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 | 174459 | 174459 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7ff75ae04280 | 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 | 16783573042989 | 16754148541192 | 16783724669610 | 16783724755920 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 174459 | 174459 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7ff75ae23f80 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 8192.0000000000 | 16384.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 8261.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783730483369 | 16783724669610 | 16783730847392 | 16783730853797 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7ff75dd33380 | 0x7ff75ae23fc0 | 0 | 0 | 0 | 0 | 0 | 0 | 262144 | 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 | 16783731445389 | 16783730847392 | 16783732090117 | 16783732090038 |
| 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 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7ff75dd33200 | 0x7ff75ae24000 | 0 | 0 | 0 | 0 | 0 | 0 | 262144 | 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 | 16783732688510 | 16783732090117 | 16783733414122 | 16783733413417 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7ff75dd33080 | 0x7ff75ae24040 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194593.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783734008268 | 16783733414122 | 16783734648366 | 16783734647098 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7ff75b703f00 | 0x7ff75ae24080 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 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 | 16783735242269 | 16783734648366 | 16783735803251 | 16783735802581 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7ff75b703d80 | 0x7ff75ae240c0 | 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 | 16783736395552 | 16783735803251 | 16783736976855 | 16783736976124 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7ff75b703c00 | 0x7ff75ae24100 | 0 | 0 | 0 | 0 | 0 | 0 | 655360 | 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 | 16783737582405 | 16783736976855 | 16783738168219 | 16783738168006 |
| 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 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7ff75b703a80 | 0x7ff75ae24140 | 0 | 0 | 0 | 0 | 0 | 0 | 786432 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194581.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783738762947 | 16783738168219 | 16783739432544 | 16783739431606 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7ff75b703900 | 0x7ff75ae24180 | 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 | 786432 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783740026258 | 16783739432544 | 16783740682789 | 16783740681437 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7ff75b703780 | 0x7ff75ae241c0 | 0 | 0 | 786432 | 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 | 16783741276838 | 16783740682789 | 16783741818953 | 16783741817151 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7ff75b703600 | 0x7ff75ae24200 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 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 | 16783742412302 | 16783741818953 | 16783742953197 | 16783742951785 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7ff75dd33480 | 0x7ff75ae24240 | 0 | 0 | 0 | 0 | 0 | 0 | 1048576 | 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 | 16783743554646 | 16783742953197 | 16783744111442 | 16783744109469 |
| 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 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7ff75dd33300 | 0x7ff75ae24280 | 0 | 0 | 0 | 0 | 0 | 0 | 1310720 | 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 | 16783744704680 | 16783744111442 | 16783745332086 | 16783745330600 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7ff75dd33180 | 0x7ff75ae242c0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194595.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 1310720 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783745924682 | 16783745332086 | 16783746607771 | 16783746605850 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7ff75dd33000 | 0x7ff75ae24300 | 0 | 0 | 1310720 | 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 | 16783747201551 | 16783746607771 | 16783747777535 | 16783747775543 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7ff75b703e80 | 0x7ff75ae24340 | 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 | 16783748370165 | 16783747777535 | 16783749000100 | 16783748998105 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7ff75b703d00 | 0x7ff75ae24380 | 0 | 0 | 0 | 0 | 0 | 0 | 1441792 | 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 | 16783749600396 | 16783749000100 | 16783750126824 | 16783750125069 |
| 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 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7ff75b703b80 | 0x7ff75ae243c0 | 0 | 0 | 0 | 0 | 0 | 0 | 1835008 | 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 | 16783750721020 | 16783750126824 | 16783751367948 | 16783751366500 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7ff75b703a00 | 0x7ff75ae24400 | 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 | 1835008 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783751961821 | 16783751367948 | 16783752593233 | 16783752591871 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7ff75b703880 | 0x7ff75ae24440 | 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 | 16783753184742 | 16783752593233 | 16783753744597 | 16783753743365 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7ff75b703700 | 0x7ff75ae24480 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 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 | 16783754337776 | 16783753744597 | 16783754896762 | 16783754895388 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7ff75dd33580 | 0x7ff75ae244c0 | 0 | 0 | 0 | 0 | 0 | 0 | 1835008 | 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 | 16783755497119 | 16783754896762 | 16783756054206 | 16783756052782 |
| 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 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7ff75dd33400 | 0x7ff75ae24500 | 0 | 0 | 0 | 0 | 0 | 0 | 2359296 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194579.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783756647213 | 16783756054206 | 16783757299491 | 16783757298443 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7ff75dd33280 | 0x7ff75ae24540 | 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 | 2359296 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783757892154 | 16783757299491 | 16783758520455 | 16783758519134 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7ff75dd33100 | 0x7ff75ae24580 | 0 | 0 | 2359296 | 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 | 16783759113075 | 16783758520455 | 16783759666539 | 16783759665048 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7ff75b703f80 | 0x7ff75ae245c0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097347.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783760259549 | 16783759666539 | 16783760819184 | 16783760817682 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7ff75b703e00 | 0x7ff75ae24600 | 0 | 0 | 0 | 0 | 0 | 0 | 2228224 | 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 | 16783761419663 | 16783760819184 | 16783761974708 | 16783761973275 |
| 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 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7ff75b703c80 | 0x7ff75ae24640 | 0 | 0 | 0 | 0 | 0 | 0 | 2883584 | 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 | 16783762568046 | 16783761974708 | 16783763236473 | 16783763235045 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7ff75b703b00 | 0x7ff75ae24680 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194591.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 2883584 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783763828666 | 16783763236473 | 16783764479997 | 16783764478526 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7ff75b703980 | 0x7ff75ae246c0 | 0 | 0 | 2883584 | 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 | 16783765071947 | 16783764479997 | 16783765633282 | 16783765631629 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7ff75b703800 | 0x7ff75ae24700 | 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 | 16783766226300 | 16783765633282 | 16783766788806 | 16783766787233 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7ff75b703680 | 0x7ff75ae24740 | 0 | 0 | 0 | 0 | 0 | 0 | 2621440 | 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 | 16783767388484 | 16783766788806 | 16783767955690 | 16783767954186 |
| 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 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7ff75dd33500 | 0x7ff75ae24780 | 0 | 0 | 0 | 0 | 0 | 0 | 3407872 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194583.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783768548587 | 16783767955690 | 16783769193775 | 16783769192517 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7ff75dd33380 | 0x7ff75ae247c0 | 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 | 3407872 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783769785598 | 16783769193775 | 16783770440179 | 16783770438798 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7ff75dd33200 | 0x7ff75ae24800 | 0 | 0 | 3407872 | 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 | 16783771033179 | 16783770440179 | 16783771615704 | 16783771614051 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7ff75dd33080 | 0x7ff75ae24840 | 0 | 0 | 0 | 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 | 16783772209592 | 16783771615704 | 16783772780188 | 16783772778814 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7ff75b703f00 | 0x7ff75ae24880 | 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 | 16783773380585 | 16783772780188 | 16783773946752 | 16783773945217 |
| 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 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7ff75b703d80 | 0x7ff75ae248c0 | 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 | 16783774539648 | 16783773946752 | 16783775183077 | 16783775181798 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7ff75b703c00 | 0x7ff75ae24900 | 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 | 3932160 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783775775350 | 16783775183077 | 16783776421642 | 16783776420099 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7ff75b703a80 | 0x7ff75ae24940 | 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 | 16783777013880 | 16783776421642 | 16783777568046 | 16783777566413 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7ff75b703900 | 0x7ff75ae24980 | 0 | 0 | 0 | 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 | 16783778160714 | 16783777568046 | 16783778733650 | 16783778732116 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7ff75b703780 | 0x7ff75ae249c0 | 0 | 0 | 0 | 0 | 0 | 0 | 3407872 | 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 | 16783779333567 | 16783778733650 | 16783779879895 | 16783779878190 |
| 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 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7ff75b703600 | 0x7ff75ae24a00 | 0 | 0 | 0 | 0 | 0 | 0 | 4456448 | 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 | 16783780472471 | 16783779879895 | 16783781113179 | 16783781111471 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7ff75dd33480 | 0x7ff75ae24a40 | 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 | 4456448 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783781706262 | 16783781113179 | 16783782364704 | 16783783617402 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7ff75dd33300 | 0x7ff75ae24a80 | 0 | 0 | 4456448 | 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 | 16783783636851 | 16783782364704 | 16783784344231 | 16783784342159 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7ff75dd33180 | 0x7ff75ae24ac0 | 0 | 0 | 0 | 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 | 16783784936950 | 16783784344231 | 16783785455115 | 16783785453554 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7ff75dd33000 | 0x7ff75ae24b00 | 0 | 0 | 0 | 0 | 0 | 0 | 3801088 | 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 | 16783786055585 | 16783785455115 | 16783786593680 | 16783786591678 |
| 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 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7ff75b703e80 | 0x7ff75ae24b40 | 0 | 0 | 0 | 0 | 0 | 0 | 4980736 | 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 | 16783787185599 | 16783786590005 | 16783787802961 | 16783787808490 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7ff75b703d00 | 0x7ff75ae24b80 | 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 | 4980736 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783788398271 | 16783787802961 | 16783789018635 | 16783789020191 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7ff75b703b80 | 0x7ff75ae24bc0 | 0 | 0 | 4980736 | 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 | 16783789613623 | 16783789018635 | 16783790137032 | 16783790138936 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7ff75b703a00 | 0x7ff75ae24c00 | 0 | 0 | 0 | 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 | 16783790733687 | 16783790137032 | 16783791277188 | 16783791279120 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7ff75b703880 | 0x7ff75ae24c40 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 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 | 16783791880481 | 16783791277188 | 16783792413024 | 16783792414924 |
| 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 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7ff75b703700 | 0x7ff75ae24c80 | 0 | 0 | 0 | 0 | 0 | 0 | 5505024 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194561.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783793008976 | 16783792413024 | 16783793636540 | 16783793638606 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7ff75dd33580 | 0x7ff75ae24cc0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194561.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 5505024 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783794233687 | 16783793636540 | 16783794893975 | 16783794896046 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7ff75dd33400 | 0x7ff75ae24d00 | 0 | 0 | 5505024 | 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 | 16783795489367 | 16783794893975 | 16783796040052 | 16783796042240 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7ff75dd33280 | 0x7ff75ae24d40 | 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 | 16783796636851 | 16783796040052 | 16783797207248 | 16783797209233 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7ff75dd33100 | 0x7ff75ae24d80 | 0 | 0 | 0 | 0 | 0 | 0 | 4587520 | 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 | 16783797812154 | 16783797207248 | 16783798396844 | 16783798399005 |
| 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 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7ff75b703f80 | 0x7ff75ae24dc0 | 0 | 0 | 0 | 0 | 0 | 0 | 6029312 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194570.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783798994336 | 16783798396844 | 16783799630919 | 16783799633086 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7ff75b703e00 | 0x7ff75ae24e00 | 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 | 6029312 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783800226647 | 16783799630919 | 16783800876035 | 16783800878297 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7ff75b703c80 | 0x7ff75ae24e40 | 0 | 0 | 6029312 | 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 | 16783801472508 | 16783800876035 | 16783802021951 | 16783802023881 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7ff75b703b00 | 0x7ff75ae24e80 | 0 | 0 | 0 | 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 | 16783802619032 | 16783802021951 | 16783803196987 | 16783803199044 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7ff75b703980 | 0x7ff75ae24ec0 | 0 | 0 | 0 | 0 | 0 | 0 | 4980736 | 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 | 16783803813864 | 16783803196987 | 16783804392023 | 16783804394386 |
| 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 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7ff75b703800 | 0x7ff75ae24f00 | 0 | 0 | 0 | 0 | 0 | 0 | 6553600 | 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 | 16783804989177 | 16783804392023 | 16783805623379 | 16783805625517 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7ff75b703680 | 0x7ff75ae24f40 | 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 | 6553600 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783806220689 | 16783805623379 | 16783806872655 | 16783806874608 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7ff75dd33500 | 0x7ff75ae24f80 | 0 | 0 | 6553600 | 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 | 16783807468499 | 16783806872655 | 16783808028171 | 16783808030221 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7ff75dd33380 | 0x7ff75ae24fc0 | 0 | 0 | 0 | 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 | 16783808624642 | 16783808028171 | 16783809190247 | 16783809192294 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7ff75dd33200 | 0x7ff75ae25000 | 0 | 0 | 0 | 0 | 0 | 0 | 5373952 | 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 | 16783809794655 | 16783809190247 | 16783810353123 | 16783810355738 |
| 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 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7ff75dd33080 | 0x7ff75ae25040 | 0 | 0 | 0 | 0 | 0 | 0 | 7077888 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194568.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783810950719 | 16783810353123 | 16783811607359 | 16783811609428 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7ff75b703f00 | 0x7ff75ae25080 | 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 | 7077888 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783812203659 | 16783811607359 | 16783812853114 | 16783812855139 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7ff75b703d80 | 0x7ff75ae250c0 | 0 | 0 | 7077888 | 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 | 16783813449760 | 16783812853114 | 16783813991511 | 16783813993333 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7ff75b703c00 | 0x7ff75ae25100 | 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 | 16783814588604 | 16783813991511 | 16783815172627 | 16783815174546 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7ff75b703a80 | 0x7ff75ae25140 | 0 | 0 | 0 | 0 | 0 | 0 | 5767168 | 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 | 16783815776157 | 16783815172627 | 16783816341103 | 16783816343049 |
| 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 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7ff75b703900 | 0x7ff75ae25180 | 0 | 0 | 0 | 0 | 0 | 0 | 7602176 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194579.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783816936800 | 16783816341103 | 16783817577738 | 16783817579960 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7ff75b703780 | 0x7ff75ae251c0 | 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 | 7602176 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783818174011 | 16783817577738 | 16783818790214 | 16783818792282 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7ff75b703600 | 0x7ff75ae25200 | 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 | 16783819385993 | 16783818790214 | 16783819955810 | 16783819957835 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7ff75dd33480 | 0x7ff75ae25240 | 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 | 16783820552326 | 16783819955810 | 16783821117566 | 16783821119458 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7ff75dd33300 | 0x7ff75ae25280 | 0 | 0 | 0 | 0 | 0 | 0 | 6160384 | 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 | 16783821722219 | 16783821117566 | 16783822291962 | 16783822294901 |
| 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 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7ff75dd33180 | 0x7ff75ae252c0 | 0 | 0 | 0 | 0 | 0 | 0 | 8126464 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194575.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783822889022 | 16783822291962 | 16783823520598 | 16783823522672 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7ff75dd33000 | 0x7ff75ae25300 | 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 | 8126464 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783824117213 | 16783823520598 | 16783824763154 | 16783824765333 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7ff75b703e80 | 0x7ff75ae25340 | 0 | 0 | 8126464 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097364.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783825359434 | 16783824763154 | 16783825926990 | 16783825929246 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7ff75b703d00 | 0x7ff75ae25380 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 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 | 16783826523767 | 16783825926990 | 16783827109866 | 16783827112069 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7ff75b703b80 | 0x7ff75ae253c0 | 0 | 0 | 0 | 0 | 0 | 0 | 6553600 | 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 | 16783827712800 | 16783827109866 | 16783828273862 | 16783828275912 |
| 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 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7ff75b703a00 | 0x7ff75ae25400 | 0 | 0 | 0 | 0 | 0 | 0 | 8650752 | 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 | 16783828869883 | 16783828273862 | 16783829515778 | 16783829517723 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7ff75b703880 | 0x7ff75ae25440 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194580.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 8650752 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783830112064 | 16783829515778 | 16783830754974 | 16783830757234 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7ff75b703700 | 0x7ff75ae25480 | 0 | 0 | 8650752 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097364.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783831351265 | 16783830754974 | 16783831912090 | 16783831914197 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7ff75dd33580 | 0x7ff75ae254c0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 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 | 16783832507959 | 16783831912090 | 16783833074326 | 16783833076281 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7ff75dd33400 | 0x7ff75ae25500 | 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 | 16783833677252 | 16783833074326 | 16783834239922 | 16783834242234 |
| 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 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7ff75dd33280 | 0x7ff75ae25540 | 0 | 0 | 0 | 0 | 0 | 0 | 9175040 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194563.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783834836395 | 16783834239922 | 16783835480878 | 16783835482975 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7ff75dd33100 | 0x7ff75ae25580 | 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 | 9175040 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783836077546 | 16783835480878 | 16783836709994 | 16783836711816 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7ff75b703f80 | 0x7ff75ae255c0 | 0 | 0 | 9175040 | 0 | 0 | 0 | 0 | 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 | 16783837306147 | 16783836709994 | 16783837878470 | 16783837880469 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7ff75b703e00 | 0x7ff75ae25600 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 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 | 16783838474970 | 16783837878470 | 16783839059746 | 16783839061972 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7ff75b703c80 | 0x7ff75ae25640 | 0 | 0 | 0 | 0 | 0 | 0 | 7340032 | 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 | 16783839663273 | 16783839059746 | 16783840217502 | 16783840219745 |
| 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 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7ff75b703b00 | 0x7ff75ae25680 | 0 | 0 | 0 | 0 | 0 | 0 | 9699328 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194575.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783840814056 | 16783840217502 | 16783841451737 | 16783841453996 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7ff75b703980 | 0x7ff75ae256c0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194591.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 9699328 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783842047067 | 16783841451737 | 16783842683093 | 16783842684927 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7ff75b703800 | 0x7ff75ae25700 | 0 | 0 | 9699328 | 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 | 16783843278758 | 16783842683093 | 16783843872689 | 16783843874710 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7ff75b703680 | 0x7ff75ae25740 | 0 | 0 | 0 | 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 | 16783844469881 | 16783843872689 | 16783845079885 | 16783845081852 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7ff75dd33500 | 0x7ff75ae25780 | 0 | 0 | 0 | 0 | 0 | 0 | 8126464 | 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 | 16783845683653 | 16783845079885 | 16783846229641 | 16783846232295 |
| 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 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7ff75dd33380 | 0x7ff75ae257c0 | 0 | 0 | 0 | 0 | 0 | 0 | 10747904 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194598.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783846825067 | 16783846229641 | 16783847471877 | 16783847473956 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7ff75dd33200 | 0x7ff75ae25800 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194597.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 10747904 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783848068187 | 16783847471877 | 16783848740193 | 16783848742266 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7ff75dd33080 | 0x7ff75ae25840 | 0 | 0 | 10747904 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097364.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783849336898 | 16783848740193 | 16783849904349 | 16783849906330 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7ff75b703f00 | 0x7ff75ae25880 | 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 | 16783850501571 | 16783849904185 | 16783851100019 | 16783851102072 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7ff75b703d80 | 0x7ff75ae258c0 | 0 | 0 | 0 | 0 | 0 | 0 | 8912896 | 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 | 16783851703743 | 16783851100019 | 16783852238095 | 16783852240166 |
| 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 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7ff75b703c00 | 0x7ff75ae25900 | 0 | 0 | 0 | 0 | 0 | 0 | 11796480 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194603.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783852833487 | 16783852238095 | 16783853468331 | 16783853470377 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7ff75b703a80 | 0x7ff75ae25940 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194590.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 11796480 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783854064248 | 16783853468331 | 16783854705606 | 16783854707758 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7ff75b703900 | 0x7ff75ae25980 | 0 | 0 | 11796480 | 0 | 0 | 0 | 0 | 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 | 16783855301509 | 16783854705606 | 16783855820962 | 16783855822722 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7ff75b703780 | 0x7ff75ae259c0 | 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 | 16783856416494 | 16783855820962 | 16783857017598 | 16783857019465 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7ff75b703600 | 0x7ff75ae25a00 | 0 | 0 | 0 | 0 | 0 | 0 | 9699328 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097369.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783857621516 | 16783857017598 | 16783858162553 | 16783858164759 |
| 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 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7ff75dd33480 | 0x7ff75ae25a40 | 0 | 0 | 0 | 0 | 0 | 0 | 12845056 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194621.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783858759290 | 16783858162553 | 16783859378229 | 16783859380550 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7ff75dd33300 | 0x7ff75ae25a80 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194595.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 12845056 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783859974362 | 16783859378229 | 16783860622544 | 16783860624861 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7ff75dd33180 | 0x7ff75ae25ac0 | 0 | 0 | 12845056 | 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 | 16783861219662 | 16783860622544 | 16783861784620 | 16783861786604 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7ff75dd33000 | 0x7ff75ae25b00 | 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 | 16783862381586 | 16783861784620 | 16783863031016 | 16783863033255 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7ff75b703e80 | 0x7ff75ae25b40 | 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 | 16783863634516 | 16783863031016 | 16783864206051 | 16783864208598 |
| 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 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7ff75b703d00 | 0x7ff75ae25b80 | 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 | 16783864802039 | 16783864206051 | 16783865449727 | 16783865453219 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7ff75b703b80 | 0x7ff75ae25bc0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194630.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 14942208 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783866045520 | 16783865449727 | 16783866717402 | 16783866720129 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7ff75b703a00 | 0x7ff75ae25c00 | 0 | 0 | 14942208 | 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 | 16783867313720 | 16783866717402 | 16783867903158 | 16783867905401 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7ff75b703880 | 0x7ff75ae25c40 | 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 | 16783868499302 | 16783867903158 | 16783869136753 | 16783869201640 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7ff75b703700 | 0x7ff75ae25c80 | 0 | 0 | 0 | 0 | 0 | 0 | 12845056 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097347.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783869740833 | 16783869136753 | 16783870313869 | 16783870316225 |
| 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 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7ff75dd33580 | 0x7ff75ae25cc0 | 0 | 0 | 0 | 0 | 0 | 0 | 17039360 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194632.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783870911016 | 16783870313869 | 16783871551784 | 16783871557256 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7ff75dd33400 | 0x7ff75ae25d00 | 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 | 17039360 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783872147707 | 16783871551784 | 16783872800100 | 16783872804216 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7ff75dd33280 | 0x7ff75ae25d40 | 0 | 0 | 17039360 | 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 | 16783873396698 | 16783872800100 | 16783873997535 | 16783873999799 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7ff75dd33100 | 0x7ff75ae25d80 | 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 | 16783874595530 | 16783873997535 | 16783875314490 | 16783875380445 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7ff75b703f80 | 0x7ff75ae25dc0 | 0 | 0 | 0 | 0 | 0 | 0 | 15990784 | 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 | 16783875919288 | 16783875314490 | 16783876512566 | 16783876514930 |
| 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 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7ff75b703e00 | 0x7ff75ae25e00 | 0 | 0 | 0 | 0 | 0 | 0 | 21233664 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194643.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783877108581 | 16783876512566 | 16783877773201 | 16783877838848 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7ff75b703c80 | 0x7ff75ae25e40 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194633.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 21233664 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783878369711 | 16783877773201 | 16783879028877 | 16783879094388 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7ff75b703b00 | 0x7ff75ae25e80 | 0 | 0 | 21233664 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097337.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783879624861 | 16783879028877 | 16783880257512 | 16783880259871 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7ff75b703980 | 0x7ff75ae25ec0 | 0 | 0 | 0 | 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 | 16783880853622 | 16783880257512 | 16783881646787 | 16783881712705 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7ff75b703800 | 0x7ff75ae25f00 | 0 | 0 | 0 | 0 | 0 | 0 | 19136512 | 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 | 16783882252908 | 16783881646787 | 16783882865983 | 16783882868529 |
| 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 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7ff75b703680 | 0x7ff75ae25f40 | 0 | 0 | 0 | 0 | 0 | 0 | 25427968 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194643.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783883462330 | 16783882865983 | 16783884128378 | 16783884194237 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7ff75dd33500 | 0x7ff75ae25f80 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194607.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 25427968 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783884724800 | 16783884128378 | 16783885386453 | 16783885452307 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7ff75dd33380 | 0x7ff75ae25fc0 | 0 | 0 | 25427968 | 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 | 16783885981680 | 16783885386453 | 16783886652849 | 16783886718597 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7ff75dd33200 | 0x7ff75ae26000 | 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 | 16783887250830 | 16783886652849 | 16783888054124 | 16783888121213 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7ff75dd33080 | 0x7ff75ae26040 | 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 | 16783888659566 | 16783888054124 | 16783889284999 | 16783889287276 |
| 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 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7ff75b703f00 | 0x7ff75ae26080 | 0 | 0 | 0 | 0 | 0 | 0 | 29622272 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194610.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783889881208 | 16783889284999 | 16783890592354 | 16783890658263 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7ff75b703d80 | 0x7ff75ae260c0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194600.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 29622272 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783891189366 | 16783890592354 | 16783891899549 | 16783891965392 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7ff75b703c00 | 0x7ff75ae26100 | 0 | 0 | 29622272 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097369.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783892495705 | 16783891899549 | 16783893155065 | 16783893221122 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7ff75b703a80 | 0x7ff75ae26140 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097376.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783893751296 | 16783893155065 | 16783894590579 | 16783894656777 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7ff75b703900 | 0x7ff75ae26180 | 0 | 0 | 0 | 0 | 0 | 0 | 25427968 | 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 | 16783895195410 | 16783894590579 | 16783895849295 | 16783895851099 |
| 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 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7ff75b703780 | 0x7ff75ae261c0 | 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 | 16783896446050 | 16783895849295 | 16783897179850 | 16783897245685 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7ff75b703600 | 0x7ff75ae26200 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194593.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 33816576 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783897776268 | 16783897179850 | 16783898505605 | 16783898571593 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7ff75dd33480 | 0x7ff75ae26240 | 0 | 0 | 33816576 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097379.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783899102576 | 16783898505605 | 16783900021919 | 16783900088245 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7ff75dd33300 | 0x7ff75ae26280 | 0 | 0 | 0 | 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 | 16783900634378 | 16783900021919 | 16783902134232 | 16783902202479 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7ff75dd33180 | 0x7ff75ae262c0 | 0 | 0 | 0 | 0 | 0 | 0 | 31719424 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097353.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783902769041 | 16783902134232 | 16783903994065 | 16783904058490 |
| 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 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7ff75dd33000 | 0x7ff75ae26300 | 0 | 0 | 0 | 0 | 0 | 0 | 42205184 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194600.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783904607053 | 16783903994065 | 16783905931178 | 16783905995679 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7ff75b703e80 | 0x7ff75ae26340 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194609.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 42205184 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783906542422 | 16783905931178 | 16783907845731 | 16783907911999 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7ff75b703d00 | 0x7ff75ae26380 | 0 | 0 | 42205184 | 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 | 16783908457011 | 16783907845731 | 16783909643484 | 16783909709122 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7ff75b703b80 | 0x7ff75ae263c0 | 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 | 16783910243605 | 16783909643484 | 16783911256758 | 16783911322411 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7ff75b703a00 | 0x7ff75ae26400 | 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 | 16783911861074 | 16783911256758 | 16783912598513 | 16783912663608 |
| 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 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7ff75b703880 | 0x7ff75ae26440 | 0 | 0 | 0 | 0 | 0 | 0 | 50593792 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194615.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783913195352 | 16783912599947 | 16783913985705 | 16783914055704 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7ff75b703700 | 0x7ff75ae26480 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194617.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 50593792 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783914580758 | 16783913985705 | 16783915383942 | 16783915449260 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7ff75dd33580 | 0x7ff75ae264c0 | 0 | 0 | 50593792 | 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 | 16783915978804 | 16783915383942 | 16783916792260 | 16783916858706 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7ff75dd33400 | 0x7ff75ae26500 | 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 | 16783917388179 | 16783916792260 | 16783918507297 | 16783918572552 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7ff75dd33280 | 0x7ff75ae26540 | 0 | 0 | 0 | 0 | 0 | 0 | 67371008 | 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 | 16783919112675 | 16783918507297 | 16783920031455 | 16783920096174 |
| 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 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7ff75dd33100 | 0x7ff75ae26580 | 0 | 0 | 0 | 0 | 0 | 0 | 67371008 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194558.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783920626607 | 16783920031455 | 16783921553533 | 16783921616026 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7ff75b703f80 | 0x7ff75ae265c0 | 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 | 67371008 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783922149719 | 16783921553533 | 16783923065370 | 16783923130188 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7ff75b703e00 | 0x7ff75ae26600 | 0 | 0 | 67371008 | 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 | 16783923659791 | 16783923065370 | 16783924542648 | 16783924606721 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7ff75b703c80 | 0x7ff75ae26640 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097317.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783925136644 | 16783924542648 | 16783926461526 | 16783926529590 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7ff75b703b00 | 0x7ff75ae26680 | 0 | 0 | 0 | 0 | 0 | 0 | 134479872 | 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 | 16783927064924 | 16783926461526 | 16783928348883 | 16783928412051 |
| 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 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7ff75b703980 | 0x7ff75ae266c0 | 0 | 0 | 0 | 0 | 0 | 0 | 134479872 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194545.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783928943134 | 16783928348883 | 16783930291760 | 16783930356440 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7ff75b703800 | 0x7ff75ae26700 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194546.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 134479872 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783930887493 | 16783930291760 | 16783932221037 | 16783932286369 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7ff75b703680 | 0x7ff75ae26740 | 0 | 0 | 134479872 | 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 | 16783932815462 | 16783932221037 | 16783934111274 | 16783934176879 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7ff75dd33500 | 0x7ff75ae26780 | 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 | 16783934706173 | 16783934111274 | 16783936850310 | 16783936913753 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7ff75dd33380 | 0x7ff75ae267c0 | 0 | 0 | 0 | 0 | 0 | 0 | 268697600 | 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 | 16783937460266 | 16783936850310 | 16783939595266 | 16783939659896 |
| 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 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7ff75dd33200 | 0x7ff75ae26800 | 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 | 16783940191279 | 16783939595266 | 16783942358462 | 16783942426789 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7ff75dd33080 | 0x7ff75ae26840 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304.0000000000 | 8388608.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 4194543.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 268697600 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783942953192 | 16783942358462 | 16783945138618 | 16783945203361 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7ff75b703f00 | 0x7ff75ae26880 | 0 | 0 | 268697600 | 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 | 16783945733834 | 16783945138618 | 16783947883094 | 16783947951435 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 174459 | 174459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7ff75b703d80 | 0x7ff75ae268c0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152.0000000000 | 2097152.0000000000 | 0.0000000000 | 0.0000000000 | 0.0000000000 | 2097313.0000000000 | 0.0000000000 | 0.0000000000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0000000000 | 0 | 0 | 16783948477998 | 16783947883094 | 16783952292848 | 16783952363745 |