | 13041664 | 3317694464 | 14548992 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 816 | 48 | 0 | 0 | 0 | 864 | 0 | 14548992 | 14547327 | 48 | 1917 | 251965 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074919468543959 | 12074933625936888 | 12074933626243125 | 12074919469101665 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7f1c6c05c300 | 0x7f1b60436ac0 | 0 | 524288 | 524288 | 65536 | 0 | 65536 | 524288 | 0 | 396539 | 396539 | 0 | 0 | 65536 | 65536 | 16384000 | 290568204 | 72991994 | 189346246 | 28228610 | 3210584 | 3039175 | 45231356 | 15007744 | 0 | 0 | 27442178 | 131072 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 65536 | 1749024768 | 3932160 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 1488 | 48 | 0 | 0 | 0 | 1536 | 0 | 3932160 | 3922285 | 48 | 11311 | 233710 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074919469127663 | 12074933626299124 | 12074933626549522 | 12074919469649423 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7f1c6c05ca00 | 0x7f1b60436b00 | 0 | 524288 | 524288 | 131072 | 0 | 131072 | 524288 | 0 | 220657 | 220657 | 0 | 0 | 65536 | 65536 | 16449536 | 173592112 | 47940922 | 109267190 | 16384000 | 1757848 | 1587677 | 23399164 | 15007744 | 0 | 0 | 15466496 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 989855744 | 3866624 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1488 | 48 | 0 | 0 | 0 | 1536 | 0 | 3866624 | 3851146 | 97 | 25208 | 255781 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919469672576 | 12074933626610642 | 12074933626737360 | 12074919470019240 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7f1c6c05c900 | 0x7f1b60436b40 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 356555 | 356555 | 0 | 0 | 65536 | 65536 | 27590656 | 328266028 | 20438943 | 268505485 | 39321600 | 2873176 | 2686874 | 39916898 | 26214400 | 0 | 0 | 38469632 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 2462056448 | 5242880 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1968 | 48 | 0 | 0 | 0 | 2016 | 0 | 5242880 | 5218668 | 48 | 30526 | 245913 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919470083540 | 12074933626778320 | 12074933627005998 | 12074919470565064 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7f1c6c05c800 | 0x7f1b60436b80 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 219209 | 219209 | 0 | 0 | 65536 | 65536 | 16973824 | 175913861 | 46596739 | 112408834 | 16908288 | 1803736 | 1633652 | 24138094 | 15597568 | 0 | 0 | 16056320 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 1027604480 | 4063232 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1536 | 48 | 0 | 0 | 0 | 1584 | 0 | 4063232 | 4048598 | 120 | 24187 | 260641 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919470600450 | 12074933627078157 | 12074933627204556 | 12074919470920074 |
| 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 | 216 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7f1c6c05c700 | 0x7f1b60436bc0 | 0 | 524288 | 524288 | 5701632 | 0 | 131072 | 524288 | 0 | 506507 | 506507 | 0 | 0 | 2228224 | 65536 | 66322432 | 470693891 | 90900619 | 315109240 | 64684032 | 4023896 | 3864420 | 57596507 | 55508992 | 0 | 0 | 56033280 | 5832704 | 0 | 2293760 | 524288 | 0 | 524288 | 131072 | 5701632 | 3586129920 | 10027008 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1200 | 48 | 0 | 0 | 0 | 1248 | 0 | 10027008 | 10024443 | 48 | 2876 | 235332 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074919470984664 | 12074933627246956 | 12074933627576073 | 12074919471583447 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7f1c6c05c600 | 0x7f1b60436c00 | 0 | 524288 | 524288 | 65536 | 0 | 65536 | 524288 | 0 | 386465 | 386465 | 0 | 0 | 65536 | 65536 | 17432576 | 337538976 | 73783961 | 233412238 | 30331109 | 3251608 | 3077383 | 45771926 | 16056320 | 0 | 0 | 29544677 | 131072 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 65536 | 1883242496 | 4194304 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 1584 | 48 | 0 | 0 | 0 | 1632 | 0 | 4194304 | 4183256 | 96 | 12435 | 236335 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074919471608694 | 12074933627634152 | 12074933627891430 | 12074919472125374 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7f1c6c05c500 | 0x7f1b60436c40 | 0 | 524288 | 524288 | 131072 | 0 | 131072 | 524288 | 0 | 225715 | 225715 | 0 | 0 | 65536 | 65536 | 17498112 | 169426622 | 49234374 | 102759672 | 17432576 | 1799512 | 1628655 | 23914248 | 16056320 | 0 | 0 | 16515072 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 1056964608 | 4128768 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1584 | 48 | 0 | 0 | 0 | 1632 | 0 | 4128768 | 4114143 | 75 | 23089 | 257758 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919472150020 | 12074933627949829 | 12074933628078948 | 12074919472492647 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7f1c6c05c400 | 0x7f1b60436c80 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 381633 | 381633 | 0 | 0 | 65536 | 65536 | 29687808 | 348674817 | 18540224 | 287667265 | 42467328 | 3061400 | 2882315 | 42885927 | 28311552 | 0 | 0 | 41615360 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 2663383040 | 5636096 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 2112 | 48 | 0 | 0 | 0 | 2160 | 0 | 5636096 | 5614841 | 96 | 24358 | 264756 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919472556676 | 12074933628120548 | 12074933628397985 | 12074919473030166 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7f1c6c05c300 | 0x7f1b60436cc0 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 222955 | 222955 | 0 | 0 | 65536 | 65536 | 19070976 | 183117451 | 44380782 | 119731229 | 19005440 | 1788312 | 1608125 | 23663135 | 17694720 | 0 | 0 | 18153472 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 1161822208 | 4587520 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1728 | 48 | 0 | 0 | 0 | 1776 | 0 | 4587520 | 4570749 | 105 | 30225 | 282393 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919473088564 | 12074933628468544 | 12074933628597823 | 12074919473410152 |
| 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 | 226 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7f1c6c05ca00 | 0x7f1b60436d00 | 0 | 524288 | 524288 | 5701632 | 0 | 131072 | 524288 | 0 | 573793 | 573793 | 0 | 0 | 2228224 | 65536 | 74711040 | 540265579 | 86488342 | 380704597 | 73072640 | 4592216 | 4424311 | 65955880 | 63897600 | 0 | 0 | 64421888 | 5832704 | 0 | 2293760 | 524288 | 0 | 524288 | 131072 | 5701632 | 4123000832 | 11075584 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1296 | 48 | 0 | 0 | 0 | 1344 | 0 | 11075584 | 11073406 | 49 | 2617 | 225709 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074919473465795 | 12074933628640063 | 12074933629014299 | 12074919474111936 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7f1c6c05c900 | 0x7f1b60436d40 | 0 | 524288 | 524288 | 65536 | 0 | 65536 | 524288 | 0 | 403859 | 403859 | 0 | 0 | 65536 | 65536 | 19529728 | 262346981 | 63908660 | 163948107 | 34510837 | 3328088 | 3125727 | 46384304 | 18153472 | 0 | 0 | 33724405 | 131072 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 65536 | 2151677952 | 4718592 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 1728 | 48 | 0 | 0 | 0 | 1776 | 0 | 4718592 | 4701891 | 49 | 18107 | 223182 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074919474136992 | 12074933629071899 | 12074933629323737 | 12074919474671506 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7f1c6c05c800 | 0x7f1b60436d80 | 0 | 524288 | 524288 | 131072 | 0 | 131072 | 524288 | 0 | 225401 | 225401 | 0 | 0 | 65536 | 65536 | 19595264 | 181738827 | 45296535 | 116912564 | 19529728 | 1894168 | 1697426 | 24942426 | 18153472 | 0 | 0 | 18612224 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 1191182336 | 4653056 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1776 | 48 | 0 | 0 | 0 | 1824 | 0 | 4653056 | 4637696 | 101 | 29224 | 243695 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919474694118 | 12074933629381336 | 12074933629511255 | 12074919475038287 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7f1c6c05c700 | 0x7f1b60436dc0 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 434195 | 434195 | 0 | 0 | 65536 | 65536 | 33882112 | 403522537 | 18657258 | 336106495 | 48758784 | 3478872 | 3307848 | 49226309 | 32505856 | 0 | 0 | 47906816 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 3066036224 | 6422528 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 2400 | 48 | 0 | 0 | 0 | 2448 | 0 | 6422528 | 6396392 | 96 | 31220 | 218524 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919475103899 | 12074933629551574 | 12074933629861332 | 12074919475637130 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7f1c6c05c600 | 0x7f1b60436e00 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 222793 | 222793 | 0 | 0 | 65536 | 65536 | 21168128 | 184059073 | 43051225 | 119905256 | 21102592 | 1816792 | 1646416 | 24322191 | 19791872 | 0 | 0 | 20250624 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 1296039936 | 5111808 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1920 | 48 | 0 | 0 | 0 | 1968 | 0 | 5111808 | 5094545 | 100 | 31510 | 222199 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919475672496 | 12074933629925971 | 12074933630060210 | 12074919475998341 |
| 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 | 236 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7f1c6c05c500 | 0x7f1b60436e40 | 0 | 524288 | 524288 | 9895936 | 0 | 131072 | 524288 | 0 | 644411 | 644411 | 0 | 0 | 4325376 | 65536 | 91488256 | 612183278 | 96989166 | 427441408 | 87752704 | 5152728 | 4984140 | 74354456 | 72286208 | 0 | 0 | 72810496 | 10027008 | 0 | 4390912 | 524288 | 0 | 524288 | 131072 | 9895936 | 4659871744 | 15007744 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1008 | 48 | 0 | 0 | 0 | 1056 | 0 | 15007744 | 15006275 | 48 | 1967 | 226910 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074919476062250 | 12074933630102129 | 12074933630524206 | 12074919476715184 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7f1c6c05c400 | 0x7f1b60436e80 | 0 | 524288 | 524288 | 65536 | 0 | 65536 | 524288 | 0 | 416225 | 416225 | 0 | 0 | 65536 | 65536 | 21626880 | 287226867 | 56774518 | 191786012 | 38679881 | 3229784 | 3020479 | 44858658 | 20250624 | 0 | 0 | 37893449 | 131072 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 65536 | 2420113408 | 5242880 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 1968 | 48 | 0 | 0 | 0 | 2016 | 0 | 5242880 | 5228208 | 48 | 16234 | 251642 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074919476757993 | 12074933630583085 | 12074933630839243 | 12074919477250168 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7f1c6c05c300 | 0x7f1b60436ec0 | 0 | 524288 | 524288 | 131072 | 0 | 131072 | 524288 | 0 | 220123 | 220123 | 0 | 0 | 65536 | 65536 | 21692416 | 180539545 | 40873258 | 118039407 | 21626880 | 1811928 | 1640808 | 24319017 | 20250624 | 0 | 0 | 20709376 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 1325400064 | 5177344 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1968 | 48 | 0 | 0 | 0 | 2016 | 0 | 5177344 | 5156992 | 155 | 39693 | 221489 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919477285163 | 12074933630895082 | 12074933631029481 | 12074919477629453 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7f1c6c05ca00 | 0x7f1b60436f00 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 488177 | 488177 | 0 | 0 | 65536 | 65536 | 38076416 | 456211324 | 20295445 | 380865639 | 55050240 | 4274648 | 3727050 | 55545201 | 36700160 | 0 | 0 | 54198272 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 3468689408 | 7208960 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 2688 | 48 | 0 | 0 | 0 | 2736 | 0 | 7208960 | 7180330 | 96 | 35590 | 219210 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919477694544 | 12074933631071880 | 12074933631385158 | 12074919478271506 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7f1c6c05c900 | 0x7f1b60436f40 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 245963 | 245963 | 0 | 0 | 65536 | 65536 | 25362432 | 214979504 | 26899017 | 162783591 | 25296896 | 1947160 | 1780918 | 26488610 | 23986176 | 0 | 0 | 24444928 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 1564475392 | 6160384 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 2304 | 48 | 0 | 0 | 0 | 2352 | 0 | 6160384 | 6140383 | 154 | 35769 | 246619 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919478307483 | 12074933631455717 | 12074933631607556 | 12074919478655019 |
| 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 | 246 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7f1c6c05c800 | 0x7f1b60436f80 | 0 | 524288 | 524288 | 9895936 | 0 | 131072 | 524288 | 0 | 785761 | 785761 | 0 | 0 | 4325376 | 65536 | 108265472 | 750416725 | 95880409 | 550006396 | 104529920 | 6279256 | 6106557 | 91129972 | 89063424 | 0 | 0 | 89587712 | 10027008 | 0 | 4390912 | 524288 | 0 | 524288 | 131072 | 9895936 | 5733613568 | 17104896 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1104 | 48 | 0 | 0 | 0 | 1152 | 0 | 17104896 | 17103129 | 48 | 2135 | 232347 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074919478721482 | 12074933631649795 | 12074933632165630 | 12074919479492435 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7f1c6c05c700 | 0x7f1b60436fc0 | 0 | 524288 | 524288 | 65536 | 0 | 65536 | 524288 | 0 | 449659 | 449659 | 0 | 0 | 65536 | 65536 | 25821184 | 374292655 | 41238228 | 286006799 | 47053683 | 3677720 | 3489405 | 51666717 | 24444928 | 0 | 0 | 46267251 | 131072 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 65536 | 2956984320 | 6291456 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 2352 | 48 | 0 | 0 | 0 | 2400 | 0 | 6291456 | 6267299 | 96 | 25713 | 231233 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074919479517501 | 12074933632230590 | 12074933632528987 | 12074919480078664 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7f1c6c05c600 | 0x7f1b60437000 | 0 | 524288 | 524288 | 131072 | 0 | 131072 | 524288 | 0 | 246561 | 246561 | 0 | 0 | 65536 | 65536 | 25886720 | 218043322 | 24437220 | 167784918 | 25821184 | 1980056 | 1814094 | 26998918 | 24444928 | 0 | 0 | 24903680 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 1593835520 | 6225920 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 2352 | 48 | 0 | 0 | 0 | 2400 | 0 | 6225920 | 6199611 | 138 | 42320 | 227748 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919480103651 | 12074933632588507 | 12074933632742905 | 12074919480465493 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7f1c6c05c500 | 0x7f1b60437040 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 593707 | 593707 | 0 | 0 | 65536 | 65536 | 46596096 | 560345225 | 20485412 | 472095589 | 67764224 | 4777240 | 4579453 | 68269084 | 45219840 | 0 | 0 | 66912256 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 4282384384 | 8781824 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 3264 | 48 | 0 | 0 | 0 | 3312 | 0 | 8781824 | 8747904 | 96 | 50665 | 252405 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919480530263 | 12074933632783865 | 12074933633169621 | 12074919481179410 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7f1c6c05c400 | 0x7f1b60437080 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 279241 | 279241 | 0 | 0 | 65536 | 65536 | 29556736 | 251472395 | 26876168 | 195105027 | 29491200 | 2223896 | 2060770 | 30643677 | 28180480 | 0 | 0 | 28639232 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 1832910848 | 7208960 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 2688 | 48 | 0 | 0 | 0 | 2736 | 0 | 7208960 | 7183387 | 159 | 52319 | 269273 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919481225806 | 12074933633240501 | 12074933633416819 | 12074919481586035 |
| 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 | 256 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7f1c6c05c300 | 0x7f1b604370c0 | 0 | 524288 | 524288 | 9895936 | 0 | 131072 | 524288 | 0 | 924803 | 924803 | 0 | 0 | 4325376 | 65536 | 125042688 | 888722762 | 96785575 | 670630051 | 121307136 | 7574936 | 7234136 | 107951734 | 105840640 | 0 | 0 | 106364928 | 10027008 | 0 | 4390912 | 524288 | 0 | 524288 | 131072 | 9895936 | 6807355392 | 19202048 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1200 | 48 | 0 | 0 | 0 | 1248 | 0 | 19202048 | 19200376 | 49 | 2022 | 197891 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074919481667767 | 12074933633457939 | 12074933634080333 | 12074919482520292 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7f1c6c05ca00 | 0x7f1b60437100 | 0 | 524288 | 524288 | 65536 | 0 | 65536 | 524288 | 0 | 497849 | 497849 | 0 | 0 | 65536 | 65536 | 30015488 | 460886933 | 28177870 | 377289914 | 55413093 | 4366872 | 3829939 | 57018631 | 28639232 | 0 | 0 | 54626661 | 131072 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 65536 | 3493855232 | 7340032 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 2736 | 48 | 0 | 0 | 0 | 2784 | 0 | 7340032 | 7304962 | 96 | 37120 | 190658 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074919482547833 | 12074933634144812 | 12074933634470569 | 12074919483145103 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7f1c6c05c900 | 0x7f1b60437140 | 0 | 524288 | 524288 | 131072 | 0 | 131072 | 524288 | 0 | 282971 | 282971 | 0 | 0 | 65536 | 65536 | 30081024 | 254182479 | 27911792 | 196255199 | 30015488 | 2259160 | 2091175 | 31101803 | 28639232 | 0 | 0 | 29097984 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 1862270976 | 7274496 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 2736 | 48 | 0 | 0 | 0 | 2784 | 0 | 7274496 | 7245235 | 188 | 54019 | 205478 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919483169448 | 12074933634535849 | 12074933634714567 | 12074919483555986 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7f1c6c05c800 | 0x7f1b60437180 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 696937 | 696937 | 0 | 0 | 65536 | 65536 | 54984704 | 666003335 | 23004353 | 562651846 | 80347136 | 5604824 | 5425378 | 80943451 | 53608448 | 0 | 0 | 79495168 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 5087690752 | 10354688 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 3840 | 48 | 0 | 0 | 0 | 3888 | 0 | 10354688 | 10314246 | 101 | 63786 | 203771 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919483648919 | 12074933634755527 | 12074933635210242 | 12074919484347317 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7f1c6c05c700 | 0x7f1b604371c0 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 313139 | 313139 | 0 | 0 | 65536 | 65536 | 33751040 | 281146122 | 25223659 | 222236959 | 33685504 | 2963352 | 2353891 | 35041411 | 32374784 | 0 | 0 | 32833536 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 2101346304 | 8257536 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 3072 | 48 | 0 | 0 | 0 | 3120 | 0 | 8257536 | 8229714 | 278 | 61474 | 203130 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919484384797 | 12074933635281282 | 12074933635480640 | 12074919484840243 |
| 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 | 266 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7f1c6c05c600 | 0x7f1b60437200 | 0 | 524288 | 524288 | 9895936 | 0 | 131072 | 524288 | 0 | 1066225 | 1066225 | 0 | 0 | 4325376 | 65536 | 141819904 | 1026418134 | 96785151 | 791548631 | 138084352 | 8533144 | 8358222 | 124759788 | 122617856 | 0 | 0 | 123142144 | 10027008 | 0 | 4390912 | 524288 | 0 | 524288 | 131072 | 9895936 | 7881097216 | 21299200 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1296 | 48 | 0 | 0 | 0 | 1344 | 0 | 21299200 | 21297376 | 48 | 2050 | 211024 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074919484870269 | 12074933635537279 | 12074933636238713 | 12074919485848527 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7f1c6c05c500 | 0x7f1b60437240 | 0 | 524288 | 524288 | 65536 | 0 | 65536 | 524288 | 0 | 566531 | 566531 | 0 | 0 | 65536 | 65536 | 34209792 | 532769284 | 20101210 | 448869860 | 63796642 | 4556248 | 4370630 | 65137132 | 32833536 | 0 | 0 | 63010210 | 131072 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 65536 | 4030726144 | 8388608 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 3120 | 48 | 0 | 0 | 0 | 3168 | 0 | 8388608 | 8351634 | 96 | 38899 | 221780 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074919485865839 | 12074933636301592 | 12074933636699509 | 12074919486522349 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7f1c6c05c400 | 0x7f1b60437280 | 0 | 524288 | 524288 | 131072 | 0 | 131072 | 524288 | 0 | 318209 | 318209 | 0 | 0 | 65536 | 65536 | 34275328 | 287288163 | 25266831 | 227811540 | 34209792 | 2558168 | 2388063 | 35539736 | 32833536 | 0 | 0 | 33292288 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 2130706432 | 8323072 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 3120 | 48 | 0 | 0 | 0 | 3168 | 0 | 8323072 | 8285796 | 154 | 72841 | 228454 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919486547415 | 12074933636759028 | 12074933636960946 | 12074919487019994 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7f1c6c05c300 | 0x7f1b604372c0 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 804067 | 804067 | 0 | 0 | 65536 | 65536 | 63373312 | 770454472 | 26817951 | 650706473 | 92930048 | 6432216 | 6264207 | 93481905 | 61997056 | 0 | 0 | 92078080 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 5892997120 | 11927552 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 4416 | 48 | 0 | 0 | 0 | 4464 | 0 | 11927552 | 11883010 | 144 | 62742 | 202427 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919487052845 | 12074933637020146 | 12074933637544461 | 12074919487838906 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7f1c6c05ca00 | 0x7f1b60437300 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 348217 | 348217 | 0 | 0 | 65536 | 65536 | 37945344 | 318618290 | 30242711 | 250495771 | 37879808 | 2802840 | 2630391 | 39195376 | 36569088 | 0 | 0 | 37027840 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 2369781760 | 9306112 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 3456 | 48 | 0 | 0 | 0 | 3504 | 0 | 9306112 | 9273444 | 314 | 75798 | 141372 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919487874492 | 12074933637622060 | 12074933637845258 | 12074919488366556 |
| 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 | 276 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7f1c6c05c900 | 0x7f1b60437340 | 0 | 524288 | 524288 | 18284544 | 0 | 131072 | 524288 | 0 | 1207147 | 1207147 | 0 | 0 | 8519680 | 65536 | 175374336 | 1169052614 | 118054491 | 883553643 | 167444480 | 9663512 | 9490739 | 141704465 | 139395072 | 0 | 0 | 139919360 | 18415616 | 0 | 8585216 | 524288 | 0 | 524288 | 131072 | 18284544 | 8954839040 | 29163520 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1008 | 48 | 0 | 0 | 0 | 1056 | 0 | 29163520 | 29162149 | 48 | 1663 | 199043 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074919488390741 | 12074933637903498 | 12074933638700130 | 12074919489457674 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7f1c6c05c800 | 0x7f1b60437380 | 0 | 524288 | 524288 | 65536 | 0 | 65536 | 524288 | 0 | 636137 | 636137 | 0 | 0 | 65536 | 65536 | 38404096 | 575513271 | 20189779 | 483137163 | 72186798 | 5372056 | 4924719 | 73435109 | 37027840 | 0 | 0 | 71400366 | 131072 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 65536 | 4567597056 | 9437184 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 3504 | 48 | 0 | 0 | 0 | 3552 | 0 | 9437184 | 9390073 | 96 | 49546 | 192329 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074919489488701 | 12074933638760450 | 12074933639178686 | 12074919490178042 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7f1c6c05c700 | 0x7f1b604373c0 | 0 | 524288 | 524288 | 131072 | 0 | 131072 | 524288 | 0 | 353379 | 353379 | 0 | 0 | 65536 | 65536 | 38469632 | 322625331 | 28187225 | 256034010 | 38404096 | 2842712 | 2663941 | 39665389 | 37027840 | 0 | 0 | 37486592 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 2399141888 | 9371648 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 3504 | 48 | 0 | 0 | 0 | 3552 | 0 | 9371648 | 9334907 | 260 | 72727 | 206158 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919490209271 | 12074933639244125 | 12074933639468923 | 12074919490701585 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7f1c6c05c600 | 0x7f1b60437400 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 907753 | 907753 | 0 | 0 | 65536 | 65536 | 71761920 | 873517023 | 26896195 | 741107868 | 105512960 | 7292376 | 7114342 | 106216492 | 70385664 | 0 | 0 | 104660992 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 6698303488 | 13500416 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 4992 | 48 | 0 | 0 | 0 | 5040 | 0 | 13500416 | 13448505 | 156 | 83916 | 209253 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919490726291 | 12074933639528603 | 12074933640125237 | 12074919491593513 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7f1c6c05c500 | 0x7f1b60437440 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 416019 | 416019 | 0 | 0 | 65536 | 65536 | 46465024 | 386677094 | 26677940 | 313599666 | 46399488 | 3358168 | 3183652 | 47310119 | 45088768 | 0 | 0 | 45547520 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 2915041280 | 11403264 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 4224 | 48 | 0 | 0 | 0 | 4272 | 0 | 11403264 | 11368529 | 517 | 107760 | 218464 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919491630472 | 12074933640195796 | 12074933640464114 | 12074919492154095 |
| 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 | 286 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7f1c6c05c400 | 0x7f1b60437480 | 0 | 524288 | 524288 | 18284544 | 0 | 131072 | 524288 | 0 | 1487945 | 1487945 | 0 | 0 | 8519680 | 65536 | 208928768 | 1446886760 | 116857873 | 1129029975 | 200998912 | 11901720 | 11736121 | 175246348 | 172949504 | 0 | 0 | 173473792 | 18415616 | 0 | 8585216 | 524288 | 0 | 524288 | 131072 | 18284544 | 11102322688 | 33357824 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1104 | 48 | 0 | 0 | 0 | 1152 | 0 | 33357824 | 33355870 | 96 | 2153 | 203722 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074919492178390 | 12074933640523633 | 12074933641507944 | 12074919493432951 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7f1c6c05c300 | 0x7f1b604374c0 | 0 | 524288 | 524288 | 65536 | 0 | 65536 | 524288 | 0 | 779331 | 779331 | 0 | 0 | 65536 | 65536 | 46923776 | 738996904 | 19775819 | 630130500 | 89090310 | 6224472 | 6056089 | 90319344 | 45547520 | 0 | 0 | 88303878 | 131072 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 65536 | 5649727488 | 11534336 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 4272 | 48 | 0 | 0 | 0 | 4320 | 0 | 11534336 | 11501619 | 96 | 41176 | 236289 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074919493467075 | 12074933641570024 | 12074933642082819 | 12074919494248647 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7f1c6c05ca00 | 0x7f1b60437500 | 0 | 524288 | 524288 | 131072 | 0 | 131072 | 524288 | 0 | 421545 | 421545 | 0 | 0 | 65536 | 65536 | 46989312 | 390301690 | 23780100 | 319597814 | 46923776 | 3369624 | 3202238 | 47665944 | 45547520 | 0 | 0 | 46006272 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 2944401408 | 11534336 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 4272 | 48 | 0 | 0 | 0 | 4320 | 0 | 11534336 | 11498414 | 501 | 87755 | 241114 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919494276830 | 12074933642151938 | 12074933642423616 | 12074919494815210 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7f1c6c05c900 | 0x7f1b60437540 | 0 | 524288 | 524288 | 4849664 | 0 | 131072 | 524288 | 0 | 1126531 | 1126531 | 0 | 0 | 2162688 | 65536 | 97845248 | 1090687515 | 80253271 | 872022212 | 138412032 | 9014232 | 8845988 | 132085879 | 87949312 | 0 | 0 | 130678784 | 4980736 | 0 | 2228224 | 524288 | 0 | 524288 | 131072 | 4849664 | 8363442176 | 19267584 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1968 | 48 | 0 | 0 | 0 | 2016 | 0 | 19267584 | 19260566 | 48 | 7009 | 294618 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919494838994 | 12074933642483455 | 12074933643220249 | 12074919495852157 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7f1c6c05c800 | 0x7f1b60437580 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 487225 | 487225 | 0 | 0 | 65536 | 65536 | 54853632 | 453023270 | 24147678 | 374087496 | 54788096 | 3933528 | 3736869 | 55595838 | 53477376 | 0 | 0 | 53936128 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 3451912192 | 13500416 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 4992 | 48 | 0 | 0 | 0 | 5040 | 0 | 13500416 | 13463896 | 889 | 123146 | 263556 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919495889236 | 12074933643290008 | 12074933643605365 | 12074919496467410 |
| 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 | 296 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7f1c6c05c700 | 0x7f1b604375c0 | 0 | 524288 | 524288 | 18284544 | 0 | 131072 | 524288 | 0 | 1768043 | 1768043 | 0 | 0 | 8519680 | 65536 | 242483200 | 1723554376 | 117638113 | 1371362919 | 234553344 | 14175832 | 13982527 | 208807354 | 206503936 | 0 | 0 | 207028224 | 18415616 | 0 | 8585216 | 524288 | 0 | 524288 | 131072 | 18284544 | 13249806336 | 37552128 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1200 | 48 | 0 | 0 | 0 | 1248 | 0 | 37552128 | 37550461 | 48 | 1930 | 257908 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074919496490884 | 12074933643667284 | 12074933644837994 | 12074919497940678 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7f1c6c05c600 | 0x7f1b60437600 | 0 | 524288 | 524288 | 65536 | 0 | 65536 | 524288 | 0 | 919857 | 919857 | 0 | 0 | 65536 | 65536 | 55312384 | 816654401 | 20677090 | 690111706 | 105866926 | 7344920 | 7168406 | 107054660 | 53936128 | 0 | 0 | 105080494 | 131072 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 65536 | 6723469312 | 13631488 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 5040 | 48 | 0 | 0 | 0 | 5088 | 0 | 13631488 | 13582745 | 144 | 64175 | 260531 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074919497970333 | 12074933644901833 | 12074933645511267 | 12074919498854096 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7f1c6c05c500 | 0x7f1b60437640 | 0 | 524288 | 524288 | 131072 | 0 | 131072 | 524288 | 0 | 491755 | 491755 | 0 | 0 | 65536 | 65536 | 55377920 | 460101202 | 27392229 | 377396589 | 55312384 | 3970456 | 3772891 | 56146940 | 53936128 | 0 | 0 | 54394880 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 3481272320 | 13631488 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 5040 | 48 | 0 | 0 | 0 | 5088 | 0 | 13631488 | 13590516 | 664 | 129830 | 256037 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919498879363 | 12074933645579747 | 12074933645897984 | 12074919499474909 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7f1c6c05c400 | 0x7f1b60437680 | 0 | 524288 | 524288 | 3801088 | 0 | 131072 | 524288 | 0 | 1335801 | 1335801 | 0 | 0 | 1638400 | 65536 | 112525312 | 1297764941 | 79197596 | 1056562353 | 162004992 | 10687512 | 10523449 | 157172800 | 104726528 | 0 | 0 | 155844608 | 3932160 | 0 | 1703936 | 524288 | 0 | 524288 | 131072 | 3801088 | 9974054912 | 21692416 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 2832 | 48 | 0 | 0 | 0 | 2880 | 0 | 21692416 | 21681962 | 96 | 10680 | 252540 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919499501108 | 12074933645958943 | 12074933646835575 | 12074919500641628 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7f1c6c05c300 | 0x7f1b604376c0 | 0 | 524288 | 524288 | 65536 | 0 | 131072 | 524288 | 0 | 632483 | 632483 | 0 | 0 | 65536 | 65536 | 71630848 | 595437390 | 29580293 | 494291785 | 71565312 | 5057240 | 4880893 | 72719057 | 70254592 | 0 | 0 | 70713344 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 65536 | 4525654016 | 17694720 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 6528 | 48 | 0 | 0 | 0 | 6576 | 0 | 17694720 | 17643625 | 1035 | 181088 | 242875 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919500677084 | 12074933646909655 | 12074933647318291 | 12074919501356797 |
| 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 | 306 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7f1c6c05ca00 | 0x7f1b60437700 | 0 | 524288 | 524288 | 35061760 | 0 | 131072 | 524288 | 0 | 2332577 | 2332577 | 0 | 0 | 16908288 | 65536 | 343146496 | 2283480637 | 161733260 | 1794919345 | 326828032 | 18671320 | 18497021 | 276326599 | 273612800 | 0 | 0 | 274137088 | 35192832 | 0 | 16973824 | 524288 | 0 | 524288 | 131072 | 35061760 | 17544773632 | 57475072 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1008 | 48 | 0 | 0 | 0 | 1056 | 0 | 57475072 | 57473833 | 50 | 1424 | 258848 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074919501381953 | 12074933647381490 | 12074933648928516 | 12074919503203829 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7f1c6c05c900 | 0x7f1b60437740 | 0 | 524288 | 524288 | 4849664 | 0 | 65536 | 524288 | 0 | 1201275 | 1201275 | 0 | 0 | 2162688 | 65536 | 80871424 | 1162158277 | 83248232 | 932215662 | 146694880 | 9611864 | 9440042 | 140898975 | 71041024 | 0 | 0 | 139027168 | 4915200 | 0 | 2228224 | 524288 | 0 | 524288 | 65536 | 4849664 | 8896118784 | 19660800 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 2064 | 48 | 0 | 0 | 0 | 2112 | 0 | 19660800 | 19653083 | 50 | 7902 | 275616 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074919503233424 | 12074933649019474 | 12074933649811308 | 12074919504301329 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7f1c6c05c800 | 0x7f1b60437780 | 0 | 524288 | 524288 | 4915200 | 0 | 131072 | 524288 | 0 | 638625 | 638625 | 0 | 0 | 2162688 | 65536 | 81461248 | 607748218 | 88151248 | 439774122 | 79822848 | 5407256 | 4959171 | 73908344 | 71499776 | 0 | 0 | 72024064 | 5046272 | 0 | 2228224 | 524288 | 0 | 524288 | 131072 | 4915200 | 4609540096 | 20381696 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 2112 | 48 | 0 | 0 | 0 | 2160 | 0 | 20381696 | 20370679 | 50 | 12078 | 235026 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919504329461 | 12074933649923786 | 12074933650337223 | 12074919505021217 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7f1c6c05c700 | 0x7f1b604377c0 | 0 | 524288 | 524288 | 4849664 | 0 | 131072 | 524288 | 0 | 1758606 | 1758606 | 0 | 0 | 2162688 | 65536 | 148176896 | 1715035510 | 83033584 | 1418092422 | 213909504 | 14060056 | 13893890 | 207516021 | 138280960 | 0 | 0 | 206176256 | 4980736 | 0 | 2228224 | 524288 | 0 | 524288 | 131072 | 4849664 | 13195280384 | 28704768 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 2832 | 48 | 0 | 0 | 0 | 2880 | 0 | 28704768 | 28693517 | 96 | 11644 | 239235 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919505052365 | 12074933650442342 | 12074933651600413 | 12074919506469157 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7f1c6c05c600 | 0x7f1b60437800 | 0 | 524288 | 524288 | 4849664 | 0 | 131072 | 524288 | 0 | 1199875 | 1199875 | 0 | 0 | 2162688 | 65536 | 148045824 | 1161179220 | 99961039 | 914810757 | 146407424 | 9591000 | 9422685 | 140663832 | 138149888 | 0 | 0 | 138674176 | 4980736 | 0 | 2228224 | 524288 | 0 | 524288 | 131072 | 4849664 | 8875147264 | 36634624 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 3600 | 48 | 0 | 0 | 0 | 3648 | 0 | 36634624 | 36613798 | 97 | 22597 | 271444 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919506506587 | 12074933651718012 | 12074933652503126 | 12074919507543744 |
| 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 | 316 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7f1c6c05c500 | 0x7f1b60437840 | 0 | 524288 | 524288 | 68616192 | 0 | 131072 | 524288 | 0 | 4584193 | 4584193 | 0 | 0 | 33685504 | 65536 | 678690816 | 4515076962 | 255224692 | 3614257134 | 645595136 | 36670936 | 36502071 | 545489997 | 542048256 | 0 | 0 | 542572544 | 68747264 | 0 | 33751040 | 524288 | 0 | 524288 | 131072 | 68616192 | 34724642816 | 105840640 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1008 | 48 | 0 | 0 | 0 | 1056 | 0 | 105840640 | 105839195 | 98 | 1792 | 253263 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074919507574051 | 12074933652612885 | 12074933655663421 | 12074919510893189 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7f1c6c05c400 | 0x7f1b60437880 | 0 | 524288 | 524288 | 9043968 | 0 | 65536 | 524288 | 0 | 2325390 | 2325390 | 0 | 0 | 4259840 | 65536 | 156368896 | 2275866287 | 95656811 | 1893003355 | 287206031 | 18592536 | 18422718 | 275220650 | 138149888 | 0 | 0 | 273246863 | 9109504 | 0 | 4325376 | 524288 | 0 | 524288 | 65536 | 9043968 | 17486053376 | 38535168 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 2064 | 48 | 0 | 0 | 0 | 2112 | 0 | 38535168 | 38528107 | 49 | 7326 | 223984 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074919510922073 | 12074933655772540 | 12074933657314288 | 12074919512743307 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7f1c6c05c300 | 0x7f1b604378c0 | 0 | 524288 | 524288 | 9109504 | 0 | 131072 | 524288 | 0 | 1201667 | 1201667 | 0 | 0 | 4259840 | 65536 | 156958720 | 1165186500 | 108617570 | 903345762 | 153223168 | 9633752 | 9459789 | 141231793 | 138608640 | 0 | 0 | 139132928 | 9240576 | 0 | 4325376 | 524288 | 0 | 524288 | 131072 | 9109504 | 8904507392 | 39124992 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 2112 | 48 | 0 | 0 | 0 | 2160 | 0 | 39124992 | 39117977 | 98 | 7357 | 199522 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919512767773 | 12074933657425967 | 12074933658214601 | 12074919513829085 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7f1c6c05ca00 | 0x7f1b60437900 | 0 | 524288 | 524288 | 9043968 | 0 | 131072 | 524288 | 0 | 3442121 | 3442121 | 0 | 0 | 4259840 | 65536 | 290783232 | 3384158102 | 98562183 | 2864068367 | 421527552 | 27545752 | 27377386 | 409067975 | 272498688 | 0 | 0 | 407502848 | 9175040 | 0 | 4325376 | 524288 | 0 | 524288 | 131072 | 9043968 | 26080182272 | 55771136 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 2832 | 48 | 0 | 0 | 0 | 2880 | 0 | 55771136 | 55759045 | 96 | 12885 | 217529 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919513858710 | 12074933658323400 | 12074933660603862 | 12074919516415992 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7f1c6c05c900 | 0x7f1b60437940 | 0 | 524288 | 524288 | 9043968 | 0 | 131072 | 524288 | 0 | 2323219 | 2323219 | 0 | 0 | 4259840 | 65536 | 290652160 | 2276004249 | 134262674 | 1854824967 | 286916608 | 18600728 | 18421994 | 275160587 | 272367616 | 0 | 0 | 272891904 | 9175040 | 0 | 4325376 | 524288 | 0 | 524288 | 131072 | 9043968 | 17465081856 | 72548352 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 3600 | 48 | 0 | 0 | 0 | 3648 | 0 | 72548352 | 72532597 | 99 | 15984 | 249135 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919516461567 | 12074933660719701 | 12074933662255209 | 12074919518247386 |
| 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 | 326 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7f1c6c05c800 | 0x7f1b60437980 | 0 | 524288 | 524288 | 135725056 | 0 | 131072 | 524288 | 0 | 9087625 | 9087625 | 0 | 0 | 67239936 | 65536 | 1349779456 | 8977336276 | 433377962 | 7260828970 | 1283129344 | 72710680 | 72530485 | 1084058941 | 1078919168 | 0 | 0 | 1079443456 | 135856128 | 0 | 67305472 | 524288 | 0 | 524288 | 131072 | 135725056 | 69084381184 | 210698240 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 1008 | 48 | 0 | 0 | 0 | 1056 | 0 | 210698240 | 210697068 | 50 | 1454 | 203512 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074919518280177 | 12074933662358408 | 12074933668411640 | 12074919524605762 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7f1c6c05c700 | 0x7f1b604379c0 | 0 | 524288 | 524288 | 17432576 | 0 | 65536 | 524288 | 0 | 4572483 | 4572483 | 0 | 0 | 8454144 | 65536 | 307363840 | 4503843940 | 151279559 | 3784333213 | 568231158 | 36592664 | 36417151 | 544148514 | 272367616 | 0 | 0 | 541689078 | 17498112 | 0 | 8519680 | 524288 | 0 | 524288 | 65536 | 17432576 | 34665922560 | 76283904 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 2064 | 48 | 0 | 0 | 0 | 2112 | 0 | 76283904 | 76278439 | 97 | 5974 | 184479 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074919524637341 | 12074933668522039 | 12074933671562175 | 12074919527953163 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7f1c6c05c600 | 0x7f1b60437a00 | 0 | 524288 | 524288 | 17498112 | 0 | 131072 | 524288 | 0 | 2328825 | 2328825 | 0 | 0 | 8454144 | 65536 | 307953664 | 2279311319 | 150816995 | 1828470516 | 300023808 | 18638040 | 18465781 | 275811859 | 272826368 | 0 | 0 | 273350656 | 17629184 | 0 | 8519680 | 524288 | 0 | 524288 | 131072 | 17498112 | 17494441984 | 77398016 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 2112 | 48 | 0 | 0 | 0 | 2160 | 0 | 77398016 | 77389345 | 100 | 8887 | 220943 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919527984571 | 12074933671672094 | 12074933673210642 | 12074919529802509 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 853819 | 853824 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7f1c6c05c500 | 0x7f1b60437a40 | 0 | 524288 | 524288 | 17432576 | 0 | 131072 | 524288 | 0 | 6813779 | 6813779 | 0 | 0 | 8454144 | 65536 | 575995904 | 6722020003 | 121777234 | 5763479121 | 836763648 | 54521112 | 54338445 | 812090316 | 540934144 | 0 | 0 | 810156032 | 17563648 | 0 | 8519680 | 524288 | 0 | 524288 | 131072 | 17432576 | 51849986048 | 110821376 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 2832 | 48 | 0 | 0 | 0 | 2880 | 0 | 110821376 | 110809780 | 96 | 11763 | 245700 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074919529829560 | 12074933673318641 | 12074933677844205 | 12074919534640169 |