66 KiB
66 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | 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 | TCP_TCC_READ_REQ_sum | TCP_TOTAL_CACHE_ACCESSES_sum | TCP_TCC_WRITE_REQ_sum | TCP_TCC_ATOMIC_WITH_RET_REQ_sum | TCC_EA_RDREQ_32B_sum | TCC_EA_RDREQ_sum | TCC_EA_WRREQ_64B_sum | TCC_EA_WRREQ_sum | SQ_INSTS_VALU_ADD_F64 | SQ_INSTS_VALU_MUL_F64 | SQ_INSTS_VALU_FMA_F64 | SQ_INSTS_VALU_TRANS_F64 | SQ_INSTS_VALU_MFMA_MOPS_F16 | SQ_INSTS_VALU_MFMA_MOPS_BF16 | SQ_INSTS_VALU_MFMA_MOPS_F32 | SQ_INSTS_VALU_MFMA_MOPS_F64 | TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum | SQ_LDS_IDX_ACTIVE | SQ_LDS_BANK_CONFLICT | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBufferAligned.kd | 0 | 0 | 0 | 141956 | 141956 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7fe9f8604280 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 8388608.0000000000 | 4194304.0000000000 | 0.0000000000 | 0.0000000000 | 311.0000000000 | 4128768.0000000000 | 4128768.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977203048375 | 15947876597242 | 15977351197736 | 15977351311147 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 141956 | 141956 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7fe9f8623f80 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 8192.0000000000 | 16384.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 8260.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977357064979 | 15977351197736 | 15977357414595 | 15977357422521 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7fe9fb6cf380 | 0x7fe9f8623fc0 | 0 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097342.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977358014418 | 15977357414595 | 15977358936530 | 15977358938757 |
| 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 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7fe9fb6cf200 | 0x7fe9f8624000 | 0 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194593.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977359550304 | 15977358936530 | 15977360553665 | 15977360556001 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7fe9fb6cf080 | 0x7fe9f8624040 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194598.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977361156078 | 15977360553665 | 15977362120721 | 15977362120796 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7fe9f902ff00 | 0x7fe9f8624080 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097341.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977362724643 | 15977362120721 | 15977363585535 | 15977363586884 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7fe9f902fd80 | 0x7fe9f86240c0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097343.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977364186451 | 15977363585535 | 15977365048909 | 15977365050261 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7fe9f902fc00 | 0x7fe9f8624100 | 0 | 0 | 0 | 0 | 0 | 0 | 655360 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097340.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977365671768 | 15977365048909 | 15977366547163 | 15977366548508 |
| 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 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7fe9f902fa80 | 0x7fe9f8624140 | 0 | 0 | 0 | 0 | 0 | 0 | 786432 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194582.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977367149765 | 15977366547163 | 15977368101098 | 15977368101144 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7fe9f902f900 | 0x7fe9f8624180 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194604.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 786432 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977368696601 | 15977368101098 | 15977369359990 | 15977369359896 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7fe9f902f780 | 0x7fe9f86241c0 | 0 | 0 | 786432 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097338.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977369952793 | 15977369359990 | 15977370534402 | 15977370534180 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7fe9f902f600 | 0x7fe9f8624200 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097342.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977371127776 | 15977370534402 | 15977371695533 | 15977371695704 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7fe9fb6cf480 | 0x7fe9f8624240 | 0 | 0 | 0 | 0 | 0 | 0 | 1048576 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097336.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977372298540 | 15977371695533 | 15977372853624 | 15977372853518 |
| 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 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7fe9fb6cf300 | 0x7fe9f8624280 | 0 | 0 | 0 | 0 | 0 | 0 | 1310720 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194590.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977373448175 | 15977372853624 | 15977374116676 | 15977374116170 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7fe9fb6cf180 | 0x7fe9f86242c0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194573.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 1310720 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977374712706 | 15977374116676 | 15977375379728 | 15977375379442 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7fe9fb6cf000 | 0x7fe9f8624300 | 0 | 0 | 1310720 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097344.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977375973808 | 15977375379728 | 15977376557660 | 15977376557316 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7fe9f902fe80 | 0x7fe9f8624340 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097344.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977377151702 | 15977376557660 | 15977377713031 | 15977377713050 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7fe9f902fd00 | 0x7fe9f8624380 | 0 | 0 | 0 | 0 | 0 | 0 | 1441792 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097339.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977378315267 | 15977377713031 | 15977378857042 | 15977378856774 |
| 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 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7fe9f902fb80 | 0x7fe9f86243c0 | 0 | 0 | 0 | 0 | 0 | 0 | 1835008 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194586.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977379449741 | 15977378857042 | 15977380103614 | 15977380103307 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7fe9f902fa00 | 0x7fe9f8624400 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194578.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 1835008 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977380696223 | 15977380103614 | 15977381347786 | 15977381347419 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7fe9f902f880 | 0x7fe9f8624440 | 0 | 0 | 1835008 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097345.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977381940236 | 15977381347786 | 15977382515477 | 15977382515403 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7fe9f902f700 | 0x7fe9f8624480 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097349.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977383108350 | 15977382515477 | 15977383663328 | 15977383663157 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7fe9fb6cf580 | 0x7fe9f86244c0 | 0 | 0 | 0 | 0 | 0 | 0 | 1835008 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097340.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977384264524 | 15977383663328 | 15977384819019 | 15977384818582 |
| 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 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7fe9fb6cf400 | 0x7fe9f8624500 | 0 | 0 | 0 | 0 | 0 | 0 | 2359296 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194597.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977385413299 | 15977384819019 | 15977386072311 | 15977386072374 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7fe9fb6cf280 | 0x7fe9f8624540 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194592.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 2359296 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977386667071 | 15977386072311 | 15977387302563 | 15977387302917 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7fe9fb6cf100 | 0x7fe9f8624580 | 0 | 0 | 2359296 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097345.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977387896063 | 15977387302563 | 15977388420974 | 15977388420482 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7fe9f902ff80 | 0x7fe9f86245c0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097350.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977389013849 | 15977388420974 | 15977389552025 | 15977389551797 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7fe9f902fe00 | 0x7fe9f8624600 | 0 | 0 | 0 | 0 | 0 | 0 | 2228224 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097346.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977390152463 | 15977389552025 | 15977390711556 | 15977390711751 |
| 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 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7fe9f902fc80 | 0x7fe9f8624640 | 0 | 0 | 0 | 0 | 0 | 0 | 2883584 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194587.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977391305698 | 15977390711556 | 15977391955408 | 15977391955283 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7fe9f902fb00 | 0x7fe9f8624680 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194578.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 2883584 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977392548300 | 15977391955408 | 15977393174299 | 15977393174086 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7fe9f902f980 | 0x7fe9f86246c0 | 0 | 0 | 2883584 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097342.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977393766253 | 15977393174299 | 15977394322631 | 15977394322340 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7fe9f902f800 | 0x7fe9f8624700 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097354.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977394915007 | 15977394322631 | 15977395445681 | 15977395445525 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7fe9f902f680 | 0x7fe9f8624740 | 0 | 0 | 0 | 0 | 0 | 0 | 2621440 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097341.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977396046422 | 15977395445681 | 15977396606332 | 15977396606400 |
| 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 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7fe9fb6cf500 | 0x7fe9f8624780 | 0 | 0 | 0 | 0 | 0 | 0 | 3407872 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194591.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977397199406 | 15977396606332 | 15977397827304 | 15977397826803 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7fe9fb6cf380 | 0x7fe9f86247c0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194601.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 3407872 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977398420479 | 15977397827304 | 15977399035316 | 15977399035176 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7fe9fb6cf200 | 0x7fe9f8624800 | 0 | 0 | 3407872 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097351.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977399629132 | 15977399035316 | 15977400176127 | 15977400176000 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7fe9fb6cf080 | 0x7fe9f8624840 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097354.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977400769947 | 15977400176127 | 15977401288138 | 15977401287735 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7fe9f902ff00 | 0x7fe9f8624880 | 0 | 0 | 0 | 0 | 0 | 0 | 3014656 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097349.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977401889232 | 15977401288138 | 15977402468149 | 15977402467979 |
| 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 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7fe9f902fd80 | 0x7fe9f86248c0 | 0 | 0 | 0 | 0 | 0 | 0 | 3932160 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194588.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977403062126 | 15977402468149 | 15977403699841 | 15977403699662 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7fe9f902fc00 | 0x7fe9f8624900 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194583.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 3932160 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977404292459 | 15977403699841 | 15977404912492 | 15977404912125 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7fe9f902fa80 | 0x7fe9f8624940 | 0 | 0 | 3932160 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097350.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977405504952 | 15977404912492 | 15977406042103 | 15977406041750 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7fe9f902f900 | 0x7fe9f8624980 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097358.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977406634627 | 15977406042103 | 15977407188194 | 15977407187914 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7fe9f902f780 | 0x7fe9f86249c0 | 0 | 0 | 0 | 0 | 0 | 0 | 3407872 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097352.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977407787921 | 15977407188194 | 15977408321805 | 15977408321429 |
| 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 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7fe9f902f600 | 0x7fe9f8624a00 | 0 | 0 | 0 | 0 | 0 | 0 | 4456448 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194555.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977408914756 | 15977408321805 | 15977409542297 | 15977409542042 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7fe9fb6cf480 | 0x7fe9f8624a40 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194574.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 4456448 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977410135739 | 15977409542297 | 15977410785669 | 15977410785474 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7fe9fb6cf300 | 0x7fe9f8624a80 | 0 | 0 | 4456448 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097350.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977411378521 | 15977410785669 | 15977411917200 | 15977411917029 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7fe9fb6cf180 | 0x7fe9f8624ac0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097358.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977412509556 | 15977411917200 | 15977413054171 | 15977413054224 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7fe9fb6cf000 | 0x7fe9f8624b00 | 0 | 0 | 0 | 0 | 0 | 0 | 3801088 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097348.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977413655250 | 15977413052282 | 15977414204448 | 15977414210828 |
| 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 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7fe9f902fe80 | 0x7fe9f8624b40 | 0 | 0 | 0 | 0 | 0 | 0 | 4980736 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194574.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977414799495 | 15977414204448 | 15977415406055 | 15977415407741 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7fe9f902fd00 | 0x7fe9f8624b80 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194569.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 4980736 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977415999748 | 15977415406055 | 15977416626702 | 15977416628244 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7fe9f902fb80 | 0x7fe9f8624bc0 | 0 | 0 | 4980736 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097354.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977417220851 | 15977416626702 | 15977417778709 | 15977417780449 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7fe9f902fa00 | 0x7fe9f8624c00 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097360.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977418374086 | 15977417778709 | 15977418918395 | 15977418920053 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7fe9f902f880 | 0x7fe9f8624c40 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097355.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977419520650 | 15977418918395 | 15977420063042 | 15977420064498 |
| 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 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7fe9f902f700 | 0x7fe9f8624c80 | 0 | 0 | 0 | 0 | 0 | 0 | 5505024 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194567.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977420657825 | 15977420063042 | 15977421291049 | 15977421292920 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7fe9fb6cf580 | 0x7fe9f8624cc0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194581.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 5505024 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977421885747 | 15977421291049 | 15977422498897 | 15977422500603 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7fe9fb6cf400 | 0x7fe9f8624d00 | 0 | 0 | 5505024 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097355.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977423093570 | 15977422498897 | 15977423647383 | 15977423648888 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7fe9fb6cf280 | 0x7fe9f8624d40 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097358.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977424242705 | 15977423647383 | 15977424767550 | 15977424769433 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7fe9fb6cf100 | 0x7fe9f8624d80 | 0 | 0 | 0 | 0 | 0 | 0 | 4587520 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097349.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977425370320 | 15977424767550 | 15977425920837 | 15977425922488 |
| 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 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7fe9f902ff80 | 0x7fe9f8624dc0 | 0 | 0 | 0 | 0 | 0 | 0 | 6029312 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194576.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977426517144 | 15977425920837 | 15977427157644 | 15977427159080 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7fe9f902fe00 | 0x7fe9f8624e00 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194551.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 6029312 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977427752607 | 15977427157644 | 15977428384212 | 15977428385933 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7fe9f902fc80 | 0x7fe9f8624e40 | 0 | 0 | 6029312 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097352.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977428978040 | 15977428384212 | 15977429510458 | 15977429511868 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7fe9f902fb00 | 0x7fe9f8624e80 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097349.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977430105185 | 15977429510458 | 15977430653985 | 15977430655473 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7fe9f902f980 | 0x7fe9f8624ec0 | 0 | 0 | 0 | 0 | 0 | 0 | 4980736 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097359.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977431266269 | 15977430653985 | 15977431797672 | 15977431799237 |
| 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 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7fe9f902f800 | 0x7fe9f8624f00 | 0 | 0 | 0 | 0 | 0 | 0 | 6553600 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194553.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977432392304 | 15977431797672 | 15977433021839 | 15977433023380 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7fe9f902f680 | 0x7fe9f8624f40 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194571.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 6553600 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977433616376 | 15977433021839 | 15977434250486 | 15977434252202 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7fe9fb6cf500 | 0x7fe9f8624f80 | 0 | 0 | 6553600 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097354.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977434844839 | 15977434250486 | 15977435389853 | 15977435391317 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7fe9fb6cf380 | 0x7fe9f8624fc0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097350.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977435984674 | 15977435389853 | 15977436553220 | 15977436554831 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7fe9fb6cf200 | 0x7fe9f8625000 | 0 | 0 | 0 | 0 | 0 | 0 | 5373952 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097355.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977437156408 | 15977436553220 | 15977437713067 | 15977437714535 |
| 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 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7fe9fb6cf080 | 0x7fe9f8625040 | 0 | 0 | 0 | 0 | 0 | 0 | 7077888 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194554.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977438309212 | 15977437713067 | 15977438954994 | 15977438956598 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7fe9f902ff00 | 0x7fe9f8625080 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194570.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 7077888 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977439550175 | 15977438954994 | 15977440181561 | 15977440183180 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7fe9f902fd80 | 0x7fe9f86250c0 | 0 | 0 | 7077888 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097358.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977440775437 | 15977440181561 | 15977441321088 | 15977441322405 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7fe9f902fc00 | 0x7fe9f8625100 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097349.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977441915152 | 15977441321088 | 15977442494855 | 15977442496379 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7fe9f902fa80 | 0x7fe9f8625140 | 0 | 0 | 0 | 0 | 0 | 0 | 5767168 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097355.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977443097415 | 15977442494855 | 15977443658702 | 15977443660543 |
| 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 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7fe9f902f900 | 0x7fe9f8625180 | 0 | 0 | 0 | 0 | 0 | 0 | 7602176 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194584.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977444253180 | 15977443658702 | 15977444883509 | 15977444885356 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7fe9f902f780 | 0x7fe9f86251c0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194556.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 7602176 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977445477593 | 15977444883509 | 15977446110237 | 15977446112049 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7fe9f902f600 | 0x7fe9f8625200 | 0 | 0 | 7602176 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097357.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977446705055 | 15977446110237 | 15977447250723 | 15977447252563 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7fe9fb6cf480 | 0x7fe9f8625240 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097349.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977447845780 | 15977447250723 | 15977448419690 | 15977448421347 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7fe9fb6cf300 | 0x7fe9f8625280 | 0 | 0 | 0 | 0 | 0 | 0 | 6160384 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097357.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977449022134 | 15977448419690 | 15977449536177 | 15977449538083 |
| 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 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7fe9fb6cf180 | 0x7fe9f86252c0 | 0 | 0 | 0 | 0 | 0 | 0 | 8126464 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194571.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977450131279 | 15977449536177 | 15977450765624 | 15977450766975 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7fe9fb6cf000 | 0x7fe9f8625300 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194567.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 8126464 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977451361792 | 15977450765624 | 15977451994752 | 15977451996068 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7fe9f902fe80 | 0x7fe9f8625340 | 0 | 0 | 8126464 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097359.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977452589075 | 15977451994752 | 15977453139398 | 15977453140872 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7fe9f902fd00 | 0x7fe9f8625380 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097335.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977453734009 | 15977453139398 | 15977454336205 | 15977454338246 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7fe9f902fb80 | 0x7fe9f86253c0 | 0 | 0 | 0 | 0 | 0 | 0 | 6553600 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097356.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977454938982 | 15977454336205 | 15977455482932 | 15977455484220 |
| 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 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7fe9f902fa00 | 0x7fe9f8625400 | 0 | 0 | 0 | 0 | 0 | 0 | 8650752 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194573.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977456077587 | 15977455482932 | 15977456709979 | 15977456711433 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7fe9f902f880 | 0x7fe9f8625440 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194584.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 8650752 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977457304460 | 15977456709979 | 15977457944227 | 15977457945766 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7fe9f902f700 | 0x7fe9f8625480 | 0 | 0 | 8650752 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097360.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977458538592 | 15977457944227 | 15977459089194 | 15977459090740 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7fe9fb6cf580 | 0x7fe9f86254c0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097332.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977459683857 | 15977459089194 | 15977460284561 | 15977460285773 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7fe9fb6cf400 | 0x7fe9f8625500 | 0 | 0 | 0 | 0 | 0 | 0 | 6946816 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097361.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977460887500 | 15977460284561 | 15977461423607 | 15977461425038 |
| 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 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7fe9fb6cf280 | 0x7fe9f8625540 | 0 | 0 | 0 | 0 | 0 | 0 | 9175040 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194577.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977462019415 | 15977461423607 | 15977462644255 | 15977462646461 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7fe9fb6cf100 | 0x7fe9f8625580 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194587.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 9175040 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977463239617 | 15977462644255 | 15977463852582 | 15977463854004 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7fe9f902ff80 | 0x7fe9f86255c0 | 0 | 0 | 9175040 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097365.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977464447701 | 15977463852582 | 15977464988589 | 15977464990209 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7fe9f902fe00 | 0x7fe9f8625600 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097333.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977465583726 | 15977464988589 | 15977466189076 | 15977466190942 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7fe9f902fc80 | 0x7fe9f8625640 | 0 | 0 | 0 | 0 | 0 | 0 | 7340032 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097355.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977466791669 | 15977466189076 | 15977467317242 | 15977467318787 |
| 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 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7fe9f902fb00 | 0x7fe9f8625680 | 0 | 0 | 0 | 0 | 0 | 0 | 9699328 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194572.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977467911774 | 15977467317242 | 15977468552290 | 15977468554039 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7fe9f902f980 | 0x7fe9f86256c0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194594.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 9699328 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977469146866 | 15977468552290 | 15977469754697 | 15977469756282 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7fe9f902f800 | 0x7fe9f8625700 | 0 | 0 | 9699328 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097361.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977470349219 | 15977469754697 | 15977470905104 | 15977470906677 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7fe9f902f680 | 0x7fe9f8625740 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097328.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977471501304 | 15977470905104 | 15977472109111 | 15977472110750 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7fe9fb6cf500 | 0x7fe9f8625780 | 0 | 0 | 0 | 0 | 0 | 0 | 8126464 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097362.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977472711487 | 15977472109111 | 15977473284798 | 15977473286024 |
| 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 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7fe9fb6cf380 | 0x7fe9f86257c0 | 0 | 0 | 0 | 0 | 0 | 0 | 10747904 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194594.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977473880131 | 15977473284798 | 15977474513765 | 15977474515317 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7fe9fb6cf200 | 0x7fe9f8625800 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194584.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 10747904 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977475109954 | 15977474513765 | 15977475757932 | 15977475759409 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7fe9fb6cf080 | 0x7fe9f8625840 | 0 | 0 | 10747904 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097361.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977476353686 | 15977475757429 | 15977476892954 | 15977476899224 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7fe9f902ff00 | 0x7fe9f8625880 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097339.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977477488061 | 15977476892954 | 15977478105440 | 15977478108067 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7fe9f902fd80 | 0x7fe9f86258c0 | 0 | 0 | 0 | 0 | 0 | 0 | 8912896 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097366.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977478711564 | 15977478105440 | 15977479252645 | 15977479254712 |
| 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 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7fe9f902fc00 | 0x7fe9f8625900 | 0 | 0 | 0 | 0 | 0 | 0 | 11796480 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194594.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977479847568 | 15977479252645 | 15977480470252 | 15977480472234 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7fe9f902fa80 | 0x7fe9f8625940 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194568.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 11796480 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977481066291 | 15977480470252 | 15977481703858 | 15977481706067 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7fe9f902f900 | 0x7fe9f8625980 | 0 | 0 | 11796480 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097351.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977482299634 | 15977481703858 | 15977482870904 | 15977482872941 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7fe9f902f780 | 0x7fe9f86259c0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097334.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977483466038 | 15977482870904 | 15977484096830 | 15977484099144 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7fe9f902f600 | 0x7fe9f8625a00 | 0 | 0 | 0 | 0 | 0 | 0 | 9699328 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097363.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977484700030 | 15977484096830 | 15977485260196 | 15977485262458 |
| 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 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7fe9fb6cf480 | 0x7fe9f8625a40 | 0 | 0 | 0 | 0 | 0 | 0 | 12845056 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194601.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977485856775 | 15977485260196 | 15977486498922 | 15977486501140 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7fe9fb6cf300 | 0x7fe9f8625a80 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194592.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 12845056 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977487095737 | 15977486498922 | 15977487755888 | 15977487758052 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7fe9fb6cf180 | 0x7fe9f8625ac0 | 0 | 0 | 12845056 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097345.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977488352529 | 15977487755888 | 15977488928694 | 15977488930776 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7fe9fb6cf000 | 0x7fe9f8625b00 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097335.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977489525843 | 15977488928694 | 15977490139900 | 15977490142069 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7fe9f902fe80 | 0x7fe9f8625b40 | 0 | 0 | 0 | 0 | 0 | 0 | 11272192 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097362.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977490743636 | 15977490139900 | 15977491325026 | 15977491327033 |
| 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 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7fe9f902fd00 | 0x7fe9f8625b80 | 0 | 0 | 0 | 0 | 0 | 0 | 14942208 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194637.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977491920510 | 15977491325026 | 15977492551113 | 15977492554875 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7fe9f902fb80 | 0x7fe9f8625bc0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194647.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 14942208 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977493145762 | 15977492551113 | 15977493788879 | 15977493790668 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7fe9f902fa00 | 0x7fe9f8625c00 | 0 | 0 | 14942208 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097334.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977494384045 | 15977493788879 | 15977494990165 | 15977494992041 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7fe9f902f880 | 0x7fe9f8625c40 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097329.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977495585898 | 15977494990165 | 15977496263131 | 15977496329282 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7fe9f902f700 | 0x7fe9f8625c80 | 0 | 0 | 0 | 0 | 0 | 0 | 12845056 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097356.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977496866220 | 15977496263131 | 15977497428097 | 15977497430037 |
| 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 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7fe9fb6cf580 | 0x7fe9f8625cc0 | 0 | 0 | 0 | 0 | 0 | 0 | 17039360 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194640.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977498023044 | 15977497428097 | 15977498673703 | 15977498677970 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7fe9fb6cf400 | 0x7fe9f8625d00 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194643.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 17039360 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977499269066 | 15977498673703 | 15977499933230 | 15977499936841 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7fe9fb6cf280 | 0x7fe9f8625d40 | 0 | 0 | 17039360 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097329.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977500529108 | 15977499933230 | 15977501128116 | 15977501130075 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7fe9fb6cf100 | 0x7fe9f8625d80 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097341.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977501723822 | 15977501128116 | 15977502437722 | 15977502504454 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7fe9f902ff80 | 0x7fe9f8625dc0 | 0 | 0 | 0 | 0 | 0 | 0 | 15990784 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097329.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977503042712 | 15977502437722 | 15977503618688 | 15977503620659 |
| 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 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7fe9f902fe00 | 0x7fe9f8625e00 | 0 | 0 | 0 | 0 | 0 | 0 | 21233664 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194644.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977504213976 | 15977503618688 | 15977504855815 | 15977504899671 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7fe9f902fc80 | 0x7fe9f8625e40 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194643.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 21233664 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977505450569 | 15977504855815 | 15977506099181 | 15977506166253 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7fe9f902fb00 | 0x7fe9f8625e80 | 0 | 0 | 21233664 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097325.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977506693451 | 15977506099181 | 15977507323027 | 15977507325407 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7fe9f902f980 | 0x7fe9f8625ec0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097346.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977507918694 | 15977507323027 | 15977508638554 | 15977508704496 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7fe9f902f800 | 0x7fe9f8625f00 | 0 | 0 | 0 | 0 | 0 | 0 | 19136512 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097329.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977509241824 | 15977508638554 | 15977509824000 | 15977509826181 |
| 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 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7fe9f902f680 | 0x7fe9f8625f40 | 0 | 0 | 0 | 0 | 0 | 0 | 25427968 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194627.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977510420418 | 15977509824000 | 15977511075846 | 15977511148152 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7fe9fb6cf500 | 0x7fe9f8625f80 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194629.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 25427968 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977511670200 | 15977511075846 | 15977512328172 | 15977512394254 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7fe9fb6cf380 | 0x7fe9f8625fc0 | 0 | 0 | 25427968 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097345.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977512923632 | 15977512328172 | 15977513573939 | 15977513640267 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7fe9fb6cf200 | 0x7fe9f8626000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097366.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977514169695 | 15977513573939 | 15977514943226 | 15977515008856 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7fe9fb6cf080 | 0x7fe9f8626040 | 0 | 0 | 0 | 0 | 0 | 0 | 22282240 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097334.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977515548164 | 15977514943226 | 15977516144352 | 15977516146271 |
| 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 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7fe9f902ff00 | 0x7fe9f8626080 | 0 | 0 | 0 | 0 | 0 | 0 | 29622272 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194617.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977516740028 | 15977516144352 | 15977517409638 | 15977517474232 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7fe9f902fd80 | 0x7fe9f86260c0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194599.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 29622272 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977518004700 | 15977517409638 | 15977518696685 | 15977518763173 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7fe9f902fc00 | 0x7fe9f8626100 | 0 | 0 | 29622272 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097345.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977519291641 | 15977518696685 | 15977519991891 | 15977520058204 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7fe9f902fa80 | 0x7fe9f8626140 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097375.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977520586702 | 15977519991891 | 15977521429018 | 15977521494712 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7fe9f902f900 | 0x7fe9f8626180 | 0 | 0 | 0 | 0 | 0 | 0 | 25427968 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097348.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977522031870 | 15977521429018 | 15977522659585 | 15977522726054 |
| 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 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7fe9f902f780 | 0x7fe9f86261c0 | 0 | 0 | 0 | 0 | 0 | 0 | 33816576 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194613.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977523254273 | 15977522659585 | 15977523960071 | 15977524026266 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7fe9f902f600 | 0x7fe9f8626200 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194575.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 33816576 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977524554984 | 15977523960071 | 15977525237998 | 15977525303477 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7fe9fb6cf480 | 0x7fe9f8626240 | 0 | 0 | 33816576 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097354.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977525833586 | 15977525237998 | 15977526534964 | 15977526602158 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7fe9fb6cf300 | 0x7fe9f8626280 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097314.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977527130637 | 15977526534964 | 15977528032732 | 15977528105055 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7fe9fb6cf180 | 0x7fe9f86262c0 | 0 | 0 | 0 | 0 | 0 | 0 | 31719424 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097352.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977528636313 | 15977528032732 | 15977529312578 | 15977529378256 |
| 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 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7fe9fb6cf000 | 0x7fe9f8626300 | 0 | 0 | 0 | 0 | 0 | 0 | 42205184 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194594.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977529910225 | 15977529312578 | 15977530666025 | 15977530732266 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7fe9f902fe80 | 0x7fe9f8626340 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194610.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 42205184 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977531262565 | 15977530666025 | 15977532022032 | 15977532067937 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7fe9f902fd00 | 0x7fe9f8626380 | 0 | 0 | 42205184 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097331.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977532617104 | 15977532022032 | 15977533372759 | 15977533436906 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7fe9f902fb80 | 0x7fe9f86263c0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097324.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977533967825 | 15977533372759 | 15977534994047 | 15977535060990 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7fe9f902fa00 | 0x7fe9f8626400 | 0 | 0 | 0 | 0 | 0 | 0 | 38010880 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097356.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977535597838 | 15977534994047 | 15977536307974 | 15977536379701 |
| 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 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7fe9f902f880 | 0x7fe9f8626440 | 0 | 0 | 0 | 0 | 0 | 0 | 50593792 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194619.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977536903049 | 15977536307974 | 15977537704141 | 15977537770370 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7fe9f902f700 | 0x7fe9f8626480 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194619.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 50593792 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977538299648 | 15977537704141 | 15977539092628 | 15977539155559 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7fe9fb6cf580 | 0x7fe9f86264c0 | 0 | 0 | 50593792 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097328.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977539688437 | 15977539092506 | 15977540496832 | 15977540561218 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7fe9fb6cf400 | 0x7fe9f8626500 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097331.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977541092326 | 15977540496832 | 15977542187080 | 15977542253980 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7fe9fb6cf280 | 0x7fe9f8626540 | 0 | 0 | 0 | 0 | 0 | 0 | 67371008 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097324.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977542790868 | 15977542187080 | 15977543673167 | 15977543739967 |
| 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 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7fe9fb6cf100 | 0x7fe9f8626580 | 0 | 0 | 0 | 0 | 0 | 0 | 67371008 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194564.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977544268995 | 15977543673167 | 15977545190295 | 15977545256874 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7fe9f902ff80 | 0x7fe9f86265c0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194548.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 67371008 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977545786492 | 15977545190295 | 15977546717982 | 15977546785370 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7fe9f902fe00 | 0x7fe9f8626600 | 0 | 0 | 67371008 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097335.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977547313178 | 15977546717982 | 15977548218949 | 15977548285356 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7fe9f902fc80 | 0x7fe9f8626640 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097316.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977548813464 | 15977548218949 | 15977550145999 | 15977550213633 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7fe9f902fb00 | 0x7fe9f8626680 | 0 | 0 | 0 | 0 | 0 | 0 | 134479872 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097322.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977550750281 | 15977550145999 | 15977552067608 | 15977552134290 |
| 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 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7fe9f902f980 | 0x7fe9f86266c0 | 0 | 0 | 0 | 0 | 0 | 0 | 134479872 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194548.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977552663149 | 15977552067608 | 15977554004257 | 15977554070387 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7fe9f902f800 | 0x7fe9f8626700 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194547.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 134479872 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977554599686 | 15977554004257 | 15977555953067 | 15977556020154 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7fe9f902f680 | 0x7fe9f8626740 | 0 | 0 | 134479872 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097326.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977556548413 | 15977555953067 | 15977557840916 | 15977557908232 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7fe9fb6cf500 | 0x7fe9f8626780 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097314.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977558436541 | 15977557840916 | 15977560576769 | 15977560644871 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7fe9fb6cf380 | 0x7fe9f86267c0 | 0 | 0 | 0 | 0 | 0 | 0 | 268697600 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097321.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977561186929 | 15977560576769 | 15977563304303 | 15977563371611 |
| 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 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7fe9fb6cf200 | 0x7fe9f8626800 | 0 | 0 | 0 | 0 | 0 | 0 | 268697600 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194547.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977563901489 | 15977563304303 | 15977566061116 | 15977566132759 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7fe9fb6cf080 | 0x7fe9f8626840 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194547.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 268697600 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977566658528 | 15977566061116 | 15977568836169 | 15977568904217 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7fe9f902ff00 | 0x7fe9f8626880 | 0 | 0 | 268697600 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097323.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977569431656 | 15977568836169 | 15977571576343 | 15977571650706 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 141956 | 141956 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7fe9f902fd80 | 0x7fe9f86268c0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097315.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 15977572171955 | 15977571576343 | 15977575984524 | 15977576055578 |