3900xt-september AMD Ryzen 9 3900XT 12-Core testing with a MSI MEG X570 GODLIKE (MS-7C34) v1.0 (1.B3 BIOS) and AMD Radeon RX 56/64 8GB on Ubuntu 22.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2209095-PTS-3900XTSE15&grs&sor .
3900xt-september Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server OpenGL Vulkan Compiler File-System Screen Resolution A AA B C AMD Ryzen 9 3900XT 12-Core @ 3.80GHz (12 Cores / 24 Threads) MSI MEG X570 GODLIKE (MS-7C34) v1.0 (1.B3 BIOS) AMD Starship/Matisse 16GB 500GB Seagate FireCuda 520 SSD ZP500GM30002 AMD Radeon RX 56/64 8GB (1630/945MHz) AMD Vega 10 HDMI Audio ASUS MG28U Realtek Device 2600 + Realtek Killer E3000 2.5GbE + Intel Wi-Fi 6 AX200 Ubuntu 22.04 5.15.0-40-generic (x86_64) GNOME Shell 42.2 X Server + Wayland 4.6 Mesa 22.0.1 (LLVM 13.0.1 DRM 3.42) 1.3.204 GCC 11.2.0 ext4 3840x2160 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Disk Details - NONE / errors=remount-ro,relatime,rw / Block Size: 4096 Processor Details - Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8701021 Graphics Details - BAR1 / Visible vRAM Size: 256 MB - vBIOS Version: 113-D0500100-102 Python Details - Python 3.10.4 Security Details - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
3900xt-september ncnn: CPU - googlenet etcd: PUT - 100 - 100 etcd: PUT - 100 - 100 - Average Latency redis: LPOP - 50 redis: LPOP - 500 etcd: PUT - 50 - 100 etcd: PUT - 50 - 100 - Average Latency unvanquished: 1920 x 1200 - Ultra unvanquished: 1920 x 1080 - High unvanquished: 1920 x 1200 - Medium mnn: SqueezeNetV1.0 mnn: squeezenetv1.1 unvanquished: 2560 x 1440 - Ultra mnn: MobileNetV2_224 redis: GET - 50 unvanquished: 1920 x 1200 - High mnn: nasnet unvanquished: 1920 x 1080 - Ultra mnn: mobilenetV3 memtier-benchmark: Redis - 500 - 1:10 unvanquished: 3840 x 2160 - Medium memtier-benchmark: Redis - 500 - 1:5 mnn: mobilenet-v1-1.0 mnn: resnet-v2-50 graphics-magick: HWB Color Space redis: SET - 500 unvanquished: 3840 x 2160 - Ultra redis: SADD - 1000 unvanquished: 2560 x 1440 - High clickhouse: 100M Rows Web Analytics Dataset, Second Run redis: SADD - 50 etcd: PUT - 500 - 100 - Average Latency graphics-magick: Rotate redis: GET - 500 redis: SET - 50 redis: SADD - 500 srsran: 4G PHY_DL_Test 100 PRB SISO 64-QAM etcd: PUT - 500 - 100 redis: LPUSH - 50 srsran: 4G PHY_DL_Test 100 PRB SISO 64-QAM unvanquished: 2560 x 1440 - Medium rocksdb: Read While Writing memtier-benchmark: Redis - 500 - 5:1 memtier-benchmark: Redis - 100 - 1:10 unvanquished: 1920 x 1080 - Medium srsran: 4G PHY_DL_Test 100 PRB SISO 256-QAM srsran: OFDM_Test memtier-benchmark: Redis - 50 - 1:1 mnn: inception-v3 redis: LPUSH - 1000 redis: SET - 1000 srsran: 4G PHY_DL_Test 100 PRB SISO 256-QAM redis: GET - 1000 redis: LPOP - 1000 unvanquished: 3840 x 2160 - High openvino: Vehicle Detection FP16 - CPU openvino: Vehicle Detection FP16 - CPU svt-av1: Preset 10 - Bosphorus 4K blosc: blosclz shuffle graphics-magick: Resizing etcd: PUT - 50 - 1000 etcd: PUT - 50 - 1000 - Average Latency memtier-benchmark: Redis - 50 - 1:5 memtier-benchmark: Redis - 100 - 1:5 openvino: Machine Translation EN To DE FP16 - CPU srsran: 4G PHY_DL_Test 100 PRB MIMO 256-QAM svt-av1: Preset 12 - Bosphorus 1080p openvino: Machine Translation EN To DE FP16 - CPU srsran: 4G PHY_DL_Test 100 PRB MIMO 256-QAM svt-av1: Preset 12 - Bosphorus 4K memtier-benchmark: Redis - 50 - 5:1 memtier-benchmark: Redis - 50 - 1:10 natron: Spaceship svt-av1: Preset 8 - Bosphorus 4K rocksdb: Rand Read clickhouse: 100M Rows Web Analytics Dataset, First Run / Cold Cache ncnn: Vulkan GPU - shufflenet-v2 memtier-benchmark: Redis - 100 - 5:1 svt-av1: Preset 8 - Bosphorus 1080p openvino: Person Detection FP32 - CPU unpack-linux: linux-5.19.tar.xz redis: LPUSH - 500 ncnn: Vulkan GPU - FastestDet graphics-magick: Noise-Gaussian clickhouse: 100M Rows Web Analytics Dataset, Third Run graphics-magick: Swirl ncnn: CPU - resnet50 build-wasmer: Time To Compile gravitymark: 1920 x 1080 - OpenGL memtier-benchmark: Redis - 500 - 1:1 dragonflydb: 50 - 5:1 openvino: Person Detection FP32 - CPU node-web-tooling: openvino: Face Detection FP16 - CPU blosc: blosclz bitshuffle gravitymark: 3840 x 2160 - OpenGL svt-av1: Preset 10 - Bosphorus 1080p srsran: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM blender: BMW27 - CPU-Only openvino: Face Detection FP16 - CPU ncnn: Vulkan GPU - vision_transformer srsran: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM blender: Classroom - CPU-Only ncnn: CPU - blazeface etcd: RANGE - 50 - 100 dragonflydb: 50 - 1:1 ncnn: Vulkan GPU - efficientnet-b0 ncnn: CPU-v2-v2 - mobilenet-v2 svt-av1: Preset 4 - Bosphorus 4K build-python: Default ncnn: CPU - vgg16 ncnn: CPU - vision_transformer ncnn: Vulkan GPU-v2-v2 - mobilenet-v2 openvino: Person Detection FP16 - CPU ncnn: CPU - mobilenet build-php: Time To Compile ncnn: CPU - efficientnet-b0 ncnn: Vulkan GPU - mobilenet blender: Fishy Cat - CPU-Only openvino: Person Detection FP16 - CPU srsran: 4G PHY_DL_Test 100 PRB MIMO 64-QAM ncnn: CPU - yolov4-tiny blender: Pabellon Barcelona - CPU-Only lammps: Rhodopsin Protein ncnn: Vulkan GPU - alexnet ncnn: CPU - mnasnet etcd: RANGE - 50 - 1000 - Average Latency etcd: RANGE - 100 - 100 build-python: Released Build, PGO + LTO Optimized ncnn: CPU - regnety_400m openvino: Face Detection FP16-INT8 - CPU etcd: RANGE - 100 - 1000 - Average Latency dragonflydb: 200 - 5:1 etcd: PUT - 100 - 1000 - Average Latency gravitymark: 2560 x 1440 - OpenGL etcd: PUT - 500 - 1000 ncnn: Vulkan GPU - yolov4-tiny build-erlang: Time To Compile rocksdb: Read Rand Write Rand srsran: 4G PHY_DL_Test 100 PRB MIMO 64-QAM openvino: Person Vehicle Bike Detection FP16 - CPU ncnn: CPU - squeezenet_ssd openvino: Person Vehicle Bike Detection FP16 - CPU dragonflydb: 200 - 1:5 openvino: Age Gender Recognition Retail 0013 FP16 - CPU ncnn: Vulkan GPU - mnasnet ncnn: Vulkan GPU - squeezenet_ssd etcd: PUT - 500 - 1000 - Average Latency gravitymark: 1920 x 1200 - OpenGL openvino: Age Gender Recognition Retail 0013 FP16 - CPU svt-av1: Preset 4 - Bosphorus 1080p rocksdb: Update Rand ncnn: CPU-v3-v3 - mobilenet-v3 dragonflydb: 200 - 1:1 openvino: Face Detection FP16-INT8 - CPU etcd: PUT - 100 - 1000 lammps: 20k Atoms ncnn: CPU - resnet18 etcd: RANGE - 100 - 1000 ncnn: CPU - FastestDet ncnn: CPU - alexnet gravitymark: 2560 x 1440 - Vulkan graphics-magick: Enhanced brl-cad: VGR Performance Metric ncnn: Vulkan GPU - blazeface gravitymark: 3840 x 2160 - Vulkan blender: Barbershop - CPU-Only ncnn: CPU - shufflenet-v2 ncnn: Vulkan GPU - resnet50 astcenc: Fast compress-7zip: Decompression Rating rocksdb: Seq Fill graphics-magick: Sharpen etcd: RANGE - 500 - 1000 etcd: RANGE - 500 - 100 ncnn: Vulkan GPU - regnety_400m etcd: RANGE - 50 - 1000 ncnn: Vulkan GPU - googlenet gravitymark: 1920 x 1200 - Vulkan gravitymark: 1920 x 1080 - Vulkan ncnn: Vulkan GPU - resnet18 primesieve: 1e12 rocksdb: Rand Fill Sync memtier-benchmark: Redis - 100 - 1:1 compress-7zip: Compression Rating rocksdb: Rand Fill openvino: Weld Porosity Detection FP16-INT8 - CPU aircrack-ng: openvino: Weld Porosity Detection FP16-INT8 - CPU openvino: Vehicle Detection FP16-INT8 - CPU build-nodejs: Time To Compile openvino: Vehicle Detection FP16-INT8 - CPU openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU primesieve: 1e13 dragonflydb: 50 - 1:5 ncnn: Vulkan GPU - vgg16 astcenc: Exhaustive astcenc: Thorough astcenc: Medium openvino: Weld Porosity Detection FP16 - CPU openvino: Weld Porosity Detection FP16 - CPU openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU ncnn: Vulkan GPU-v3-v3 - mobilenet-v3 etcd: RANGE - 500 - 1000 - Average Latency etcd: RANGE - 500 - 100 - Average Latency etcd: RANGE - 100 - 100 - Average Latency etcd: RANGE - 50 - 100 - Average Latency clickhouse: A AA B C 15.11 75898.3301 1.3 2668279.75 2489960.5 78352.9225 1.3 268.6 371.5 290.3 6.116 4.098 317.1 4.002 2522240.5 333.9 13.268 264.2 2.053 277.6 1956692.55 5.205 32.121 1410 1828453.75 269.7 1944702.25 287.4 1965904.5 1.3 746 2329306.75 1680645.88 2113398.5 166.3 77475.5478 1626151.25 384.4 276.8 2614220 1601060.47 1852262.31 285.6 410.8 152100000 1810859.67 28.557 1659306 1709316.62 174.5 2213727.5 1564536.5 276.6 170.86 35.09 74.161 16319.2 1456 94397.2765 10.6 1911666.23 1824325.88 203.27 161.8 346.647 29.48 407.5 100.169 1684780.17 1891611.75 3.2 41.883 60836317 2.47 1648819.65 111.03 1.92 6.885 1655878.12 2.88 375 710 20.87 55.918 104.1 2772545.65 3084.38 11.41 2269.21 9276.4 64.2 234.535 109.2 100.04 2.64 153.75 61.4 257.49 2.09 78944.0628 2920540.96 7.73 4.63 1.875 16.499 49.1 155.14 2.41 3099 14.02 52.74 6.45 8.42 125.98 1.91 153.7 25.75 321.22 9.382 2.05 4.18 10.5 76759.9354 254.067 13.75 4.35 10.9 2581692.96 11 88.9 77982.748 11.45 82.548 1918881 384 17.23 21.03 347.84 2849837.44 1.26 2.52 5.13 12.8 103.1 9457.64 5.218 550239 4.06 2678725.83 1378.25 90990.3655 9.401 12.62 91454.5468 5.62 9.94 90.2 309 1.59 64.4 1032.04 4.84 5.05 186.9099 92591 1059712 199 77738.8612 77585.9498 4.25 94964.8661 5.09 104.4 104.6 2.68 13.88 13085 1696795.22 87251 914759 28.03 45430.832 427.87 369.89 412.357 16.21 12924.91 174.017 3129187.64 5.58 0.7872 7.2108 60.9154 302.2 19.83 0.92 3.07 12.8 1.3 1.3 1.3 33.08 76528.4826 1.3 1561893.5 1484164.5 78823.2849 1.3 365.1 276 282.1 7.699 5.094 340.9 4.95 2079443.25 275.9 16.042 264.9 2.408 1868279.59 275.7 5.883 36.1 1334 1797752.75 277.2 1904873.75 266.2 152.36 2004169.75 1.3 717 2177739.5 1757006.62 1984162.5 163.7 77587.4382 1556351.25 381.5 275.8 2597712 1682664.97 1816335.46 282.7 411.6 145400000 1739112.82 29.868 1652420.5 1692135 174.4 2307918 1516645.12 268.9 173.53 34.55 75.625 16165.9 1431 94162.7765 10.6 1868299.86 1794814.33 209.5 162.1 354.967 28.62 407.7 103.527 1631076.43 1909295.85 3.1 43.188 60052818 141.26 2.5 1640264.17 113.974 1.89 6.816 1619934.5 2.84 370 164.16 703 21.35 55.394 106 2828285.63 3105.06 11.38 2279.05 9131.8 64.5 235.312 109.1 98.54 2.63 153.04 61.3 254.68 2.1 77874.5773 2907432.83 7.73 4.65 1.897 16.506 49.72 157.08 2.43 3123.95 14.17 53.012 6.52 8.42 126.53 1.9 153.8 25.73 318.03 9.32 2.07 4.21 10.5 76764.8229 255.927 13.82 4.31 11 2575239.57 11.1 89.2 77975.9952 11.4 83.223 1908955 384.1 17.21 21.03 348.24 2872811.95 1.25 2.54 5.16 12.8 103.9 9530.87 5.2 547827 4.09 2698410.83 1387 90337.6207 9.359 12.68 91001.3671 5.65 9.99 90.2 308 187035 1.6 64.4 1029.03 4.87 5.08 187.9758 92604 1057965 199 78128.3938 77604.2776 4.25 94925.4009 5.1 104.4 104.6 2.69 13.928 13069 1699071.04 87486 916583 28.07 45409.453 427.35 369.9 411.323 16.21 12948.36 173.897 3135276.2 5.58 0.7866 7.1996 60.8401 302.44 19.82 0.92 3.07 12.8 1.3 1.3 1.3 15.21 76772.8591 1.3 1607074 1582056.5 78206.3524 1.3 288.6 293.2 372.4 6.201 4.147 275.4 4.336 2240760.5 284.7 13.922 303.1 2.188 1741550.91 269.7 1717057.55 5.336 32.686 1340 1667975.38 254.6 2065007.5 279.1 157.24 2064020.5 1.3 720 2269879 1643631 2029669 166.3 77587.3129 1634363 385 288.5 2643393 1918907.4 271.6 409.7 144100000 1719792.39 28.38 1581548.5 1756954.75 174.4 2276087.5 1586939.12 273.1 166.57 35.99 72.547 16330.8 1425 94329.6742 10.6 1844254.53 1811033.68 210.33 163.9 352.19 28.5 411.8 101.896 1642719.18 1875260.09 3.2 42.947 59015149 137.77 2.51 1621199.15 113.765 1.91 6.708 1614598.75 2.88 369 164.51 703 20.9 56.583 103.8 1624385.73 2808028.85 3092.99 11.2 2238.36 9116.1 63.6 237.139 109 98.5 2.67 155.34 61.3 254.59 2.11 78644.0984 2934355.48 7.65 4.64 1.899 16.531 49.31 155.89 2.42 3120.76 14.05 53.336 6.48 8.51 125.77 1.9 153.6 25.87 319.01 9.356 2.07 4.19 10.6 76892.649 256.385 13.88 4.31 11 2558359.14 11 89.7 77402.7592 11.45 82.507 1909640 382.9 17.35 21.16 345.45 2869778.7 1.26 2.53 5.12 12.9 103.7 9479.38 5.179 546189 4.07 2678724.09 1385.55 90993.3897 9.418 12.64 90811.024 5.65 9.92 90.1 308 188216 1.6 64.2 1033.81 4.87 5.07 187.2165 92125 1054349 199 78090.4598 77467.6397 4.27 94577.7159 5.1 104.4 104.8 2.68 13.908 13040 1694596.39 87489 917048 28.11 45339.305 426.73 368.92 412.148 16.25 12954.74 174.23 3135021.28 5.57 0.7858 7.2038 60.8701 302.53 19.81 0.92 3.07 12.8 1.3 1.3 1.3 15.09 39885.1633 2.5 1584211.88 1488288.88 47230.9782 2.1 265.9 347.1 333.3 6.419 4.232 328.5 4.364 2154908 279.8 13.903 315.1 2.188 2002479.02 308.6 1768277.08 5.282 32.383 1284 1761153 253.9 1972683.38 280.6 164.39 1913001 1.4 697 2222756 1739321.38 1980390.38 174.5 72877.7202 1535984.25 405.5 271.6 2749536 1692892.31 1868139.8 270.4 432.6 145800000 1730287.32 29.313 1605826.75 1678740 182.5 2205646 1557074.5 281.1 174.02 34.45 72.694 15704.2 1402 90956.379 11 1865191.56 1857393.23 206.98 167.4 358.604 28.94 421.3 101.6 1663746.58 1936392.38 3.2 43.017 59735063 141.89 2.52 1666964.92 113.015 1.94 6.814 1623722 2.91 366 160.78 694 20.87 56.57 104.6 1591304.98 2819421.36 3044.33 11.41 2250.83 9159 63.4 238.439 107.5 98.52 2.65 153.44 60.5 253.84 2.12 78992.0959 2949072.75 7.74 4.69 1.889 16.71 49.31 156.99 2.44 3087.45 14.18 53.266 6.5 8.45 125.2 1.92 152.2 25.99 319.32 9.291 2.07 4.22 10.5 76167.5711 256.474 13.86 4.31 10.9 2574045.53 11 89.1 78092.7111 11.5 83 1924607 381 17.3 21.2 346.46 2859261.77 1.25 2.54 5.13 12.8 103.4 9527.71 5.206 549826 4.09 2685467.32 1388.28 90622.198 9.351 12.59 91457.694 5.66 9.92 89.6 307 188128 1.6 64 1027.44 4.87 5.08 187.3579 92255 1059729 198 78062.458 77235.7439 4.26 94756.8235 5.11 104 104.4 2.69 13.893 13076 1693867.55 87228 917383 28.11 45303.348 426.7 369.83 411.677 16.21 12937 174.29 3129879.97 5.58 0.7865 7.2072 60.8695 302.39 19.82 0.92 3.07 12.8 1.3 1.3 1.3 OpenBenchmarking.org
NCNN Target: CPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: googlenet C A B AA 8 16 24 32 40 15.09 15.11 15.21 33.08 MIN: 14.47 / MAX: 16.27 MIN: 14.47 / MAX: 16.25 MIN: 14.46 / MAX: 16.37 MIN: 14.26 / MAX: 3907.66 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
etcd Test: PUT - Connections: 100 - Clients: 100 OpenBenchmarking.org Requests/sec, More Is Better etcd 3.5.4 Test: PUT - Connections: 100 - Clients: 100 B AA A C 16K 32K 48K 64K 80K 76772.86 76528.48 75898.33 39885.16
etcd Test: PUT - Connections: 100 - Clients: 100 - Average Latency OpenBenchmarking.org ms, Fewer Is Better etcd 3.5.4 Test: PUT - Connections: 100 - Clients: 100 - Average Latency A AA B C 0.5625 1.125 1.6875 2.25 2.8125 1.3 1.3 1.3 2.5
Redis Test: LPOP - Parallel Connections: 50 OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: LPOP - Parallel Connections: 50 A B C AA 600K 1200K 1800K 2400K 3000K 2668279.75 1607074.00 1584211.88 1561893.50 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Redis Test: LPOP - Parallel Connections: 500 OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: LPOP - Parallel Connections: 500 A B C AA 500K 1000K 1500K 2000K 2500K 2489960.50 1582056.50 1488288.88 1484164.50 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
etcd Test: PUT - Connections: 50 - Clients: 100 OpenBenchmarking.org Requests/sec, More Is Better etcd 3.5.4 Test: PUT - Connections: 50 - Clients: 100 AA A B C 20K 40K 60K 80K 100K 78823.28 78352.92 78206.35 47230.98
etcd Test: PUT - Connections: 50 - Clients: 100 - Average Latency OpenBenchmarking.org ms, Fewer Is Better etcd 3.5.4 Test: PUT - Connections: 50 - Clients: 100 - Average Latency A AA B C 0.4725 0.945 1.4175 1.89 2.3625 1.3 1.3 1.3 2.1
Unvanquished Resolution: 1920 x 1200 - Effects Quality: Ultra OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.53 Resolution: 1920 x 1200 - Effects Quality: Ultra AA B A C 80 160 240 320 400 365.1 288.6 268.6 265.9
Unvanquished Resolution: 1920 x 1080 - Effects Quality: High OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.53 Resolution: 1920 x 1080 - Effects Quality: High A C B AA 80 160 240 320 400 371.5 347.1 293.2 276.0
Unvanquished Resolution: 1920 x 1200 - Effects Quality: Medium OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.53 Resolution: 1920 x 1200 - Effects Quality: Medium B C A AA 80 160 240 320 400 372.4 333.3 290.3 282.1
Mobile Neural Network Model: SqueezeNetV1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: SqueezeNetV1.0 A B C AA 2 4 6 8 10 6.116 6.201 6.419 7.699 MIN: 6.05 / MAX: 6.55 MIN: 6.12 / MAX: 13.82 MIN: 6.35 / MAX: 7.41 MIN: 6.51 / MAX: 58.65 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Mobile Neural Network Model: squeezenetv1.1 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: squeezenetv1.1 A B C AA 1.1462 2.2924 3.4386 4.5848 5.731 4.098 4.147 4.232 5.094 MIN: 4.05 / MAX: 5.82 MIN: 4.1 / MAX: 4.58 MIN: 4.18 / MAX: 4.86 MIN: 3.95 / MAX: 93.8 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Unvanquished Resolution: 2560 x 1440 - Effects Quality: Ultra OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.53 Resolution: 2560 x 1440 - Effects Quality: Ultra AA C A B 70 140 210 280 350 340.9 328.5 317.1 275.4
Mobile Neural Network Model: MobileNetV2_224 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: MobileNetV2_224 A B C AA 1.1138 2.2276 3.3414 4.4552 5.569 4.002 4.336 4.364 4.950 MIN: 3.96 / MAX: 5.11 MIN: 4.29 / MAX: 4.88 MIN: 4.32 / MAX: 4.77 MIN: 4.18 / MAX: 114.69 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Redis Test: GET - Parallel Connections: 50 OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: GET - Parallel Connections: 50 A B C AA 500K 1000K 1500K 2000K 2500K 2522240.50 2240760.50 2154908.00 2079443.25 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Unvanquished Resolution: 1920 x 1200 - Effects Quality: High OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.53 Resolution: 1920 x 1200 - Effects Quality: High A B C AA 70 140 210 280 350 333.9 284.7 279.8 275.9
Mobile Neural Network Model: nasnet OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: nasnet A C B AA 4 8 12 16 20 13.27 13.90 13.92 16.04 MIN: 13.15 / MAX: 21.58 MIN: 13.81 / MAX: 14.56 MIN: 13.83 / MAX: 14.72 MIN: 13.24 / MAX: 59.16 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Unvanquished Resolution: 1920 x 1080 - Effects Quality: Ultra OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.53 Resolution: 1920 x 1080 - Effects Quality: Ultra C B AA A 70 140 210 280 350 315.1 303.1 264.9 264.2
Mobile Neural Network Model: mobilenetV3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: mobilenetV3 A B C AA 0.5418 1.0836 1.6254 2.1672 2.709 2.053 2.188 2.188 2.408 MIN: 2.03 / MAX: 2.49 MIN: 2.16 / MAX: 2.54 MIN: 2.16 / MAX: 2.51 MIN: 2.16 / MAX: 26.83 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
memtier_benchmark Protocol: Redis - Clients: 500 - Set To Get Ratio: 1:10 OpenBenchmarking.org Ops/sec, More Is Better memtier_benchmark 1.4 Protocol: Redis - Clients: 500 - Set To Get Ratio: 1:10 C AA B 400K 800K 1200K 1600K 2000K 2002479.02 1868279.59 1741550.91 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Unvanquished Resolution: 3840 x 2160 - Effects Quality: Medium OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.53 Resolution: 3840 x 2160 - Effects Quality: Medium C A AA B 70 140 210 280 350 308.6 277.6 275.7 269.7
memtier_benchmark Protocol: Redis - Clients: 500 - Set To Get Ratio: 1:5 OpenBenchmarking.org Ops/sec, More Is Better memtier_benchmark 1.4 Protocol: Redis - Clients: 500 - Set To Get Ratio: 1:5 A B C 400K 800K 1200K 1600K 2000K 1956692.55 1837227.79 1768277.08 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Mobile Neural Network Model: mobilenet-v1-1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: mobilenet-v1-1.0 A C B AA 1.3237 2.6474 3.9711 5.2948 6.6185 5.205 5.282 5.336 5.883 MIN: 5.08 / MAX: 7.3 MIN: 5.18 / MAX: 5.73 MIN: 5.25 / MAX: 5.82 MIN: 5.14 / MAX: 33.46 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Mobile Neural Network Model: resnet-v2-50 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: resnet-v2-50 A C B AA 8 16 24 32 40 32.12 32.38 32.69 36.10 MIN: 31.61 / MAX: 40.21 MIN: 31.76 / MAX: 39.9 MIN: 32.09 / MAX: 41.41 MIN: 29.81 / MAX: 128.2 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
GraphicsMagick Operation: HWB Color Space OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: HWB Color Space A B AA C 300 600 900 1200 1500 1410 1340 1334 1284 1. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
Redis Test: SET - Parallel Connections: 500 OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: SET - Parallel Connections: 500 A AA C B 400K 800K 1200K 1600K 2000K 1828453.75 1797752.75 1761153.00 1667975.38 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Unvanquished Resolution: 3840 x 2160 - Effects Quality: Ultra OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.53 Resolution: 3840 x 2160 - Effects Quality: Ultra AA A B C 60 120 180 240 300 277.2 269.7 254.6 253.9
Redis Test: SADD - Parallel Connections: 1000 OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: SADD - Parallel Connections: 1000 B C A AA 400K 800K 1200K 1600K 2000K 2065007.50 1972683.38 1944702.25 1904873.75 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Unvanquished Resolution: 2560 x 1440 - Effects Quality: High OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.53 Resolution: 2560 x 1440 - Effects Quality: High A C B AA 60 120 180 240 300 287.4 280.6 279.1 266.2
ClickHouse 100M Rows Web Analytics Dataset, Second Run OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.5.4.19 100M Rows Web Analytics Dataset, Second Run C B AA 40 80 120 160 200 164.39 157.24 152.36 MIN: 8.21 / MAX: 20000 MIN: 7.89 / MAX: 6000 MIN: 8.77 / MAX: 4000 1. ClickHouse server version 22.5.4.19 (official build).
Redis Test: SADD - Parallel Connections: 50 OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: SADD - Parallel Connections: 50 B AA A C 400K 800K 1200K 1600K 2000K 2064020.50 2004169.75 1965904.50 1913001.00 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
etcd Test: PUT - Connections: 500 - Clients: 100 - Average Latency OpenBenchmarking.org ms, Fewer Is Better etcd 3.5.4 Test: PUT - Connections: 500 - Clients: 100 - Average Latency A AA B C 0.315 0.63 0.945 1.26 1.575 1.3 1.3 1.3 1.4
GraphicsMagick Operation: Rotate OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Rotate A B AA C 160 320 480 640 800 746 720 717 697 1. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
Redis Test: GET - Parallel Connections: 500 OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: GET - Parallel Connections: 500 A B C AA 500K 1000K 1500K 2000K 2500K 2329306.75 2269879.00 2222756.00 2177739.50 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Redis Test: SET - Parallel Connections: 50 OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: SET - Parallel Connections: 50 AA C A B 400K 800K 1200K 1600K 2000K 1757006.62 1739321.38 1680645.88 1643631.00 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Redis Test: SADD - Parallel Connections: 500 OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: SADD - Parallel Connections: 500 A B AA C 500K 1000K 1500K 2000K 2500K 2113398.50 2029669.00 1984162.50 1980390.38 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
srsRAN Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM C B A AA 40 80 120 160 200 174.5 166.3 166.3 163.7 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
etcd Test: PUT - Connections: 500 - Clients: 100 OpenBenchmarking.org Requests/sec, More Is Better etcd 3.5.4 Test: PUT - Connections: 500 - Clients: 100 AA B A C 17K 34K 51K 68K 85K 77587.44 77587.31 77475.55 72877.72
Redis Test: LPUSH - Parallel Connections: 50 OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: LPUSH - Parallel Connections: 50 B A AA C 400K 800K 1200K 1600K 2000K 1634363.00 1626151.25 1556351.25 1535984.25 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
srsRAN Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM C B A AA 90 180 270 360 450 405.5 385.0 384.4 381.5 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
Unvanquished Resolution: 2560 x 1440 - Effects Quality: Medium OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.53 Resolution: 2560 x 1440 - Effects Quality: Medium B A AA C 60 120 180 240 300 288.5 276.8 275.8 271.6
Facebook RocksDB Test: Read While Writing OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.5.3 Test: Read While Writing C B A AA 600K 1200K 1800K 2400K 3000K 2749536 2643393 2614220 2597712 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
memtier_benchmark Protocol: Redis - Clients: 500 - Set To Get Ratio: 5:1 OpenBenchmarking.org Ops/sec, More Is Better memtier_benchmark 1.4 Protocol: Redis - Clients: 500 - Set To Get Ratio: 5:1 C AA A 400K 800K 1200K 1600K 2000K 1692892.31 1682664.97 1601060.47 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
memtier_benchmark Protocol: Redis - Clients: 100 - Set To Get Ratio: 1:10 OpenBenchmarking.org Ops/sec, More Is Better memtier_benchmark 1.4 Protocol: Redis - Clients: 100 - Set To Get Ratio: 1:10 B C A AA 400K 800K 1200K 1600K 2000K 1918907.40 1868139.80 1852262.31 1816335.46 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Unvanquished Resolution: 1920 x 1080 - Effects Quality: Medium OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.53 Resolution: 1920 x 1080 - Effects Quality: Medium A AA B C 60 120 180 240 300 285.6 282.7 271.6 270.4
srsRAN Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM C AA A B 90 180 270 360 450 432.6 411.6 410.8 409.7 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
srsRAN Test: OFDM_Test OpenBenchmarking.org Samples / Second, More Is Better srsRAN 22.04.1 Test: OFDM_Test A C AA B 30M 60M 90M 120M 150M 152100000 145800000 145400000 144100000 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
memtier_benchmark Protocol: Redis - Clients: 50 - Set To Get Ratio: 1:1 OpenBenchmarking.org Ops/sec, More Is Better memtier_benchmark 1.4 Protocol: Redis - Clients: 50 - Set To Get Ratio: 1:1 A AA C B 400K 800K 1200K 1600K 2000K 1810859.67 1739112.82 1730287.32 1719792.39 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Mobile Neural Network Model: inception-v3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: inception-v3 B A C AA 7 14 21 28 35 28.38 28.56 29.31 29.87 MIN: 27.9 / MAX: 37.14 MIN: 28.07 / MAX: 37.02 MIN: 28.85 / MAX: 37.57 MIN: 28.53 / MAX: 68.86 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Redis Test: LPUSH - Parallel Connections: 1000 OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: LPUSH - Parallel Connections: 1000 A AA C B 400K 800K 1200K 1600K 2000K 1659306.00 1652420.50 1605826.75 1581548.50 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Redis Test: SET - Parallel Connections: 1000 OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: SET - Parallel Connections: 1000 B A AA C 400K 800K 1200K 1600K 2000K 1756954.75 1709316.62 1692135.00 1678740.00 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
srsRAN Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM C A B AA 40 80 120 160 200 182.5 174.5 174.4 174.4 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
Redis Test: GET - Parallel Connections: 1000 OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: GET - Parallel Connections: 1000 AA B A C 500K 1000K 1500K 2000K 2500K 2307918.0 2276087.5 2213727.5 2205646.0 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Redis Test: LPOP - Parallel Connections: 1000 OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: LPOP - Parallel Connections: 1000 B A C AA 300K 600K 900K 1200K 1500K 1586939.12 1564536.50 1557074.50 1516645.12 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Unvanquished Resolution: 3840 x 2160 - Effects Quality: High OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.53 Resolution: 3840 x 2160 - Effects Quality: High C A B AA 60 120 180 240 300 281.1 276.6 273.1 268.9
OpenVINO Model: Vehicle Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16 - Device: CPU C AA A B 40 80 120 160 200 174.02 173.53 170.86 166.57 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Vehicle Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16 - Device: CPU C AA A B 8 16 24 32 40 34.45 34.55 35.09 35.99 MIN: 20.8 / MAX: 53.68 MIN: 13.25 / MAX: 50.41 MIN: 22.45 / MAX: 47.1 MIN: 12.61 / MAX: 44.51 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
SVT-AV1 Encoder Mode: Preset 10 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 10 - Input: Bosphorus 4K AA A C B 20 40 60 80 100 75.63 74.16 72.69 72.55 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
C-Blosc Test: blosclz shuffle OpenBenchmarking.org MB/s, More Is Better C-Blosc 2.3 Test: blosclz shuffle B A AA C 3K 6K 9K 12K 15K 16330.8 16319.2 16165.9 15704.2 1. (CC) gcc options: -std=gnu99 -O3 -lrt -lm
GraphicsMagick Operation: Resizing OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Resizing A AA B C 300 600 900 1200 1500 1456 1431 1425 1402 1. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
etcd Test: PUT - Connections: 50 - Clients: 1000 OpenBenchmarking.org Requests/sec, More Is Better etcd 3.5.4 Test: PUT - Connections: 50 - Clients: 1000 A B AA C 20K 40K 60K 80K 100K 94397.28 94329.67 94162.78 90956.38
etcd Test: PUT - Connections: 50 - Clients: 1000 - Average Latency OpenBenchmarking.org ms, Fewer Is Better etcd 3.5.4 Test: PUT - Connections: 50 - Clients: 1000 - Average Latency A AA B C 3 6 9 12 15 10.6 10.6 10.6 11.0
memtier_benchmark Protocol: Redis - Clients: 50 - Set To Get Ratio: 1:5 OpenBenchmarking.org Ops/sec, More Is Better memtier_benchmark 1.4 Protocol: Redis - Clients: 50 - Set To Get Ratio: 1:5 A AA C B 400K 800K 1200K 1600K 2000K 1911666.23 1868299.86 1865191.56 1844254.53 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
memtier_benchmark Protocol: Redis - Clients: 100 - Set To Get Ratio: 1:5 OpenBenchmarking.org Ops/sec, More Is Better memtier_benchmark 1.4 Protocol: Redis - Clients: 100 - Set To Get Ratio: 1:5 C A B AA 400K 800K 1200K 1600K 2000K 1857393.23 1824325.88 1811033.68 1794814.33 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenVINO Model: Machine Translation EN To DE FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Machine Translation EN To DE FP16 - Device: CPU A C AA B 50 100 150 200 250 203.27 206.98 209.50 210.33 MIN: 113.88 / MAX: 231.66 MIN: 172.44 / MAX: 233.79 MIN: 173.72 / MAX: 239.08 MIN: 163.75 / MAX: 236.77 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
srsRAN Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM C B AA A 40 80 120 160 200 167.4 163.9 162.1 161.8 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
SVT-AV1 Encoder Mode: Preset 12 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 12 - Input: Bosphorus 1080p C AA B A 80 160 240 320 400 358.60 354.97 352.19 346.65 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenVINO Model: Machine Translation EN To DE FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Machine Translation EN To DE FP16 - Device: CPU A C AA B 7 14 21 28 35 29.48 28.94 28.62 28.50 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
srsRAN Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM C B AA A 90 180 270 360 450 421.3 411.8 407.7 407.5 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
SVT-AV1 Encoder Mode: Preset 12 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 12 - Input: Bosphorus 4K AA B C A 20 40 60 80 100 103.53 101.90 101.60 100.17 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
memtier_benchmark Protocol: Redis - Clients: 50 - Set To Get Ratio: 5:1 OpenBenchmarking.org Ops/sec, More Is Better memtier_benchmark 1.4 Protocol: Redis - Clients: 50 - Set To Get Ratio: 5:1 A C B AA 400K 800K 1200K 1600K 2000K 1684780.17 1663746.58 1642719.18 1631076.43 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
memtier_benchmark Protocol: Redis - Clients: 50 - Set To Get Ratio: 1:10 OpenBenchmarking.org Ops/sec, More Is Better memtier_benchmark 1.4 Protocol: Redis - Clients: 50 - Set To Get Ratio: 1:10 C AA A B 400K 800K 1200K 1600K 2000K 1936392.38 1909295.85 1891611.75 1875260.09 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Natron Input: Spaceship OpenBenchmarking.org FPS, More Is Better Natron 2.4.3 Input: Spaceship C B A AA 0.72 1.44 2.16 2.88 3.6 3.2 3.2 3.2 3.1
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 8 - Input: Bosphorus 4K AA C B A 10 20 30 40 50 43.19 43.02 42.95 41.88 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Facebook RocksDB Test: Random Read OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.5.3 Test: Random Read A AA C B 13M 26M 39M 52M 65M 60836317 60052818 59735063 59015149 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
ClickHouse 100M Rows Web Analytics Dataset, First Run / Cold Cache OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.5.4.19 100M Rows Web Analytics Dataset, First Run / Cold Cache C AA B 30 60 90 120 150 141.89 141.26 137.77 MIN: 8.34 / MAX: 6666.67 MIN: 8.21 / MAX: 10000 MIN: 8.31 / MAX: 3750 1. ClickHouse server version 22.5.4.19 (official build).
NCNN Target: Vulkan GPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: shufflenet-v2 A AA B C 0.5715 1.143 1.7145 2.286 2.8575 2.47 2.50 2.51 2.52 MIN: 2.3 / MAX: 3.16 MIN: 2.31 / MAX: 2.97 MIN: 2.31 / MAX: 2.95 MIN: 2.31 / MAX: 3.27 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
memtier_benchmark Protocol: Redis - Clients: 100 - Set To Get Ratio: 5:1 OpenBenchmarking.org Ops/sec, More Is Better memtier_benchmark 1.4 Protocol: Redis - Clients: 100 - Set To Get Ratio: 5:1 C A AA B 400K 800K 1200K 1600K 2000K 1666964.92 1648819.65 1640264.17 1621199.15 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 8 - Input: Bosphorus 1080p AA B C A 30 60 90 120 150 113.97 113.77 113.02 111.03 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenVINO Model: Person Detection FP32 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Person Detection FP32 - Device: CPU C A B AA 0.4365 0.873 1.3095 1.746 2.1825 1.94 1.92 1.91 1.89 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
Unpacking The Linux Kernel linux-5.19.tar.xz OpenBenchmarking.org Seconds, Fewer Is Better Unpacking The Linux Kernel 5.19 linux-5.19.tar.xz B C AA A 2 4 6 8 10 6.708 6.814 6.816 6.885
Redis Test: LPUSH - Parallel Connections: 500 OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: LPUSH - Parallel Connections: 500 A C AA B 400K 800K 1200K 1600K 2000K 1655878.12 1623722.00 1619934.50 1614598.75 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
NCNN Target: Vulkan GPU - Model: FastestDet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: FastestDet AA A B C 0.6548 1.3096 1.9644 2.6192 3.274 2.84 2.88 2.88 2.88 MIN: 2.68 / MAX: 3.17 MIN: 2.86 / MAX: 3.19 MIN: 2.86 / MAX: 3.13 MIN: 2.85 / MAX: 3.18 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
GraphicsMagick Operation: Noise-Gaussian OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Noise-Gaussian A AA B C 80 160 240 320 400 375 370 369 366 1. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
ClickHouse 100M Rows Web Analytics Dataset, Third Run OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.5.4.19 100M Rows Web Analytics Dataset, Third Run B AA C 40 80 120 160 200 164.51 164.16 160.78 MIN: 8.8 / MAX: 15000 MIN: 8.64 / MAX: 15000 MIN: 8.34 / MAX: 10000 1. ClickHouse server version 22.5.4.19 (official build).
GraphicsMagick Operation: Swirl OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Swirl A B AA C 150 300 450 600 750 710 703 703 694 1. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
NCNN Target: CPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: resnet50 A C B AA 5 10 15 20 25 20.87 20.87 20.90 21.35 MIN: 20.63 / MAX: 21.65 MIN: 20.65 / MAX: 21.68 MIN: 20.64 / MAX: 21.64 MIN: 20.94 / MAX: 22.57 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Timed Wasmer Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Wasmer Compilation 2.3 Time To Compile AA A C B 13 26 39 52 65 55.39 55.92 56.57 56.58 1. (CC) gcc options: -m64 -ldl -lgcc_s -lutil -lrt -lpthread -lm -lc -pie -nodefaultlibs
GravityMark Resolution: 1920 x 1080 - Renderer: OpenGL OpenBenchmarking.org Frames Per Second, More Is Better GravityMark 1.70 Resolution: 1920 x 1080 - Renderer: OpenGL AA C A B 20 40 60 80 100 106.0 104.6 104.1 103.8
memtier_benchmark Protocol: Redis - Clients: 500 - Set To Get Ratio: 1:1 OpenBenchmarking.org Ops/sec, More Is Better memtier_benchmark 1.4 Protocol: Redis - Clients: 500 - Set To Get Ratio: 1:1 B C 300K 600K 900K 1200K 1500K 1624385.73 1591304.98 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Dragonflydb Clients: 50 - Set To Get Ratio: 5:1 OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 0.6 Clients: 50 - Set To Get Ratio: 5:1 AA C B A 600K 1200K 1800K 2400K 3000K 2828285.63 2819421.36 2808028.85 2772545.65 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenVINO Model: Person Detection FP32 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Person Detection FP32 - Device: CPU C A B AA 700 1400 2100 2800 3500 3044.33 3084.38 3092.99 3105.06 MIN: 2536.5 / MAX: 3437.01 MIN: 2539.51 / MAX: 3366.56 MIN: 2798.44 / MAX: 3409.97 MIN: 2706.58 / MAX: 3469.14 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
Node.js V8 Web Tooling Benchmark OpenBenchmarking.org runs/s, More Is Better Node.js V8 Web Tooling Benchmark C A AA B 3 6 9 12 15 11.41 11.41 11.38 11.20
OpenVINO Model: Face Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Face Detection FP16 - Device: CPU B C A AA 500 1000 1500 2000 2500 2238.36 2250.83 2269.21 2279.05 MIN: 2082.75 / MAX: 2340.6 MIN: 2090.14 / MAX: 2336.79 MIN: 2172.69 / MAX: 2379.8 MIN: 2164.97 / MAX: 2394.44 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
C-Blosc Test: blosclz bitshuffle OpenBenchmarking.org MB/s, More Is Better C-Blosc 2.3 Test: blosclz bitshuffle A C AA B 2K 4K 6K 8K 10K 9276.4 9159.0 9131.8 9116.1 1. (CC) gcc options: -std=gnu99 -O3 -lrt -lm
GravityMark Resolution: 3840 x 2160 - Renderer: OpenGL OpenBenchmarking.org Frames Per Second, More Is Better GravityMark 1.70 Resolution: 3840 x 2160 - Renderer: OpenGL AA A B C 14 28 42 56 70 64.5 64.2 63.6 63.4
SVT-AV1 Encoder Mode: Preset 10 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 10 - Input: Bosphorus 1080p C B AA A 50 100 150 200 250 238.44 237.14 235.31 234.54 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
srsRAN Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 22.04.1 Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM A AA B C 20 40 60 80 100 109.2 109.1 109.0 107.5 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
Blender Blend File: BMW27 - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.3 Blend File: BMW27 - Compute: CPU-Only B C AA A 20 40 60 80 100 98.50 98.52 98.54 100.04
OpenVINO Model: Face Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Face Detection FP16 - Device: CPU B C A AA 0.6008 1.2016 1.8024 2.4032 3.004 2.67 2.65 2.64 2.63 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
NCNN Target: Vulkan GPU - Model: vision_transformer OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: vision_transformer AA C A B 30 60 90 120 150 153.04 153.44 153.75 155.34 MIN: 152.05 / MAX: 158 MIN: 152.41 / MAX: 156.1 MIN: 152.07 / MAX: 161.2 MIN: 154.17 / MAX: 159.14 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
srsRAN Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 22.04.1 Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM A B AA C 14 28 42 56 70 61.4 61.3 61.3 60.5 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
Blender Blend File: Classroom - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.3 Blend File: Classroom - Compute: CPU-Only C B AA A 60 120 180 240 300 253.84 254.59 254.68 257.49
NCNN Target: CPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: blazeface A AA B C 0.477 0.954 1.431 1.908 2.385 2.09 2.10 2.11 2.12 MIN: 2.07 / MAX: 2.36 MIN: 2.08 / MAX: 2.4 MIN: 2.09 / MAX: 2.46 MIN: 2.09 / MAX: 2.44 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
etcd Test: RANGE - Connections: 50 - Clients: 100 OpenBenchmarking.org Requests/sec, More Is Better etcd 3.5.4 Test: RANGE - Connections: 50 - Clients: 100 C A B AA 20K 40K 60K 80K 100K 78992.10 78944.06 78644.10 77874.58
Dragonflydb Clients: 50 - Set To Get Ratio: 1:1 OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 0.6 Clients: 50 - Set To Get Ratio: 1:1 C B A AA 600K 1200K 1800K 2400K 3000K 2949072.75 2934355.48 2920540.96 2907432.83 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
NCNN Target: Vulkan GPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: efficientnet-b0 C B A AA 2 4 6 8 10 7.64 7.65 7.73 7.73 MIN: 7.54 / MAX: 8.43 MIN: 7.55 / MAX: 8.03 MIN: 7.61 / MAX: 11.64 MIN: 7.62 / MAX: 10.89 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU-v2-v2 - Model: mobilenet-v2 A B AA C 1.0553 2.1106 3.1659 4.2212 5.2765 4.63 4.64 4.65 4.69 MIN: 4.57 / MAX: 5.41 MIN: 4.58 / MAX: 5.19 MIN: 4.58 / MAX: 5.2 MIN: 4.62 / MAX: 5.29 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
SVT-AV1 Encoder Mode: Preset 4 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 4 - Input: Bosphorus 4K B AA C A 0.4273 0.8546 1.2819 1.7092 2.1365 1.899 1.897 1.889 1.875 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Timed CPython Compilation Build Configuration: Default OpenBenchmarking.org Seconds, Fewer Is Better Timed CPython Compilation 3.10.6 Build Configuration: Default A AA B C 4 8 12 16 20 16.50 16.51 16.53 16.71
NCNN Target: CPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: vgg16 A B C AA 11 22 33 44 55 49.10 49.31 49.31 49.72 MIN: 48.53 / MAX: 52.21 MIN: 48.7 / MAX: 50.46 MIN: 48.78 / MAX: 50.28 MIN: 48.67 / MAX: 75.83 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: vision_transformer OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: vision_transformer A B C AA 30 60 90 120 150 155.14 155.89 156.99 157.08 MIN: 154.65 / MAX: 163.24 MIN: 155.39 / MAX: 159.87 MIN: 155.28 / MAX: 339.54 MIN: 155.45 / MAX: 162.23 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 A B AA C 0.549 1.098 1.647 2.196 2.745 2.41 2.42 2.43 2.43 MIN: 2.25 / MAX: 3.33 MIN: 2.25 / MAX: 3.33 MIN: 2.26 / MAX: 3.35 MIN: 2.26 / MAX: 3.34 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenVINO Model: Person Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Person Detection FP16 - Device: CPU C A B AA 700 1400 2100 2800 3500 3087.45 3099.00 3120.76 3123.95 MIN: 1583.7 / MAX: 3401.16 MIN: 2806.76 / MAX: 3365.69 MIN: 2826.01 / MAX: 3435.4 MIN: 2805.37 / MAX: 3397.57 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
NCNN Target: CPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: mobilenet A B AA C 4 8 12 16 20 14.02 14.05 14.17 14.18 MIN: 13.8 / MAX: 14.44 MIN: 13.85 / MAX: 14.54 MIN: 14.02 / MAX: 14.79 MIN: 14.01 / MAX: 14.71 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Timed PHP Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed PHP Compilation 8.1.9 Time To Compile A AA C B 12 24 36 48 60 52.74 53.01 53.27 53.34
NCNN Target: CPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: efficientnet-b0 A B C AA 2 4 6 8 10 6.45 6.48 6.50 6.52 MIN: 6.4 / MAX: 6.98 MIN: 6.42 / MAX: 7.1 MIN: 6.43 / MAX: 7.42 MIN: 6.45 / MAX: 7.26 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: mobilenet A AA C B 2 4 6 8 10 8.42 8.42 8.45 8.51 MIN: 7.27 / MAX: 9.34 MIN: 7.28 / MAX: 9.25 MIN: 7.27 / MAX: 9.24 MIN: 7.27 / MAX: 28.34 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Blender Blend File: Fishy Cat - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.3 Blend File: Fishy Cat - Compute: CPU-Only C B A AA 30 60 90 120 150 125.20 125.77 125.98 126.53
OpenVINO Model: Person Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Person Detection FP16 - Device: CPU C A B AA 0.432 0.864 1.296 1.728 2.16 1.92 1.91 1.90 1.90 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
srsRAN Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM AA A B C 30 60 90 120 150 153.8 153.7 153.6 152.2 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
NCNN Target: CPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: yolov4-tiny AA A B C 6 12 18 24 30 25.73 25.75 25.87 25.99 MIN: 24.98 / MAX: 26.6 MIN: 24.81 / MAX: 29.44 MIN: 24.93 / MAX: 27 MIN: 24.91 / MAX: 71 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Blender Blend File: Pabellon Barcelona - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.3 Blend File: Pabellon Barcelona - Compute: CPU-Only AA B C A 70 140 210 280 350 318.03 319.01 319.32 321.22
LAMMPS Molecular Dynamics Simulator Model: Rhodopsin Protein OpenBenchmarking.org ns/day, More Is Better LAMMPS Molecular Dynamics Simulator 23Jun2022 Model: Rhodopsin Protein A B AA C 3 6 9 12 15 9.382 9.356 9.320 9.291 1. (CXX) g++ options: -O3 -lm -ldl
NCNN Target: Vulkan GPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: alexnet A AA B C 0.4658 0.9316 1.3974 1.8632 2.329 2.05 2.07 2.07 2.07 MIN: 1.89 / MAX: 2.77 MIN: 1.9 / MAX: 2.79 MIN: 1.91 / MAX: 2.77 MIN: 1.9 / MAX: 2.77 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: mnasnet A B AA C 0.9495 1.899 2.8485 3.798 4.7475 4.18 4.19 4.21 4.22 MIN: 4.12 / MAX: 4.48 MIN: 4.14 / MAX: 4.65 MIN: 4.17 / MAX: 4.56 MIN: 4.17 / MAX: 4.52 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
etcd Test: RANGE - Connections: 50 - Clients: 1000 - Average Latency OpenBenchmarking.org ms, Fewer Is Better etcd 3.5.4 Test: RANGE - Connections: 50 - Clients: 1000 - Average Latency A AA C B 3 6 9 12 15 10.5 10.5 10.5 10.6
etcd Test: RANGE - Connections: 100 - Clients: 100 OpenBenchmarking.org Requests/sec, More Is Better etcd 3.5.4 Test: RANGE - Connections: 100 - Clients: 100 B AA A C 16K 32K 48K 64K 80K 76892.65 76764.82 76759.94 76167.57
Timed CPython Compilation Build Configuration: Released Build, PGO + LTO Optimized OpenBenchmarking.org Seconds, Fewer Is Better Timed CPython Compilation 3.10.6 Build Configuration: Released Build, PGO + LTO Optimized A AA B C 60 120 180 240 300 254.07 255.93 256.39 256.47
NCNN Target: CPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: regnety_400m A AA C B 4 8 12 16 20 13.75 13.82 13.86 13.88 MIN: 13.62 / MAX: 14.22 MIN: 13.71 / MAX: 14.65 MIN: 13.72 / MAX: 14.33 MIN: 13.75 / MAX: 14.54 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenVINO Model: Face Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Face Detection FP16-INT8 - Device: CPU A C B AA 0.9788 1.9576 2.9364 3.9152 4.894 4.35 4.31 4.31 4.31 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
etcd Test: RANGE - Connections: 100 - Clients: 1000 - Average Latency OpenBenchmarking.org ms, Fewer Is Better etcd 3.5.4 Test: RANGE - Connections: 100 - Clients: 1000 - Average Latency A C AA B 3 6 9 12 15 10.9 10.9 11.0 11.0
Dragonflydb Clients: 200 - Set To Get Ratio: 5:1 OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 0.6 Clients: 200 - Set To Get Ratio: 5:1 A AA C B 600K 1200K 1800K 2400K 3000K 2581692.96 2575239.57 2574045.53 2558359.14 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
etcd Test: PUT - Connections: 100 - Clients: 1000 - Average Latency OpenBenchmarking.org ms, Fewer Is Better etcd 3.5.4 Test: PUT - Connections: 100 - Clients: 1000 - Average Latency A B C AA 3 6 9 12 15 11.0 11.0 11.0 11.1
GravityMark Resolution: 2560 x 1440 - Renderer: OpenGL OpenBenchmarking.org Frames Per Second, More Is Better GravityMark 1.70 Resolution: 2560 x 1440 - Renderer: OpenGL B AA C A 20 40 60 80 100 89.7 89.2 89.1 88.9
etcd Test: PUT - Connections: 500 - Clients: 1000 OpenBenchmarking.org Requests/sec, More Is Better etcd 3.5.4 Test: PUT - Connections: 500 - Clients: 1000 C A AA B 20K 40K 60K 80K 100K 78092.71 77982.75 77976.00 77402.76
NCNN Target: Vulkan GPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: yolov4-tiny AA A B C 3 6 9 12 15 11.40 11.45 11.45 11.48 MIN: 11.2 / MAX: 11.63 MIN: 11.18 / MAX: 12.04 MIN: 11.24 / MAX: 13.43 MIN: 11.23 / MAX: 16.37 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Timed Erlang/OTP Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Erlang/OTP Compilation 25.0 Time To Compile B A C AA 20 40 60 80 100 82.51 82.55 83.00 83.22
Facebook RocksDB Test: Read Random Write Random OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.5.3 Test: Read Random Write Random C A B AA 400K 800K 1200K 1600K 2000K 1924607 1918881 1909640 1908955 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
srsRAN Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM AA A B C 80 160 240 320 400 384.1 384.0 382.9 381.0 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
OpenVINO Model: Person Vehicle Bike Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Person Vehicle Bike Detection FP16 - Device: CPU AA A C B 4 8 12 16 20 17.21 17.23 17.30 17.35 MIN: 8.7 / MAX: 30.28 MIN: 9.63 / MAX: 31.12 MIN: 14.64 / MAX: 24.15 MIN: 8.63 / MAX: 30.43 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
NCNN Target: CPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: squeezenet_ssd A AA B C 5 10 15 20 25 21.03 21.03 21.16 21.20 MIN: 19.53 / MAX: 22.34 MIN: 19.61 / MAX: 22.57 MIN: 19.08 / MAX: 22.51 MIN: 19.55 / MAX: 22.51 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenVINO Model: Person Vehicle Bike Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Person Vehicle Bike Detection FP16 - Device: CPU AA A C B 80 160 240 320 400 348.24 347.84 346.46 345.45 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
Dragonflydb Clients: 200 - Set To Get Ratio: 1:5 OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 0.6 Clients: 200 - Set To Get Ratio: 1:5 AA B C A 600K 1200K 1800K 2400K 3000K 2872811.95 2869778.70 2859261.77 2849837.44 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenVINO Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU AA C A B 0.2835 0.567 0.8505 1.134 1.4175 1.25 1.25 1.26 1.26 MIN: 0.67 / MAX: 12.4 MIN: 0.7 / MAX: 12.45 MIN: 0.71 / MAX: 10.9 MIN: 0.7 / MAX: 12.17 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
NCNN Target: Vulkan GPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: mnasnet A B AA C 0.5715 1.143 1.7145 2.286 2.8575 2.52 2.53 2.54 2.54 MIN: 2.38 / MAX: 3.53 MIN: 2.39 / MAX: 3.5 MIN: 2.39 / MAX: 3.56 MIN: 2.39 / MAX: 3.56 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: squeezenet_ssd B A C AA 1.161 2.322 3.483 4.644 5.805 5.12 5.13 5.13 5.16 MIN: 4.92 / MAX: 6.75 MIN: 4.91 / MAX: 6.74 MIN: 4.92 / MAX: 6.8 MIN: 4.52 / MAX: 10.07 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
etcd Test: PUT - Connections: 500 - Clients: 1000 - Average Latency OpenBenchmarking.org ms, Fewer Is Better etcd 3.5.4 Test: PUT - Connections: 500 - Clients: 1000 - Average Latency A AA C B 3 6 9 12 15 12.8 12.8 12.8 12.9
GravityMark Resolution: 1920 x 1200 - Renderer: OpenGL OpenBenchmarking.org Frames Per Second, More Is Better GravityMark 1.70 Resolution: 1920 x 1200 - Renderer: OpenGL AA B C A 20 40 60 80 100 103.9 103.7 103.4 103.1
OpenVINO Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU AA C B A 2K 4K 6K 8K 10K 9530.87 9527.71 9479.38 9457.64 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
SVT-AV1 Encoder Mode: Preset 4 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 4 - Input: Bosphorus 1080p A C AA B 1.1741 2.3482 3.5223 4.6964 5.8705 5.218 5.206 5.200 5.179 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Facebook RocksDB Test: Update Random OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.5.3 Test: Update Random A C AA B 120K 240K 360K 480K 600K 550239 549826 547827 546189 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
NCNN Target: CPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU-v3-v3 - Model: mobilenet-v3 A B AA C 0.9203 1.8406 2.7609 3.6812 4.6015 4.06 4.07 4.09 4.09 MIN: 3.98 / MAX: 5.9 MIN: 4.01 / MAX: 4.53 MIN: 4.02 / MAX: 4.71 MIN: 4.04 / MAX: 4.56 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Dragonflydb Clients: 200 - Set To Get Ratio: 1:1 OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 0.6 Clients: 200 - Set To Get Ratio: 1:1 AA C A B 600K 1200K 1800K 2400K 3000K 2698410.83 2685467.32 2678725.83 2678724.09 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenVINO Model: Face Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Face Detection FP16-INT8 - Device: CPU A B AA C 300 600 900 1200 1500 1378.25 1385.55 1387.00 1388.28 MIN: 1353.01 / MAX: 1432.99 MIN: 1351.27 / MAX: 1417.45 MIN: 1370.49 / MAX: 1411.36 MIN: 1368.44 / MAX: 1418.89 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
etcd Test: PUT - Connections: 100 - Clients: 1000 OpenBenchmarking.org Requests/sec, More Is Better etcd 3.5.4 Test: PUT - Connections: 100 - Clients: 1000 B A C AA 20K 40K 60K 80K 100K 90993.39 90990.37 90622.20 90337.62
LAMMPS Molecular Dynamics Simulator Model: 20k Atoms OpenBenchmarking.org ns/day, More Is Better LAMMPS Molecular Dynamics Simulator 23Jun2022 Model: 20k Atoms B A AA C 3 6 9 12 15 9.418 9.401 9.359 9.351 1. (CXX) g++ options: -O3 -lm -ldl
NCNN Target: CPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: resnet18 C A B AA 3 6 9 12 15 12.59 12.62 12.64 12.68 MIN: 12.24 / MAX: 13.42 MIN: 12.27 / MAX: 19.5 MIN: 12.31 / MAX: 13.26 MIN: 12.22 / MAX: 14.05 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
etcd Test: RANGE - Connections: 100 - Clients: 1000 OpenBenchmarking.org Requests/sec, More Is Better etcd 3.5.4 Test: RANGE - Connections: 100 - Clients: 1000 C A AA B 20K 40K 60K 80K 100K 91457.69 91454.55 91001.37 90811.02
NCNN Target: CPU - Model: FastestDet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: FastestDet A AA B C 1.2735 2.547 3.8205 5.094 6.3675 5.62 5.65 5.65 5.66 MIN: 5.56 / MAX: 5.74 MIN: 5.6 / MAX: 5.9 MIN: 5.61 / MAX: 5.88 MIN: 5.6 / MAX: 5.98 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: alexnet B C A AA 3 6 9 12 15 9.92 9.92 9.94 9.99 MIN: 9.63 / MAX: 10.7 MIN: 9.62 / MAX: 10.47 MIN: 9.63 / MAX: 10.63 MIN: 9.6 / MAX: 10.63 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
GravityMark Resolution: 2560 x 1440 - Renderer: Vulkan OpenBenchmarking.org Frames Per Second, More Is Better GravityMark 1.70 Resolution: 2560 x 1440 - Renderer: Vulkan AA A B C 20 40 60 80 100 90.2 90.2 90.1 89.6
GraphicsMagick Operation: Enhanced OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Enhanced A B AA C 70 140 210 280 350 309 308 308 307 1. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
BRL-CAD VGR Performance Metric OpenBenchmarking.org VGR Performance Metric, More Is Better BRL-CAD 7.32.6 VGR Performance Metric B C AA 40K 80K 120K 160K 200K 188216 188128 187035 1. (CXX) g++ options: -std=c++11 -pipe -fvisibility=hidden -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -pedantic -ldl -lm
NCNN Target: Vulkan GPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: blazeface A AA B C 0.36 0.72 1.08 1.44 1.8 1.59 1.60 1.60 1.60 MIN: 1.51 / MAX: 1.85 MIN: 1.53 / MAX: 1.96 MIN: 1.52 / MAX: 2.08 MIN: 1.52 / MAX: 1.89 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
GravityMark Resolution: 3840 x 2160 - Renderer: Vulkan OpenBenchmarking.org Frames Per Second, More Is Better GravityMark 1.70 Resolution: 3840 x 2160 - Renderer: Vulkan AA A B C 14 28 42 56 70 64.4 64.4 64.2 64.0
Blender Blend File: Barbershop - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.3 Blend File: Barbershop - Compute: CPU-Only C AA A B 200 400 600 800 1000 1027.44 1029.03 1032.04 1033.81
NCNN Target: CPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: shufflenet-v2 A AA B C 1.0958 2.1916 3.2874 4.3832 5.479 4.84 4.87 4.87 4.87 MIN: 4.77 / MAX: 5.08 MIN: 4.83 / MAX: 5.25 MIN: 4.79 / MAX: 5.16 MIN: 4.82 / MAX: 5.25 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: resnet50 A C B AA 1.143 2.286 3.429 4.572 5.715 5.05 5.06 5.07 5.08 MIN: 4.99 / MAX: 5.82 MIN: 5.02 / MAX: 5.88 MIN: 5.02 / MAX: 6.23 MIN: 5.01 / MAX: 7.86 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
ASTC Encoder Preset: Fast OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.0 Preset: Fast AA C B A 40 80 120 160 200 187.98 187.36 187.22 186.91 1. (CXX) g++ options: -O3 -flto -pthread
7-Zip Compression Test: Decompression Rating OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 22.01 Test: Decompression Rating AA A C B 20K 40K 60K 80K 100K 92604 92591 92255 92125 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
Facebook RocksDB Test: Sequential Fill OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.5.3 Test: Sequential Fill C A AA B 200K 400K 600K 800K 1000K 1059729 1059712 1057965 1054349 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
GraphicsMagick Operation: Sharpen OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Sharpen B AA A C 40 80 120 160 200 199 199 199 198 1. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
etcd Test: RANGE - Connections: 500 - Clients: 1000 OpenBenchmarking.org Requests/sec, More Is Better etcd 3.5.4 Test: RANGE - Connections: 500 - Clients: 1000 AA B C A 20K 40K 60K 80K 100K 78128.39 78090.46 78062.46 77738.86
etcd Test: RANGE - Connections: 500 - Clients: 100 OpenBenchmarking.org Requests/sec, More Is Better etcd 3.5.4 Test: RANGE - Connections: 500 - Clients: 100 AA A B C 17K 34K 51K 68K 85K 77604.28 77585.95 77467.64 77235.74
NCNN Target: Vulkan GPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: regnety_400m A AA C B 0.9608 1.9216 2.8824 3.8432 4.804 4.25 4.25 4.25 4.27 MIN: 4.18 / MAX: 5.67 MIN: 4.17 / MAX: 5.65 MIN: 4.18 / MAX: 5.67 MIN: 4.2 / MAX: 5.66 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
etcd Test: RANGE - Connections: 50 - Clients: 1000 OpenBenchmarking.org Requests/sec, More Is Better etcd 3.5.4 Test: RANGE - Connections: 50 - Clients: 1000 A AA C B 20K 40K 60K 80K 100K 94964.87 94925.40 94756.82 94577.72
NCNN Target: Vulkan GPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: googlenet A AA B C 1.1498 2.2996 3.4494 4.5992 5.749 5.09 5.10 5.10 5.10 MIN: 5.03 / MAX: 6.71 MIN: 5.04 / MAX: 6.7 MIN: 5.06 / MAX: 6.73 MIN: 5.05 / MAX: 6.75 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
GravityMark Resolution: 1920 x 1200 - Renderer: Vulkan OpenBenchmarking.org Frames Per Second, More Is Better GravityMark 1.70 Resolution: 1920 x 1200 - Renderer: Vulkan B AA A C 20 40 60 80 100 104.4 104.4 104.4 104.0
GravityMark Resolution: 1920 x 1080 - Renderer: Vulkan OpenBenchmarking.org Frames Per Second, More Is Better GravityMark 1.70 Resolution: 1920 x 1080 - Renderer: Vulkan B AA A C 20 40 60 80 100 104.8 104.6 104.6 104.4
NCNN Target: Vulkan GPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: resnet18 A B AA C 0.6053 1.2106 1.8159 2.4212 3.0265 2.68 2.68 2.69 2.69 MIN: 2.55 / MAX: 3.49 MIN: 2.56 / MAX: 3.48 MIN: 2.56 / MAX: 3.58 MIN: 2.56 / MAX: 3.48 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Primesieve Length: 1e12 OpenBenchmarking.org Seconds, Fewer Is Better Primesieve 8.0 Length: 1e12 A C B AA 4 8 12 16 20 13.88 13.89 13.91 13.93 1. (CXX) g++ options: -O3
Facebook RocksDB Test: Random Fill Sync OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.5.3 Test: Random Fill Sync A C AA B 3K 6K 9K 12K 15K 13085 13076 13069 13040 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
memtier_benchmark Protocol: Redis - Clients: 100 - Set To Get Ratio: 1:1 OpenBenchmarking.org Ops/sec, More Is Better memtier_benchmark 1.4 Protocol: Redis - Clients: 100 - Set To Get Ratio: 1:1 AA A B C 400K 800K 1200K 1600K 2000K 1699071.04 1696795.22 1694596.39 1693867.55 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
7-Zip Compression Test: Compression Rating OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 22.01 Test: Compression Rating B AA A C 20K 40K 60K 80K 100K 87489 87486 87251 87228 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
Facebook RocksDB Test: Random Fill OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.5.3 Test: Random Fill C B AA A 200K 400K 600K 800K 1000K 917383 917048 916583 914759 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenVINO Model: Weld Porosity Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Weld Porosity Detection FP16-INT8 - Device: CPU A AA B C 7 14 21 28 35 28.03 28.07 28.11 28.11 MIN: 15.92 / MAX: 33.62 MIN: 20.47 / MAX: 37.33 MIN: 22.38 / MAX: 36.76 MIN: 21.15 / MAX: 36.53 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
Aircrack-ng OpenBenchmarking.org k/s, More Is Better Aircrack-ng 1.7 A AA B C 10K 20K 30K 40K 50K 45430.83 45409.45 45339.31 45303.35 1. (CXX) g++ options: -std=gnu++17 -O3 -fvisibility=hidden -fcommon -rdynamic -lnl-3 -lnl-genl-3 -lpcre -lsqlite3 -lpthread -lz -lssl -lcrypto -lhwloc -ldl -lm -pthread
OpenVINO Model: Weld Porosity Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Weld Porosity Detection FP16-INT8 - Device: CPU A AA B C 90 180 270 360 450 427.87 427.35 426.73 426.70 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Vehicle Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16-INT8 - Device: CPU AA A C B 80 160 240 320 400 369.90 369.89 369.83 368.92 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
Timed Node.js Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Node.js Compilation 18.8 Time To Compile AA C B A 90 180 270 360 450 411.32 411.68 412.15 412.36
OpenVINO Model: Vehicle Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16-INT8 - Device: CPU A AA C B 4 8 12 16 20 16.21 16.21 16.21 16.25 MIN: 10.98 / MAX: 24.75 MIN: 11.48 / MAX: 24.91 MIN: 11.31 / MAX: 25.92 MIN: 11.68 / MAX: 26.33 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU B AA C A 3K 6K 9K 12K 15K 12954.74 12948.36 12937.00 12924.91 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
Primesieve Length: 1e13 OpenBenchmarking.org Seconds, Fewer Is Better Primesieve 8.0 Length: 1e13 AA A B C 40 80 120 160 200 173.90 174.02 174.23 174.29 1. (CXX) g++ options: -O3
Dragonflydb Clients: 50 - Set To Get Ratio: 1:5 OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 0.6 Clients: 50 - Set To Get Ratio: 1:5 AA B C A 700K 1400K 2100K 2800K 3500K 3135276.20 3135021.28 3129879.97 3129187.64 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
NCNN Target: Vulkan GPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: vgg16 B A AA C 1.2555 2.511 3.7665 5.022 6.2775 5.57 5.58 5.58 5.58 MIN: 5.53 / MAX: 5.84 MIN: 5.52 / MAX: 8.52 MIN: 5.54 / MAX: 5.81 MIN: 5.53 / MAX: 5.93 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
ASTC Encoder Preset: Exhaustive OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.0 Preset: Exhaustive A AA C B 0.1771 0.3542 0.5313 0.7084 0.8855 0.7872 0.7866 0.7865 0.7858 1. (CXX) g++ options: -O3 -flto -pthread
ASTC Encoder Preset: Thorough OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.0 Preset: Thorough A C B AA 2 4 6 8 10 7.2108 7.2072 7.2038 7.1996 1. (CXX) g++ options: -O3 -flto -pthread
ASTC Encoder Preset: Medium OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.0 Preset: Medium A B C AA 14 28 42 56 70 60.92 60.87 60.87 60.84 1. (CXX) g++ options: -O3 -flto -pthread
OpenVINO Model: Weld Porosity Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Weld Porosity Detection FP16 - Device: CPU B AA C A 70 140 210 280 350 302.53 302.44 302.39 302.20 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Weld Porosity Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Weld Porosity Detection FP16 - Device: CPU B AA C A 5 10 15 20 25 19.81 19.82 19.82 19.83 MIN: 10.65 / MAX: 32.44 MIN: 10.46 / MAX: 44.36 MIN: 14.28 / MAX: 34.13 MIN: 10.34 / MAX: 29.08 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU A AA B C 0.207 0.414 0.621 0.828 1.035 0.92 0.92 0.92 0.92 MIN: 0.54 / MAX: 32.37 MIN: 0.54 / MAX: 2.2 MIN: 0.54 / MAX: 9.48 MIN: 0.55 / MAX: 2.72 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
NCNN Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 A AA B C 0.6908 1.3816 2.0724 2.7632 3.454 3.07 3.07 3.07 3.07 MIN: 2.93 / MAX: 5.4 MIN: 2.95 / MAX: 4.07 MIN: 2.94 / MAX: 4.06 MIN: 2.95 / MAX: 4.06 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
etcd Test: RANGE - Connections: 500 - Clients: 1000 - Average Latency OpenBenchmarking.org ms, Fewer Is Better etcd 3.5.4 Test: RANGE - Connections: 500 - Clients: 1000 - Average Latency A AA B C 3 6 9 12 15 12.8 12.8 12.8 12.8
etcd Test: RANGE - Connections: 500 - Clients: 100 - Average Latency OpenBenchmarking.org ms, Fewer Is Better etcd 3.5.4 Test: RANGE - Connections: 500 - Clients: 100 - Average Latency A AA B C 0.2925 0.585 0.8775 1.17 1.4625 1.3 1.3 1.3 1.3
etcd Test: RANGE - Connections: 100 - Clients: 100 - Average Latency OpenBenchmarking.org ms, Fewer Is Better etcd 3.5.4 Test: RANGE - Connections: 100 - Clients: 100 - Average Latency A AA B C 0.2925 0.585 0.8775 1.17 1.4625 1.3 1.3 1.3 1.3
etcd Test: RANGE - Connections: 50 - Clients: 100 - Average Latency OpenBenchmarking.org ms, Fewer Is Better etcd 3.5.4 Test: RANGE - Connections: 50 - Clients: 100 - Average Latency A AA B C 0.2925 0.585 0.8775 1.17 1.4625 1.3 1.3 1.3 1.3
Phoronix Test Suite v10.8.4