111 KiB
111 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | SQ_INSTS_VALU_CVT | SQ_INSTS_VMEM_WR | SQ_INSTS_VMEM_RD | SQ_INSTS_VMEM | SQ_INSTS_SALU | SQ_INSTS_VSKIPPED | SQ_INSTS | SQ_INSTS_VALU | GRBM_COUNT | GRBM_GUI_ACTIVE | SQ_INSTS_VALU_ADD_F16 | SQ_INSTS_VALU_MUL_F16 | SQ_INSTS_VALU_FMA_F16 | SQ_INSTS_VALU_TRANS_F16 | SQ_INSTS_VALU_ADD_F32 | SQ_INSTS_VALU_MUL_F32 | SQ_INSTS_VALU_FMA_F32 | SQ_INSTS_VALU_TRANS_F32 | 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 | SQ_INSTS_VALU_ADD_F64 | SQ_INSTS_VALU_MUL_F64 | SQ_INSTS_VALU_FMA_F64 | SQ_INSTS_VALU_TRANS_F64 | SQ_INSTS_VALU_INT32 | SQ_INSTS_VALU_INT64 | SQ_INSTS_SMEM | SQ_INSTS_FLAT | SQ_INSTS_LDS | SQ_INSTS_GDS | SQ_INSTS_EXP_GDS | SQ_INSTS_BRANCH | SQ_INSTS_SENDMSG | SQ_WAVE_CYCLES | SQ_WAIT_ANY | SQ_WAIT_INST_ANY | SQ_ACTIVE_INST_ANY | SQ_CYCLES | SQ_BUSY_CYCLES | SQ_BUSY_CU_CYCLES | 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 | SQ_INSTS_MFMA | SQ_INSTS_VALU_MFMA_I8 | SQ_INSTS_VALU_MFMA_F16 | SQ_INSTS_VALU_MFMA_BF16 | SQ_INSTS_VALU_MFMA_F32 | SQ_INSTS_VALU_MFMA_F64 | SQ_VALU_MFMA_BUSY_CYCLES | SQ_INSTS_FLAT_LDS_ONLY | SQ_INSTS_VALU_MFMA_MOPS_I8 | SQ_INSTS_VALU_MFMA_MOPS_F16 | SQ_INSTS_VALU_MFMA_MOPS_BF16 | SQ_INSTS_VALU_MFMA_MOPS_F32 | SQ_INSTS_VALU_MFMA_MOPS_F64 | SQC_TC_INST_REQ | SQC_TC_DATA_READ_REQ | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBufferAligned.kd | 0 | 0 | 0 | 137896 | 137896 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7f6ef5c04280 | 0 | 524288 | 0 | 524288 | 7340032 | 0 | 25690112 | 9437184 | 386272 | 386272 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 616 | 0 | 4718592 | 4714901 | 112 | 3510 | 1131343 | 0 | 524288 | 3670016 | 3663234 | 224 | 6558 | 1048576 | 1048576 | 1048576 | 0 | 0 | 0 | 0 | 5767168 | 1048576 | 3670016 | 524288 | 0 | 0 | 0 | 2621440 | 524288 | 246413115 | 178736228 | 43559639 | 24117248 | 3073544 | 2986786 | 38806136 | 0 | 0 | 9437184 | 11010048 | 0 | 3145728 | 524288 | 524288 | 0 | 3670016 | 7340032 | 603979776 | 4718592 | 0 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 0 | 33554432 | 0 | 0 | 0 | 0 | 0 | 7340032 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 392 | 224 | 15896002897487 | 15906971870954 | 15906972109355 | 15896147670838 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 137896 | 137896 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7f6ef5c23f80 | 0 | 0 | 4096 | 4096 | 512 | 0 | 35328 | 26112 | 33732 | 33732 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 560 | 0 | 8192 | 6202 | 56 | 2001 | 670 | 0 | 0 | 512 | 0 | 56 | 456 | 0 | 512 | 0 | 0 | 0 | 0 | 0 | 10752 | 3584 | 512 | 4096 | 0 | 0 | 0 | 512 | 512 | 1667298 | 1615115 | 19927 | 32256 | 260520 | 154115 | 1394994 | 0 | 0 | 26112 | 1024 | 0 | 1024 | 4096 | 0 | 4096 | 512 | 512 | 1671168 | 8192 | 0 | 0 | 0 | 512 | 512 | 0 | 0 | 0 | 0 | 32768 | 0 | 0 | 0 | 0 | 0 | 1024 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 504 | 56 | 15896152854722 | 15906976935930 | 15906976949530 | 15896152998919 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7f6ef8b5e380 | 0x7f6ef5c23fc0 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 4063232 | 2883584 | 164664 | 164664 | 0 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 448 | 0 | 917504 | 912756 | 0 | 3554 | 907658 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 76929059 | 47981683 | 25211824 | 3735552 | 1311456 | 1210376 | 15640237 | 0 | 0 | 2883584 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 184549376 | 917504 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 392 | 56 | 15896153048378 | 15906977018810 | 15906977110971 | 15896153397420 |
| 5 | 3 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 8 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7f6ef8b5e200 | 0x7f6ef5c24000 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 5308416 | 3014656 | 309892 | 309892 | 0 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 616 | 0 | 1114112 | 1110707 | 56 | 3523 | 443398 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 215432999 | 50024766 | 160427497 | 4980736 | 2497448 | 2394757 | 31013674 | 0 | 0 | 3014656 | 1245184 | 0 | 196608 | 524288 | 0 | 524288 | 65536 | 1179648 | 192937984 | 1114112 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 560 | 56 | 15896153447629 | 15906977144891 | 15906977324411 | 15896153834960 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7f6ef8b5e080 | 0x7f6ef5c24040 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 4063232 | 2883584 | 310413 | 310413 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 504 | 0 | 917504 | 914296 | 56 | 3325 | 621610 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 65536 | 0 | 0 | 0 | 262144 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 226324128 | 50245966 | 172342610 | 3735552 | 2481144 | 2379116 | 30825229 | 0 | 0 | 2883584 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 184549376 | 917504 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 448 | 56 | 15896153881659 | 15906977349691 | 15906977530332 | 15896154262361 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7f6ef63fdf00 | 0x7f6ef5c24080 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 4587520 | 3342336 | 166213 | 166213 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 560 | 0 | 1048576 | 1044651 | 56 | 3895 | 698004 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 84288826 | 48641896 | 31387090 | 4259840 | 1325680 | 1220026 | 15776358 | 0 | 0 | 3342336 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 196608 | 213909504 | 1048576 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 504 | 56 | 15896154309379 | 15906977554812 | 15906977648092 | 15896154606783 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7f6ef63fdd80 | 0x7f6ef5c240c0 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 4194304 | 3014656 | 164967 | 164967 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 504 | 0 | 983040 | 979582 | 56 | 3352 | 915618 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 65536 | 0 | 0 | 0 | 0 | 0 | 1966080 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 76721981 | 47756038 | 25099319 | 3866624 | 1313680 | 1209172 | 15631100 | 0 | 0 | 3014656 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 192937984 | 983040 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 448 | 56 | 15896154652682 | 15906977673532 | 15906977765853 | 15896154952865 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7f6ef63fdc00 | 0x7f6ef5c24100 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 5111808 | 3538944 | 163313 | 163313 | 0 | 0 | 0 | 0 | 0 | 0 | 655360 | 0 | 0 | 0 | 0 | 560 | 0 | 1114112 | 1111843 | 0 | 2360 | 865324 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 92468537 | 47730774 | 40215779 | 4521984 | 1324064 | 1217402 | 15770955 | 0 | 0 | 3538944 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 226492416 | 1114112 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 504 | 56 | 15896155012234 | 15906977805533 | 15906977898013 | 15896155292758 |
| 10 | 8 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 23 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7f6ef63fda80 | 0x7f6ef5c24140 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 6094848 | 3538944 | 310858 | 310858 | 0 | 0 | 0 | 0 | 0 | 0 | 786432 | 0 | 0 | 0 | 0 | 672 | 0 | 1310720 | 1307553 | 56 | 3204 | 623244 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 222437893 | 50681011 | 166186322 | 5570560 | 2482672 | 2374185 | 30765247 | 0 | 0 | 3538944 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 226492416 | 1310720 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 616 | 56 | 15896155337877 | 15906977935293 | 15906978114334 | 15896155735798 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7f6ef63fd900 | 0x7f6ef5c24180 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 5242880 | 3801088 | 310341 | 310341 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 616 | 0 | 1179648 | 1175728 | 56 | 4172 | 665514 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 786432 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 222875168 | 73976735 | 144245377 | 4653056 | 2495424 | 2392124 | 30941883 | 0 | 0 | 3801088 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 243269632 | 1179648 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 560 | 56 | 15896155780437 | 15906978142174 | 15906978322335 | 15896156162798 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7f6ef63fd780 | 0x7f6ef5c241c0 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 5439488 | 3866624 | 166138 | 166138 | 0 | 0 | 786432 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 616 | 0 | 1245184 | 1241174 | 56 | 4298 | 443828 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 88577246 | 46974988 | 36752594 | 4849664 | 1323880 | 1219663 | 15779401 | 0 | 0 | 3866624 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 247463936 | 1245184 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 560 | 56 | 15896156208027 | 15906978350335 | 15906978444255 | 15896156498281 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7f6ef63fd600 | 0x7f6ef5c24200 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 5636096 | 4063232 | 165356 | 165356 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 616 | 0 | 1245184 | 1241274 | 56 | 3794 | 694227 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 3014656 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 86034400 | 47816840 | 33236824 | 4980736 | 1321320 | 1215070 | 15718482 | 0 | 0 | 4063232 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 260046848 | 1245184 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 560 | 56 | 15896156544450 | 15906978484575 | 15906978578175 | 15896156833494 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7f6ef8b5e480 | 0x7f6ef5c24240 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 5439488 | 3932160 | 164522 | 164522 | 0 | 0 | 0 | 0 | 0 | 0 | 1048576 | 0 | 0 | 0 | 0 | 616 | 0 | 1245184 | 1241550 | 56 | 4968 | 438212 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 93263715 | 47839613 | 40443366 | 4980736 | 1325008 | 1220964 | 15811579 | 0 | 0 | 3932160 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 251658240 | 1245184 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 560 | 56 | 15896156889362 | 15906978617696 | 15906978710336 | 15896157170166 |
| 15 | 13 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 38 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7f6ef8b5e300 | 0x7f6ef5c24280 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 6619136 | 4063232 | 309766 | 309766 | 0 | 0 | 0 | 0 | 0 | 0 | 1310720 | 0 | 0 | 0 | 0 | 728 | 0 | 1441792 | 1437192 | 56 | 3560 | 462054 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 230407168 | 50154373 | 174157947 | 6094848 | 2483376 | 2379343 | 30809835 | 0 | 0 | 4063232 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 260046848 | 1441792 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 672 | 56 | 15896157216855 | 15906978745536 | 15906978924417 | 15896157593017 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7f6ef8b5e180 | 0x7f6ef5c242c0 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 5767168 | 4325376 | 309746 | 309746 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 672 | 0 | 1310720 | 1306320 | 56 | 4341 | 648945 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 1310720 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 216940946 | 72222017 | 139541585 | 5177344 | 2450800 | 2346988 | 30425744 | 0 | 0 | 4325376 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 276824064 | 1310720 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 616 | 56 | 15896157638536 | 15906978949057 | 15906979127617 | 15896158015647 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7f6ef8b5e000 | 0x7f6ef5c24300 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 5963776 | 4390912 | 164524 | 164524 | 0 | 0 | 1310720 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 672 | 0 | 1376256 | 1371884 | 56 | 4656 | 593709 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 90628681 | 48151913 | 37102816 | 5373952 | 1317616 | 1212903 | 15682786 | 0 | 0 | 4390912 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 281018368 | 1376256 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 616 | 56 | 15896158061166 | 15906979162817 | 15906979255618 | 15896158394789 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7f6ef63fde80 | 0x7f6ef5c24340 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 6619136 | 5111808 | 163844 | 163844 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 728 | 0 | 1441792 | 1437688 | 56 | 4154 | 505246 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 4063232 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 87142358 | 46635342 | 34477704 | 6029312 | 1310880 | 1209056 | 15656786 | 0 | 0 | 5111808 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 327155712 | 1441792 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 672 | 56 | 15896158440518 | 15906979288898 | 15906979381858 | 15896158742851 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7f6ef63fdd00 | 0x7f6ef5c24380 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 5898240 | 4325376 | 163500 | 163500 | 0 | 0 | 0 | 0 | 0 | 0 | 1441792 | 0 | 0 | 0 | 0 | 672 | 0 | 1310720 | 1306447 | 112 | 4200 | 689410 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 102306469 | 48908876 | 48023641 | 5373952 | 1304768 | 1204258 | 15592697 | 0 | 0 | 4325376 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 276824064 | 1310720 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 616 | 56 | 15896158799180 | 15906979415618 | 15906979509539 | 15896159049774 |
| 20 | 18 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 53 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7f6ef63fdb80 | 0x7f6ef5c243c0 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 7143424 | 4587520 | 308792 | 308792 | 0 | 0 | 0 | 0 | 0 | 0 | 1835008 | 0 | 0 | 0 | 0 | 784 | 0 | 1572864 | 1569271 | 56 | 3454 | 457291 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 226304788 | 50157360 | 169528292 | 6619136 | 2477712 | 2367688 | 30695265 | 0 | 0 | 4587520 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 293601280 | 1572864 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 728 | 56 | 15896159095933 | 15906979542019 | 15906979722499 | 15896159444495 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7f6ef63fda00 | 0x7f6ef5c24400 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 6291456 | 4849664 | 306740 | 306740 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 672 | 0 | 1441792 | 1439314 | 0 | 2350 | 878855 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 1835008 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 217823358 | 69913556 | 142208170 | 5701632 | 2449168 | 2345147 | 30374962 | 0 | 0 | 4849664 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 310378496 | 1441792 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 616 | 56 | 15896159493694 | 15906979750499 | 15906979931460 | 15896159835947 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7f6ef63fd880 | 0x7f6ef5c24440 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 6422528 | 4915200 | 164431 | 164431 | 0 | 0 | 1835008 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 728 | 0 | 1507328 | 1502946 | 56 | 3861 | 474600 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 88620238 | 46716839 | 36005159 | 5898240 | 1309456 | 1208156 | 15627852 | 0 | 0 | 4915200 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 314572800 | 1507328 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 672 | 56 | 15896159882186 | 15906979980580 | 15906980073700 | 15896160138290 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7f6ef63fd700 | 0x7f6ef5c24480 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 7733248 | 6160384 | 164064 | 164064 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 784 | 0 | 1638400 | 1633829 | 56 | 4501 | 584210 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 5111808 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 103115823 | 44996822 | 51041113 | 7077888 | 1302376 | 1201463 | 15545586 | 0 | 0 | 6160384 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 394264576 | 1638400 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 728 | 56 | 15896160184299 | 15906980110181 | 15906980204421 | 15896160445983 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7f6ef8b5e580 | 0x7f6ef5c244c0 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 6291456 | 4718592 | 163042 | 163042 | 0 | 0 | 0 | 0 | 0 | 0 | 1835008 | 0 | 0 | 0 | 0 | 672 | 0 | 1441792 | 1438270 | 56 | 3772 | 848969 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 103597544 | 46669602 | 51160774 | 5767168 | 1302920 | 1199465 | 15528650 | 0 | 0 | 4718592 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 301989888 | 1441792 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 616 | 56 | 15896160500122 | 15906980238661 | 15906980331141 | 15896160750626 |
| 25 | 23 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 68 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7f6ef8b5e400 | 0x7f6ef5c24500 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 7667712 | 5111808 | 310644 | 310644 | 0 | 0 | 0 | 0 | 0 | 0 | 2359296 | 0 | 0 | 0 | 0 | 840 | 0 | 1703936 | 1700235 | 56 | 3597 | 627698 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 223442841 | 49494164 | 166805253 | 7143424 | 2476472 | 2373241 | 30745334 | 0 | 0 | 5111808 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 327155712 | 1703936 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 784 | 56 | 15896160802395 | 15906980366021 | 15906980544262 | 15896161153747 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7f6ef8b5e280 | 0x7f6ef5c24540 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 6815744 | 5373952 | 308475 | 308475 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 784 | 0 | 1572864 | 1568631 | 56 | 4218 | 683235 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 2359296 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 218757695 | 69784770 | 142747005 | 6225920 | 2465816 | 2361137 | 30576099 | 0 | 0 | 5373952 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 343932928 | 1572864 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 728 | 56 | 15896161201046 | 15906980570662 | 15906980750183 | 15896161547048 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7f6ef8b5e100 | 0x7f6ef5c24580 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 6946816 | 5439488 | 162105 | 162105 | 0 | 0 | 2359296 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 728 | 0 | 1638400 | 1634777 | 0 | 3791 | 901190 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 87639955 | 46146850 | 35070577 | 6422528 | 1304448 | 1199931 | 15527311 | 0 | 0 | 5439488 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 348127232 | 1638400 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 672 | 56 | 15896161595407 | 15906980774503 | 15906980867143 | 15896161850952 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7f6ef63fdf80 | 0x7f6ef5c245c0 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 8781824 | 7208960 | 163215 | 163215 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 840 | 0 | 1835008 | 1830009 | 0 | 4188 | 892610 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 6160384 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 92278612 | 42135143 | 42017005 | 8126464 | 1302368 | 1200267 | 15505502 | 0 | 0 | 7208960 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 461373440 | 1835008 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 784 | 56 | 15896161898691 | 15906980890983 | 15906980982983 | 15896162154765 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7f6ef63fde00 | 0x7f6ef5c24600 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 6684672 | 5111808 | 164271 | 164271 | 0 | 0 | 0 | 0 | 0 | 0 | 2228224 | 0 | 0 | 0 | 0 | 784 | 0 | 1507328 | 1502385 | 112 | 6384 | 444326 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 102398159 | 46982706 | 49255069 | 6160384 | 1302848 | 1201004 | 15553675 | 0 | 0 | 5111808 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 327155712 | 1507328 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 728 | 56 | 15896162208504 | 15906981016104 | 15906981109064 | 15896162465418 |
| 30 | 28 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 83 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7f6ef63fdc80 | 0x7f6ef5c24640 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 8192000 | 5636096 | 306730 | 306730 | 0 | 0 | 0 | 0 | 0 | 0 | 2883584 | 0 | 0 | 0 | 0 | 840 | 0 | 1835008 | 1831399 | 0 | 3677 | 869811 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 220698600 | 48261147 | 164769741 | 7667712 | 2450256 | 2345035 | 30351557 | 0 | 0 | 5636096 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 360710144 | 1835008 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 784 | 56 | 15896162511927 | 15906981134184 | 15906981314985 | 15896162861899 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7f6ef63fdb00 | 0x7f6ef5c24680 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 7340032 | 5898240 | 309440 | 309440 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 840 | 0 | 1703936 | 1700257 | 56 | 4038 | 863959 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 2883584 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 217251109 | 64386292 | 146114609 | 6750208 | 2447568 | 2343117 | 30356247 | 0 | 0 | 5898240 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 377487360 | 1703936 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 784 | 56 | 15896162909538 | 15906981338345 | 15906981519145 | 15896163255320 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7f6ef63fd980 | 0x7f6ef5c246c0 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 7471104 | 5963776 | 163328 | 163328 | 0 | 0 | 2883584 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 840 | 0 | 1769472 | 1764732 | 56 | 5245 | 441959 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 91060935 | 45734585 | 38379534 | 6946816 | 1307488 | 1202838 | 15534400 | 0 | 0 | 5963776 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 381681664 | 1769472 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 784 | 56 | 15896163302379 | 15906981543305 | 15906981636746 | 15896163561883 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7f6ef63fd800 | 0x7f6ef5c24700 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 9830400 | 8257536 | 163308 | 163308 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 952 | 0 | 2031616 | 2025539 | 112 | 6764 | 441604 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 7208960 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 84792798 | 41389402 | 34228356 | 9175040 | 1311888 | 1206031 | 15569072 | 0 | 0 | 8257536 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 528482304 | 2031616 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 896 | 56 | 15896163608972 | 15906981661546 | 15906981755466 | 15896163867447 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7f6ef63fd680 | 0x7f6ef5c24740 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 7077888 | 5505024 | 163978 | 163978 | 0 | 0 | 0 | 0 | 0 | 0 | 2621440 | 0 | 0 | 0 | 0 | 784 | 0 | 1638400 | 1633425 | 56 | 4871 | 450162 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 97488167 | 45786504 | 45148063 | 6553600 | 1305344 | 1201826 | 15553403 | 0 | 0 | 5505024 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 352321536 | 1638400 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 728 | 56 | 15896163920555 | 15906981787946 | 15906981880906 | 15896164178160 |
| 35 | 33 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 98 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7f6ef8b5e500 | 0x7f6ef5c24780 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 8781824 | 6160384 | 308738 | 308738 | 0 | 0 | 0 | 0 | 0 | 0 | 3407872 | 0 | 0 | 0 | 0 | 896 | 0 | 1966080 | 1962964 | 0 | 3376 | 839333 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 224740016 | 48160016 | 168388000 | 8192000 | 2461024 | 2355784 | 30510167 | 0 | 0 | 6160384 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 394264576 | 1966080 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 840 | 56 | 15896164224629 | 15906981905226 | 15906982085227 | 15896164570601 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7f6ef8b5e380 | 0x7f6ef5c247c0 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 7929856 | 6422528 | 307376 | 307376 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 896 | 0 | 1835008 | 1829143 | 56 | 5720 | 439822 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 3407872 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 209468685 | 60629992 | 141564197 | 7274496 | 2452768 | 2352108 | 30473435 | 0 | 0 | 6422528 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 411041792 | 1835008 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 840 | 56 | 15896164619740 | 15906982110827 | 15906982290508 | 15896164964632 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7f6ef8b5e200 | 0x7f6ef5c24800 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 8060928 | 6488064 | 163882 | 163882 | 0 | 0 | 3407872 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 896 | 0 | 1900544 | 1894992 | 112 | 4942 | 733795 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 87766281 | 44383991 | 35911186 | 7471104 | 1307000 | 1202902 | 15547023 | 0 | 0 | 6488064 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 415236096 | 1900544 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 840 | 56 | 15896165011331 | 15906982314508 | 15906982408748 | 15896165270925 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7f6ef8b5e080 | 0x7f6ef5c24840 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 10813440 | 9306112 | 163203 | 163203 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1064 | 0 | 2228224 | 2222179 | 56 | 5133 | 697231 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 8257536 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 91501532 | 39243924 | 42033992 | 10223616 | 1304328 | 1196148 | 15434702 | 0 | 0 | 9306112 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 595591168 | 2228224 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1008 | 56 | 15896165318714 | 15906982431788 | 15906982526349 | 15896165577048 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7f6ef63fdf00 | 0x7f6ef5c24880 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 7471104 | 5898240 | 162629 | 162629 | 0 | 0 | 0 | 0 | 0 | 0 | 3014656 | 0 | 0 | 0 | 0 | 840 | 0 | 1703936 | 1699218 | 56 | 5340 | 438745 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 95816920 | 44943072 | 43927032 | 6946816 | 1304472 | 1203072 | 15565541 | 0 | 0 | 5898240 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 377487360 | 1703936 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 784 | 56 | 15896165631267 | 15906982559789 | 15906982653229 | 15896165888151 |
| 40 | 38 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 113 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7f6ef63fdd80 | 0x7f6ef5c248c0 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 9306112 | 6684672 | 306025 | 306025 | 0 | 0 | 0 | 0 | 0 | 0 | 3932160 | 0 | 0 | 0 | 0 | 1008 | 0 | 2097152 | 2092983 | 56 | 4354 | 441100 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 227044051 | 48918773 | 169408990 | 8716288 | 2434808 | 2329122 | 30195367 | 0 | 0 | 6684672 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 427819008 | 2097152 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 952 | 56 | 15896165938910 | 15906982679309 | 15906982858830 | 15896166303592 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7f6ef63fdc00 | 0x7f6ef5c24900 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 8388608 | 6946816 | 303553 | 303553 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 896 | 0 | 1966080 | 1963216 | 56 | 2954 | 853152 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 3932160 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 214827846 | 59103320 | 147925742 | 7798784 | 2434920 | 2331641 | 30215579 | 0 | 0 | 6946816 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 444596224 | 1966080 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 840 | 56 | 15896166350811 | 15906982883150 | 15906983063630 | 15896166701173 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7f6ef63fda80 | 0x7f6ef5c24940 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 8585216 | 7012352 | 163821 | 163821 | 0 | 0 | 3932160 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 952 | 0 | 2031616 | 2025694 | 56 | 5007 | 446107 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 83868682 | 44027724 | 31845566 | 7995392 | 1315512 | 1210223 | 15635919 | 0 | 0 | 7012352 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 448790528 | 2031616 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 896 | 56 | 15896166746932 | 15906983089070 | 15906983183471 | 15896167006506 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7f6ef63fd900 | 0x7f6ef5c24980 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 11927552 | 10354688 | 165099 | 165099 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1120 | 0 | 2424832 | 2418626 | 56 | 7893 | 566940 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 9306112 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 92469457 | 37881613 | 43315652 | 11272192 | 1301784 | 1199874 | 15472205 | 0 | 0 | 10354688 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 662700032 | 2424832 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1064 | 56 | 15896167053265 | 15906983207791 | 15906983302351 | 15896167311190 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7f6ef63fd780 | 0x7f6ef5c249c0 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 7995392 | 6291456 | 162701 | 162701 | 0 | 0 | 0 | 0 | 0 | 0 | 3407872 | 0 | 0 | 0 | 0 | 896 | 0 | 1835008 | 1829771 | 56 | 6885 | 441751 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 87878688 | 43524863 | 37013793 | 7340032 | 1295032 | 1195120 | 15454508 | 0 | 0 | 6291456 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 402653184 | 1835008 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 840 | 56 | 15896167364778 | 15906983334991 | 15906983427791 | 15896167631912 |
| 45 | 43 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 128 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7f6ef63fd600 | 0x7f6ef5c24a00 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 9830400 | 7208960 | 302471 | 302471 | 0 | 0 | 0 | 0 | 0 | 0 | 4456448 | 0 | 0 | 0 | 0 | 1064 | 0 | 2228224 | 2223427 | 112 | 4750 | 450793 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 227719499 | 47349595 | 171129328 | 9240576 | 2438168 | 2331409 | 30180115 | 0 | 0 | 7208960 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 461373440 | 2228224 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1008 | 56 | 15896167679441 | 15906983452112 | 15906983631792 | 15896168022694 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7f6ef8b5e480 | 0x7f6ef5c24a40 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 8912896 | 7471104 | 302851 | 302851 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1008 | 0 | 2097152 | 2091878 | 56 | 5812 | 450298 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 4456448 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 213235142 | 57358449 | 147553621 | 8323072 | 2407528 | 2301232 | 29813278 | 0 | 0 | 7471104 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 478150656 | 2097152 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 952 | 56 | 15896168070303 | 15906983655152 | 15906983835313 | 15896168412765 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7f6ef8b5e300 | 0x7f6ef5c24a80 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 9109504 | 7536640 | 162923 | 162923 | 0 | 0 | 4456448 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 952 | 0 | 2162688 | 2157259 | 0 | 5437 | 841862 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 87909890 | 42068999 | 37321211 | 8519680 | 1294440 | 1190097 | 15369158 | 0 | 0 | 7536640 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 482344960 | 2162688 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 896 | 56 | 15896168459754 | 15906983858993 | 15906983951633 | 15896168716808 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7f6ef8b5e180 | 0x7f6ef5c24ac0 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 12976128 | 11403264 | 162311 | 162311 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1176 | 0 | 2621440 | 2614218 | 56 | 6639 | 870565 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 10354688 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 94618224 | 34258117 | 48039339 | 12320768 | 1295304 | 1191209 | 15357980 | 0 | 0 | 11403264 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 729808896 | 2621440 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1120 | 56 | 15896168766317 | 15906983975633 | 15906984069234 | 15896169032451 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7f6ef8b5e000 | 0x7f6ef5c24b00 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 8388608 | 6684672 | 161836 | 161836 | 0 | 0 | 0 | 0 | 0 | 0 | 3801088 | 0 | 0 | 0 | 0 | 896 | 0 | 1966080 | 1960801 | 0 | 5441 | 857835 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 87582411 | 41530009 | 38319154 | 7733248 | 1297656 | 1193470 | 15427819 | 0 | 0 | 6684672 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 427819008 | 1966080 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 840 | 56 | 15896169086660 | 15906984101714 | 15906984193234 | 15896169335154 |
| 50 | 48 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 143 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7f6ef63fde80 | 0x7f6ef5c24b40 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 10354688 | 7733248 | 303104 | 303104 | 0 | 0 | 0 | 0 | 0 | 0 | 4980736 | 0 | 0 | 0 | 0 | 1120 | 0 | 2359296 | 2353825 | 56 | 5165 | 462635 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 216572282 | 46639027 | 160168391 | 9764864 | 2427528 | 2322472 | 30056791 | 0 | 0 | 7733248 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 494927872 | 2359296 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1064 | 56 | 15896169387023 | 15906984217874 | 15906984397395 | 15896169733896 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7f6ef63fdd00 | 0x7f6ef5c24b80 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 9437184 | 7995392 | 303410 | 303410 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1064 | 0 | 2228224 | 2222587 | 56 | 5159 | 672644 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 4980736 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 216597529 | 56294661 | 151455508 | 8847360 | 2431576 | 2329097 | 30161822 | 0 | 0 | 7995392 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 511705088 | 2228224 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1008 | 56 | 15896169779005 | 15906984421075 | 15906984601235 | 15896170132997 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7f6ef63fdb80 | 0x7f6ef5c24bc0 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 9633792 | 8060928 | 164702 | 164702 | 0 | 0 | 4980736 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1064 | 0 | 2293760 | 2287847 | 112 | 7434 | 440141 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 90043205 | 41492541 | 39506696 | 9043968 | 1306280 | 1202097 | 15520087 | 0 | 0 | 8060928 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 515899392 | 2293760 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1008 | 56 | 15896170179656 | 15906984624915 | 15906984719636 | 15896170441470 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7f6ef63fda00 | 0x7f6ef5c24c00 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 14024704 | 12451840 | 162489 | 162489 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1288 | 0 | 2752512 | 2744019 | 56 | 7630 | 736786 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 11403264 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 100213796 | 32142909 | 54701543 | 13369344 | 1301048 | 1197668 | 15453488 | 0 | 0 | 12451840 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 796917760 | 2752512 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1232 | 56 | 15896170488479 | 15906984744756 | 15906984839956 | 15896170746903 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7f6ef63fd880 | 0x7f6ef5c24c40 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 8781824 | 7077888 | 162608 | 162608 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 1008 | 0 | 2031616 | 2025930 | 56 | 7392 | 626202 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 88863764 | 42580643 | 38156657 | 8126464 | 1299144 | 1196001 | 15472157 | 0 | 0 | 7077888 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 452984832 | 2031616 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 952 | 56 | 15896170800392 | 15906984871796 | 15906984965237 | 15896171056406 |
| 55 | 53 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 158 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7f6ef63fd700 | 0x7f6ef5c24c80 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 10878976 | 8257536 | 302772 | 302772 | 0 | 0 | 0 | 0 | 0 | 0 | 5505024 | 0 | 0 | 0 | 0 | 1120 | 0 | 2490368 | 2485059 | 56 | 4520 | 879741 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 221014538 | 45525622 | 165199764 | 10289152 | 2428760 | 2322460 | 30060257 | 0 | 0 | 8257536 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 528482304 | 2490368 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1064 | 56 | 15896171103865 | 15906984989397 | 15906985169077 | 15896171446787 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7f6ef8b5e580 | 0x7f6ef5c24cc0 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 9961472 | 8519680 | 303201 | 303201 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1120 | 0 | 2359296 | 2352826 | 56 | 6130 | 455612 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 5505024 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 203054697 | 55216102 | 138466947 | 9371648 | 2423752 | 2316146 | 30013650 | 0 | 0 | 8519680 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 545259520 | 2359296 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1064 | 56 | 15896171493226 | 15906985193237 | 15906985374198 | 15896171836549 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7f6ef8b5e400 | 0x7f6ef5c24d00 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 10158080 | 8585216 | 163168 | 163168 | 0 | 0 | 5505024 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1120 | 0 | 2424832 | 2417567 | 56 | 6535 | 562414 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 89982381 | 41637150 | 38776975 | 9568256 | 1308824 | 1202044 | 15511241 | 0 | 0 | 8585216 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 549453824 | 2424832 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1064 | 56 | 15896171882488 | 15906985398198 | 15906985492118 | 15896172144822 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7f6ef8b5e280 | 0x7f6ef5c24d40 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 15073280 | 13500416 | 168651 | 168651 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1400 | 0 | 2949120 | 2939867 | 112 | 8799 | 504589 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 12451840 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 99677967 | 27846537 | 57413510 | 14417920 | 1353224 | 1250540 | 16079803 | 0 | 0 | 13500416 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 864026624 | 2949120 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1344 | 56 | 15896172190931 | 15906985515958 | 15906985615319 | 15896172453785 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7f6ef8b5e100 | 0x7f6ef5c24d80 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 9175040 | 7471104 | 162689 | 162689 | 0 | 0 | 0 | 0 | 0 | 0 | 4587520 | 0 | 0 | 0 | 0 | 1008 | 0 | 2162688 | 2157506 | 56 | 5823 | 444717 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 96697929 | 41794034 | 46384215 | 8519680 | 1292120 | 1190970 | 15398015 | 0 | 0 | 7471104 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 478150656 | 2162688 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 952 | 56 | 15896172508674 | 15906985648439 | 15906985742519 | 15896172760628 |
| 60 | 58 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 173 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7f6ef63fdf80 | 0x7f6ef5c24dc0 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 11403264 | 8781824 | 304567 | 304567 | 0 | 0 | 0 | 0 | 0 | 0 | 6029312 | 0 | 0 | 0 | 0 | 1176 | 0 | 2621440 | 2615878 | 0 | 6180 | 879214 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 214196449 | 45131342 | 158251667 | 10813440 | 2410280 | 2307959 | 29891190 | 0 | 0 | 8781824 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 562036736 | 2621440 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1120 | 56 | 15896172811207 | 15906985765559 | 15906985944280 | 15896173160559 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7f6ef63fde00 | 0x7f6ef5c24e00 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 10485760 | 9043968 | 304965 | 304965 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1120 | 0 | 2490368 | 2486003 | 56 | 4746 | 859905 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 6029312 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 201038798 | 53998363 | 137144499 | 9895936 | 2427064 | 2316832 | 29979340 | 0 | 0 | 9043968 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 578813952 | 2490368 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1064 | 56 | 15896173206918 | 15906985968760 | 15906986147640 | 15896173553351 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7f6ef63fdc80 | 0x7f6ef5c24e40 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 10682368 | 9109504 | 162987 | 162987 | 0 | 0 | 6029312 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1176 | 0 | 2555904 | 2548110 | 56 | 9198 | 603388 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 87159750 | 40286455 | 36780751 | 10092544 | 1305224 | 1202336 | 15499239 | 0 | 0 | 9109504 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 583008256 | 2555904 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1120 | 56 | 15896173599450 | 15906986170521 | 15906986264441 | 15896173858434 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7f6ef63fdb00 | 0x7f6ef5c24e80 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 16121856 | 14548992 | 176909 | 176909 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1456 | 0 | 3145728 | 3136874 | 56 | 9498 | 621746 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 13500416 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 108689322 | 26422777 | 66800049 | 15466496 | 1414744 | 1309485 | 16881146 | 0 | 0 | 14548992 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 931135488 | 3145728 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1400 | 56 | 15896173904913 | 15906986288601 | 15906986392121 | 15896174174257 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7f6ef63fd980 | 0x7f6ef5c24ec0 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 9568256 | 7864320 | 161069 | 161069 | 0 | 0 | 0 | 0 | 0 | 0 | 4980736 | 0 | 0 | 0 | 0 | 1008 | 0 | 2228224 | 2221945 | 56 | 5040 | 872249 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 80186869 | 40285176 | 30988797 | 8912896 | 1292104 | 1189225 | 15357070 | 0 | 0 | 7864320 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 503316480 | 2228224 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 952 | 56 | 15896174228026 | 15906986424281 | 15906986517242 | 15896174489590 |
| 65 | 63 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 188 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7f6ef63fd800 | 0x7f6ef5c24f00 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 11927552 | 9306112 | 302108 | 302108 | 0 | 0 | 0 | 0 | 0 | 0 | 6553600 | 0 | 0 | 0 | 0 | 1288 | 0 | 2752512 | 2746080 | 57 | 6988 | 459740 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 225134773 | 50464519 | 163332526 | 11337728 | 2417720 | 2315441 | 30008101 | 0 | 0 | 9306112 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 595591168 | 2752512 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1232 | 56 | 15896174535339 | 15906986541402 | 15906986721722 | 15896174882701 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7f6ef63fd680 | 0x7f6ef5c24f40 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 11010048 | 9568256 | 303920 | 303920 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1232 | 0 | 2621440 | 2615527 | 56 | 6718 | 445646 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 6553600 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 215015814 | 46259103 | 158336487 | 10420224 | 2421720 | 2312869 | 29949939 | 0 | 0 | 9568256 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 612368384 | 2621440 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1176 | 56 | 15896174930920 | 15906986746362 | 15906986927163 | 15896175275602 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7f6ef8b5e500 | 0x7f6ef5c24f80 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 11141120 | 9633792 | 161450 | 161450 | 0 | 0 | 6553600 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1176 | 0 | 2686976 | 2681283 | 56 | 6310 | 865036 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 84929768 | 37024254 | 37288682 | 10616832 | 1290232 | 1186562 | 15300136 | 0 | 0 | 9633792 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 616562688 | 2686976 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1120 | 56 | 15896175321351 | 15906986950523 | 15906987043803 | 15896175580866 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7f6ef8b5e380 | 0x7f6ef5c24fc0 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 17170432 | 15597568 | 182258 | 182258 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1512 | 0 | 3342336 | 3330039 | 1 | 11986 | 475177 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 14548992 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 110761106 | 22211814 | 72034220 | 16515072 | 1456824 | 1349833 | 17423709 | 0 | 0 | 15597568 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 998244352 | 3342336 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1456 | 56 | 15896175628145 | 15906987066523 | 15906987173564 | 15896175898898 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7f6ef8b5e200 | 0x7f6ef5c25000 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 9961472 | 8257536 | 161326 | 161326 | 0 | 0 | 0 | 0 | 0 | 0 | 5373952 | 0 | 0 | 0 | 0 | 1120 | 0 | 2359296 | 2352582 | 56 | 6467 | 623872 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 91049167 | 40800232 | 40942823 | 9306112 | 1293432 | 1187579 | 15343896 | 0 | 0 | 8257536 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 528482304 | 2359296 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1064 | 56 | 15896175966087 | 15906987205564 | 15906987300124 | 15896176205262 |
| 70 | 68 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 203 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7f6ef8b5e080 | 0x7f6ef5c25040 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 12451840 | 9830400 | 302864 | 302864 | 0 | 0 | 0 | 0 | 0 | 0 | 7077888 | 0 | 0 | 0 | 0 | 1344 | 0 | 2883584 | 2876338 | 112 | 6946 | 497934 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 208456417 | 49363627 | 147230774 | 11862016 | 2395752 | 2285705 | 29610278 | 0 | 0 | 9830400 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 629145600 | 2883584 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1288 | 56 | 15896176251771 | 15906987323804 | 15906987503485 | 15896176605173 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7f6ef63fdf00 | 0x7f6ef5c25080 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 11534336 | 10092544 | 301470 | 301470 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1288 | 0 | 2686976 | 2679952 | 56 | 6404 | 440018 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 7077888 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 222158878 | 46335159 | 164879207 | 10944512 | 2406088 | 2299985 | 29810048 | 0 | 0 | 10092544 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 645922816 | 2686976 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1232 | 56 | 15896176653792 | 15906987526845 | 15906987707486 | 15896177000544 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7f6ef63fdd80 | 0x7f6ef5c250c0 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 11730944 | 10158080 | 162074 | 162074 | 0 | 0 | 7077888 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1288 | 0 | 2818048 | 2810901 | 56 | 8065 | 460559 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 93963236 | 38636453 | 44185663 | 11141120 | 1306760 | 1203170 | 15526449 | 0 | 0 | 10158080 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 650117120 | 2818048 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1232 | 56 | 15896177045463 | 15906987731806 | 15906987826846 | 15896177304547 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7f6ef63fdc00 | 0x7f6ef5c25100 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 18219008 | 16646144 | 190896 | 190896 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1624 | 0 | 3538944 | 3527020 | 112 | 13133 | 442060 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 15597568 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 108206130 | 20046307 | 70596175 | 17563648 | 1532856 | 1423955 | 18366632 | 0 | 0 | 16646144 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 1065353216 | 3538944 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1568 | 56 | 15896177352586 | 15906987850206 | 15906987965406 | 15896177628350 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7f6ef63fda80 | 0x7f6ef5c25140 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 10354688 | 8650752 | 162904 | 162904 | 0 | 0 | 0 | 0 | 0 | 0 | 5767168 | 0 | 0 | 0 | 0 | 1176 | 0 | 2424832 | 2417007 | 56 | 8381 | 580419 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 92375472 | 40725499 | 41950645 | 9699328 | 1297080 | 1194520 | 15421456 | 0 | 0 | 8650752 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 553648128 | 2424832 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1120 | 56 | 15896177681409 | 15906988008447 | 15906988102527 | 15896177941623 |
| 75 | 73 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 218 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7f6ef63fd900 | 0x7f6ef5c25180 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 12976128 | 10354688 | 301664 | 301664 | 0 | 0 | 0 | 0 | 0 | 0 | 7602176 | 0 | 0 | 0 | 0 | 1400 | 0 | 3014656 | 3005827 | 112 | 7992 | 450162 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 221891008 | 50116107 | 159388597 | 12386304 | 2432520 | 2323542 | 30053629 | 0 | 0 | 10354688 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 662700032 | 3014656 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1344 | 56 | 15896177987142 | 15906988126207 | 15906988305408 | 15896178340554 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7f6ef63fd780 | 0x7f6ef5c251c0 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 12058624 | 10616832 | 299840 | 299840 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1344 | 0 | 2818048 | 2809360 | 56 | 7043 | 451306 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 7602176 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 201430579 | 46427326 | 143534453 | 11468800 | 2399752 | 2293535 | 29708746 | 0 | 0 | 10616832 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 679477248 | 2818048 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1288 | 56 | 15896178388093 | 15906988329408 | 15906988508128 | 15896178738225 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7f6ef63fd600 | 0x7f6ef5c25200 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 12255232 | 10682368 | 163134 | 163134 | 0 | 0 | 7602176 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1344 | 0 | 2949120 | 2940228 | 56 | 8259 | 589247 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 92626256 | 38288984 | 42671864 | 11665408 | 1303480 | 1197054 | 15443357 | 0 | 0 | 10682368 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 683671552 | 2949120 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1288 | 56 | 15896178784094 | 15906988531488 | 15906988626689 | 15896179044618 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7f6ef8b5e480 | 0x7f6ef5c25240 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 19267584 | 17694720 | 202408 | 202408 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1736 | 0 | 3735552 | 3722767 | 116 | 11743 | 449696 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 16646144 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 117640121 | 20188244 | 78839653 | 18612224 | 1620264 | 1507355 | 19423550 | 0 | 0 | 17694720 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 1132462080 | 3735552 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1680 | 56 | 15896179090867 | 15906988650049 | 15906988770849 | 15896179379691 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7f6ef8b5e300 | 0x7f6ef5c25280 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 10747904 | 9043968 | 162438 | 162438 | 0 | 0 | 0 | 0 | 0 | 0 | 6160384 | 0 | 0 | 0 | 0 | 1176 | 0 | 2555904 | 2547270 | 56 | 9115 | 456357 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 92954134 | 38630296 | 44231294 | 10092544 | 1305888 | 1196966 | 15435038 | 0 | 0 | 9043968 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 578813952 | 2555904 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1120 | 56 | 15896179433070 | 15906988802689 | 15906988896290 | 15896179689324 |
| 80 | 78 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 233 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7f6ef8b5e180 | 0x7f6ef5c252c0 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 13500416 | 10878976 | 302444 | 302444 | 0 | 0 | 0 | 0 | 0 | 0 | 8126464 | 0 | 0 | 0 | 0 | 1400 | 0 | 3145728 | 3138001 | 56 | 8628 | 735828 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 221905558 | 50813466 | 158181500 | 12910592 | 2412640 | 2308186 | 29844201 | 0 | 0 | 10878976 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 696254464 | 3145728 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1344 | 56 | 15896179740433 | 15906988919330 | 15906989099810 | 15896180088785 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7f6ef8b5e000 | 0x7f6ef5c25300 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 12582912 | 11141120 | 300544 | 300544 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1400 | 0 | 2949120 | 2942129 | 56 | 6703 | 659637 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 8126464 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 208933581 | 51396437 | 145544056 | 11993088 | 2386848 | 2285059 | 29601948 | 0 | 0 | 11141120 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 713031680 | 2949120 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1344 | 56 | 15896180136684 | 15906989122210 | 15906989302211 | 15896180484036 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7f6ef63fde80 | 0x7f6ef5c25340 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 12845056 | 11206656 | 163508 | 163508 | 0 | 0 | 8126464 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1400 | 0 | 3080192 | 3069645 | 56 | 10352 | 442008 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 97416086 | 36981444 | 48244946 | 12189696 | 1302464 | 1198332 | 15418058 | 0 | 0 | 11206656 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 717225984 | 3080192 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1344 | 56 | 15896180530755 | 15906989326531 | 15906989421731 | 15896180792449 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7f6ef63fdd00 | 0x7f6ef5c25380 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 20316160 | 18743296 | 210378 | 210378 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1792 | 0 | 3932160 | 3919187 | 115 | 14211 | 666707 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 17694720 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 136004720 | 19836009 | 96507911 | 19660800 | 1688176 | 1578440 | 20358286 | 0 | 0 | 18743296 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 1199570944 | 3932160 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1736 | 56 | 15896180837518 | 15906989445571 | 15906989572292 | 15896181128682 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7f6ef63fdb80 | 0x7f6ef5c253c0 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 11141120 | 9437184 | 164116 | 164116 | 0 | 0 | 0 | 0 | 0 | 0 | 6553600 | 0 | 0 | 0 | 0 | 1232 | 0 | 2621440 | 2612439 | 56 | 8152 | 694903 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 85673634 | 38787504 | 36400370 | 10485760 | 1289592 | 1186339 | 15300450 | 0 | 0 | 9437184 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 603979776 | 2621440 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1176 | 56 | 15896181181940 | 15906989604292 | 15906989698212 | 15896181440315 |
| 85 | 83 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 248 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7f6ef63fda00 | 0x7f6ef5c25400 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 14024704 | 11403264 | 300066 | 300066 | 0 | 0 | 0 | 0 | 0 | 0 | 8650752 | 0 | 0 | 0 | 0 | 1456 | 0 | 3276800 | 3268529 | 0 | 8005 | 878189 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 220753752 | 45742941 | 161575931 | 13434880 | 2398128 | 2295885 | 29729101 | 0 | 0 | 11403264 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 729808896 | 3276800 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1400 | 56 | 15896181491504 | 15906989722372 | 15906989900933 | 15896181834146 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7f6ef63fd880 | 0x7f6ef5c25440 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 13041664 | 11599872 | 300732 | 300732 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1456 | 0 | 3080192 | 3073893 | 56 | 7066 | 447774 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 8650752 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 203919567 | 50650224 | 140817503 | 12451840 | 2391328 | 2288743 | 29652156 | 0 | 0 | 11599872 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 742391808 | 3080192 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1400 | 56 | 15896181880455 | 15906989924773 | 15906990104294 | 15896182233197 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7f6ef63fd700 | 0x7f6ef5c25480 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 13303808 | 11730944 | 162978 | 162978 | 0 | 0 | 8650752 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1400 | 0 | 3211264 | 3202175 | 0 | 8022 | 866589 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 97027007 | 35359660 | 48953363 | 12713984 | 1292144 | 1187246 | 15320490 | 0 | 0 | 11730944 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 750780416 | 3211264 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1344 | 56 | 15896182280286 | 15906990129574 | 15906990224454 | 15896182547260 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7f6ef8b5e580 | 0x7f6ef5c254c0 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 21364736 | 19791872 | 219430 | 219430 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1848 | 0 | 4128768 | 4115943 | 56 | 14361 | 881061 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 18743296 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 137069691 | 17403001 | 98957314 | 20709376 | 1764208 | 1648021 | 21265962 | 0 | 0 | 19791872 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 1266679808 | 4128768 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1792 | 56 | 15896182593449 | 15906990247974 | 15906990377894 | 15896182892942 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7f6ef8b5e400 | 0x7f6ef5c25500 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 11534336 | 9830400 | 162278 | 162278 | 0 | 0 | 0 | 0 | 0 | 0 | 6946816 | 0 | 0 | 0 | 0 | 1232 | 0 | 2752512 | 2744021 | 0 | 8698 | 867197 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 89788921 | 38113760 | 40796185 | 10878976 | 1288888 | 1182637 | 15237752 | 0 | 0 | 9830400 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 629145600 | 2752512 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1176 | 56 | 15896182947201 | 15906990409895 | 15906990503175 | 15896183202145 |
| 90 | 88 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 263 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7f6ef8b5e280 | 0x7f6ef5c25540 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 14548992 | 11927552 | 298860 | 298860 | 0 | 0 | 0 | 0 | 0 | 0 | 9175040 | 0 | 0 | 0 | 0 | 1568 | 0 | 3407872 | 3398834 | 112 | 9342 | 621423 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 217292414 | 45051657 | 158281589 | 13959168 | 2403856 | 2297891 | 29753998 | 0 | 0 | 11927552 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 763363328 | 3407872 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1512 | 56 | 15896183248864 | 15906990527815 | 15906990707816 | 15896183592857 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7f6ef8b5e100 | 0x7f6ef5c25580 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 13565952 | 12124160 | 299726 | 299726 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1512 | 0 | 3211264 | 3203044 | 56 | 6953 | 656579 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 9175040 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 213361514 | 47600516 | 152784870 | 12976128 | 2385408 | 2284579 | 29585056 | 0 | 0 | 12124160 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 775946240 | 3211264 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1456 | 56 | 15896183638866 | 15906990731176 | 15906990911176 | 15896183986998 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7f6ef63fdf80 | 0x7f6ef5c255c0 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 13828096 | 12255232 | 164476 | 164476 | 0 | 0 | 9175040 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1512 | 0 | 3276800 | 3267211 | 56 | 12910 | 622650 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 102231647 | 34522240 | 54471135 | 13238272 | 1304400 | 1202569 | 15502678 | 0 | 0 | 12255232 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 784334848 | 3276800 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1456 | 56 | 15896184034137 | 15906990934696 | 15906991031017 | 15896184295291 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7f6ef63fde00 | 0x7f6ef5c25600 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 22413312 | 20840448 | 230124 | 230124 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1960 | 0 | 4325376 | 4308461 | 119 | 16011 | 631803 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 19791872 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 145775746 | 18265828 | 105751966 | 21757952 | 1839872 | 1727975 | 22298961 | 0 | 0 | 20840448 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 1333788672 | 4325376 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1904 | 56 | 15896184341360 | 15906991054697 | 15906991194057 | 15896184643233 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7f6ef63fdc80 | 0x7f6ef5c25640 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 11796480 | 10223616 | 162970 | 162970 | 0 | 0 | 0 | 0 | 0 | 0 | 7340032 | 0 | 0 | 0 | 0 | 1288 | 0 | 2818048 | 2810237 | 56 | 8145 | 617857 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 92182546 | 38213836 | 42696518 | 11272192 | 1297368 | 1191433 | 15353410 | 0 | 0 | 10223616 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 654311424 | 2818048 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1232 | 56 | 15896184696592 | 15906991225897 | 15906991320298 | 15896184948176 |
| 95 | 93 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 278 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7f6ef63fdb00 | 0x7f6ef5c25680 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 15073280 | 12451840 | 298408 | 298408 | 0 | 0 | 0 | 0 | 0 | 0 | 9699328 | 0 | 0 | 0 | 0 | 1624 | 0 | 3538944 | 3529092 | 112 | 9906 | 441973 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 204532262 | 45292209 | 144756597 | 14483456 | 2378392 | 2272743 | 29440486 | 0 | 0 | 12451840 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 796917760 | 3538944 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1568 | 56 | 15896184993805 | 15906991344458 | 15906991523178 | 15896185335338 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7f6ef63fd980 | 0x7f6ef5c256c0 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 14221312 | 12713984 | 297704 | 297704 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1568 | 0 | 3407872 | 3400545 | 56 | 6495 | 605239 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 9699328 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 208095066 | 51281865 | 143247249 | 13565952 | 2389528 | 2287057 | 29605714 | 0 | 0 | 12713984 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 813694976 | 3407872 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1512 | 56 | 15896185381437 | 15906991547978 | 15906991728619 | 15896185725769 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7f6ef63fd800 | 0x7f6ef5c25700 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 14352384 | 12779520 | 164180 | 164180 | 0 | 0 | 9699328 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1568 | 0 | 3407872 | 3395789 | 112 | 12595 | 445512 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 98314337 | 30447000 | 54104777 | 13762560 | 1313208 | 1212954 | 15664090 | 0 | 0 | 12779520 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 817889280 | 3407872 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1512 | 56 | 15896185770878 | 15906991752779 | 15906991848939 | 15896186033492 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7f6ef63fd680 | 0x7f6ef5c25740 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 23461888 | 21889024 | 239112 | 239112 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2072 | 0 | 4521984 | 4504171 | 58 | 18288 | 740003 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 20840448 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 150260062 | 17874864 | 109578670 | 22806528 | 1914048 | 1804554 | 23318190 | 0 | 0 | 21889024 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 1400897536 | 4521984 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2016 | 56 | 15896186085961 | 15906991873419 | 15906992019180 | 15896186408394 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7f6ef8b5e500 | 0x7f6ef5c25780 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 12582912 | 11010048 | 162726 | 162726 | 0 | 0 | 0 | 0 | 0 | 0 | 8126464 | 0 | 0 | 0 | 0 | 1400 | 0 | 3014656 | 3005927 | 112 | 15679 | 442289 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 93105991 | 37500431 | 43546936 | 12058624 | 1297344 | 1190849 | 15351541 | 0 | 0 | 11010048 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 704643072 | 3014656 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1344 | 56 | 15896186461452 | 15906992051020 | 15906992146540 | 15896186720567 |
| 100 | 98 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 293 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7f6ef8b5e380 | 0x7f6ef5c257c0 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 16121856 | 13500416 | 298176 | 298176 | 0 | 0 | 0 | 0 | 0 | 0 | 10747904 | 0 | 0 | 0 | 0 | 1736 | 0 | 3801088 | 3792619 | 56 | 10474 | 443255 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 195212195 | 55970797 | 123709366 | 15532032 | 2386608 | 2278781 | 29480341 | 0 | 0 | 13500416 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 864026624 | 3801088 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1680 | 56 | 15896186767256 | 15906992171340 | 15906992351981 | 15896187112258 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7f6ef8b5e200 | 0x7f6ef5c25800 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 15269888 | 13762560 | 300247 | 300247 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1680 | 0 | 3670016 | 3661773 | 112 | 9402 | 481547 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 10747904 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 200051981 | 52879806 | 132557647 | 14614528 | 2394200 | 2284749 | 29599394 | 0 | 0 | 13762560 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 880803840 | 3670016 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1624 | 56 | 15896187160067 | 15906992376461 | 15906992558382 | 15896187508549 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7f6ef8b5e080 | 0x7f6ef5c25840 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 15400960 | 13828096 | 171087 | 171087 | 0 | 0 | 10747904 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1624 | 0 | 3670016 | 3657221 | 0 | 18665 | 875215 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 101664675 | 28561326 | 58292213 | 14811136 | 1372056 | 1262806 | 16311420 | 0 | 0 | 13828096 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 884998144 | 3670016 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1568 | 56 | 15896187554538 | 15906992583022 | 15906992684142 | 15896187822802 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7f6ef63fdf00 | 0x7f6ef5c25880 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 25559040 | 23986176 | 259530 | 259530 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2184 | 0 | 4915200 | 4895154 | 102 | 15477 | 879440 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 22937600 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 160366026 | 17560657 | 117901689 | 24903680 | 2080008 | 1966446 | 25380839 | 0 | 0 | 23986176 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 1535115264 | 4915200 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2128 | 56 | 15896187871491 | 15906992706862 | 15906992862063 | 15896188188884 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7f6ef63fdd80 | 0x7f6ef5c258c0 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 13303808 | 11796480 | 161750 | 161750 | 0 | 0 | 0 | 0 | 0 | 0 | 8912896 | 0 | 0 | 0 | 0 | 1456 | 0 | 3145728 | 3135833 | 61 | 10725 | 1008509 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 98555534 | 31754030 | 53956448 | 12845056 | 1297288 | 1192570 | 15376486 | 0 | 0 | 11796480 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 754974720 | 3145728 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1400 | 56 | 15896188242713 | 15906992898863 | 15906992993743 | 15896188499877 |
| 105 | 103 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 308 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7f6ef63fdc00 | 0x7f6ef5c25900 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 17104896 | 14548992 | 295865 | 295865 | 0 | 0 | 0 | 0 | 0 | 0 | 11796480 | 0 | 0 | 0 | 0 | 1792 | 0 | 4063232 | 4053551 | 0 | 13824 | 903987 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 196531672 | 61690974 | 118260090 | 16580608 | 2368160 | 2261877 | 29264333 | 0 | 0 | 14548992 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 931135488 | 4063232 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1736 | 56 | 15896188546386 | 15906993019343 | 15906993198384 | 15896188897488 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7f6ef63fda80 | 0x7f6ef5c25940 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 16252928 | 14811136 | 296639 | 296639 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1792 | 0 | 3932160 | 3921373 | 56 | 12043 | 458304 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 11796480 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 208080272 | 44356318 | 148060850 | 15663104 | 2388360 | 2279759 | 29500767 | 0 | 0 | 14811136 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 947912704 | 3932160 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1736 | 56 | 15896188944067 | 15906993225104 | 15906993405104 | 15896189289429 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7f6ef63fd900 | 0x7f6ef5c25980 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 16449536 | 14876672 | 179253 | 179253 | 0 | 0 | 11796480 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1792 | 0 | 3932160 | 3917618 | 56 | 14526 | 574240 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 98759070 | 23544596 | 59354762 | 15859712 | 1436568 | 1326519 | 17123400 | 0 | 0 | 14876672 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 952107008 | 3932160 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1736 | 56 | 15896189335388 | 15906993428464 | 15906993534065 | 15896189606932 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7f6ef63fd780 | 0x7f6ef5c259c0 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 27656192 | 26083328 | 280653 | 280653 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2408 | 0 | 5308416 | 5289673 | 58 | 21054 | 433577 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 25034752 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 184625413 | 18051638 | 139572943 | 27000832 | 2247592 | 2128013 | 27503693 | 0 | 0 | 26083328 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 1669332992 | 5308416 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2352 | 56 | 15896189652231 | 15906993557905 | 15906993727985 | 15896189986804 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7f6ef63fd600 | 0x7f6ef5c25a00 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 14090240 | 12582912 | 162486 | 162486 | 0 | 0 | 0 | 0 | 0 | 0 | 9699328 | 0 | 0 | 0 | 0 | 1568 | 0 | 3342336 | 3331478 | 115 | 12121 | 1009652 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 98048262 | 28012995 | 56403779 | 13631488 | 1301632 | 1194223 | 15414638 | 0 | 0 | 12582912 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 805306368 | 3342336 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1512 | 56 | 15896190040443 | 15906993759986 | 15906993855186 | 15896190305817 |
| 110 | 108 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 323 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7f6ef8b5e480 | 0x7f6ef5c25a40 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 18219008 | 15597568 | 298194 | 298194 | 0 | 0 | 0 | 0 | 0 | 0 | 12845056 | 0 | 0 | 0 | 0 | 1960 | 0 | 4325376 | 4312864 | 56 | 13325 | 441768 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 207747496 | 42982117 | 147136195 | 17629184 | 2360744 | 2255662 | 29163189 | 0 | 0 | 15597568 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 998244352 | 4325376 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1904 | 56 | 15896190352926 | 15906993881266 | 15906994064147 | 15896190699758 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7f6ef8b5e300 | 0x7f6ef5c25a80 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 17301504 | 15859712 | 296298 | 296298 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1904 | 0 | 4194304 | 4182752 | 112 | 15197 | 731551 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 12845056 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 196783079 | 42974665 | 137096734 | 16711680 | 2367848 | 2264466 | 29302198 | 0 | 0 | 15859712 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 1015021568 | 4194304 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1848 | 56 | 15896190746017 | 15906994100467 | 15906994281107 | 15896191096789 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7f6ef8b5e180 | 0x7f6ef5c25ac0 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 17498112 | 15925248 | 187572 | 187572 | 0 | 0 | 12845056 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1848 | 0 | 4194304 | 4179332 | 0 | 15828 | 855294 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 105112950 | 20809365 | 67395297 | 16908288 | 1495424 | 1383662 | 17824957 | 0 | 0 | 15925248 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 1019215872 | 4194304 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1792 | 56 | 15896191142368 | 15906994305107 | 15906994415508 | 15896191417682 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7f6ef8b5e000 | 0x7f6ef5c25b00 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 29753344 | 28180480 | 300569 | 300569 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2520 | 0 | 5701632 | 5678299 | 65 | 21966 | 875863 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 27131904 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 192765126 | 17112412 | 146554730 | 29097984 | 2401360 | 2287313 | 29522686 | 0 | 0 | 28180480 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 1803550720 | 5701632 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2464 | 56 | 15896191467611 | 15906994439028 | 15906994619988 | 15896191817523 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7f6ef63fde80 | 0x7f6ef5c25b40 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 15663104 | 14155776 | 172598 | 172598 | 0 | 0 | 0 | 0 | 0 | 0 | 11272192 | 0 | 0 | 0 | 0 | 1680 | 0 | 3735552 | 3722649 | 16 | 15277 | 1009827 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 97973407 | 22669908 | 60099147 | 15204352 | 1377760 | 1276267 | 16463501 | 0 | 0 | 14155776 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 905969664 | 3735552 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1624 | 56 | 15896191871442 | 15906994651829 | 15906994753109 | 15896192130836 |
| 115 | 113 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 338 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7f6ef63fdd00 | 0x7f6ef5c25b80 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 20316160 | 17694720 | 299053 | 299053 | 0 | 0 | 0 | 0 | 0 | 0 | 14942208 | 0 | 0 | 0 | 0 | 2184 | 0 | 4849664 | 4832549 | 112 | 15074 | 443850 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 156762461 | 66022374 | 71013751 | 19726336 | 2390160 | 2261503 | 29179118 | 0 | 0 | 17694720 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 1132462080 | 4849664 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2128 | 56 | 15896192176405 | 15906994777749 | 15906994962070 | 15896192523707 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7f6ef63fdb80 | 0x7f6ef5c25bc0 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 19398656 | 17956864 | 296983 | 296983 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2128 | 0 | 4718592 | 4701353 | 112 | 20823 | 448421 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 14942208 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 186372431 | 59227766 | 108335833 | 18808832 | 2378192 | 2258710 | 29176658 | 0 | 0 | 17956864 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 1149239296 | 4718592 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2072 | 56 | 15896192570316 | 15906994985430 | 15906995170390 | 15896192917199 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7f6ef63fda00 | 0x7f6ef5c25c00 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 19595264 | 18022400 | 207344 | 207344 | 0 | 0 | 14942208 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2072 | 0 | 4718592 | 4694144 | 0 | 21059 | 848256 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 120766998 | 20213266 | 81548292 | 19005440 | 1656776 | 1533994 | 19772886 | 0 | 0 | 18022400 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 1153433600 | 4718592 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2016 | 56 | 15896192963248 | 15906995193910 | 15906995316791 | 15896193253761 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7f6ef63fd880 | 0x7f6ef5c25c40 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 33947648 | 32374784 | 340272 | 340272 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2856 | 0 | 6488064 | 6457240 | 78 | 23643 | 883607 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 31326208 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 235714018 | 17045134 | 185376596 | 33292288 | 2720344 | 2606627 | 33672602 | 0 | 0 | 32374784 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 2071986176 | 6488064 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2800 | 56 | 15896193299140 | 15906995341111 | 15906995547351 | 15896193698791 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7f6ef63fd700 | 0x7f6ef5c25c80 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 17235968 | 15728640 | 184064 | 184064 | 0 | 0 | 0 | 0 | 0 | 0 | 12845056 | 0 | 0 | 0 | 0 | 1904 | 0 | 4128768 | 4112037 | 56 | 15318 | 1016216 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 115463451 | 18116738 | 80569497 | 16777216 | 1478824 | 1366866 | 17624545 | 0 | 0 | 15728640 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 1006632960 | 4128768 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1848 | 56 | 15896193734811 | 15906995618712 | 15906995729912 | 15896194007265 |
| 120 | 118 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 353 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7f6ef8b5e580 | 0x7f6ef5c25cc0 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 22347776 | 19791872 | 296256 | 296256 | 0 | 0 | 0 | 0 | 0 | 0 | 17039360 | 0 | 0 | 0 | 0 | 2352 | 0 | 5373952 | 5354445 | 56 | 18885 | 875049 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 158741919 | 65220401 | 71698030 | 21823488 | 2365160 | 2238750 | 28909217 | 0 | 0 | 19791872 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 1266679808 | 5373952 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2296 | 56 | 15896194053234 | 15906995755032 | 15906995936953 | 15896194415855 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7f6ef8b5e400 | 0x7f6ef5c25d00 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 21495808 | 20054016 | 296926 | 296926 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2352 | 0 | 5242880 | 5225123 | 112 | 19986 | 553230 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 17039360 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 166994289 | 67604837 | 78483468 | 20905984 | 2427024 | 2294697 | 29647207 | 0 | 0 | 20054016 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 1283457024 | 5242880 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2296 | 56 | 15896194462874 | 15906995961753 | 15906996147673 | 15896194812767 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7f6ef8b5e280 | 0x7f6ef5c25d40 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 21692416 | 20119552 | 226165 | 226165 | 0 | 0 | 17039360 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2296 | 0 | 5242880 | 5221639 | 0 | 20655 | 875253 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 150148428 | 16705700 | 112340136 | 21102592 | 1804288 | 1694317 | 21838336 | 0 | 0 | 20119552 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 1287651328 | 5242880 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2240 | 56 | 15896194859256 | 15906996173114 | 15906996307514 | 15896195160369 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7f6ef8b5e100 | 0x7f6ef5c25d80 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 38141952 | 36569088 | 380800 | 380800 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3192 | 0 | 7274496 | 7243505 | 66 | 31797 | 857352 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 35520512 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 268270400 | 16762135 | 214021673 | 37486592 | 3045136 | 2932899 | 37952243 | 0 | 0 | 36569088 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 2340421632 | 7274496 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3136 | 56 | 15896195208638 | 15906996331034 | 15906996563035 | 15896195650308 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7f6ef63fdf80 | 0x7f6ef5c25dc0 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 20381696 | 18874368 | 211734 | 211734 | 0 | 0 | 0 | 0 | 0 | 0 | 15990784 | 0 | 0 | 0 | 0 | 2184 | 0 | 4915200 | 4895989 | 64 | 19843 | 984786 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 137378046 | 15937488 | 101517614 | 19922944 | 1693216 | 1582471 | 20411562 | 0 | 0 | 18874368 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 1207959552 | 4915200 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2128 | 56 | 15896195673607 | 15906996610075 | 15906996736635 | 15896195966401 |
| 125 | 123 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 368 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7f6ef63fde00 | 0x7f6ef5c25e00 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 26607616 | 23986176 | 307598 | 307598 | 0 | 0 | 0 | 0 | 0 | 0 | 21233664 | 0 | 0 | 0 | 0 | 2856 | 0 | 6422528 | 6395605 | 173 | 26254 | 446261 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 191298289 | 48851508 | 116428989 | 26017792 | 2468808 | 2350204 | 30292477 | 0 | 0 | 23986176 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 1535115264 | 6422528 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2800 | 56 | 15896196013500 | 15906996762075 | 15906996955516 | 15896196419291 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7f6ef63fdc80 | 0x7f6ef5c25e40 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 25690112 | 24248320 | 312320 | 312320 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2800 | 0 | 6291456 | 6258412 | 56 | 29012 | 442022 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 21233664 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 169940398 | 50918431 | 93921679 | 25100288 | 2487960 | 2354801 | 30375131 | 0 | 0 | 24248320 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 1551892480 | 6291456 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2744 | 56 | 15896196429970 | 15906996982876 | 15906997173437 | 15896196841641 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7f6ef63fdb00 | 0x7f6ef5c25e80 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 25886720 | 24313856 | 266809 | 266809 | 0 | 0 | 21233664 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2744 | 0 | 6291456 | 6263008 | 56 | 29338 | 865848 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 167801597 | 17400836 | 125103865 | 25296896 | 2130440 | 2019772 | 26021678 | 0 | 0 | 24313856 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 1556086784 | 6291456 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2688 | 56 | 15896196852121 | 15906997198557 | 15906997358717 | 15896197190253 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7f6ef63fd980 | 0x7f6ef5c25ec0 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 46596096 | 45023232 | 461203 | 461203 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3808 | 0 | 8847360 | 8805795 | 68 | 38974 | 872689 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 43974656 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 337057310 | 16544669 | 274571905 | 45940736 | 3695160 | 3577852 | 46270239 | 0 | 0 | 45023232 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 2881486848 | 8847360 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3752 | 56 | 15896197237312 | 15906997383038 | 15906997665918 | 15896197726911 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7f6ef63fd800 | 0x7f6ef5c25f00 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 23461888 | 22020096 | 242454 | 242454 | 0 | 0 | 0 | 0 | 0 | 0 | 19136512 | 0 | 0 | 0 | 0 | 2576 | 0 | 5701632 | 5674663 | 131 | 22314 | 1004767 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 171042245 | 14302365 | 133671208 | 23068672 | 1941720 | 1836400 | 23713109 | 0 | 0 | 22020096 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 1409286144 | 5701632 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2520 | 56 | 15896197746791 | 15906997712159 | 15906997860959 | 15896198062044 |
| 130 | 128 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 383 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7f6ef63fd680 | 0x7f6ef5c25f40 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 30801920 | 28180480 | 337010 | 337010 | 0 | 0 | 0 | 0 | 0 | 0 | 25427968 | 0 | 0 | 0 | 0 | 3248 | 0 | 7471104 | 7440375 | 100 | 30558 | 1013281 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 212218264 | 41200076 | 140806092 | 30212096 | 2690264 | 2565056 | 33075076 | 0 | 0 | 28180480 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 1803550720 | 7471104 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3192 | 56 | 15896198108773 | 15906997885599 | 15906998093600 | 15896198541543 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7f6ef8b5e500 | 0x7f6ef5c25f80 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 29884416 | 28442624 | 332651 | 332651 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3248 | 0 | 7340032 | 7302735 | 114 | 43666 | 444352 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 25427968 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 184667823 | 40840406 | 114532825 | 29294592 | 2640264 | 2512358 | 32403086 | 0 | 0 | 28442624 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 1820327936 | 7340032 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3192 | 56 | 15896198551723 | 15906998132320 | 15906998340321 | 15896198985293 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7f6ef8b5e380 | 0x7f6ef5c25fc0 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 30081024 | 28508160 | 307110 | 307110 | 0 | 0 | 25427968 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3192 | 0 | 7340032 | 7308184 | 56 | 34967 | 863033 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 218185478 | 19133303 | 169560975 | 29491200 | 2449224 | 2343038 | 30266562 | 0 | 0 | 28508160 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 1824522240 | 7340032 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3136 | 56 | 15896198995703 | 15906998401121 | 15906998586882 | 15896199361105 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7f6ef8b5e200 | 0x7f6ef5c26000 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 54984704 | 53411840 | 543444 | 543444 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4480 | 0 | 10420224 | 10374130 | 67 | 48838 | 869458 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 52363264 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 395104670 | 18382350 | 322392976 | 54329344 | 4341688 | 4224046 | 54684268 | 0 | 0 | 53411840 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 3418357760 | 10420224 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4424 | 56 | 15896199410714 | 15906998610882 | 15906998944803 | 15896199955962 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7f6ef8b5e080 | 0x7f6ef5c26040 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 26673152 | 25165824 | 271924 | 271924 | 0 | 0 | 0 | 0 | 0 | 0 | 22282240 | 0 | 0 | 0 | 0 | 2912 | 0 | 6488064 | 6459567 | 145 | 28739 | 1007338 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 189844518 | 14797393 | 148832725 | 26214400 | 2173432 | 2069694 | 26800009 | 0 | 0 | 25165824 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 1610612736 | 6488064 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2856 | 56 | 15896199975641 | 15906999010243 | 15906999177603 | 15896200311114 |
| 135 | 133 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 398 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7f6ef63fdf00 | 0x7f6ef5c26080 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 34996224 | 32374784 | 367338 | 367338 | 0 | 0 | 0 | 0 | 0 | 0 | 29622272 | 0 | 0 | 0 | 0 | 3752 | 0 | 8519680 | 8476879 | 210 | 45979 | 1012953 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 242651665 | 36758756 | 171486509 | 34406400 | 2906768 | 2788111 | 35935413 | 0 | 0 | 32374784 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 2071986176 | 8519680 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3696 | 56 | 15896200362163 | 15906999201124 | 15906999429444 | 15896200798223 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7f6ef63fdd80 | 0x7f6ef5c260c0 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 34078720 | 32636928 | 364789 | 364789 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3696 | 0 | 8388608 | 8348868 | 112 | 49069 | 446677 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 29622272 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 255355507 | 38104942 | 183761669 | 33488896 | 2934168 | 2820043 | 36270658 | 0 | 0 | 32636928 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 2088763392 | 8388608 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3640 | 56 | 15896200808843 | 15906999463524 | 15906999693445 | 15896201255153 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7f6ef63fdc00 | 0x7f6ef5c26100 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 34275328 | 32702464 | 347659 | 347659 | 0 | 0 | 29622272 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3640 | 0 | 8388608 | 8344859 | 57 | 48538 | 847318 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 236775053 | 19970886 | 183118663 | 33685504 | 2776984 | 2664804 | 34418998 | 0 | 0 | 32702464 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 2092957696 | 8388608 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3584 | 56 | 15896201265702 | 15906999725125 | 15906999937126 | 15896201670233 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7f6ef63fda80 | 0x7f6ef5c26140 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 63373312 | 61800448 | 623555 | 623555 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5152 | 0 | 11993088 | 11938919 | 67 | 52240 | 850767 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 60751872 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 473894918 | 18566846 | 392610120 | 62717952 | 4991904 | 4876059 | 63125652 | 0 | 0 | 61800448 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 3955228672 | 11993088 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5096 | 56 | 15896201699073 | 15906999969766 | 15907000354887 | 15896202303169 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7f6ef63fd900 | 0x7f6ef5c26180 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 29818880 | 28311552 | 304705 | 304705 | 0 | 0 | 0 | 0 | 0 | 0 | 25427968 | 0 | 0 | 0 | 0 | 3248 | 0 | 7274496 | 7239128 | 139 | 44047 | 1008294 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 207726774 | 16511995 | 161854651 | 29360128 | 2431240 | 2317954 | 29876905 | 0 | 0 | 28311552 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 1811939328 | 7274496 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3192 | 56 | 15896202322559 | 15907000395047 | 15907000581448 | 15896202680481 |
| 140 | 138 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 413 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7f6ef63fd780 | 0x7f6ef5c261c0 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 39190528 | 36569088 | 398420 | 398420 | 0 | 0 | 0 | 0 | 0 | 0 | 33816576 | 0 | 0 | 0 | 0 | 4144 | 0 | 9568256 | 9515653 | 186 | 46079 | 1006178 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 269325624 | 32476448 | 198248472 | 38600704 | 3195072 | 3084113 | 39756500 | 0 | 0 | 36569088 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 2340421632 | 9568256 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4088 | 56 | 15896202731210 | 15907000605288 | 15907000855689 | 15896203195239 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7f6ef63fd600 | 0x7f6ef5c26200 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 38273024 | 36831232 | 391830 | 391830 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4144 | 0 | 9437184 | 9384738 | 113 | 51110 | 437365 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 33816576 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 278512517 | 30692425 | 210136892 | 37683200 | 3138880 | 3028140 | 39214528 | 0 | 0 | 36831232 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 2357198848 | 9437184 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4088 | 56 | 15896203205869 | 15907000890249 | 15907001138890 | 15896203671239 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7f6ef8b5e480 | 0x7f6ef5c26240 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 38469632 | 36896768 | 388406 | 388406 | 0 | 0 | 33816576 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4032 | 0 | 9437184 | 9385854 | 58 | 54737 | 887883 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 279933558 | 20427164 | 221626586 | 37879808 | 3094600 | 2991075 | 38664937 | 0 | 0 | 36896768 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 2361393152 | 9437184 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3976 | 56 | 15896203682158 | 15907001170890 | 15907001407531 | 15896204135798 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7f6ef8b5e300 | 0x7f6ef5c26280 | 0 | 0 | 524288 | 524288 | 4784128 | 0 | 81002496 | 71172096 | 719128 | 719128 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2016 | 0 | 16056320 | 16051872 | 56 | 4384 | 1013089 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 69468160 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 2162688 | 65536 | 536530980 | 82919222 | 374771950 | 78839808 | 5751104 | 5632133 | 72896807 | 0 | 0 | 71172096 | 4915200 | 0 | 2228224 | 524288 | 0 | 524288 | 131072 | 4784128 | 4555014144 | 16056320 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1960 | 56 | 15896204146258 | 15907001439371 | 15907001891692 | 15896204815513 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7f6ef8b5e180 | 0x7f6ef5c262c0 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 36110336 | 34603008 | 365541 | 365541 | 0 | 0 | 0 | 0 | 0 | 0 | 31719424 | 0 | 0 | 0 | 0 | 3920 | 0 | 8847360 | 8801026 | 174 | 48425 | 1010764 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 252967044 | 16666707 | 200648753 | 35651584 | 2910000 | 2800894 | 36230230 | 0 | 0 | 34603008 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 2214592512 | 8847360 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3864 | 56 | 15896204835193 | 15907001929933 | 15907002155533 | 15896205268063 |
| 145 | 143 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 428 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7f6ef8b5e000 | 0x7f6ef5c26300 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 47644672 | 45023232 | 470031 | 470031 | 0 | 0 | 0 | 0 | 0 | 0 | 42205184 | 0 | 0 | 0 | 0 | 5040 | 0 | 11665408 | 11606993 | 112 | 67059 | 1007459 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1572864 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 348399066 | 29134286 | 272209932 | 47054848 | 3771448 | 3661209 | 47371416 | 0 | 0 | 45023232 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 2881486848 | 11665408 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4984 | 56 | 15896205279273 | 15907002215693 | 15907002513774 | 15896205774282 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7f6ef63fde80 | 0x7f6ef5c26340 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 46727168 | 45285376 | 473111 | 473111 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5040 | 0 | 11468800 | 11395339 | 293 | 78243 | 687766 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 42205184 | 0 | 1572864 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 344656706 | 29945631 | 268573731 | 46137344 | 3783024 | 3674010 | 47469609 | 0 | 0 | 45285376 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 2898264064 | 11468800 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4984 | 56 | 15896205804831 | 15907002549455 | 15907002848176 | 15896206311710 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7f6ef63fdd00 | 0x7f6ef5c26380 | 0 | 0 | 524288 | 524288 | 4849664 | 0 | 56229888 | 46333952 | 483121 | 483121 | 0 | 0 | 42205184 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1792 | 0 | 14090240 | 14085960 | 3 | 4599 | 1006422 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1900544 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 2162688 | 65536 | 349450976 | 87272242 | 208111534 | 54067200 | 3861328 | 3749553 | 48510186 | 0 | 0 | 46333952 | 4980736 | 0 | 2228224 | 524288 | 0 | 524288 | 131072 | 4849664 | 2965372928 | 14090240 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1736 | 56 | 15896206323339 | 15907002885616 | 15907003182257 | 15896206850948 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7f6ef63fdb80 | 0x7f6ef5c263c0 | 0 | 0 | 524288 | 524288 | 4784128 | 0 | 97779712 | 87949312 | 879498 | 879498 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2352 | 0 | 19202048 | 19194504 | 112 | 7301 | 1022529 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 86245376 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 2162688 | 65536 | 675545295 | 83131504 | 496796767 | 95617024 | 7040120 | 6926298 | 89689538 | 0 | 0 | 87949312 | 4915200 | 0 | 2228224 | 524288 | 0 | 524288 | 131072 | 4784128 | 5628755968 | 19202048 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2296 | 56 | 15896206861648 | 15907003220177 | 15907003777139 | 15896207632790 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7f6ef63fda00 | 0x7f6ef5c26400 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 42401792 | 40960000 | 427239 | 427239 | 0 | 0 | 0 | 0 | 0 | 0 | 38010880 | 0 | 0 | 0 | 0 | 4480 | 0 | 10420224 | 10359905 | 83 | 60775 | 1008427 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1572864 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 319164755 | 17866454 | 259289725 | 42008576 | 3416824 | 3307122 | 42771671 | 0 | 0 | 40960000 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 2621440000 | 10420224 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4424 | 56 | 15896207653170 | 15907003818099 | 15907004081940 | 15896208128759 |
| 150 | 148 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 443 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7f6ef63fd880 | 0x7f6ef5c26440 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 55967744 | 53411840 | 550931 | 550931 | 0 | 0 | 0 | 0 | 0 | 0 | 50593792 | 0 | 0 | 0 | 0 | 5992 | 0 | 13762560 | 13663442 | 476 | 82169 | 1025642 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1572864 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 406480028 | 27411924 | 323624648 | 55443456 | 4413968 | 4307645 | 55749486 | 0 | 0 | 53411840 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 3418357760 | 13762560 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5936 | 56 | 15896208139119 | 15907004116820 | 15907004467701 | 15896208710797 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7f6ef63fd700 | 0x7f6ef5c26480 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 55115776 | 53673984 | 552920 | 552920 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5936 | 0 | 13565952 | 13482160 | 389 | 84473 | 445448 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 50593792 | 0 | 1572864 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 415407635 | 27169647 | 333712036 | 54525952 | 4409016 | 4295664 | 55620598 | 0 | 0 | 53673984 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 3435134976 | 13565952 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5880 | 56 | 15896208721336 | 15907004533461 | 15907004883542 | 15896209289164 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7f6ef8b5e580 | 0x7f6ef5c264c0 | 0 | 0 | 524288 | 524288 | 3801088 | 0 | 62521344 | 54722560 | 563650 | 563650 | 0 | 0 | 50593792 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2464 | 0 | 15466496 | 15457543 | 1 | 10774 | 1005260 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1900544 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 1638400 | 65536 | 414528923 | 85383587 | 268262392 | 60882944 | 4510072 | 4394196 | 56825316 | 0 | 0 | 54722560 | 3932160 | 0 | 1703936 | 524288 | 0 | 524288 | 131072 | 3801088 | 3502243840 | 15466496 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2408 | 56 | 15896209300843 | 15907004946902 | 15907005294104 | 15896209848551 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7f6ef8b5e400 | 0x7f6ef5c26500 | 0 | 0 | 524288 | 524288 | 4784128 | 0 | 114556928 | 104726528 | 1041285 | 1041285 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2688 | 0 | 22347776 | 22337039 | 112 | 10144 | 1008455 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 103022592 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 2162688 | 65536 | 792736297 | 83962591 | 596379466 | 112394240 | 8339912 | 8216878 | 106424920 | 0 | 0 | 104726528 | 4915200 | 0 | 2228224 | 524288 | 0 | 524288 | 131072 | 4784128 | 6702497792 | 22347776 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2632 | 56 | 15896209877721 | 15907005353624 | 15907006015226 | 15896210753961 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7f6ef8b5e280 | 0x7f6ef5c26540 | 0 | 0 | 524288 | 524288 | 4784128 | 0 | 80871424 | 71041024 | 720690 | 720690 | 0 | 0 | 0 | 0 | 0 | 0 | 67371008 | 0 | 0 | 0 | 0 | 2464 | 0 | 20250624 | 20242026 | 113 | 7780 | 1020265 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1900544 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 2162688 | 65536 | 546998530 | 90249312 | 378040482 | 78708736 | 5781928 | 5656104 | 73198342 | 0 | 0 | 71041024 | 4915200 | 0 | 2228224 | 524288 | 0 | 524288 | 131072 | 4784128 | 4546625536 | 20250624 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2408 | 56 | 15896210773461 | 15907006055546 | 15907006503228 | 15896211432866 |
| 155 | 153 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 458 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7f6ef8b5e100 | 0x7f6ef5c26580 | 0 | 0 | 524288 | 524288 | 5832704 | 0 | 82116608 | 71172096 | 724553 | 724553 | 0 | 0 | 0 | 0 | 0 | 0 | 67371008 | 0 | 0 | 0 | 0 | 2520 | 0 | 20447232 | 20437396 | 57 | 9758 | 1007015 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1900544 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 2228224 | 65536 | 544124059 | 96395122 | 367775017 | 79953920 | 5768392 | 5666264 | 73391418 | 0 | 0 | 71172096 | 5963776 | 0 | 2293760 | 524288 | 0 | 524288 | 131072 | 5832704 | 4555014144 | 20447232 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2464 | 56 | 15896211444236 | 15907006572828 | 15907007037949 | 15896212132560 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7f6ef63fdf80 | 0x7f6ef5c265c0 | 0 | 0 | 524288 | 524288 | 4784128 | 0 | 80805888 | 71041024 | 722160 | 722160 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2464 | 0 | 19595264 | 19586295 | 112 | 8599 | 443975 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 67371008 | 0 | 1900544 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 2162688 | 65536 | 552225870 | 98714773 | 374867897 | 78643200 | 5786024 | 5661464 | 73311954 | 0 | 0 | 71041024 | 4849664 | 0 | 2228224 | 524288 | 0 | 524288 | 65536 | 4784128 | 4546625536 | 19595264 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2408 | 56 | 15896212143570 | 15907007101630 | 15907007563551 | 15896212838965 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7f6ef63fde00 | 0x7f6ef5c26600 | 0 | 0 | 524288 | 524288 | 4849664 | 0 | 81395712 | 71499776 | 724551 | 724551 | 0 | 0 | 67371008 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2520 | 0 | 20381696 | 20372652 | 113 | 9175 | 1025078 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1900544 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 2162688 | 65536 | 557276813 | 90345413 | 387698376 | 79233024 | 5800608 | 5693393 | 73708935 | 0 | 0 | 71499776 | 4980736 | 0 | 2228224 | 524288 | 0 | 524288 | 131072 | 4849664 | 4575985664 | 20381696 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2464 | 56 | 15896212850264 | 15907007627551 | 15907008079233 | 15896213529859 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7f6ef63fdc80 | 0x7f6ef5c26640 | 0 | 0 | 524288 | 524288 | 8978432 | 0 | 156499968 | 138280960 | 1370046 | 1370046 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2016 | 0 | 31522816 | 31517140 | 56 | 4441 | 1014613 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 136577024 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 4259840 | 65536 | 1074120840 | 96100563 | 825780149 | 152240128 | 10948336 | 10814091 | 140106697 | 0 | 0 | 138280960 | 9109504 | 0 | 4325376 | 524288 | 0 | 524288 | 131072 | 8978432 | 8849981440 | 31522816 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1960 | 56 | 15896213541079 | 15907008142273 | 15907009010916 | 15896214657144 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7f6ef63fdb00 | 0x7f6ef5c26680 | 0 | 0 | 524288 | 524288 | 8978432 | 0 | 156368896 | 138149888 | 1370184 | 1370184 | 0 | 0 | 0 | 0 | 0 | 0 | 134479872 | 0 | 0 | 0 | 0 | 2464 | 0 | 38993920 | 38986121 | 113 | 7467 | 1013446 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1900544 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 4259840 | 65536 | 1075110241 | 110954909 | 812046276 | 152109056 | 10964160 | 10843347 | 140535259 | 0 | 0 | 138149888 | 9109504 | 0 | 4325376 | 524288 | 0 | 524288 | 131072 | 8978432 | 8841592832 | 38993920 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2408 | 56 | 15896214678293 | 15907009059876 | 15907009913639 | 15896215784939 |
| 160 | 158 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 473 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7f6ef63fd980 | 0x7f6ef5c266c0 | 0 | 0 | 524288 | 524288 | 10027008 | 0 | 157614080 | 138280960 | 1373532 | 1373532 | 0 | 0 | 0 | 0 | 0 | 0 | 134479872 | 0 | 0 | 0 | 0 | 2520 | 0 | 39124992 | 39116793 | 112 | 8532 | 1007116 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1900544 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 4325376 | 65536 | 1067303771 | 115602568 | 798346963 | 153354240 | 10998064 | 10856418 | 140686736 | 0 | 0 | 138280960 | 10158080 | 0 | 4390912 | 524288 | 0 | 524288 | 131072 | 10027008 | 8849981440 | 39124992 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2464 | 56 | 15896215796408 | 15907009953159 | 15907010838122 | 15896216935843 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7f6ef63fd800 | 0x7f6ef5c26700 | 0 | 0 | 524288 | 524288 | 8978432 | 0 | 156303360 | 138149888 | 1369598 | 1369598 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2464 | 0 | 38469632 | 38461829 | 56 | 7694 | 593789 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 134479872 | 0 | 1900544 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 4259840 | 65536 | 1069201789 | 114402723 | 802755546 | 152043520 | 10983088 | 10852319 | 140544252 | 0 | 0 | 138149888 | 9043968 | 0 | 4325376 | 524288 | 0 | 524288 | 65536 | 8978432 | 8841592832 | 38469632 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2408 | 56 | 15896216946603 | 15907010881962 | 15907011760685 | 15896218086997 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7f6ef63fd680 | 0x7f6ef5c26740 | 0 | 0 | 524288 | 524288 | 9043968 | 0 | 156893184 | 138608640 | 1376486 | 1376486 | 0 | 0 | 134479872 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2520 | 0 | 39059456 | 39049927 | 114 | 8334 | 1010089 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1900544 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 4259840 | 65536 | 1078083375 | 110863102 | 814586929 | 152633344 | 11004240 | 10880917 | 140993823 | 0 | 0 | 138608640 | 9175040 | 0 | 4325376 | 524288 | 0 | 524288 | 131072 | 9043968 | 8870952960 | 39059456 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2464 | 56 | 15896218098687 | 15907011812045 | 15907012671408 | 15896219221492 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7f6ef8b5e500 | 0x7f6ef5c26780 | 0 | 0 | 524288 | 524288 | 17367040 | 0 | 307494912 | 272498688 | 2661762 | 2661762 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2016 | 0 | 60489728 | 60483968 | 112 | 5123 | 1011178 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 270794752 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 8454144 | 65536 | 2126112344 | 118155279 | 1708916297 | 299040768 | 21318256 | 21186857 | 274515807 | 0 | 0 | 272498688 | 17498112 | 0 | 8519680 | 524288 | 0 | 524288 | 131072 | 17367040 | 17439916032 | 60489728 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1960 | 56 | 15896219232322 | 15907012710448 | 15907014409494 | 15896221186338 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7f6ef8b5e380 | 0x7f6ef5c267c0 | 0 | 0 | 524288 | 524288 | 17367040 | 0 | 307363840 | 272367616 | 2671023 | 2671023 | 0 | 0 | 0 | 0 | 0 | 0 | 268697600 | 0 | 0 | 0 | 0 | 2464 | 0 | 77266944 | 77258460 | 57 | 8639 | 1011655 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1900544 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 8454144 | 65536 | 2111591696 | 149543935 | 1663138065 | 298909696 | 21360632 | 21225349 | 275023332 | 0 | 0 | 272367616 | 17498112 | 0 | 8519680 | 524288 | 0 | 524288 | 131072 | 17367040 | 17431527424 | 77266944 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2408 | 56 | 15896221204378 | 15907014507254 | 15907016172060 | 15896223130265 |
| 165 | 163 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 488 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7f6ef8b5e200 | 0x7f6ef5c26800 | 0 | 0 | 524288 | 524288 | 18415616 | 0 | 308609024 | 272498688 | 2669886 | 2669886 | 0 | 0 | 0 | 0 | 0 | 0 | 268697600 | 0 | 0 | 0 | 0 | 2520 | 0 | 77398016 | 77389486 | 112 | 7992 | 1005431 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1900544 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 8519680 | 65536 | 2125855763 | 153750414 | 1671950469 | 300154880 | 21347896 | 21233274 | 275176560 | 0 | 0 | 272498688 | 18546688 | 0 | 8585216 | 524288 | 0 | 524288 | 131072 | 18415616 | 17439916032 | 77398016 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2464 | 56 | 15896223141185 | 15907016261500 | 15907017985826 | 15896225137790 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7f6ef8b5e080 | 0x7f6ef5c26840 | 0 | 0 | 524288 | 524288 | 17367040 | 0 | 307298304 | 272367616 | 2671049 | 2671049 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2464 | 0 | 76218368 | 76210492 | 113 | 7760 | 492429 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 268697600 | 0 | 1900544 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 8454144 | 65536 | 2120152905 | 150387006 | 1670921739 | 298844160 | 21358536 | 21227966 | 275040755 | 0 | 0 | 272367616 | 17432576 | 0 | 8519680 | 524288 | 0 | 524288 | 65536 | 17367040 | 17431527424 | 76218368 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2408 | 56 | 15896225148710 | 15907018086306 | 15907019801192 | 15896227128056 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7f6ef63fdf00 | 0x7f6ef5c26880 | 0 | 0 | 524288 | 524288 | 17432576 | 0 | 307888128 | 272826368 | 2673475 | 2673475 | 0 | 0 | 268697600 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2520 | 0 | 77332480 | 77322771 | 57 | 9463 | 1022721 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1900544 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 8454144 | 65536 | 2132210146 | 149782980 | 1682993182 | 299433984 | 21390448 | 21257250 | 275485214 | 0 | 0 | 272826368 | 17563648 | 0 | 8519680 | 524288 | 0 | 524288 | 131072 | 17432576 | 17460887552 | 77332480 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2464 | 56 | 15896227139446 | 15907019889832 | 15907021563437 | 15896229078312 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 137896 | 137896 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7f6ef63fdd80 | 0x7f6ef5c268c0 | 0 | 0 | 524288 | 524288 | 34144256 | 0 | 609484800 | 540934144 | 5258589 | 5258589 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2016 | 0 | 120258560 | 120253200 | 112 | 5305 | 1010290 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 539230208 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 16842752 | 65536 | 4229324231 | 167639577 | 3469042606 | 592642048 | 42050184 | 41922128 | 543375553 | 0 | 0 | 540934144 | 34275328 | 0 | 16908288 | 524288 | 0 | 524288 | 131072 | 34144256 | 34619785216 | 120258560 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1960 | 56 | 15896229088542 | 15907021650158 | 15907025006809 | 15896232708551 |