50 KiB
50 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | GRBM_COUNT | GRBM_GUI_ACTIVE | CPC_ME1_BUSY_FOR_PACKET_DECODE | SQ_CYCLES | SQ_WAVES | SQ_WAVE_CYCLES | SQ_BUSY_CYCLES | SQ_LEVEL_WAVES | SQ_ACCUM_PREV_HIRES | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBuffer.kd | 0 | 0 | 0 | 896508 | 896513 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7fce1aa04180 | 502309 | 502309 | 16285 | 4018480 | 524288 | 366559346 | 3822785 | 0 | 1481022520 | 12075849713232663 | 12075849959550332 | 12075849959873691 | 12075849959985773 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 896508 | 896513 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7fce1aa35100 | 27422 | 27422 | 20382 | 219384 | 512 | 1165855 | 78921 | 0 | 4677784 | 12075849974536505 | 12075849974861105 | 12075849974867505 | 12075849974874844 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7fcf4aae6900 | 0x7fce1aa35140 | 219277 | 219277 | 19662 | 1754224 | 65536 | 133685285 | 1589660 | 0 | 536552300 | 12075849974944253 | 12075849975195344 | 12075849975329423 | 12075849975332574 |
| 5 | 3 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 6 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7fcf4aae6800 | 0x7fce1aa35180 | 392741 | 392741 | 23835 | 3141936 | 65536 | 226165974 | 2969768 | 0 | 906481096 | 12075849975410399 | 12075849975601902 | 12075849975851981 | 12075849975921800 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7fcf4aae6700 | 0x7fce1aa351c0 | 386612 | 386612 | 31383 | 3092904 | 65536 | 351236304 | 2927364 | 0 | 1406762128 | 12075849975955642 | 12075849976173260 | 12075849976419019 | 12075849976489224 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7fcf4aae6600 | 0x7fce1aa35200 | 215917 | 215917 | 20055 | 1727344 | 65536 | 131214594 | 1565980 | 0 | 526674012 | 12075849976515353 | 12075849976729417 | 12075849976861417 | 12075849976863860 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7fcf4aae6500 | 0x7fce1aa35240 | 215077 | 215077 | 21826 | 1720624 | 65536 | 148982019 | 1556052 | 0 | 597745028 | 12075849976924333 | 12075849977124616 | 12075849977255975 | 12075849977258434 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7fcf4aae6400 | 0x7fce1aa35280 | 219773 | 219773 | 19498 | 1758192 | 65536 | 149621700 | 1578084 | 0 | 600303548 | 12075849977344594 | 12075849977531334 | 12075849977665573 | 12075849977668606 |
| 10 | 8 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 16 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7fcf4aae6300 | 0x7fce1aa352c0 | 394732 | 394732 | 33423 | 3157864 | 65536 | 354840335 | 2991466 | 0 | 1421177992 | 12075849977727595 | 12075849977932612 | 12075849978184451 | 12075849978227324 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7fcf4aae6a00 | 0x7fce1aa35300 | 404252 | 404252 | 28605 | 3234024 | 65536 | 312171930 | 3063544 | 0 | 1250506032 | 12075849978259785 | 12075849978462690 | 12075849978719969 | 12075849978762389 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7fcf4aae6900 | 0x7fce1aa35340 | 210549 | 210549 | 20111 | 1684400 | 65536 | 166593615 | 1519950 | 0 | 668191072 | 12075849978794328 | 12075849978995648 | 12075849979124447 | 12075849979127397 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7fcf4aae6800 | 0x7fce1aa35380 | 215572 | 215572 | 21142 | 1724584 | 65536 | 140478829 | 1560982 | 0 | 563733936 | 12075849979187559 | 12075849979385886 | 12075849979518045 | 12075849979520387 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7fcf4aae6700 | 0x7fce1aa353c0 | 214525 | 214525 | 23578 | 1716208 | 65536 | 155062995 | 1546303 | 0 | 622068548 | 12075849979593173 | 12075849979775484 | 12075849979906684 | 12075849979909180 |
| 15 | 13 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 26 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7fcf4aae6600 | 0x7fce1aa35400 | 403373 | 403373 | 29845 | 3226992 | 65536 | 334325952 | 3059440 | 0 | 1339120448 | 12075849979967338 | 12075849980170522 | 12075849980428121 | 12075849980497934 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7fcf4aae6500 | 0x7fce1aa35440 | 395436 | 395436 | 32262 | 3163496 | 65536 | 349956317 | 3000036 | 0 | 1401641804 | 12075849980524393 | 12075849980733720 | 12075849980986039 | 12075849981055390 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7fcf4aae6400 | 0x7fce1aa35480 | 211244 | 211244 | 21887 | 1689960 | 65536 | 150933753 | 1522904 | 0 | 605552928 | 12075849981079254 | 12075849981286998 | 12075849981415957 | 12075849981418635 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7fcf4aae6300 | 0x7fce1aa354c0 | 223364 | 223364 | 18909 | 1786920 | 65536 | 127660580 | 1610069 | 0 | 512456088 | 12075849981478096 | 12075849981671796 | 12075849981809395 | 12075849981811776 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7fcf4aae6a00 | 0x7fce1aa35500 | 211485 | 211485 | 22369 | 1691888 | 65536 | 141753443 | 1530636 | 0 | 568831764 | 12075849981882427 | 12075849982075794 | 12075849982205394 | 12075849982207772 |
| 20 | 18 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 36 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7fcf4aae6900 | 0x7fce1aa35540 | 397140 | 397140 | 30493 | 3177128 | 65536 | 355062871 | 3017582 | 0 | 1422068740 | 12075849982268324 | 12075849982470353 | 12075849982724431 | 12075849982792468 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7fcf4aae6800 | 0x7fce1aa35580 | 402053 | 402053 | 26970 | 3216432 | 65536 | 301251755 | 3050978 | 0 | 1206825256 | 12075849982817044 | 12075849983032110 | 12075849983288909 | 12075849983358490 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7fcf4aae6700 | 0x7fce1aa355c0 | 207669 | 207669 | 20826 | 1661360 | 65536 | 164562366 | 1504929 | 0 | 660079928 | 12075849983384098 | 12075849983588748 | 12075849983715947 | 12075849983718329 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7fcf4aae6600 | 0x7fce1aa35600 | 215636 | 215636 | 23498 | 1725096 | 65536 | 143053683 | 1559635 | 0 | 574033644 | 12075849983776988 | 12075849983977066 | 12075849984109225 | 12075849984111750 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7fcf4aae6500 | 0x7fce1aa35640 | 213468 | 213468 | 22293 | 1707752 | 65536 | 157835100 | 1540703 | 0 | 633158420 | 12075849984186198 | 12075849984371144 | 12075849984502024 | 12075849984504260 |
| 25 | 23 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 46 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7fcf4aae6400 | 0x7fce1aa35680 | 394276 | 394276 | 33489 | 3154216 | 65536 | 355501178 | 2986686 | 0 | 1423823372 | 12075849984562207 | 12075849984758663 | 12075849985011142 | 12075849985080711 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7fcf4aae6300 | 0x7fce1aa356c0 | 402252 | 402252 | 25701 | 3218024 | 65536 | 323854802 | 3038812 | 0 | 1297233780 | 12075849985106850 | 12075849985311780 | 12075849985568579 | 12075849985638037 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7fcf4aae6a00 | 0x7fce1aa35700 | 213508 | 213508 | 23275 | 1708072 | 65536 | 143579633 | 1546767 | 0 | 576144172 | 12075849985662091 | 12075849985870178 | 12075849986000897 | 12075849986005029 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7fcf4aae6900 | 0x7fce1aa35740 | 214404 | 214404 | 21932 | 1715240 | 65536 | 150354073 | 1555352 | 0 | 603237600 | 12075849986063778 | 12075849986265056 | 12075849986397216 | 12075849986399592 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7fcf4aae6800 | 0x7fce1aa35780 | 214037 | 214037 | 21461 | 1712304 | 65536 | 152765841 | 1555966 | 0 | 612885916 | 12075849986471255 | 12075849986649855 | 12075849986781214 | 12075849986783305 |
| 30 | 28 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 56 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7fcf4aae6700 | 0x7fce1aa357c0 | 397116 | 397116 | 27054 | 3176936 | 65536 | 322866490 | 3013442 | 0 | 1293286464 | 12075849986840421 | 12075849987042013 | 12075849987297052 | 12075849987367942 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7fcf4aae6600 | 0x7fce1aa35800 | 393732 | 393732 | 32343 | 3149864 | 65536 | 358466800 | 2993509 | 0 | 1435685084 | 12075849987395222 | 12075849987596890 | 12075849987848729 | 12075849987916471 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7fcf4aae6500 | 0x7fce1aa35840 | 217508 | 217508 | 20372 | 1740072 | 65536 | 152318278 | 1581358 | 0 | 611092976 | 12075849987940977 | 12075849988149208 | 12075849988282967 | 12075849988285096 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7fcf4aae6400 | 0x7fce1aa35880 | 225469 | 225469 | 23838 | 1803760 | 65536 | 140411590 | 1635221 | 0 | 563495236 | 12075849988338165 | 12075849988537046 | 12075849988676086 | 12075849988678477 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7fcf4aae6300 | 0x7fce1aa358c0 | 215269 | 215269 | 21758 | 1722160 | 65536 | 141776619 | 1561204 | 0 | 568919796 | 12075849988749038 | 12075849988928085 | 12075849989060404 | 12075849989062691 |
| 35 | 33 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 66 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7fcf4aae6a00 | 0x7fce1aa35900 | 395901 | 395901 | 32652 | 3167216 | 65536 | 355682262 | 3003719 | 0 | 1424549168 | 12075849989123424 | 12075849989318003 | 12075849989572242 | 12075849989640204 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7fcf4aae6900 | 0x7fce1aa35940 | 400429 | 400429 | 28271 | 3203440 | 65536 | 319025825 | 3040144 | 0 | 1277920212 | 12075849989665592 | 12075849989869521 | 12075849990125840 | 12075849990195056 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7fcf4aae6800 | 0x7fce1aa35980 | 220964 | 220964 | 22613 | 1767720 | 65536 | 151392006 | 1579670 | 0 | 607405368 | 12075849990220703 | 12075849990422478 | 12075849990556558 | 12075849990558892 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7fcf4aae6700 | 0x7fce1aa359c0 | 221500 | 221500 | 24024 | 1772008 | 65536 | 136832425 | 1607323 | 0 | 549160888 | 12075849990619965 | 12075849990809357 | 12075849990945836 | 12075849990948135 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7fcf4aae6600 | 0x7fce1aa35a00 | 216900 | 216900 | 21927 | 1735208 | 65536 | 159322178 | 1570843 | 0 | 639114700 | 12075849991025860 | 12075849991206635 | 12075849991339754 | 12075849991342408 |
| 40 | 38 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 76 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7fcf4aae6500 | 0x7fce1aa35a40 | 403388 | 403388 | 24844 | 3227112 | 65536 | 305497422 | 3035588 | 0 | 1223806544 | 12075849991400967 | 12075849991591273 | 12075849991850472 | 12075849991920112 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7fcf4aae6400 | 0x7fce1aa35a80 | 406588 | 406588 | 29599 | 3252712 | 65536 | 320353671 | 3064456 | 0 | 1283232736 | 12075849991945188 | 12075849992162951 | 12075849992421350 | 12075849992492365 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7fcf4aae6300 | 0x7fce1aa35ac0 | 215796 | 215796 | 22731 | 1726376 | 65536 | 143824888 | 1566567 | 0 | 577121408 | 12075849992524836 | 12075849992721188 | 12075849992853668 | 12075849992856051 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7fcf4aae6a00 | 0x7fce1aa35b00 | 215132 | 215132 | 24734 | 1721064 | 65536 | 161069954 | 1553247 | 0 | 646098464 | 12075849992915532 | 12075849993109027 | 12075849993241506 | 12075849993244293 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7fcf4aae6900 | 0x7fce1aa35b40 | 208469 | 208469 | 20611 | 1667760 | 65536 | 154878328 | 1498735 | 0 | 621353796 | 12075849993318460 | 12075849993503425 | 12075849993631264 | 12075849993633867 |
| 45 | 43 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 86 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7fcf4aae6800 | 0x7fce1aa35b80 | 406149 | 406149 | 32933 | 3249200 | 65536 | 332294302 | 3080022 | 0 | 1331005024 | 12075849993692526 | 12075849993881983 | 12075849994142942 | 12075849994211320 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7fcf4aae6700 | 0x7fce1aa35bc0 | 399397 | 399397 | 26882 | 3195184 | 65536 | 315527924 | 3022408 | 0 | 1263927624 | 12075849994239372 | 12075849994439581 | 12075849994695580 | 12075849994764297 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7fcf4aae6600 | 0x7fce1aa35c00 | 219204 | 219204 | 22571 | 1753640 | 65536 | 146540757 | 1590885 | 0 | 587981140 | 12075849994789304 | 12075849994991899 | 12075849995126778 | 12075849995129807 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7fcf4aae6500 | 0x7fce1aa35c40 | 225820 | 225820 | 25249 | 1806568 | 65536 | 150864816 | 1637669 | 0 | 605284844 | 12075849995191742 | 12075849995385017 | 12075849995524536 | 12075849995527145 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7fcf4aae6400 | 0x7fce1aa35c80 | 210924 | 210924 | 22333 | 1687400 | 65536 | 152035166 | 1522711 | 0 | 609960764 | 12075849995599209 | 12075849995779095 | 12075849995908695 | 12075849995911690 |
| 50 | 48 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 96 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7fcf4aae6300 | 0x7fce1aa35cc0 | 417524 | 417524 | 34282 | 3340200 | 65536 | 344790092 | 3166582 | 0 | 1380981844 | 12075849995967794 | 12075849996174453 | 12075849996443572 | 12075849996514851 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7fcf4aae6a00 | 0x7fce1aa35d00 | 388477 | 388477 | 28883 | 3107824 | 65536 | 352140800 | 2938996 | 0 | 1410380900 | 12075849996540779 | 12075849996745331 | 12075849996994610 | 12075849997064142 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7fcf4aae6900 | 0x7fce1aa35d40 | 222380 | 222380 | 20899 | 1779048 | 65536 | 148263312 | 1616029 | 0 | 594897408 | 12075849997088567 | 12075849997291409 | 12075849997428688 | 12075849997430953 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7fcf4aae6800 | 0x7fce1aa35d80 | 229700 | 229700 | 26737 | 1837608 | 65536 | 151357086 | 1670062 | 0 | 607261760 | 12075849997491606 | 12075849997679727 | 12075849997822446 | 12075849997824795 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7fcf4aae6700 | 0x7fce1aa35dc0 | 216445 | 216445 | 21578 | 1731568 | 65536 | 143362149 | 1570824 | 0 | 575298924 | 12075849997896589 | 12075849998076685 | 12075849998210285 | 12075849998213097 |
| 55 | 53 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 106 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7fcf4aae6600 | 0x7fce1aa35e00 | 415405 | 415405 | 32616 | 3323248 | 65536 | 344673418 | 3155357 | 0 | 1380517300 | 12075849998272738 | 12075849998463084 | 12075849998731242 | 12075849998799156 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7fcf4aae6500 | 0x7fce1aa35e40 | 382357 | 382357 | 32397 | 3058864 | 65536 | 345802878 | 2898594 | 0 | 1385029180 | 12075849998824984 | 12075849999028841 | 12075849999274920 | 12075849999315946 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7fcf4aae6400 | 0x7fce1aa35e80 | 214276 | 214276 | 23748 | 1714216 | 65536 | 144241496 | 1524558 | 0 | 578791280 | 12075849999348818 | 12075849999545959 | 12075849999676038 | 12075849999678530 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7fcf4aae6300 | 0x7fce1aa35ec0 | 224348 | 224348 | 27619 | 1794792 | 65536 | 175162934 | 1622495 | 0 | 702499764 | 12075849999738812 | 12075849999931077 | 12075850000070757 | 12075850000073645 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7fcf4aae6a00 | 0x7fce1aa35f00 | 222333 | 222333 | 23279 | 1778672 | 65536 | 136052983 | 1610476 | 0 | 546074152 | 12075850000146230 | 12075850000328996 | 12075850000466115 | 12075850000468508 |
| 60 | 58 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 116 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7fcf4aae6900 | 0x7fce1aa35f40 | 407524 | 407524 | 31892 | 3260200 | 65536 | 333484520 | 3079309 | 0 | 1335803080 | 12075850000527288 | 12075850000721794 | 12075850000984673 | 12075850001054157 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7fcf4aae6800 | 0x7fce1aa35f80 | 451725 | 451725 | 15608 | 3613808 | 65536 | 326602262 | 2966558 | 0 | 1308227564 | 12075850001082059 | 12075850001283071 | 12075850001574590 | 12075850001644264 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7fcf4aae6700 | 0x7fce1aa35fc0 | 209908 | 209908 | 22144 | 1679272 | 65536 | 149607228 | 1507339 | 0 | 600289500 | 12075850001669290 | 12075850001867709 | 12075850001995708 | 12075850001998151 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7fcf4aae6600 | 0x7fce1aa36000 | 223189 | 223189 | 27606 | 1785520 | 65536 | 182839811 | 1614728 | 0 | 733211032 | 12075850002059996 | 12075850002251067 | 12075850002389787 | 12075850002392344 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7fcf4aae6500 | 0x7fce1aa36040 | 212301 | 212301 | 23007 | 1698416 | 65536 | 143412075 | 1536196 | 0 | 575491376 | 12075850002463927 | 12075850002642266 | 12075850002772985 | 12075850002775215 |
| 65 | 63 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 126 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7fcf4aae6400 | 0x7fce1aa36080 | 411117 | 411117 | 32313 | 3288944 | 65536 | 334611228 | 3113051 | 0 | 1340278736 | 12075850002833143 | 12075850003028344 | 12075850003293943 | 12075850003336929 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7fcf4aae6300 | 0x7fce1aa360c0 | 401124 | 401124 | 28322 | 3209000 | 65536 | 280030950 | 3034325 | 0 | 1121941488 | 12075850003382364 | 12075850003564822 | 12075850003822901 | 12075850003890979 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7fcf4aae6a00 | 0x7fce1aa36100 | 211028 | 211028 | 22202 | 1688232 | 65536 | 151237790 | 1519553 | 0 | 606783600 | 12075850003915615 | 12075850004123379 | 12075850004253139 | 12075850004256168 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7fcf4aae6900 | 0x7fce1aa36140 | 231684 | 231684 | 26405 | 1853480 | 65536 | 191989039 | 1682573 | 0 | 769828024 | 12075850004318043 | 12075850004500498 | 12075850004644977 | 12075850004647485 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7fcf4aae6800 | 0x7fce1aa36180 | 212933 | 212933 | 24974 | 1703472 | 65536 | 157320487 | 1533208 | 0 | 631105120 | 12075850004721683 | 12075850004899056 | 12075850005030415 | 12075850005033322 |
| 70 | 68 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 136 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7fcf4aae6700 | 0x7fce1aa361c0 | 412588 | 412588 | 34237 | 3300712 | 65536 | 329025103 | 3116020 | 0 | 1317952968 | 12075850005093183 | 12075850005288014 | 12075850005554413 | 12075850005622327 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7fcf4aae6600 | 0x7fce1aa36200 | 399029 | 399029 | 31073 | 3192240 | 65536 | 338608239 | 3030247 | 0 | 1356251188 | 12075850005645580 | 12075850005845772 | 12075850006102731 | 12075850006171477 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7fcf4aae6500 | 0x7fce1aa36240 | 224572 | 224572 | 23848 | 1796584 | 65536 | 143758910 | 1635725 | 0 | 576909464 | 12075850006197185 | 12075850006398569 | 12075850006537289 | 12075850006539762 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7fcf4aae6400 | 0x7fce1aa36280 | 239365 | 239365 | 27123 | 1914928 | 65536 | 204668913 | 1750188 | 0 | 820527420 | 12075850006600595 | 12075850006788648 | 12075850006938087 | 12075850006940637 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7fcf4aae6300 | 0x7fce1aa362c0 | 217013 | 217013 | 23897 | 1736112 | 65536 | 157858417 | 1567266 | 0 | 633277136 | 12075850007041574 | 12075850007225286 | 12075850007358725 | 12075850007361198 |
| 75 | 73 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 146 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7fcf4aae6a00 | 0x7fce1aa36300 | 413428 | 413428 | 34702 | 3307432 | 65536 | 330451836 | 3134184 | 0 | 1323667220 | 12075850007419787 | 12075850007610404 | 12075850007878083 | 12075850007946756 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7fcf4aae6900 | 0x7fce1aa36340 | 394052 | 394052 | 34728 | 3152424 | 65536 | 358145876 | 2980150 | 0 | 1434402348 | 12075850007975871 | 12075850008177602 | 12075850008430561 | 12075850008501387 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7fcf4aae6800 | 0x7fce1aa36380 | 220292 | 220292 | 21604 | 1762344 | 65536 | 148810423 | 1594296 | 0 | 597067828 | 12075850008526273 | 12075850008728639 | 12075850008864799 | 12075850008867347 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7fcf4aae6700 | 0x7fce1aa363c0 | 253477 | 253477 | 28307 | 2027824 | 65536 | 223766589 | 1867668 | 0 | 896917772 | 12075850008926628 | 12075850009119838 | 12075850009278717 | 12075850009281727 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7fcf4aae6600 | 0x7fce1aa36400 | 219253 | 219253 | 21293 | 1754032 | 65536 | 154163301 | 1590399 | 0 | 618475848 | 12075850009353300 | 12075850009531996 | 12075850009667515 | 12075850009670049 |
| 80 | 78 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 156 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7fcf4aae6500 | 0x7fce1aa36440 | 402532 | 402532 | 33195 | 3220264 | 65536 | 349602874 | 3047973 | 0 | 1400243400 | 12075850009728317 | 12075850009916154 | 12075850010176793 | 12075850010245458 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7fcf4aae6400 | 0x7fce1aa36480 | 398124 | 398124 | 33993 | 3185000 | 65536 | 354508424 | 3017787 | 0 | 1419863620 | 12075850010270214 | 12075850010472152 | 12075850010728951 | 12075850010799278 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7fcf4aae6300 | 0x7fce1aa364c0 | 224388 | 224388 | 22584 | 1795112 | 65536 | 146993952 | 1630262 | 0 | 589845372 | 12075850010823743 | 12075850011030549 | 12075850011169429 | 12075850011172281 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7fcf4aae6a00 | 0x7fce1aa36500 | 266597 | 266597 | 28766 | 2132784 | 65536 | 235126301 | 1946606 | 0 | 942357220 | 12075850011233174 | 12075850011428148 | 12075850011593747 | 12075850011596349 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7fcf4aae6900 | 0x7fce1aa36540 | 217828 | 217828 | 23871 | 1742632 | 65536 | 158439726 | 1566300 | 0 | 635619428 | 12075850011669214 | 12075850011846546 | 12075850011980465 | 12075850011983008 |
| 85 | 83 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 166 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7fcf4aae6800 | 0x7fce1aa36580 | 406436 | 406436 | 33952 | 3251496 | 65536 | 327052930 | 3063697 | 0 | 1310080580 | 12075850012042418 | 12075850012232944 | 12075850012496143 | 12075850012566191 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7fcf4aae6700 | 0x7fce1aa365c0 | 397364 | 397364 | 31111 | 3178920 | 65536 | 330510350 | 3000339 | 0 | 1323859732 | 12075850012590988 | 12075850012790542 | 12075850013046221 | 12075850013116053 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7fcf4aae6600 | 0x7fce1aa36600 | 223212 | 223212 | 25868 | 1785704 | 65536 | 140535039 | 1618344 | 0 | 563974720 | 12075850013141270 | 12075850013343019 | 12075850013481099 | 12075850013483657 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7fcf4aae6500 | 0x7fce1aa36640 | 276524 | 276524 | 30047 | 2212200 | 65536 | 245668380 | 2050233 | 0 | 984521368 | 12075850013541494 | 12075850013732138 | 12075850013906697 | 12075850013909318 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7fcf4aae6400 | 0x7fce1aa36680 | 226380 | 226380 | 25818 | 1811048 | 65536 | 144194132 | 1641109 | 0 | 578628936 | 12075850013981011 | 12075850014166856 | 12075850014307015 | 12075850014309752 |
| 90 | 88 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 176 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7fcf4aae6300 | 0x7fce1aa366c0 | 403533 | 403533 | 35445 | 3228272 | 65536 | 334624201 | 3030197 | 0 | 1340368004 | 12075850014367269 | 12075850014563174 | 12075850014824773 | 12075850014893537 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7fcf4aae6a00 | 0x7fce1aa36700 | 401805 | 401805 | 29228 | 3214448 | 65536 | 256221234 | 3021525 | 0 | 1026703388 | 12075850014919465 | 12075850015122052 | 12075850015381411 | 12075850015450271 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7fcf4aae6900 | 0x7fce1aa36740 | 227373 | 227373 | 25345 | 1818992 | 65536 | 142563152 | 1648640 | 0 | 572127612 | 12075850015475839 | 12075850015675489 | 12075850015816769 | 12075850015819227 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7fcf4aae6800 | 0x7fce1aa36780 | 288964 | 288964 | 30475 | 2311720 | 65536 | 259584985 | 2152483 | 0 | 1040185260 | 12075850015879509 | 12075850016068928 | 12075850016252607 | 12075850016255788 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7fcf4aae6700 | 0x7fce1aa367c0 | 226796 | 226796 | 25049 | 1814376 | 65536 | 148938686 | 1650810 | 0 | 597647396 | 12075850016361134 | 12075850016546366 | 12075850016686845 | 12075850016689394 |
| 95 | 93 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 186 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7fcf4aae6600 | 0x7fce1aa36800 | 411140 | 411140 | 37138 | 3289128 | 65536 | 379336466 | 3123474 | 0 | 1519166264 | 12075850016747071 | 12075850016939164 | 12075850017206523 | 12075850017277287 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7fcf4aae6500 | 0x7fce1aa36840 | 398572 | 398572 | 31660 | 3188584 | 65536 | 336758203 | 3019684 | 0 | 1348854172 | 12075850017301422 | 12075850017509082 | 12075850017767000 | 12075850017836997 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7fcf4aae6400 | 0x7fce1aa36880 | 278980 | 278980 | 15235 | 2231848 | 65536 | 150778608 | 1534634 | 0 | 604948688 | 12075850017863416 | 12075850018076439 | 12075850018252118 | 12075850018255094 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7fcf4aae6300 | 0x7fce1aa368c0 | 303077 | 303077 | 31685 | 2424624 | 65536 | 270563234 | 2257627 | 0 | 1084112372 | 12075850018316598 | 12075850018505877 | 12075850018698036 | 12075850018766895 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7fcf4aae6a00 | 0x7fce1aa36900 | 225349 | 225349 | 25925 | 1802800 | 65536 | 146885560 | 1628453 | 0 | 589406772 | 12075850018801590 | 12075850018992115 | 12075850019131795 | 12075850019134859 |
| 100 | 98 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 196 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7fcf4aae6900 | 0x7fce1aa36940 | 436172 | 436172 | 39872 | 3489384 | 65536 | 405051377 | 3324094 | 0 | 1622025280 | 12075850019193759 | 12075850019384113 | 12075850019668112 | 12075850019737219 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7fcf4aae6800 | 0x7fce1aa36980 | 401437 | 401437 | 28898 | 3211504 | 65536 | 256933417 | 3028846 | 0 | 1029557880 | 12075850019762025 | 12075850019961071 | 12075850020220910 | 12075850020291779 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7fcf4aae6700 | 0x7fce1aa369c0 | 222381 | 222381 | 26647 | 1779056 | 65536 | 144820237 | 1604014 | 0 | 581150368 | 12075850020317437 | 12075850020523469 | 12075850020661708 | 12075850020664261 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7fcf4aae6600 | 0x7fce1aa36a00 | 331460 | 331460 | 33256 | 2651688 | 65536 | 296394437 | 2486463 | 0 | 1187424108 | 12075850020723261 | 12075850020916427 | 12075850021128106 | 12075850021199266 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7fcf4aae6500 | 0x7fce1aa36a40 | 227189 | 227189 | 26311 | 1817520 | 65536 | 151274808 | 1649737 | 0 | 606971176 | 12075850021236254 | 12075850021426185 | 12075850021567624 | 12075850021570205 |
| 105 | 103 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 206 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7fcf4aae6400 | 0x7fce1aa36a80 | 470572 | 470572 | 41370 | 3764584 | 65536 | 438579798 | 3601301 | 0 | 1756138968 | 12075850021627982 | 12075850021819783 | 12075850022127302 | 12075850022196419 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7fcf4aae6300 | 0x7fce1aa36ac0 | 389332 | 389332 | 35099 | 3114664 | 65536 | 349965678 | 2933275 | 0 | 1401687548 | 12075850022222898 | 12075850022425431 | 12075850022677270 | 12075850022751721 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7fcf4aae6a00 | 0x7fce1aa36b00 | 226317 | 226317 | 22230 | 1810544 | 65536 | 148042543 | 1624301 | 0 | 594053844 | 12075850022773511 | 12075850022979828 | 12075850023120627 | 12075850023123251 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7fcf4aae6900 | 0x7fce1aa36b40 | 356332 | 356332 | 35655 | 2850664 | 65536 | 324920912 | 2691527 | 0 | 1301524784 | 12075850023182181 | 12075850023372146 | 12075850023600465 | 12075850023670318 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7fcf4aae6800 | 0x7fce1aa36b80 | 225197 | 225197 | 24423 | 1801584 | 65536 | 148558492 | 1634932 | 0 | 596086532 | 12075850023706275 | 12075850023894224 | 12075850024034383 | 12075850024036999 |
| 110 | 108 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 216 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7fcf4aae6700 | 0x7fce1aa36bc0 | 506596 | 506596 | 44452 | 4052776 | 65536 | 472905203 | 3885433 | 0 | 1893440424 | 12075850024096600 | 12075850024293902 | 12075850024625101 | 12075850024672160 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7fcf4aae6600 | 0x7fce1aa36c00 | 391852 | 391852 | 34391 | 3134824 | 65536 | 350525172 | 2963678 | 0 | 1403934824 | 12075850024696565 | 12075850024895659 | 12075850025149258 | 12075850025220018 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7fcf4aae6500 | 0x7fce1aa36c40 | 227557 | 227557 | 26484 | 1820464 | 65536 | 150275874 | 1649441 | 0 | 602967428 | 12075850025245195 | 12075850025448137 | 12075850025589576 | 12075850025592180 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7fcf4aae6400 | 0x7fce1aa36c80 | 383684 | 383684 | 36058 | 3069480 | 65536 | 341902817 | 2903138 | 0 | 1369455808 | 12075850025651861 | 12075850025839495 | 12075850026086054 | 12075850026155937 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7fcf4aae6300 | 0x7fce1aa36cc0 | 223764 | 223764 | 24131 | 1790120 | 65536 | 158568667 | 1622536 | 0 | 636166912 | 12075850026192656 | 12075850026375813 | 12075850026515493 | 12075850026518110 |
| 115 | 113 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 226 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7fcf4aae6a00 | 0x7fce1aa36d00 | 574597 | 574597 | 48574 | 4596784 | 65536 | 540103566 | 4430216 | 0 | 2162234040 | 12075850026576970 | 12075850026769731 | 12075850027146530 | 12075850027216689 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7fcf4aae6900 | 0x7fce1aa36d40 | 406261 | 406261 | 34156 | 3250096 | 65536 | 350080083 | 3086694 | 0 | 1402158160 | 12075850027244450 | 12075850027458688 | 12075850027722527 | 12075850027792439 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7fcf4aae6800 | 0x7fce1aa36d80 | 224685 | 224685 | 29928 | 1797488 | 65536 | 175254554 | 1622466 | 0 | 702910832 | 12075850027817385 | 12075850028029406 | 12075850028169085 | 12075850028172114 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7fcf4aae6700 | 0x7fce1aa36dc0 | 434572 | 434572 | 39891 | 3476584 | 65536 | 404217170 | 3314668 | 0 | 1618718988 | 12075850028224983 | 12075850028431484 | 12075850028711483 | 12075850028781066 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7fcf4aae6600 | 0x7fce1aa36e00 | 224125 | 224125 | 26817 | 1793008 | 65536 | 162388756 | 1625331 | 0 | 651448428 | 12075850028817464 | 12075850028998682 | 12075850029138361 | 12075850029141867 |
| 120 | 118 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 236 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7fcf4aae6500 | 0x7fce1aa36e40 | 645604 | 645604 | 51895 | 5164840 | 65536 | 613139088 | 5004549 | 0 | 2454375140 | 12075850029202369 | 12075850029395000 | 12075850029819958 | 12075850029863247 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7fcf4aae6400 | 0x7fce1aa36e80 | 402996 | 402996 | 33941 | 3223976 | 65536 | 309574767 | 3025030 | 0 | 1240140636 | 12075850029902771 | 12075850030088437 | 12075850030349716 | 12075850030420052 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7fcf4aae6300 | 0x7fce1aa36ec0 | 224476 | 224476 | 25369 | 1795816 | 65536 | 166426181 | 1623282 | 0 | 667614176 | 12075850030444417 | 12075850030650195 | 12075850030790194 | 12075850030792925 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7fcf4aae6a00 | 0x7fce1aa36f00 | 489756 | 489756 | 43686 | 3918056 | 65536 | 457789309 | 3751566 | 0 | 1833010548 | 12075850030855341 | 12075850031057873 | 12075850031374672 | 12075850031445177 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7fcf4aae6900 | 0x7fce1aa36f40 | 244204 | 244204 | 27236 | 1953640 | 65536 | 213096911 | 1792288 | 0 | 854279428 | 12075850031490071 | 12075850031672271 | 12075850031825710 | 12075850031828279 |
| 125 | 123 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 246 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7fcf4aae6800 | 0x7fce1aa36f80 | 784948 | 784948 | 60238 | 6279592 | 65536 | 750361619 | 6111978 | 0 | 3003268712 | 12075850031887449 | 12075850032084429 | 12075850032602507 | 12075850032673811 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7fcf4aae6700 | 0x7fce1aa36fc0 | 458300 | 458300 | 41649 | 3666408 | 65536 | 382104054 | 3478742 | 0 | 1530264948 | 12075850032698396 | 12075850032899465 | 12075850033199144 | 12075850033269027 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7fcf4aae6600 | 0x7fce1aa37000 | 249052 | 249052 | 27908 | 1992424 | 65536 | 219140100 | 1830254 | 0 | 878453280 | 12075850033294143 | 12075850033498023 | 12075850033654982 | 12075850033657459 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7fcf4aae6500 | 0x7fce1aa37040 | 592909 | 592909 | 48476 | 4743280 | 65536 | 561710865 | 4582273 | 0 | 2248698828 | 12075850033718292 | 12075850033905861 | 12075850034291939 | 12075850034361457 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7fcf4aae6400 | 0x7fce1aa37080 | 278173 | 278173 | 29568 | 2225392 | 65536 | 249539040 | 2064063 | 0 | 1000045068 | 12075850034398816 | 12075850034588578 | 12075850034764897 | 12075850034767842 |
| 130 | 128 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 256 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7fcf4aae6300 | 0x7fce1aa370c0 | 924908 | 924908 | 68195 | 7399272 | 65536 | 889705220 | 7237399 | 0 | 3560641072 | 12075850034827633 | 12075850035026976 | 12075850035638494 | 12075850035707749 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7fcf4aae6a00 | 0x7fce1aa37100 | 503420 | 503420 | 43488 | 4027368 | 65536 | 458345816 | 3853504 | 0 | 1835218276 | 12075850035733106 | 12075850035935132 | 12075850036266491 | 12075850036336728 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7fcf4aae6900 | 0x7fce1aa37140 | 282365 | 282365 | 30403 | 2258928 | 65536 | 253525941 | 2095071 | 0 | 1015987556 | 12075850036362005 | 12075850036563930 | 12075850036743449 | 12075850036745878 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7fcf4aae6800 | 0x7fce1aa37180 | 697812 | 697812 | 54183 | 5582504 | 65536 | 665315708 | 5424823 | 0 | 2663120396 | 12075850036804087 | 12075850036994968 | 12075850037451606 | 12075850037522281 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7fcf4aae6700 | 0x7fce1aa371c0 | 314413 | 314413 | 31712 | 2515312 | 65536 | 285511664 | 2355907 | 0 | 1143939520 | 12075850037559240 | 12075850037750485 | 12075850037951764 | 12075850038021830 |
| 135 | 133 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 266 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7fcf4aae6600 | 0x7fce1aa37200 | 1063541 | 1063541 | 74807 | 8508336 | 65536 | 1029000729 | 8352826 | 0 | 4117824352 | 12075850038045644 | 12075850038248083 | 12075850038951920 | 12075850039022008 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7fcf4aae6500 | 0x7fce1aa37240 | 571509 | 571509 | 47152 | 4572080 | 65536 | 529536495 | 4385615 | 0 | 2119999504 | 12075850039056523 | 12075850039251918 | 12075850039627277 | 12075850039696232 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7fcf4aae6400 | 0x7fce1aa37280 | 320196 | 320196 | 31930 | 2561576 | 65536 | 290672994 | 2402553 | 0 | 1164599192 | 12075850039720917 | 12075850039921036 | 12075850040125995 | 12075850040196551 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7fcf4aae6300 | 0x7fce1aa372c0 | 828428 | 828428 | 15565 | 6627432 | 65536 | 766008978 | 6261965 | 0 | 3065878936 | 12075850040221307 | 12075850040421513 | 12075850040965031 | 12075850041035430 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7fcf4aae6a00 | 0x7fce1aa37300 | 351525 | 351525 | 35544 | 2812208 | 65536 | 320319347 | 2637921 | 0 | 1283174464 | 12075850041073160 | 12075850041258150 | 12075850041483269 | 12075850041551860 |
| 140 | 138 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 276 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7fcf4aae6900 | 0x7fce1aa37340 | 1208164 | 1208164 | 15297 | 9665320 | 65536 | 1168110323 | 9494496 | 0 | 4674262092 | 12075850041575454 | 12075850041776548 | 12075850042577664 | 12075850042647316 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7fcf4aae6800 | 0x7fce1aa37380 | 639892 | 639892 | 53469 | 5119144 | 65536 | 602326320 | 4944859 | 0 | 2411148664 | 12075850042684004 | 12075850042879583 | 12075850043301021 | 12075850043373325 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7fcf4aae6700 | 0x7fce1aa373c0 | 353700 | 353700 | 33914 | 2829608 | 65536 | 325024869 | 2674073 | 0 | 1301994104 | 12075850043405265 | 12075850043605660 | 12075850043833659 | 12075850043902248 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7fcf4aae6600 | 0x7fce1aa37400 | 909565 | 909565 | 67270 | 7276528 | 65536 | 874827830 | 7114643 | 0 | 3501164104 | 12075850043935099 | 12075850044138618 | 12075850044736375 | 12075850044806970 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7fcf4aae6500 | 0x7fce1aa37440 | 416452 | 416452 | 37896 | 3331624 | 65536 | 385224866 | 3177308 | 0 | 1542802264 | 12075850044843517 | 12075850045041814 | 12075850045311253 | 12075850045380686 |
| 145 | 143 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 286 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7fcf4aae6400 | 0x7fce1aa37480 | 1486980 | 1486980 | 99936 | 11895848 | 65536 | 1448260530 | 11738129 | 0 | 5794862416 | 12075850045406013 | 12075850045608211 | 12075850046594607 | 12075850046664792 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7fcf4aae6300 | 0x7fce1aa374c0 | 802556 | 802556 | 15285 | 6420456 | 65536 | 743543197 | 6059831 | 0 | 2976020276 | 12075850046701450 | 12075850046896846 | 12075850047429324 | 12075850047500936 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7fcf4aae6a00 | 0x7fce1aa37500 | 422788 | 422788 | 39410 | 3382312 | 65536 | 389066205 | 3212132 | 0 | 1558159056 | 12075850047532986 | 12075850047735082 | 12075850048008201 | 12075850048077588 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7fcf4aae6900 | 0x7fce1aa37540 | 1126813 | 1126813 | 79723 | 9014512 | 65536 | 1090326031 | 8854379 | 0 | 4363126348 | 12075850048110269 | 12075850048303880 | 12075850049042917 | 12075850049113192 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7fcf4aae6800 | 0x7fce1aa37580 | 531492 | 531492 | 15373 | 4251944 | 65536 | 451687198 | 3744925 | 0 | 1808639124 | 12075850049155631 | 12075850049337476 | 12075850049683234 | 12075850049752020 |
| 150 | 148 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 296 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7fcf4aae6700 | 0x7fce1aa375c0 | 1768709 | 1768709 | 117952 | 14149680 | 65536 | 1725840035 | 13980092 | 0 | 6905180996 | 12075850049788007 | 12075850049989633 | 12075850051162108 | 12075850051234304 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7fcf4aae6600 | 0x7fce1aa37600 | 922341 | 922341 | 64502 | 7378736 | 65536 | 808319421 | 7214171 | 0 | 3235147016 | 12075850051269099 | 12075850051467226 | 12075850052079224 | 12075850052148804 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7fcf4aae6500 | 0x7fce1aa37640 | 493405 | 493405 | 45125 | 3947248 | 65536 | 460613878 | 3777925 | 0 | 1844350904 | 12075850052175664 | 12075850052384663 | 12075850052704661 | 12075850052774337 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7fcf4aae6400 | 0x7fce1aa37680 | 1336908 | 1336908 | 92195 | 10695272 | 65536 | 1297522663 | 10536360 | 0 | 5191913904 | 12075850052810434 | 12075850052999540 | 12075850053878576 | 12075850053949300 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7fcf4aae6300 | 0x7fce1aa376c0 | 629173 | 629173 | 51972 | 5033392 | 65536 | 593218017 | 4864288 | 0 | 2374775296 | 12075850053998652 | 12075850054187855 | 12075850054598733 | 12075850054669639 |
| 155 | 153 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 306 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7fcf4aae6a00 | 0x7fce1aa37700 | 2332549 | 2332549 | 150729 | 18660400 | 65536 | 2284601534 | 18498131 | 0 | 9140227240 | 12075850054696218 | 12075850054901292 | 12075850056451685 | 12075850056521761 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7fcf4aae6900 | 0x7fce1aa37740 | 1199781 | 1199781 | 83385 | 9598256 | 65536 | 1163658381 | 9440900 | 0 | 4656456848 | 12075850056557978 | 12075850056760324 | 12075850057555841 | 12075850057626053 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7fcf4aae6800 | 0x7fce1aa37780 | 640044 | 640044 | 50902 | 5120360 | 65536 | 608648714 | 4959181 | 0 | 2436426508 | 12075850057663493 | 12075850057858559 | 12075850058274078 | 12075850058345871 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7fcf4aae6700 | 0x7fce1aa377c0 | 1757140 | 1757140 | 115741 | 14057128 | 65536 | 1714527034 | 13900398 | 0 | 6859930956 | 12075850058378011 | 12075850058573916 | 12075850059732951 | 12075850059803119 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7fcf4aae6600 | 0x7fce1aa37800 | 1198924 | 1198924 | 83726 | 9591400 | 65536 | 1161588688 | 9427500 | 0 | 4648182328 | 12075850059847672 | 12075850060035830 | 12075850060822227 | 12075850060892915 |
| 160 | 158 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 316 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7fcf4aae6500 | 0x7fce1aa37840 | 4583884 | 4583884 | 282037 | 36671080 | 65536 | 4514045020 | 36507990 | 0 | 18058000196 | 12075850060917831 | 12075850061123505 | 12075850064173892 | 12075850064244634 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7fcf4aae6400 | 0x7fce1aa37880 | 2324677 | 2324677 | 80054 | 18597424 | 65536 | 2274993684 | 18433442 | 0 | 9101798524 | 12075850064275070 | 12075850064482371 | 12075850066025565 | 12075850066096245 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7fcf4aae6300 | 0x7fce1aa378c0 | 1203636 | 1203636 | 84153 | 9629096 | 65536 | 1166876286 | 9459873 | 0 | 4669329296 | 12075850066128334 | 12075850066332123 | 12075850067122200 | 12075850067192662 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7fcf4aae6a00 | 0x7fce1aa37900 | 3442876 | 3442876 | 214364 | 27543016 | 65536 | 3385576437 | 27381935 | 0 | 13544135028 | 12075850067217839 | 12075850067433879 | 12075850069716269 | 12075850069786463 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7fcf4aae6900 | 0x7fce1aa37940 | 2323725 | 2323725 | 150776 | 18589808 | 65536 | 2274957586 | 18425900 | 0 | 9101655288 | 12075850069832478 | 12075850070022828 | 12075850071558821 | 12075850071631311 |
| 165 | 163 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 326 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7fcf4aae6800 | 0x7fce1aa37980 | 9087661 | 9087661 | 543854 | 72701296 | 65536 | 8978499358 | 72538309 | 0 | 35915819164 | 12075850071663591 | 12075850071866980 | 12075850077924394 | 12075850077996180 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7fcf4aae6700 | 0x7fce1aa379c0 | 4572109 | 4572109 | 281873 | 36576880 | 65536 | 4502714304 | 36413576 | 0 | 18012681716 | 12075850078035293 | 12075850078236073 | 12075850081279580 | 12075850081351646 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7fcf4aae6600 | 0x7fce1aa37a00 | 2330077 | 2330077 | 150454 | 18640624 | 65536 | 2281774978 | 18470740 | 0 | 9128926504 | 12075850081385349 | 12075850081585818 | 12075850083126772 | 12075850083197016 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 896508 | 896513 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7fcf4aae6500 | 0x7fce1aa37a40 | 6813492 | 6813492 | 342604 | 54507944 | 65536 | 6723313959 | 54337633 | 0 | 26895080712 | 12075850083229606 | 12075850083429566 | 12075850087957552 | 12075850088032432 |