55 KiB
55 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | SQ_CYCLES | SQ_BUSY_CYCLES | SQ_WAVES | GRBM_COUNT | GRBM_GUI_ACTIVE | CPC_CPC_STAT_BUSY | CPC_CPC_STAT_IDLE | CPC_CPC_TCIU_BUSY | CPC_CPC_TCIU_IDLE | CPC_CPC_STAT_STALL | CPC_UTCL1_STALL_ON_TRANSLATION | CPC_CPC_UTCL2IU_BUSY | CPC_CPC_UTCL2IU_IDLE | CPC_CPC_UTCL2IU_STALL | CPC_ME1_BUSY_FOR_PACKET_DECODE | CPC_ME1_DC0_SPI_BUSY | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBuffer.kd | 0 | 0 | 0 | 868852 | 868857 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7fe0c3a04180 | 4029584 | 3826331 | 524288 | 503697 | 503697 | 503697 | 0 | 730 | 502466 | 11423 | 2560 | 2851 | 506751 | 0 | 17018 | 476693 | 12075292247429918 | 12075298394918942 | 12075298395241339 | 12075292494715737 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 868852 | 868857 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7fe0c3a35100 | 224040 | 75644 | 512 | 28004 | 28004 | 28004 | 0 | 650 | 28192 | 12267 | 2716 | 2440 | 24402 | 0 | 20912 | 695 | 12075292509297973 | 12075298410199883 | 12075298410206763 | 12075292509625201 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7fe1f39f1900 | 0x7fe0c3a35140 | 1824800 | 1659275 | 65536 | 228099 | 228099 | 228099 | 0 | 732 | 217693 | 11599 | 2614 | 2438 | 213008 | 0 | 19759 | 199686 | 12075292509682647 | 12075298410323561 | 12075298410454600 | 12075292510053456 |
| 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 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7fe1f39f1800 | 0x7fe0c3a35180 | 3125072 | 2943385 | 65536 | 390633 | 390633 | 390633 | 0 | 760 | 392243 | 11377 | 2674 | 2423 | 387447 | 0 | 30376 | 370866 | 12075292510120992 | 12075298410524200 | 12075298410768357 | 12075292510616803 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7fe1f39f1700 | 0x7fe0c3a351c0 | 3196192 | 3033951 | 65536 | 399523 | 399523 | 399523 | 0 | 732 | 401837 | 12672 | 2601 | 2430 | 394960 | 0 | 23874 | 359229 | 12075292510648823 | 12075298410880516 | 12075298411126274 | 12075292511167416 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7fe1f39f1600 | 0x7fe0c3a35200 | 1714960 | 1555521 | 65536 | 214369 | 214369 | 214369 | 0 | 760 | 217875 | 11637 | 2665 | 2432 | 205926 | 0 | 20314 | 199606 | 12075292511197242 | 12075298411248193 | 12075298411373312 | 12075292511523338 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7fe1f39f1500 | 0x7fe0c3a35240 | 1805216 | 1639455 | 65536 | 225651 | 225651 | 225651 | 0 | 732 | 217669 | 11921 | 2600 | 2437 | 211433 | 0 | 21835 | 200670 | 12075292511574863 | 12075298411419872 | 12075298411545310 | 12075292511893305 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7fe1f39f1400 | 0x7fe0c3a35280 | 1721488 | 1560652 | 65536 | 215185 | 215185 | 215185 | 0 | 760 | 212019 | 11529 | 2688 | 2431 | 208991 | 0 | 22989 | 180730 | 12075292511973033 | 12075298411617310 | 12075298411741149 | 12075292512300081 |
| 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 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7fe1f39f1300 | 0x7fe0c3a352c0 | 3132320 | 2968263 | 65536 | 391539 | 391539 | 391539 | 0 | 732 | 386373 | 12880 | 2885 | 2701 | 386793 | 0 | 32836 | 371439 | 12075292512352138 | 12075298411787868 | 12075298412073306 | 12075292512828192 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7fe1f39f1a00 | 0x7fe0c3a35300 | 3202704 | 3039115 | 65536 | 400337 | 400337 | 400337 | 0 | 760 | 391939 | 11788 | 2586 | 2431 | 390655 | 0 | 32656 | 366451 | 12075292512851425 | 12075298412186585 | 12075298412429942 | 12075292513382031 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7fe1f39f1900 | 0x7fe0c3a35340 | 1753504 | 1583968 | 65536 | 219187 | 219187 | 219187 | 0 | 732 | 214045 | 11846 | 2485 | 2429 | 211273 | 0 | 26272 | 185666 | 12075292513406837 | 12075298412533941 | 12075298412658420 | 12075292513739145 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7fe1f39f1800 | 0x7fe0c3a35380 | 1692752 | 1528499 | 65536 | 211593 | 211593 | 211593 | 0 | 760 | 214987 | 11128 | 2488 | 2425 | 214125 | 0 | 20647 | 183558 | 12075292513788617 | 12075298412698740 | 12075298412824179 | 12075292514099615 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7fe1f39f1700 | 0x7fe0c3a353c0 | 1688864 | 1519057 | 65536 | 211107 | 211107 | 211107 | 0 | 732 | 214429 | 12444 | 2890 | 2421 | 208873 | 0 | 20065 | 184374 | 12075292514163854 | 12075298412875058 | 12075298412999217 | 12075292514473339 |
| 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 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7fe1f39f1600 | 0x7fe0c3a35400 | 3210512 | 3040371 | 65536 | 401313 | 401313 | 401313 | 0 | 760 | 400195 | 11368 | 2735 | 2944 | 403246 | 0 | 30167 | 357769 | 12075292514525496 | 12075298413041457 | 12075298413326894 | 12075292515021858 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7fe1f39f1500 | 0x7fe0c3a35440 | 3206624 | 3015271 | 65536 | 400827 | 400827 | 400827 | 0 | 732 | 395365 | 11752 | 2895 | 2454 | 394840 | 0 | 29232 | 365485 | 12075292515046765 | 12075298413434093 | 12075298413679051 | 12075292515563375 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7fe1f39f1400 | 0x7fe0c3a35480 | 1706064 | 1536037 | 65536 | 213257 | 213257 | 213257 | 0 | 760 | 215331 | 11239 | 2594 | 2395 | 206779 | 0 | 22164 | 187334 | 12075292515590104 | 12075298413780490 | 12075298413905289 | 12075292515915479 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7fe1f39f1300 | 0x7fe0c3a354c0 | 1708064 | 1544602 | 65536 | 213507 | 213507 | 213507 | 0 | 732 | 220189 | 11951 | 2600 | 2718 | 212576 | 0 | 23318 | 197490 | 12075292515966954 | 12075298413944489 | 12075298414069928 | 12075292516292820 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7fe1f39f1a00 | 0x7fe0c3a35500 | 1703120 | 1541800 | 65536 | 212889 | 212889 | 212889 | 0 | 760 | 210179 | 11381 | 3138 | 2432 | 219510 | 0 | 15683 | 189630 | 12075292516358462 | 12075298414121447 | 12075298414245926 | 12075292516663338 |
| 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 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7fe1f39f1900 | 0x7fe0c3a35540 | 3249760 | 3077412 | 65536 | 406219 | 406219 | 406219 | 0 | 732 | 392733 | 13130 | 2591 | 2428 | 400546 | 0 | 29167 | 352546 | 12075292516714343 | 12075298414286246 | 12075298414532963 | 12075292517222798 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7fe1f39f1800 | 0x7fe0c3a35580 | 3226256 | 3043554 | 65536 | 403281 | 403281 | 403281 | 0 | 760 | 395939 | 13124 | 2592 | 2432 | 385982 | 0 | 31860 | 361721 | 12075292517247223 | 12075298414632642 | 12075298414875680 | 12075292517761158 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7fe1f39f1700 | 0x7fe0c3a355c0 | 1726688 | 1566645 | 65536 | 215835 | 215835 | 215835 | 0 | 732 | 216437 | 12078 | 2599 | 2420 | 213738 | 0 | 21704 | 182854 | 12075292517787598 | 12075298414951520 | 12075298415075678 | 12075292518109816 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7fe1f39f1600 | 0x7fe0c3a35600 | 1680720 | 1518631 | 65536 | 210089 | 210089 | 210089 | 0 | 760 | 212803 | 11551 | 2594 | 2442 | 213260 | 0 | 23381 | 185729 | 12075292518160581 | 12075298415115678 | 12075298415241597 | 12075292518473843 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7fe1f39f1500 | 0x7fe0c3a35640 | 1739680 | 1571766 | 65536 | 217459 | 217459 | 217459 | 0 | 732 | 214621 | 11898 | 2879 | 2454 | 216064 | 0 | 23266 | 185057 | 12075292518536579 | 12075298415291676 | 12075298415415995 | 12075292518845824 |
| 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 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7fe1f39f1400 | 0x7fe0c3a35680 | 3244112 | 3086150 | 65536 | 405513 | 405513 | 405513 | 0 | 1190 | 451760 | 13497 | 2593 | 2432 | 402550 | 0 | 30602 | 361671 | 12075292518894645 | 12075298415456155 | 12075298415704473 | 12075292519420572 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7fe1f39f1300 | 0x7fe0c3a356c0 | 3223904 | 3062068 | 65536 | 402987 | 402987 | 402987 | 0 | 787 | 397928 | 12779 | 3102 | 2443 | 399003 | 0 | 33233 | 358911 | 12075292519444005 | 12075298415799672 | 12075298416043510 | 12075292519964813 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7fe1f39f1a00 | 0x7fe0c3a35700 | 1693328 | 1538939 | 65536 | 211665 | 211665 | 211665 | 0 | 758 | 211075 | 11790 | 2625 | 2439 | 214463 | 0 | 20591 | 185935 | 12075292519988868 | 12075298416143829 | 12075298416267988 | 12075292520331294 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7fe1f39f1900 | 0x7fe0c3a35740 | 1834208 | 1664980 | 65536 | 229275 | 229275 | 229275 | 0 | 760 | 222747 | 12004 | 2607 | 2430 | 212016 | 0 | 22492 | 185429 | 12075292520378211 | 12075298416308467 | 12075298416433426 | 12075292520703656 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7fe1f39f1800 | 0x7fe0c3a35780 | 1723088 | 1564547 | 65536 | 215385 | 215385 | 215385 | 0 | 732 | 218325 | 11805 | 2587 | 2432 | 206430 | 0 | 21815 | 187718 | 12075292520766843 | 12075298416482386 | 12075298416607345 | 12075292521071459 |
| 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 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7fe1f39f1700 | 0x7fe0c3a357c0 | 3138656 | 2976600 | 65536 | 392331 | 392331 | 392331 | 0 | 760 | 398883 | 12681 | 2856 | 2454 | 394448 | 0 | 34835 | 369423 | 12075292521124648 | 12075298416647344 | 12075298416899022 | 12075292521619287 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7fe1f39f1600 | 0x7fe0c3a35800 | 3208400 | 3035514 | 65536 | 401049 | 401049 | 401049 | 0 | 732 | 397085 | 12266 | 2588 | 2432 | 381822 | 0 | 28514 | 355019 | 12075292521644234 | 12075298416967821 | 12075298417212619 | 12075292522161705 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7fe1f39f1500 | 0x7fe0c3a35840 | 1706784 | 1545312 | 65536 | 213347 | 213347 | 213347 | 0 | 760 | 211915 | 12057 | 2593 | 2438 | 215056 | 0 | 23717 | 180955 | 12075292522186662 | 12075298417297738 | 12075298417422057 | 12075292522511064 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7fe1f39f1400 | 0x7fe0c3a35880 | 1722000 | 1568372 | 65536 | 215249 | 215249 | 215249 | 0 | 732 | 218805 | 11690 | 2595 | 2435 | 205851 | 0 | 23784 | 185565 | 12075292522561478 | 12075298417461897 | 12075298417587816 | 12075292522877766 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7fe1f39f1300 | 0x7fe0c3a358c0 | 1743712 | 1567592 | 65536 | 217963 | 217963 | 217963 | 0 | 760 | 212651 | 12563 | 2869 | 2444 | 211506 | 0 | 23203 | 185510 | 12075292522940442 | 12075298417637735 | 12075298417763014 | 12075292523251801 |
| 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 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7fe1f39f1a00 | 0x7fe0c3a35900 | 3195792 | 3031415 | 65536 | 399473 | 399473 | 399473 | 0 | 732 | 404045 | 12231 | 2601 | 2432 | 398974 | 0 | 31482 | 374169 | 12075292523302024 | 12075298417801894 | 12075298418053891 | 12075292523805079 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7fe1f39f1900 | 0x7fe0c3a35940 | 3219424 | 3036388 | 65536 | 402427 | 402427 | 402427 | 0 | 760 | 393139 | 13521 | 2872 | 2443 | 384947 | 0 | 30065 | 365735 | 12075292523830807 | 12075298418109891 | 12075298418354529 | 12075292524348318 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7fe1f39f1800 | 0x7fe0c3a35980 | 1692752 | 1530658 | 65536 | 211593 | 211593 | 211593 | 0 | 732 | 212021 | 11724 | 2585 | 2439 | 205207 | 0 | 23286 | 179086 | 12075292524374657 | 12075298418408128 | 12075298418532927 | 12075292524698669 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7fe1f39f1700 | 0x7fe0c3a359c0 | 1773728 | 1603739 | 65536 | 221715 | 221715 | 221715 | 0 | 760 | 216811 | 12333 | 2597 | 2429 | 210049 | 0 | 27231 | 191850 | 12075292524750035 | 12075298418572767 | 12075298418698526 | 12075292525071071 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7fe1f39f1600 | 0x7fe0c3a35a00 | 1684432 | 1526482 | 65536 | 210553 | 210553 | 210553 | 0 | 732 | 216957 | 11533 | 2591 | 2392 | 212734 | 0 | 23702 | 185539 | 12075292525133577 | 12075298418746525 | 12075298418870524 | 12075292525438574 |
| 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 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7fe1f39f1500 | 0x7fe0c3a35a40 | 3213024 | 3044087 | 65536 | 401627 | 401627 | 401627 | 0 | 760 | 403091 | 13752 | 2876 | 2428 | 397018 | 0 | 32415 | 365781 | 12075292525482696 | 12075298418908924 | 12075298419158201 | 12075292525995319 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7fe1f39f1400 | 0x7fe0c3a35a80 | 3177616 | 3015399 | 65536 | 397201 | 397201 | 397201 | 0 | 732 | 393213 | 12472 | 2617 | 2431 | 384527 | 0 | 31401 | 362515 | 12075292526024783 | 12075298419257560 | 12075298419504598 | 12075292526544369 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7fe1f39f1300 | 0x7fe0c3a35ac0 | 1730656 | 1566473 | 65536 | 216331 | 216331 | 216331 | 0 | 760 | 212507 | 12105 | 2599 | 2444 | 210754 | 0 | 22661 | 190123 | 12075292526567111 | 12075298419557718 | 12075298419682357 | 12075292526893537 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7fe1f39f1a00 | 0x7fe0c3a35b00 | 1782736 | 1615091 | 65536 | 222841 | 222841 | 222841 | 0 | 732 | 211357 | 12699 | 3017 | 2457 | 214229 | 0 | 24028 | 183903 | 12075292526944763 | 12075298419721236 | 12075298419846675 | 12075292527269055 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7fe1f39f1900 | 0x7fe0c3a35b40 | 1733920 | 1569319 | 65536 | 216739 | 216739 | 216739 | 0 | 760 | 215075 | 12343 | 2599 | 2443 | 207691 | 0 | 23643 | 186222 | 12075292527334617 | 12075298419896115 | 12075298420020594 | 12075292527642750 |
| 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 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7fe1f39f1800 | 0x7fe0c3a35b80 | 3261904 | 3082783 | 65536 | 407737 | 407737 | 407737 | 0 | 732 | 403269 | 12593 | 2604 | 2432 | 401550 | 0 | 31472 | 383170 | 12075292527691771 | 12075298420060593 | 12075298420311311 | 12075292528202680 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7fe1f39f1700 | 0x7fe0c3a35bc0 | 3163232 | 2995900 | 65536 | 395403 | 395403 | 395403 | 0 | 760 | 395779 | 12706 | 2600 | 2437 | 394465 | 0 | 29385 | 358597 | 12075292528225833 | 12075298420362990 | 12075298420609068 | 12075292528735701 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7fe1f39f1600 | 0x7fe0c3a35c00 | 1701456 | 1541670 | 65536 | 212681 | 212681 | 212681 | 0 | 732 | 208829 | 11542 | 2593 | 2408 | 210286 | 0 | 20384 | 182123 | 12075292528759505 | 12075298420659148 | 12075298420783627 | 12075292529080561 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7fe1f39f1500 | 0x7fe0c3a35c40 | 1800480 | 1614158 | 65536 | 225059 | 225059 | 225059 | 0 | 760 | 218731 | 12946 | 2874 | 2438 | 216408 | 0 | 26498 | 189749 | 12075292529126056 | 12075298420822346 | 12075298420949385 | 12075292529457642 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7fe1f39f1400 | 0x7fe0c3a35c80 | 1678672 | 1516077 | 65536 | 209833 | 209833 | 209833 | 0 | 732 | 217893 | 11382 | 2600 | 2435 | 216811 | 0 | 20770 | 180209 | 12075292529518415 | 12075298420998505 | 12075298421123304 | 12075292529818993 |
| 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 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7fe1f39f1300 | 0x7fe0c3a35cc0 | 3342816 | 3169356 | 65536 | 417851 | 417851 | 417851 | 0 | 760 | 409307 | 13077 | 2598 | 2429 | 404305 | 0 | 31843 | 365461 | 12075292529863145 | 12075298421162023 | 12075298421413701 | 12075292530390155 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7fe1f39f1a00 | 0x7fe0c3a35d00 | 3146256 | 2985162 | 65536 | 393281 | 393281 | 393281 | 0 | 732 | 395341 | 12621 | 3108 | 2432 | 383430 | 0 | 14103 | 362041 | 12075292530414510 | 12075298421466180 | 12075298421717058 | 12075292530921873 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7fe1f39f1900 | 0x7fe0c3a35d40 | 1743968 | 1572133 | 65536 | 217995 | 217995 | 217995 | 0 | 760 | 215443 | 12650 | 2604 | 2453 | 210937 | 0 | 26030 | 191123 | 12075292530946318 | 12075298421765058 | 12075298421890017 | 12075292531278435 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7fe1f39f1800 | 0x7fe0c3a35d80 | 1844560 | 1683327 | 65536 | 230569 | 230569 | 230569 | 0 | 732 | 221325 | 12318 | 2591 | 2433 | 218469 | 0 | 27174 | 196938 | 12075292531320133 | 12075298421928896 | 12075298422057215 | 12075292531652190 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7fe1f39f1700 | 0x7fe0c3a35dc0 | 1724320 | 1557628 | 65536 | 215539 | 215539 | 215539 | 0 | 760 | 214611 | 12227 | 2622 | 2437 | 214145 | 0 | 26581 | 181106 | 12075292531714796 | 12075298422106175 | 12075298422231934 | 12075292532020765 |
| 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 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7fe1f39f1600 | 0x7fe0c3a35e00 | 3209104 | 3025321 | 65536 | 401137 | 401137 | 401137 | 0 | 732 | 412037 | 12526 | 2593 | 2439 | 403231 | 0 | 28739 | 363406 | 12075292532071549 | 12075298422273213 | 12075298422531451 | 12075292532575115 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7fe1f39f1500 | 0x7fe0c3a35e40 | 3215904 | 3019639 | 65536 | 401987 | 401987 | 401987 | 0 | 760 | 394851 | 12824 | 2783 | 2430 | 391992 | 0 | 32575 | 365681 | 12075292532599320 | 12075298422581850 | 12075298422828888 | 12075292533092556 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7fe1f39f1400 | 0x7fe0c3a35e80 | 1713808 | 1553004 | 65536 | 214225 | 214225 | 214225 | 0 | 732 | 216189 | 11713 | 2563 | 2919 | 214383 | 0 | 22506 | 189647 | 12075292533116631 | 12075298422880728 | 12075298423006327 | 12075292533440773 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7fe1f39f1300 | 0x7fe0c3a35ec0 | 1851680 | 1670004 | 65536 | 231459 | 231459 | 231459 | 0 | 760 | 221091 | 12993 | 2598 | 2447 | 228399 | 0 | 29188 | 194678 | 12075292533490285 | 12075298423048566 | 12075298423176565 | 12075292533811312 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7fe1f39f1a00 | 0x7fe0c3a35f00 | 1710864 | 1526921 | 65536 | 213857 | 213857 | 213857 | 0 | 732 | 214445 | 11880 | 2600 | 2441 | 210589 | 0 | 24412 | 179718 | 12075292533874379 | 12075298423225525 | 12075298423350643 | 12075292534181930 |
| 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 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7fe1f39f1900 | 0x7fe0c3a35f40 | 3298656 | 3124696 | 65536 | 412331 | 412331 | 412331 | 0 | 760 | 408027 | 13517 | 2599 | 2430 | 400792 | 0 | 37063 | 360086 | 12075292534233636 | 12075298423388723 | 12075298423642641 | 12075292534749525 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7fe1f39f1800 | 0x7fe0c3a35f80 | 3171472 | 3001489 | 65536 | 396433 | 396433 | 396433 | 0 | 732 | 381733 | 12789 | 2602 | 2449 | 388821 | 0 | 14453 | 366555 | 12075292534771967 | 12075298423694320 | 12075298423941998 | 12075292535283477 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7fe1f39f1700 | 0x7fe0c3a35fc0 | 1756320 | 1582148 | 65536 | 219539 | 219539 | 219539 | 0 | 760 | 214891 | 12442 | 2846 | 2429 | 208401 | 0 | 25356 | 193369 | 12075292535310768 | 12075298423992558 | 12075298424117836 | 12075292535633237 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7fe1f39f1600 | 0x7fe0c3a36000 | 1778704 | 1617843 | 65536 | 222337 | 222337 | 222337 | 0 | 732 | 222645 | 12326 | 2584 | 2430 | 222336 | 0 | 25229 | 191705 | 12075292535683871 | 12075298424160076 | 12075298424296875 | 12075292535992785 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7fe1f39f1500 | 0x7fe0c3a36040 | 1751520 | 1578031 | 65536 | 218939 | 218939 | 218939 | 0 | 760 | 214451 | 12181 | 2864 | 2438 | 216200 | 0 | 24961 | 181674 | 12075292536055802 | 12075298424346154 | 12075298424471113 | 12075292536358845 |
| 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 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7fe1f39f1400 | 0x7fe0c3a36080 | 3321424 | 3145320 | 65536 | 415177 | 415177 | 415177 | 0 | 732 | 404773 | 13683 | 2601 | 2418 | 407804 | 0 | 28173 | 371902 | 12075292536409249 | 12075298424509193 | 12075298424767431 | 12075292536895022 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7fe1f39f1300 | 0x7fe0c3a360c0 | 3202976 | 3005961 | 65536 | 400371 | 400371 | 400371 | 0 | 760 | 385707 | 12842 | 2612 | 2437 | 392593 | 0 | 33667 | 363803 | 12075292536922162 | 12075298424818790 | 12075298425068388 | 12075292537431769 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7fe1f39f1a00 | 0x7fe0c3a36100 | 1779984 | 1616818 | 65536 | 222497 | 222497 | 222497 | 0 | 1003 | 282030 | 11781 | 2592 | 2433 | 212997 | 0 | 25290 | 184869 | 12075292537456044 | 12075298425123747 | 12075298425248226 | 12075292537785987 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7fe1f39f1900 | 0x7fe0c3a36140 | 1872672 | 1681470 | 65536 | 234083 | 234083 | 234083 | 0 | 787 | 233744 | 12438 | 2607 | 2439 | 226919 | 0 | 27531 | 198589 | 12075292537835920 | 12075298425289186 | 12075298425431745 | 12075292538159912 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7fe1f39f1800 | 0x7fe0c3a36180 | 1732688 | 1557290 | 65536 | 216585 | 216585 | 216585 | 0 | 959 | 275578 | 11778 | 2593 | 2432 | 209166 | 0 | 23470 | 184659 | 12075292538223861 | 12075298425479744 | 12075298425605183 | 12075292538530320 |
| 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 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7fe1f39f1700 | 0x7fe0c3a361c0 | 3347104 | 3170695 | 65536 | 418387 | 418387 | 418387 | 0 | 760 | 416835 | 13046 | 2471 | 2437 | 405241 | 0 | 35051 | 371238 | 12075292538574663 | 12075298425643423 | 12075298425902620 | 12075292539094308 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7fe1f39f1600 | 0x7fe0c3a36200 | 3161488 | 2999062 | 65536 | 395185 | 395185 | 395185 | 0 | 1003 | 458158 | 12162 | 2603 | 2898 | 445644 | 0 | 32133 | 356931 | 12075292539118583 | 12075298425953820 | 12075298426197818 | 12075292539631025 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7fe1f39f1500 | 0x7fe0c3a36240 | 1804832 | 1630035 | 65536 | 225603 | 225603 | 225603 | 0 | 787 | 213208 | 12184 | 2655 | 2822 | 221776 | 0 | 25289 | 186937 | 12075292539655922 | 12075298426251737 | 12075298426376696 | 12075292539991796 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7fe1f39f1400 | 0x7fe0c3a36280 | 1923600 | 1762688 | 65536 | 240449 | 240449 | 240449 | 0 | 758 | 239939 | 12076 | 2587 | 2418 | 239580 | 0 | 27876 | 208307 | 12075292540042440 | 12075298426416536 | 12075298426566454 | 12075292540371181 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7fe1f39f1300 | 0x7fe0c3a362c0 | 1761056 | 1594001 | 65536 | 220131 | 220131 | 220131 | 0 | 760 | 209019 | 12007 | 2599 | 2427 | 207803 | 0 | 24998 | 191627 | 12075292540452031 | 12075298426630614 | 12075298426756213 | 12075292540755855 |
| 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 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7fe1f39f1a00 | 0x7fe0c3a36300 | 3329168 | 3170314 | 65536 | 416145 | 416145 | 416145 | 0 | 732 | 412301 | 12572 | 2608 | 2439 | 408255 | 0 | 38268 | 371502 | 12075292540806059 | 12075298426795252 | 12075298427049010 | 12075292541300287 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7fe1f39f1900 | 0x7fe0c3a36340 | 3192352 | 3013827 | 65536 | 399043 | 399043 | 399043 | 0 | 1084 | 443202 | 12785 | 2605 | 2886 | 383496 | 0 | 35525 | 359353 | 12075292541326215 | 12075298427103889 | 12075298427348847 | 12075292541818179 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7fe1f39f1800 | 0x7fe0c3a36380 | 1769552 | 1612634 | 65536 | 221193 | 221193 | 221193 | 0 | 787 | 213256 | 11328 | 2593 | 2416 | 207734 | 0 | 22134 | 181383 | 12075292541841132 | 12075298427403567 | 12075298427529166 | 12075292542172017 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7fe1f39f1700 | 0x7fe0c3a363c0 | 2013472 | 1845948 | 65536 | 251683 | 251683 | 251683 | 0 | 758 | 252427 | 12660 | 2590 | 2438 | 249608 | 0 | 28446 | 217501 | 12075292542224785 | 12075298427568525 | 12075298427725964 | 12075292542561300 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7fe1f39f1600 | 0x7fe0c3a36400 | 1810448 | 1647595 | 65536 | 226305 | 226305 | 226305 | 0 | 760 | 209675 | 11777 | 2593 | 2432 | 210270 | 0 | 23907 | 184501 | 12075292542624718 | 12075298427773803 | 12075298427898602 | 12075292542934654 |
| 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 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7fe1f39f1500 | 0x7fe0c3a36440 | 3313760 | 3120225 | 65536 | 414219 | 414219 | 414219 | 0 | 732 | 410045 | 13032 | 2893 | 2435 | 407715 | 0 | 38170 | 364802 | 12075292542985398 | 12075298427936522 | 12075298428189480 | 12075292543491879 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7fe1f39f1400 | 0x7fe0c3a36480 | 3191248 | 3013773 | 65536 | 398905 | 398905 | 398905 | 0 | 760 | 395251 | 12751 | 2599 | 2438 | 383752 | 0 | 24016 | 355886 | 12075292543517146 | 12075298428242119 | 12075298428486757 | 12075292543982301 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7fe1f39f1300 | 0x7fe0c3a364c0 | 1744864 | 1581137 | 65536 | 218107 | 218107 | 218107 | 0 | 732 | 220453 | 12416 | 2596 | 2420 | 217474 | 0 | 27631 | 191431 | 12075292544036281 | 12075298428537956 | 12075298428663395 | 12075292544341007 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7fe1f39f1a00 | 0x7fe0c3a36500 | 2097488 | 1943403 | 65536 | 262185 | 262185 | 262185 | 0 | 760 | 263571 | 12424 | 2594 | 2431 | 260695 | 0 | 27836 | 228189 | 12075292544392543 | 12075298428701955 | 12075298428867553 | 12075292544729279 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7fe1f39f1900 | 0x7fe0c3a36540 | 1754016 | 1585466 | 65536 | 219251 | 219251 | 219251 | 0 | 732 | 208853 | 12218 | 2967 | 2428 | 212394 | 0 | 26102 | 184543 | 12075292544792767 | 12075298428916673 | 12075298429042752 | 12075292545097363 |
| 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 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7fe1f39f1800 | 0x7fe0c3a36580 | 3307600 | 3133837 | 65536 | 413449 | 413449 | 413449 | 0 | 760 | 401379 | 13308 | 2594 | 2441 | 398629 | 0 | 36003 | 369622 | 12075292545147626 | 12075298429083871 | 12075298429341309 | 12075292545622118 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7fe1f39f1700 | 0x7fe0c3a365c0 | 3081248 | 2895542 | 65536 | 385155 | 385155 | 385155 | 0 | 732 | 401845 | 13015 | 2607 | 2438 | 388784 | 0 | 31362 | 351365 | 12075292545658846 | 12075298429395869 | 12075298429643866 | 12075292546112850 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7fe1f39f1600 | 0x7fe0c3a36600 | 1773392 | 1621242 | 65536 | 221673 | 221673 | 221673 | 0 | 760 | 222803 | 11605 | 2484 | 2415 | 210711 | 0 | 25472 | 186869 | 12075292546154016 | 12075298429695226 | 12075298429820185 | 12075292546463040 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7fe1f39f1500 | 0x7fe0c3a36640 | 2205472 | 2040326 | 65536 | 275683 | 275683 | 275683 | 0 | 732 | 275213 | 13183 | 2480 | 2436 | 274370 | 0 | 30375 | 240477 | 12075292546513434 | 12075298429859384 | 12075298430032183 | 12075292546863995 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7fe1f39f1400 | 0x7fe0c3a36680 | 1764432 | 1603659 | 65536 | 220553 | 220553 | 220553 | 0 | 760 | 219027 | 11824 | 2473 | 2433 | 207621 | 0 | 24794 | 190055 | 12075292546929817 | 12075298430083062 | 12075298430209461 | 12075292547241306 |
| 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 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7fe1f39f1300 | 0x7fe0c3a366c0 | 3280928 | 3074901 | 65536 | 410115 | 410115 | 410115 | 0 | 732 | 406797 | 13781 | 2567 | 2431 | 408839 | 0 | 34813 | 362514 | 12075292547294856 | 12075298430248181 | 12075298430506899 | 12075292547786720 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7fe1f39f1a00 | 0x7fe0c3a36700 | 3174608 | 3016450 | 65536 | 396825 | 396825 | 396825 | 0 | 760 | 394979 | 12661 | 2586 | 2433 | 389269 | 0 | 29100 | 361191 | 12075292547828357 | 12075298430558738 | 12075298430809616 | 12075292548278464 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7fe1f39f1900 | 0x7fe0c3a36740 | 1819104 | 1648090 | 65536 | 227387 | 227387 | 227387 | 0 | 732 | 216053 | 12169 | 2605 | 2902 | 212432 | 0 | 26429 | 193133 | 12075292548325401 | 12075298430862735 | 12075298430988014 | 12075292548637370 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7fe1f39f1800 | 0x7fe0c3a36780 | 2300880 | 2145738 | 65536 | 287609 | 287609 | 287609 | 0 | 760 | 287971 | 13112 | 3058 | 2411 | 285771 | 0 | 29564 | 253065 | 12075292548687764 | 12075298431032494 | 12075298431215052 | 12075292549042393 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7fe1f39f1700 | 0x7fe0c3a367c0 | 1775712 | 1609391 | 65536 | 221963 | 221963 | 221963 | 0 | 732 | 218813 | 11898 | 2630 | 2446 | 213048 | 0 | 24631 | 192921 | 12075292549107694 | 12075298431263212 | 12075298431388811 | 12075292549416428 |
| 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 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7fe1f39f1600 | 0x7fe0c3a36800 | 3272144 | 3119044 | 65536 | 409017 | 409017 | 409017 | 0 | 760 | 411923 | 13594 | 2591 | 2424 | 406862 | 0 | 33844 | 369384 | 12075292549461542 | 12075298431428010 | 12075298431691368 | 12075292549925574 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7fe1f39f1500 | 0x7fe0c3a36840 | 3147936 | 2960316 | 65536 | 393491 | 393491 | 393491 | 0 | 732 | 399701 | 13630 | 2588 | 2436 | 388338 | 0 | 27098 | 357157 | 12075292549969646 | 12075298431747367 | 12075298431998885 | 12075292550423670 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7fe1f39f1400 | 0x7fe0c3a36880 | 1705936 | 1545780 | 65536 | 213241 | 213241 | 213241 | 0 | 760 | 222411 | 12597 | 2640 | 2431 | 212023 | 0 | 23952 | 187386 | 12075292550467251 | 12075298432056484 | 12075298432182083 | 12075292550764383 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7fe1f39f1300 | 0x7fe0c3a368c0 | 2412512 | 2247955 | 65536 | 301563 | 301563 | 301563 | 0 | 732 | 301909 | 13086 | 2612 | 2879 | 299615 | 0 | 32083 | 264757 | 12075292550814155 | 12075298432220323 | 12075298432411361 | 12075292551207396 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7fe1f39f1a00 | 0x7fe0c3a36900 | 1738128 | 1573638 | 65536 | 217265 | 217265 | 217265 | 0 | 760 | 219955 | 11458 | 2592 | 2435 | 215971 | 0 | 23782 | 186805 | 12075292551262168 | 12075298432458881 | 12075298432584800 | 12075292551570841 |
| 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 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7fe1f39f1900 | 0x7fe0c3a36940 | 3908832 | 3344484 | 65536 | 488603 | 488603 | 426606 | 61997 | 732 | 438461 | 14323 | 2596 | 2430 | 432456 | 0 | 39558 | 392085 | 12075292551621565 | 12075298432623039 | 12075298432905597 | 12075292552141582 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7fe1f39f1800 | 0x7fe0c3a36980 | 3210896 | 3028439 | 65536 | 401361 | 401361 | 401361 | 0 | 760 | 387059 | 12925 | 2671 | 2448 | 386406 | 0 | 33964 | 365213 | 12075292552184361 | 12075298432955996 | 12075298433207834 | 12075292552637182 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7fe1f39f1700 | 0x7fe0c3a369c0 | 1719392 | 1558968 | 65536 | 214923 | 214923 | 214923 | 0 | 732 | 223421 | 12273 | 2607 | 2427 | 217099 | 0 | 24583 | 193787 | 12075292552682487 | 12075298433267673 | 12075298433392792 | 12075292552989076 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7fe1f39f1600 | 0x7fe0c3a36a00 | 2673744 | 2491234 | 65536 | 334217 | 334217 | 334217 | 0 | 1084 | 384346 | 13025 | 2594 | 2430 | 327392 | 0 | 33446 | 290849 | 12075292553041574 | 12075298433433592 | 12075298433643030 | 12075292553460021 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7fe1f39f1500 | 0x7fe0c3a36a40 | 1807840 | 1634194 | 65536 | 225979 | 225979 | 225979 | 0 | 787 | 226432 | 12335 | 2598 | 2428 | 221594 | 0 | 28749 | 192590 | 12075292553512329 | 12075298433703350 | 12075298433830548 | 12075292553824689 |
| 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 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7fe1f39f1400 | 0x7fe0c3a36a80 | 3764752 | 3603294 | 65536 | 470593 | 470593 | 470593 | 0 | 758 | 470059 | 14046 | 2825 | 2430 | 468984 | 0 | 40361 | 423139 | 12075292553875193 | 12075298433869748 | 12075298434175825 | 12075292554392384 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7fe1f39f1300 | 0x7fe0c3a36ac0 | 3270176 | 3091042 | 65536 | 408771 | 408771 | 408771 | 0 | 760 | 397003 | 13853 | 2598 | 2436 | 394282 | 0 | 34549 | 361650 | 12075292554433691 | 12075298434231665 | 12075298434479822 | 12075292554889117 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7fe1f39f1a00 | 0x7fe0c3a36b00 | 1787600 | 1625457 | 65536 | 223449 | 223449 | 223449 | 0 | 732 | 225573 | 12068 | 2593 | 2423 | 216287 | 0 | 24112 | 193463 | 12075292554933990 | 12075298434534062 | 12075298434661261 | 12075292555253674 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7fe1f39f1900 | 0x7fe0c3a36b40 | 2852576 | 2690978 | 65536 | 356571 | 356571 | 356571 | 0 | 760 | 356467 | 13707 | 2599 | 2439 | 353247 | 0 | 35689 | 316087 | 12075292555303337 | 12075298434700300 | 12075298434927018 | 12075292555732384 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7fe1f39f1800 | 0x7fe0c3a36b80 | 1754704 | 1573338 | 65536 | 219337 | 219337 | 219337 | 0 | 732 | 220085 | 11972 | 2592 | 2554 | 220812 | 0 | 26245 | 194478 | 12075292555795271 | 12075298434989578 | 12075298435116137 | 12075292556102932 |
| 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 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7fe1f39f1700 | 0x7fe0c3a36bc0 | 4034848 | 3873846 | 65536 | 504355 | 504355 | 504355 | 0 | 760 | 503275 | 12529 | 2985 | 2422 | 503760 | 0 | 42632 | 456733 | 12075292556152044 | 12075298435155656 | 12075298435483973 | 12075292556685174 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7fe1f39f1600 | 0x7fe0c3a36c00 | 3149264 | 2983986 | 65536 | 393657 | 393657 | 393657 | 0 | 732 | 401925 | 13568 | 2609 | 2426 | 388700 | 0 | 32917 | 366246 | 12075292556729406 | 12075298435536773 | 12075298435790691 | 12075292557175085 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7fe1f39f1500 | 0x7fe0c3a36c40 | 1824800 | 1645874 | 65536 | 228099 | 228099 | 228099 | 0 | 760 | 226171 | 12017 | 2585 | 2437 | 226185 | 0 | 27944 | 194351 | 12075292557218155 | 12075298435841090 | 12075298435969409 | 12075292557535114 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7fe1f39f1400 | 0x7fe0c3a36c80 | 3049424 | 2893578 | 65536 | 381177 | 381177 | 381177 | 0 | 732 | 381397 | 14388 | 2990 | 2417 | 379893 | 0 | 36067 | 339591 | 12075292557583664 | 12075298436012289 | 12075298436256126 | 12075292558026346 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7fe1f39f1300 | 0x7fe0c3a36cc0 | 1850592 | 1658202 | 65536 | 231323 | 231323 | 231323 | 0 | 760 | 219451 | 12396 | 2593 | 2439 | 226431 | 0 | 27369 | 196602 | 12075292558087610 | 12075298436318046 | 12075298436447965 | 12075292558402575 |
| 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 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7fe1f39f1a00 | 0x7fe0c3a36d00 | 4583760 | 4433102 | 65536 | 572969 | 572969 | 572969 | 0 | 732 | 572125 | 15263 | 2597 | 2401 | 571093 | 0 | 49426 | 520389 | 12075292558457698 | 12075298436487004 | 12075298436861881 | 12075292559024030 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7fe1f39f1900 | 0x7fe0c3a36d40 | 3298528 | 3126539 | 65536 | 412315 | 412315 | 412315 | 0 | 760 | 409003 | 13657 | 3049 | 2445 | 408521 | 0 | 35964 | 366030 | 12075292559069645 | 12075298436917080 | 12075298437175958 | 12075292559528037 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7fe1f39f1800 | 0x7fe0c3a36d80 | 1808016 | 1648121 | 65536 | 226001 | 226001 | 226001 | 0 | 732 | 228245 | 12889 | 2903 | 2431 | 223351 | 0 | 28166 | 186267 | 12075292559572900 | 12075298437231318 | 12075298437359956 | 12075292559882656 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7fe1f39f1700 | 0x7fe0c3a36dc0 | 3467296 | 3308894 | 65536 | 433411 | 433411 | 433411 | 0 | 760 | 433899 | 13712 | 2449 | 2422 | 430000 | 0 | 40922 | 389269 | 12075292559931777 | 12075298437399636 | 12075298437677394 | 12075292560421026 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7fe1f39f1600 | 0x7fe0c3a36e00 | 1765136 | 1582766 | 65536 | 220641 | 220641 | 220641 | 0 | 732 | 220165 | 13334 | 2605 | 2424 | 222206 | 0 | 28296 | 187411 | 12075292560475457 | 12075298437737873 | 12075298437873552 | 12075292560782908 |
| 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 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7fe1f39f1500 | 0x7fe0c3a36e40 | 5161888 | 5010017 | 65536 | 645235 | 645235 | 645235 | 0 | 760 | 643211 | 12285 | 2918 | 2451 | 641043 | 0 | 52555 | 587433 | 12075292560833953 | 12075298437911311 | 12075298438333548 | 12075292561458414 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7fe1f39f1400 | 0x7fe0c3a36e80 | 3253904 | 3051436 | 65536 | 406737 | 406737 | 406737 | 0 | 732 | 410757 | 13894 | 3086 | 2944 | 404838 | 0 | 35471 | 366154 | 12075292561501283 | 12075298438397547 | 12075298438659945 | 12075292561958172 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7fe1f39f1300 | 0x7fe0c3a36ec0 | 1805536 | 1643529 | 65536 | 225691 | 225691 | 225691 | 0 | 760 | 224923 | 12014 | 2592 | 2943 | 223623 | 0 | 26052 | 190657 | 12075292562007644 | 12075298438715304 | 12075298438851143 | 12075292562316468 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7fe1f39f1a00 | 0x7fe0c3a36f00 | 3885776 | 3726488 | 65536 | 485721 | 485721 | 485721 | 0 | 1003 | 529110 | 14767 | 2600 | 2894 | 527280 | 0 | 15368 | 440019 | 12075292562370478 | 12075298438890183 | 12075298439233219 | 12075292562875928 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7fe1f39f1900 | 0x7fe0c3a36f40 | 1946592 | 1791306 | 65536 | 243323 | 243323 | 243323 | 0 | 787 | 243072 | 12193 | 2603 | 2430 | 244792 | 0 | 28592 | 212073 | 12075292562939486 | 12075298439298659 | 12075298439449377 | 12075292563269809 |
| 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 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7fe1f39f1800 | 0x7fe0c3a36f80 | 6271568 | 6115247 | 65536 | 783945 | 783945 | 783945 | 0 | 758 | 783043 | 16679 | 2597 | 2808 | 807990 | 0 | 58894 | 718795 | 12075292563320954 | 12075298439489857 | 12075298440006492 | 12075292564049989 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7fe1f39f1700 | 0x7fe0c3a36fc0 | 3635360 | 3448432 | 65536 | 454419 | 454419 | 454419 | 0 | 760 | 457707 | 13593 | 2591 | 2885 | 458441 | 0 | 42270 | 409058 | 12075292564100232 | 12075298440066172 | 12075298440364889 | 12075292564593108 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7fe1f39f1600 | 0x7fe0c3a37000 | 1965328 | 1807086 | 65536 | 245665 | 245665 | 245665 | 0 | 732 | 245141 | 12640 | 2596 | 2433 | 245637 | 0 | 27081 | 212353 | 12075292564637831 | 12075298440420569 | 12075298440575287 | 12075292564960761 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7fe1f39f1500 | 0x7fe0c3a37040 | 4731808 | 4578993 | 65536 | 591475 | 591475 | 591475 | 0 | 760 | 593667 | 14902 | 2592 | 2448 | 589342 | 0 | 49586 | 537151 | 12075292565018108 | 12075298440615767 | 12075298441000243 | 12075292565610679 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7fe1f39f1400 | 0x7fe0c3a37080 | 2221904 | 2065904 | 65536 | 277737 | 277737 | 277737 | 0 | 732 | 276437 | 12743 | 2599 | 2955 | 275019 | 0 | 29433 | 242845 | 12075292565666062 | 12075298441067123 | 12075298441242001 | 12075292566012616 |
| 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 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7fe1f39f1300 | 0x7fe0c3a370c0 | 7388128 | 7233318 | 65536 | 923515 | 923515 | 923515 | 0 | 1084 | 942722 | 16390 | 2674 | 2440 | 926630 | 0 | 70150 | 851215 | 12075292566064001 | 12075298441280241 | 12075298441889675 | 12075292566873806 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7fe1f39f1a00 | 0x7fe0c3a37100 | 4341008 | 3832847 | 65536 | 542625 | 542625 | 480000 | 62625 | 787 | 496712 | 13962 | 2596 | 2434 | 496268 | 0 | 43457 | 451934 | 12075292566912688 | 12075298441945035 | 12075298442275752 | 12075292567476275 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7fe1f39f1900 | 0x7fe0c3a37140 | 2289312 | 2117978 | 65536 | 286163 | 286163 | 286163 | 0 | 758 | 283243 | 12299 | 2585 | 2429 | 281057 | 0 | 30228 | 246015 | 12075292567521800 | 12075298442336071 | 12075298442514470 | 12075292567869907 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7fe1f39f1800 | 0x7fe0c3a37180 | 5582096 | 5430131 | 65536 | 697761 | 697761 | 697761 | 0 | 760 | 697323 | 15166 | 3118 | 2401 | 695765 | 0 | 14693 | 638175 | 12075292567919920 | 12075298442555109 | 12075298443010465 | 12075292568591137 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7fe1f39f1700 | 0x7fe0c3a371c0 | 2516576 | 2357699 | 65536 | 314571 | 314571 | 314571 | 0 | 732 | 311669 | 12145 | 2591 | 2421 | 310865 | 0 | 32847 | 275385 | 12075292568652080 | 12075298443079745 | 12075298443279263 | 12075292569048737 |
| 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 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7fe1f39f1600 | 0x7fe0c3a37200 | 8512656 | 8358361 | 65536 | 1064081 | 1064081 | 1064081 | 0 | 1084 | 1075058 | 11672 | 2820 | 2803 | 1071651 | 0 | 75655 | 983117 | 12075292569100313 | 12075298443332222 | 12075298444036056 | 12075292570004313 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7fe1f39f1500 | 0x7fe0c3a37240 | 4542112 | 4379440 | 65536 | 567763 | 567763 | 567763 | 0 | 787 | 566936 | 14928 | 2599 | 2743 | 564719 | 0 | 48077 | 513829 | 12075292570049657 | 12075298444093495 | 12075298444466132 | 12075292570612523 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7fe1f39f1400 | 0x7fe0c3a37280 | 2533136 | 2386558 | 65536 | 316641 | 316641 | 316641 | 0 | 758 | 318331 | 12252 | 2594 | 2431 | 314095 | 0 | 31690 | 280157 | 12075292570656625 | 12075298444521651 | 12075298444723730 | 12075292571047050 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7fe1f39f1300 | 0x7fe0c3a372c0 | 6423392 | 6262244 | 65536 | 802923 | 802923 | 802923 | 0 | 760 | 802635 | 16032 | 2615 | 2734 | 801352 | 0 | 61212 | 736485 | 12075292571091152 | 12075298444779409 | 12075298445304844 | 12075292571804478 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7fe1f39f1a00 | 0x7fe0c3a37300 | 2799504 | 2650045 | 65536 | 349937 | 349937 | 349937 | 0 | 732 | 348181 | 12333 | 2587 | 2954 | 347020 | 0 | 34187 | 309355 | 12075292571861844 | 12075298445370924 | 12075298445594602 | 12075292572286814 |
| 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 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7fe1f39f1900 | 0x7fe0c3a37340 | 9660192 | 9490566 | 65536 | 1207523 | 1207523 | 1144857 | 62666 | 760 | 1206539 | 18700 | 2598 | 3331 | 1206019 | 0 | 85113 | 1116383 | 12075292572331006 | 12075298445649641 | 12075298446448194 | 12075292573327408 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7fe1f39f1800 | 0x7fe0c3a37380 | 5098064 | 4934083 | 65536 | 637257 | 637257 | 637257 | 0 | 732 | 636629 | 14483 | 2482 | 2656 | 636182 | 0 | 51384 | 581113 | 12075292573376379 | 12075298446507873 | 12075298446927710 | 12075292573999647 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7fe1f39f1700 | 0x7fe0c3a373c0 | 2804768 | 2654274 | 65536 | 350595 | 350595 | 350595 | 0 | 760 | 352827 | 13003 | 2591 | 2420 | 350242 | 0 | 35628 | 312923 | 12075292574053697 | 12075298446982429 | 12075298447209147 | 12075292574471343 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7fe1f39f1600 | 0x7fe0c3a37400 | 7271440 | 7114322 | 65536 | 908929 | 908929 | 908929 | 0 | 732 | 909053 | 16489 | 2588 | 2913 | 926149 | 0 | 66937 | 835121 | 12075292574520545 | 12075298447270907 | 12075298447866741 | 12075292575312586 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7fe1f39f1500 | 0x7fe0c3a37440 | 3333984 | 3177258 | 65536 | 416747 | 416747 | 416747 | 0 | 760 | 416379 | 13768 | 2886 | 2437 | 416889 | 0 | 39879 | 373745 | 12075292575373459 | 12075298447933781 | 12075298448201618 | 12075292575841930 |
| 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 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7fe1f39f1400 | 0x7fe0c3a37480 | 11896400 | 11736989 | 65536 | 1487049 | 1487049 | 1487049 | 0 | 732 | 1486325 | 20033 | 2595 | 2425 | 1485605 | 0 | 99936 | 1380575 | 12075292575888196 | 12075298448257618 | 12075298449242409 | 12075292577111609 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7fe1f39f1300 | 0x7fe0c3a374c0 | 6218976 | 6055928 | 65536 | 777371 | 777371 | 777371 | 0 | 760 | 778867 | 16768 | 2607 | 2913 | 801133 | 0 | 60942 | 713405 | 12075292577141455 | 12075298449298408 | 12075298449812964 | 12075292577917256 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7fe1f39f1a00 | 0x7fe0c3a37500 | 3380048 | 3218929 | 65536 | 422505 | 422505 | 422505 | 0 | 732 | 420821 | 13938 | 2593 | 2438 | 421000 | 0 | 38308 | 376509 | 12075292577941682 | 12075298449868323 | 12075298450139041 | 12075292578476004 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7fe1f39f1900 | 0x7fe0c3a37540 | 8999328 | 8847394 | 65536 | 1124915 | 1124915 | 1124915 | 0 | 760 | 1125251 | 18795 | 2598 | 2428 | 1122994 | 0 | 79497 | 1041109 | 12075292578504127 | 12075298450201280 | 12075298450938553 | 12075292579490179 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7fe1f39f1800 | 0x7fe0c3a37580 | 3905808 | 3748355 | 65536 | 488225 | 488225 | 488225 | 0 | 732 | 488613 | 14573 | 3129 | 2422 | 488976 | 0 | 42522 | 439851 | 12075292579530193 | 12075298451002393 | 12075298451347030 | 12075292580087849 |
| 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 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7fe1f39f1700 | 0x7fe0c3a375c0 | 14141152 | 13983516 | 65536 | 1767643 | 1767643 | 1767643 | 0 | 760 | 1767739 | 23263 | 2893 | 2424 | 1766062 | 0 | 117233 | 1643951 | 12075292580119178 | 12075298451403349 | 12075298452573898 | 12075292581547191 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7fe1f39f1600 | 0x7fe0c3a37600 | 7331024 | 7168228 | 65536 | 916377 | 916377 | 916377 | 0 | 732 | 914661 | 16864 | 2593 | 2422 | 915432 | 0 | 63863 | 847946 | 12075292581578910 | 12075298452631338 | 12075298453241732 | 12075292582441873 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7fe1f39f1500 | 0x7fe0c3a37640 | 3920608 | 3765594 | 65536 | 490075 | 490075 | 490075 | 0 | 760 | 491587 | 12471 | 2994 | 2419 | 488451 | 0 | 15700 | 443519 | 12075292582468814 | 12075298453299172 | 12075298453617409 | 12075292583050464 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7fe1f39f1400 | 0x7fe0c3a37680 | 10690768 | 10528236 | 65536 | 1336345 | 1336345 | 1336345 | 0 | 732 | 1334901 | 20231 | 2708 | 2428 | 1334818 | 0 | 92088 | 1238417 | 12075292583081211 | 12075298453669729 | 12075298454546521 | 12075292584215108 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7fe1f39f1300 | 0x7fe0c3a376c0 | 5062176 | 4879488 | 65536 | 632771 | 632771 | 632771 | 0 | 1084 | 660882 | 15395 | 2595 | 3051 | 659315 | 0 | 52569 | 571689 | 12075292584253089 | 12075298454612280 | 12075298455022676 | 12075292584910681 |
| 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 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7fe1f39f1a00 | 0x7fe0c3a37700 | 18647376 | 18498636 | 65536 | 2330921 | 2330921 | 2330921 | 0 | 787 | 2332360 | 19949 | 2916 | 2429 | 2330729 | 0 | 150145 | 2177183 | 12075292584941428 | 12075298455080596 | 12075298456629222 | 12075292586753886 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7fe1f39f1900 | 0x7fe0c3a37740 | 9596192 | 9442537 | 65536 | 1199523 | 1199523 | 1199523 | 0 | 758 | 1199635 | 19552 | 2599 | 2433 | 1196989 | 0 | 84640 | 1110857 | 12075292586778091 | 12075298456709221 | 12075298457504734 | 12075292587834774 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7fe1f39f1800 | 0x7fe0c3a37780 | 5131408 | 4955254 | 65536 | 641425 | 641425 | 641425 | 0 | 760 | 639411 | 15624 | 2563 | 2432 | 638086 | 0 | 49721 | 582901 | 12075292587862396 | 12075298457582807 | 12075298457995924 | 12075292588533543 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7fe1f39f1700 | 0x7fe0c3a377c0 | 14052960 | 13898639 | 65536 | 1756619 | 1756619 | 1756619 | 0 | 732 | 1757413 | 22882 | 2607 | 2427 | 1755235 | 0 | 115319 | 1635033 | 12075292588558228 | 12075298458078162 | 12075298459235913 | 12075292589969691 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7fe1f39f1600 | 0x7fe0c3a37800 | 9575568 | 9420806 | 65536 | 1196945 | 1196945 | 1196945 | 0 | 760 | 1196851 | 18855 | 2594 | 2973 | 1195481 | 0 | 82931 | 1109035 | 12075292590014244 | 12075298459323913 | 12075298460111267 | 12075292591039088 |
| 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 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7fe1f39f1500 | 0x7fe0c3a37840 | 36661664 | 36503946 | 65536 | 4582707 | 4582707 | 4582707 | 0 | 732 | 4582845 | 41572 | 2622 | 2811 | 4580355 | 0 | 280624 | 4296433 | 12075292591069455 | 12075298460188226 | 12075298463238443 | 12075292594376119 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7fe1f39f1400 | 0x7fe0c3a37880 | 18585680 | 18427675 | 65536 | 2323209 | 2323209 | 2323209 | 0 | 760 | 2323507 | 26106 | 2583 | 2431 | 2321815 | 0 | 150186 | 2168295 | 12075292594405413 | 12075298463315722 | 12075298464856991 | 12075292596211710 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7fe1f39f1300 | 0x7fe0c3a378c0 | 9613600 | 9457580 | 65536 | 1201699 | 1201699 | 1201699 | 0 | 732 | 1200933 | 19396 | 2454 | 2857 | 1199413 | 0 | 83162 | 1113023 | 12075292596235113 | 12075298464934110 | 12075298465722744 | 12075292597289843 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7fe1f39f1a00 | 0x7fe0c3a37900 | 27543056 | 27379725 | 65536 | 3442881 | 3442881 | 3380612 | 62269 | 760 | 3441867 | 33987 | 2594 | 2431 | 3440351 | 0 | 215539 | 3222361 | 12075292597313647 | 12075298465807383 | 12075298468089286 | 12075292599857414 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7fe1f39f1900 | 0x7fe0c3a37940 | 18598240 | 18425491 | 65536 | 2324779 | 2324779 | 2324779 | 0 | 732 | 2323061 | 27055 | 3030 | 2552 | 2318886 | 0 | 149301 | 2167267 | 12075292599903099 | 12075298468184325 | 12075298469719834 | 12075292601688336 |
| 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 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7fe1f39f1800 | 0x7fe0c3a37980 | 72681744 | 72533786 | 65536 | 9085217 | 9085217 | 9085217 | 0 | 760 | 9086211 | 64695 | 3443 | 3239 | 9084503 | 0 | 546260 | 8536989 | 12075292601717220 | 12075298469798233 | 12075298475856107 | 12075292608030991 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7fe1f39f1700 | 0x7fe0c3a379c0 | 36597664 | 36421546 | 65536 | 4574707 | 4574707 | 4574707 | 0 | 1003 | 4571238 | 41883 | 2604 | 2437 | 4571569 | 0 | 210212 | 4285366 | 12075292608062119 | 12075298475955626 | 12075298478998643 | 12075292611363203 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7fe1f39f1600 | 0x7fe0c3a37a00 | 18616976 | 18465677 | 65536 | 2327121 | 2327121 | 2327121 | 0 | 787 | 2328344 | 26489 | 2585 | 2400 | 2326326 | 0 | 150651 | 2172603 | 12075292611387799 | 12075298479081362 | 12075298480620071 | 12075292613187603 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 868852 | 868857 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7fe1f39f1500 | 0x7fe0c3a37a40 | 54496608 | 54333455 | 65536 | 6812075 | 6812075 | 6749800 | 62275 | 758 | 6811459 | 57758 | 2891 | 2973 | 6810449 | 0 | 410871 | 6393503 | 12075292613218060 | 12075298480698310 | 12075298485224356 | 12075292618006788 |