8700k september Intel Core i7-8700K testing with a ASUS TUF Z370-PLUS GAMING (2001 BIOS) and ASUS Intel UHD 630 CFL GT2 3GB on Ubuntu 20.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2109241-TJ-8700KSEPT60&sor&grs .
8700k september Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server OpenGL OpenCL Compiler File-System Screen Resolution 1 2 3 4 Intel Core i7-8700K @ 4.70GHz (6 Cores / 12 Threads) ASUS TUF Z370-PLUS GAMING (2001 BIOS) Intel 8th Gen Core 16GB 128GB Toshiba THNSN5128GPU7 ASUS Intel UHD 630 CFL GT2 3GB (1200MHz) Realtek ALC887-VD VA2431 Intel I219-V Ubuntu 20.04 5.9.0-050900rc6daily20200923-generic (x86_64) 20200922 GNOME Shell 3.36.4 X Server 1.20.9 4.6 Mesa 20.0.8 OpenCL 2.1 GCC 9.3.0 ext4 1920x1080 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,hsa --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-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 Processor Details - Scaling Governor: intel_pstate powersave - CPU Microcode: 0xde - Thermald 1.9.1 Java Details - OpenJDK Runtime Environment (build 11.0.11+9-Ubuntu-0ubuntu2.20.04) Python Details - Python 2.7.18 + Python 3.8.10 Security Details - itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT vulnerable + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Mitigation of PTI + 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 Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Mitigation of Microcode + tsx_async_abort: Mitigation of Clear buffers; SMT vulnerable
8700k september stress-ng: Memory Copying stress-ng: MMAP ncnn: Vulkan GPU-v2-v2 - mobilenet-v2 renaissance: Apache Spark Bayes ncnn: Vulkan GPU - blazeface renaissance: Apache Spark PageRank renaissance: Scala Dotty cassandra: Reads cassandra: Mixed 1:3 compress-zstd: 8, Long Mode - Compression Speed nginx: 1 rocksdb: Seq Fill stress-ng: Atomic rocksdb: Rand Fill rocksdb: Read While Writing npb: EP.D natron: Spaceship cassandra: Mixed 1:1 ncnn: Vulkan GPU - mnasnet ecp-candle: P1B2 ncnn: Vulkan GPU - mobilenet npb: EP.C vpxenc: Speed 0 - Bosphorus 1080p embree: Pathtracer - Crown openvkl: vklBenchmark Scalar stress-ng: CPU Cache lczero: BLAS rocksdb: Rand Fill Sync lczero: Eigen ncnn: Vulkan GPU - alexnet renaissance: Rand Forest npb: FT.C srsran: OFDM_Test stress-ng: Matrix Math renaissance: In-Memory Database Shootout renaissance: Apache Spark ALS stress-ng: Context Switching vpxenc: Speed 5 - Bosphorus 4K ncnn: CPU - blazeface renaissance: Genetic Algorithm Using Jenetics + Futures rocksdb: Read Rand Write Rand compress-zstd: 3, Long Mode - Compression Speed cassandra: Writes npb: CG.C ncnn: CPU - shufflenet-v2 ncnn: Vulkan GPU-v3-v3 - mobilenet-v3 rocksdb: Rand Read ncnn: CPU-v3-v3 - mobilenet-v3 renaissance: Akka Unbalanced Cobwebbed Tree renaissance: Finagle HTTP Requests compress-zstd: 3 - Compression Speed mnn: squeezenetv1.1 compress-zstd: 8 - Compression Speed renaissance: Savina Reactors.IO renaissance: ALS Movie Lens npb: LU.C ncnn: Vulkan GPU - shufflenet-v2 stress-ng: Forking yquake2: OpenGL 3.x - 1920 x 1080 ncnn: Vulkan GPU - regnety_400m stress-ng: Glibc Qsort Data Sorting rocksdb: Update Rand stress-ng: Socket Activity srsran: 4G PHY_DL_Test 100 PRB SISO 256-QAM vpxenc: Speed 5 - Bosphorus 1080p jpegxl-decode: 1 stress-ng: Semaphores yquake2: OpenGL 1.x - 1920 x 1080 glmark2: 1920 x 1080 compress-zstd: 19 - Compression Speed ncnn: Vulkan GPU - vgg16 jpegxl: JPEG - 8 svt-av1: Preset 4 - Bosphorus 1080p ncnn: Vulkan GPU - yolov4-tiny simdjson: Kostya srsran: 4G PHY_DL_Test 100 PRB MIMO 256-QAM mnn: inception-v3 simdjson: LargeRand srsran: 4G PHY_DL_Test 100 PRB SISO 256-QAM glmark2: 1024 x 768 dav1d: Summer Nature 1080p mnn: MobileNetV2_224 yquake2: Software CPU - 1920 x 1080 astcenc: Medium compress-zstd: 19, Long Mode - Compression Speed embree: Pathtracer ISPC - Crown embree: Pathtracer ISPC - Asian Dragon Obj build-gcc: Time To Compile simdjson: DistinctUserID stress-ng: System V Message Passing npb: BT.C dav1d: Chimera 1080p stress-ng: Glibc C String Functions compress-zstd: 19, Long Mode - Decompression Speed mnn: mobilenetV3 gromacs: MPI CPU - water_GMX50_bare glmark2: 1280 x 1024 ncnn: CPU - mnasnet ncnn: CPU - regnety_400m srsran: 4G PHY_DL_Test 100 PRB MIMO 64-QAM brl-cad: VGR Performance Metric tnn: CPU - DenseNet srsran: 5G PHY_DL_NR Test 270 PRB SISO 256-QAM build-ffmpeg: Time To Compile stress-ng: RdRand ncnn: Vulkan GPU - efficientnet-b0 stress-ng: NUMA srsran: 4G PHY_DL_Test 100 PRB MIMO 64-QAM compress-zstd: 8 - Decompression Speed jpegxl-decode: All srsran: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM jpegxl: PNG - 7 tnn: CPU - MobileNet v2 yafaray: Total Time For Sample Scene nginx: 500 build-gdb: Time To Compile yquake2: Vulkan - 1920 x 1080 compress-zstd: 8, Long Mode - Decompression Speed svt-av1: Preset 8 - Bosphorus 4K embree: Pathtracer - Asian Dragon jpegxl: PNG - 5 stress-ng: MEMFD ncnn: CPU - resnet50 mnn: SqueezeNetV1.0 blosc: blosclz svt-av1: Preset 8 - Bosphorus 1080p mnn: resnet-v2-50 compress-zstd: 19 - Decompression Speed glmark2: 800 x 600 keydb: ncnn: CPU - alexnet embree: Pathtracer ISPC - Asian Dragon nginx: 1000 srsran: 4G PHY_DL_Test 100 PRB SISO 64-QAM stress-ng: CPU Stress jpegxl: JPEG - 7 synthmark: VoiceMark_100 ncnn: CPU - googlenet mnn: mobilenet-v1-1.0 jpegxl: JPEG - 5 ecp-candle: P3B2 srsran: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM compress-zstd: 3, Long Mode - Decompression Speed svt-av1: Preset 4 - Bosphorus 4K srsran: 4G PHY_DL_Test 100 PRB MIMO 256-QAM srsran: 4G PHY_DL_Test 100 PRB SISO 64-QAM ncnn: CPU - resnet18 ncnn: Vulkan GPU - googlenet embree: Pathtracer - Asian Dragon Obj simdjson: PartialTweets ncnn: CPU - mobilenet stress-ng: Vector Math npb: MG.C tachyon: Total Time astcenc: Thorough ncnn: CPU-v2-v2 - mobilenet-v2 ncnn: Vulkan GPU - squeezenet_ssd ncnn: CPU - yolov4-tiny stress-ng: Malloc dav1d: Summer Nature 4K stress-ng: SENDFILE ncnn: Vulkan GPU - resnet18 ncnn: CPU - vgg16 tnn: CPU - SqueezeNet v2 tnn: CPU - SqueezeNet v1.1 openssl: RSA4096 nginx: 20 npb: SP.B build-linux-kernel: Time To Compile srsran: 5G PHY_DL_NR Test 270 PRB SISO 256-QAM nginx: 200 nginx: 100 ncnn: Vulkan GPU - resnet50 dav1d: Chimera 1080p 10-bit openssl: RSA4096 astcenc: Exhaustive stress-ng: Crypto ecp-candle: P3B1 npb: SP.C ncnn: CPU - squeezenet_ssd openssl: SHA256 ncnn: CPU - efficientnet-b0 openvkl: vklBenchmark ISPC oidn: RTLightmap.hdr.4096x4096 oidn: RT.ldr_alb_nrm.3840x2160 oidn: RT.hdr_alb_nrm.3840x2160 vpxenc: Speed 0 - Bosphorus 4K jpegxl: PNG - 8 npb: IS.D 1 2 3 4 2861.38 82.1 16.35 1943.3 3.34 3714.4 837.8 59507 50971 267.6 25589.31 895892 198492.65 588391 1256835 947.62 1.8 52402 16.68 39.137 34.63 900.51 9.42 7.3522 24 183.16 1076 1036 1033 44.82 681.9 10034.43 119200000 31887.67 3082.0 2394.0 2404623.57 10.57 1.52 1379.1 1212611 1001.2 67763 4205 3.66 16.95 34111986 4.05 11785.7 2263.3 1956.6 3.664 217 10119.0 6931.0 19134 16.97 40882.32 227.8 17.24 106.6 356642 6244.83 266.3 27.06 55.14 836841.96 165.8 713 27.2 187.81 28.17 3.119 74.98 2.97 140.4 37.154 1 426.5 2095 500.2 3.164 121.5 5.2883 22.2 8.6217 9.3601 1246.309 4.94 5045343.65 18433.22 547.92 854399.5 3466.8 1.923 0.778 1170 3.91 9.62 128.4 85965 3470.262 148.6 80.916 5756.81 24.63 137.69 385.1 3941.1 241.96 60.4 8.2 330.699 208.641 338833.88 89.744 65.1 4224.8 11.882 8.8994 31.96 587.49 28.16 5.11 13281.3 38.149 36.473 3432.1 3204 604573.44 13.82 10.3291 324545.2 223.8 12709.69 72.4 737.084 15 4.223 72.35 482.081 132 4097.8 1.121 423.9 390.4 16.08 33.24 8.3126 4.25 17.58 22943.85 9824.5 125.2927 10.0999 5 40.34 26.87 44237988.76 142.64 89585.63 29.33 64.69 68.236 288.053 130208.3 351418.03 5904.07 131.962 82 344510.8 343249.44 69.61 408.18 1982.4 93.7305 1405.32 886.95 5975.89 20.36 2253793670 6.64 54 0.14 0.29 0.29 4.42 0.8 2803.6 64.28 15.96 1832.2 2.7 3134.0 963.8 56706 51719 265.7 27640.39 888058 211339.73 553494 1278309 946.23 1.9 53528 15.85 37.199 34.7 945.49 9.61 7.6673 23 183.06 1080 1029 995 46.01 667.4 10318.42 120300000 31065.31 3151.8 2351.5 2347275.53 10.62 1.54 1412.4 1220547 1017.8 66242 4185.3 3.74 16.79 34523483 4.13 11706.0 2292.6 1980.4 3.679 219.3 10112.3 6901.3 19423.32 16.72 41030.42 230.2 17.4 105.23 355812 6167.73 269.6 26.73 55.81 846677.12 166.4 710 27 187.06 28.36 3.151 75.37 2.96 140.5 37.267 1 426.1 2114 502.74 3.142 120.4 5.3328 22.2 8.5676 9.2938 1255.031 4.95 5031152.84 18533.07 546.2 854447.49 3485.8 1.938 0.778 1179 3.94 9.69 128.5 86546 3488.811 147.7 81.388 5723.69 24.6 138.46 387.2 3961.1 243.18 60.1 8.17 329.114 208.008 339409.53 89.928 65.4 4205.8 11.829 8.8749 31.87 584.95 28.16 5.114 13323.9 38.005 36.383 3440.9 3206 602322.29 13.77 10.3665 323378.31 224.4 12739.37 72.59 734.609 15.05 4.237 72.56 482.333 131.6 4102.3 1.122 422.9 389.7 16.11 33.17 8.3322 4.25 17.55 22983.35 9831.5 125.5128 10.1208 4.99 40.35 26.84 44158669.27 142.89 89742.16 29.31 64.71 68.193 287.92 130221.2 351021.37 5911.75 131.799 81.9 344929.75 342834.35 69.67 407.88 1981.6 93.7767 1404.25 887.696 5979.89 20.37 2253807270 6.64 54 0.14 0.29 0.29 4.42 0.8 1413.05 49.6 15.81 1925.7 2.58 3111.8 954.3 52074 56102 254.5 26183.42 958352 211695.36 556988 1329713 944.43 1.8 55154 16.44 37.668 36.36 943.65 9.87 7.6921 24 190.9 1084 997 1003 45.71 659.3 10284.15 116700000 30999.8 3143.0 2327.6 2413518.88 10.33 1.5 1394.3 1240848 1024.5 67639 4279.83 3.71 17.15 34795505 4.06 11573.8 2252.0 1947.9 3.725 220.5 10001.7 6891.1 19390.39 16.72 41476.37 230.6 17.2 106.37 352203 6191.15 269.4 26.88 55.57 836974.47 166.3 718 27.1 189.1 28.46 3.141 74.84 2.99 139.1 37.526 1.01 422.4 2094 504.84 3.135 121.3 5.3364 22.2 8.6429 9.2822 1256.557 4.91 5072092.35 18384.85 543.56 847660.01 3461 1.93 0.772 1173 3.91 9.64 127.6 3467.117 148.4 81.217 5746.08 24.58 138.4 386.6 3946.2 242.65 60.1 8.17 330.725 207.628 337779.64 89.51 65.4 4225.1 11.862 8.914 31.96 584.92 28.28 5.093 13292.1 38.157 36.528 3427.7 3198 603560.52 13.78 10.3568 323869.57 224.6 12753.63 72.65 735.625 15.04 4.236 72.58 483.596 131.6 4099 1.124 424 389.4 16.12 33.16 8.332 4.26 17.59 22932.66 9844.16 125.5626 10.1154 5 40.42 26.89 44174105.62 142.72 89689.69 29.28 64.8 68.134 288.326 130379.6 350959.64 5908.31 131.896 81.9 344691.3 343172.13 69.62 407.79 1980.6 93.6921 1404.06 887.231 5980.76 20.36 2253767030 6.64 54 0.14 0.29 0.29 4.42 0.8 2373.9 3673.6 849.1 246.2 897.17 941.83 1120 1016 664.4 10350.48 3170.2 2359.4 1403.0 1018.6 4203.38 11683.1 2267.9 1978.2 218.6 10156.9 6826.2 19394.41 230.9 167.7 715 26.9 2.98 1 2102 120.8 22 4.94 18485.52 3458.7 1179 3948.3 8.21 65.3 4210.5 31.82 13334.5 3434.8 3210 4091 4.26 9846.21 5904.69 5977.62 0.8 OpenBenchmarking.org
Stress-NG Test: Memory Copying OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Memory Copying 1 2 3 600 1200 1800 2400 3000 2861.38 2803.60 1413.05 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
Stress-NG Test: MMAP OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: MMAP 1 2 3 20 40 60 80 100 82.10 64.28 49.60 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
NCNN Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 3 2 1 4 8 12 16 20 12.32 15.96 16.35 MIN: 11.4 / MAX: 12.44 MIN: 15.16 / MAX: 16.17 MIN: 16.18 / MAX: 17.05 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Renaissance Test: Apache Spark Bayes OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Apache Spark Bayes 2 3 1 4 500 1000 1500 2000 2500 1832.2 1925.7 1943.3 2373.9 MIN: 1380.94 MIN: 1437.66 MIN: 1468.54 / MAX: 1943.32 MIN: 1789.92 / MAX: 2557.61
NCNN Target: Vulkan GPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: blazeface 3 2 1 0.7515 1.503 2.2545 3.006 3.7575 2.58 2.70 3.34 MIN: 2.34 / MAX: 3.8 MIN: 2.35 / MAX: 2.99 MIN: 2.6 / MAX: 4.16 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Renaissance Test: Apache Spark PageRank OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Apache Spark PageRank 3 2 4 1 800 1600 2400 3200 4000 3111.8 3134.0 3673.6 3714.4 MIN: 2864.35 / MAX: 3232.47 MIN: 2833.85 / MAX: 3575.15 MIN: 3303.14 / MAX: 4025.05 MIN: 3343.16 / MAX: 3940.45
Renaissance Test: Scala Dotty OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Scala Dotty 1 4 3 2 200 400 600 800 1000 837.8 849.1 954.3 963.8 MIN: 658.6 / MAX: 1615.39 MIN: 657.99 / MAX: 1635.22 MIN: 675.19 / MAX: 1551.37 MIN: 661.53 / MAX: 1553.29
Apache Cassandra Test: Reads OpenBenchmarking.org Op/s, More Is Better Apache Cassandra 4.0 Test: Reads 1 2 3 13K 26K 39K 52K 65K 59507 56706 52074
Apache Cassandra Test: Mixed 1:3 OpenBenchmarking.org Op/s, More Is Better Apache Cassandra 4.0 Test: Mixed 1:3 3 2 1 12K 24K 36K 48K 60K 56102 51719 50971
Zstd Compression Compression Level: 8, Long Mode - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 8, Long Mode - Compression Speed 1 2 3 4 60 120 180 240 300 267.6 265.7 254.5 246.2 1. (CC) gcc options: -O3 -pthread -lz -llzma
nginx Concurrent Requests: 1 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.21.1 Concurrent Requests: 1 2 3 1 6K 12K 18K 24K 30K 27640.39 26183.42 25589.31 1. (CC) gcc options: -ldl -lpthread -lcrypt -lz -O3 -march=native
Facebook RocksDB Test: Sequential Fill OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Sequential Fill 3 1 2 200K 400K 600K 800K 1000K 958352 895892 888058 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Stress-NG Test: Atomic OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Atomic 3 2 1 50K 100K 150K 200K 250K 211695.36 211339.73 198492.65 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
Facebook RocksDB Test: Random Fill OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Random Fill 1 3 2 130K 260K 390K 520K 650K 588391 556988 553494 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Facebook RocksDB Test: Read While Writing OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Read While Writing 3 2 1 300K 600K 900K 1200K 1500K 1329713 1278309 1256835 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
NAS Parallel Benchmarks Test / Class: EP.D OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.D 1 2 3 4 200 400 600 800 1000 947.62 946.23 944.43 897.17 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.3
Natron Input: Spaceship OpenBenchmarking.org FPS, More Is Better Natron 2.4 Input: Spaceship 2 3 1 0.4275 0.855 1.2825 1.71 2.1375 1.9 1.8 1.8
Apache Cassandra Test: Mixed 1:1 OpenBenchmarking.org Op/s, More Is Better Apache Cassandra 4.0 Test: Mixed 1:1 3 2 1 12K 24K 36K 48K 60K 55154 53528 52402
NCNN Target: Vulkan GPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: mnasnet 2 3 1 4 8 12 16 20 15.85 16.40 16.68 MIN: 14.52 / MAX: 16.49 MIN: 15.96 / MAX: 18.66 MIN: 16.44 / MAX: 18.63 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
ECP-CANDLE Benchmark: P1B2 OpenBenchmarking.org Seconds, Fewer Is Better ECP-CANDLE 0.4 Benchmark: P1B2 2 3 1 9 18 27 36 45 37.20 37.67 39.14
NCNN Target: Vulkan GPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: mobilenet 1 2 3 8 16 24 32 40 34.63 34.70 36.36 MIN: 33.27 / MAX: 44.56 MIN: 34.38 / MAX: 42.41 MIN: 35.84 / MAX: 37.57 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NAS Parallel Benchmarks Test / Class: EP.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.C 2 3 4 1 200 400 600 800 1000 945.49 943.65 941.83 900.51 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.3
VP9 libvpx Encoding Speed: Speed 0 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.10.0 Speed: Speed 0 - Input: Bosphorus 1080p 3 2 1 3 6 9 12 15 9.87 9.61 9.42 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
Embree Binary: Pathtracer - Model: Crown OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer - Model: Crown 3 2 1 2 4 6 8 10 7.6921 7.6673 7.3522 MIN: 7.65 / MAX: 7.79 MIN: 7.62 / MAX: 7.78 MIN: 7.29 / MAX: 7.54
OpenVKL Benchmark: vklBenchmark Scalar OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 1.0 Benchmark: vklBenchmark Scalar 3 1 2 6 12 18 24 30 24 24 23 MIN: 2 / MAX: 430 MIN: 2 / MAX: 429 MIN: 2 / MAX: 427
Stress-NG Test: CPU Cache OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: CPU Cache 3 1 2 40 80 120 160 200 190.90 183.16 183.06 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
LeelaChessZero Backend: BLAS OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.28 Backend: BLAS 4 3 2 1 200 400 600 800 1000 1120 1084 1080 1076 1. (CXX) g++ options: -flto -pthread
Facebook RocksDB Test: Random Fill Sync OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Random Fill Sync 1 2 3 200 400 600 800 1000 1036 1029 997 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
LeelaChessZero Backend: Eigen OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.28 Backend: Eigen 1 4 3 2 200 400 600 800 1000 1033 1016 1003 995 1. (CXX) g++ options: -flto -pthread
NCNN Target: Vulkan GPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: alexnet 1 3 2 11 22 33 44 55 44.82 45.71 46.01 MIN: 43.05 / MAX: 47.81 MIN: 43.86 / MAX: 49.34 MIN: 43.93 / MAX: 48.73 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Renaissance Test: Random Forest OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Random Forest 3 4 2 1 150 300 450 600 750 659.3 664.4 667.4 681.9 MIN: 589.9 / MAX: 870.19 MIN: 597.87 / MAX: 819.34 MIN: 594.24 / MAX: 808.57 MIN: 626.97 / MAX: 854.53
NAS Parallel Benchmarks Test / Class: FT.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: FT.C 4 2 3 1 2K 4K 6K 8K 10K 10350.48 10318.42 10284.15 10034.43 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.3
srsRAN Test: OFDM_Test OpenBenchmarking.org Samples / Second, More Is Better srsRAN 21.04 Test: OFDM_Test 2 1 3 30M 60M 90M 120M 150M 120300000 119200000 116700000 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lm -lfftw3f
Stress-NG Test: Matrix Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Matrix Math 1 2 3 7K 14K 21K 28K 35K 31887.67 31065.31 30999.80 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
Renaissance Test: In-Memory Database Shootout OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: In-Memory Database Shootout 1 3 2 4 700 1400 2100 2800 3500 3082.0 3143.0 3151.8 3170.2 MIN: 2812.15 / MAX: 3369.52 MIN: 2835.33 / MAX: 3277.78 MIN: 2916.1 / MAX: 3397.29 MIN: 2840.28 / MAX: 3425.3
Renaissance Test: Apache Spark ALS OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Apache Spark ALS 3 2 4 1 500 1000 1500 2000 2500 2327.6 2351.5 2359.4 2394.0 MIN: 2196.84 / MAX: 2599.78 MIN: 2195.25 / MAX: 2645.91 MIN: 2217.17 / MAX: 2596.35 MIN: 2269.78 / MAX: 2631.65
Stress-NG Test: Context Switching OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Context Switching 3 1 2 500K 1000K 1500K 2000K 2500K 2413518.88 2404623.57 2347275.53 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
VP9 libvpx Encoding Speed: Speed 5 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.10.0 Speed: Speed 5 - Input: Bosphorus 4K 2 1 3 3 6 9 12 15 10.62 10.57 10.33 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
NCNN Target: CPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: blazeface 3 1 2 0.3465 0.693 1.0395 1.386 1.7325 1.50 1.52 1.54 MIN: 1.47 / MAX: 1.7 MIN: 1.49 / MAX: 1.76 MIN: 1.53 / MAX: 1.71 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Renaissance Test: Genetic Algorithm Using Jenetics + Futures OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Genetic Algorithm Using Jenetics + Futures 1 3 4 2 300 600 900 1200 1500 1379.1 1394.3 1403.0 1412.4 MIN: 1335.09 / MAX: 1438.71 MIN: 1358.13 / MAX: 1410.9 MIN: 1365.73 / MAX: 1429.32 MIN: 1396.58 / MAX: 1435.51
Facebook RocksDB Test: Read Random Write Random OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Read Random Write Random 3 2 1 300K 600K 900K 1200K 1500K 1240848 1220547 1212611 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Zstd Compression Compression Level: 3, Long Mode - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 3, Long Mode - Compression Speed 3 4 2 1 200 400 600 800 1000 1024.5 1018.6 1017.8 1001.2 1. (CC) gcc options: -O3 -pthread -lz -llzma
Apache Cassandra Test: Writes OpenBenchmarking.org Op/s, More Is Better Apache Cassandra 4.0 Test: Writes 1 3 2 15K 30K 45K 60K 75K 67763 67639 66242
NAS Parallel Benchmarks Test / Class: CG.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: CG.C 3 1 4 2 900 1800 2700 3600 4500 4279.83 4205.00 4203.38 4185.30 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.3
NCNN Target: CPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: shufflenet-v2 1 3 2 0.8415 1.683 2.5245 3.366 4.2075 3.66 3.71 3.74 MIN: 3.63 / MAX: 3.81 MIN: 3.69 / MAX: 3.88 MIN: 3.71 / MAX: 3.95 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 2 3 1 4 8 12 16 20 16.79 16.83 16.95 MIN: 16.33 / MAX: 18.05 MIN: 12.8 / MAX: 17.86 MIN: 16.57 / MAX: 18.51 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Facebook RocksDB Test: Random Read OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Random Read 3 2 1 7M 14M 21M 28M 35M 34795505 34523483 34111986 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 20210720 Target: CPU-v3-v3 - Model: mobilenet-v3 1 3 2 0.9293 1.8586 2.7879 3.7172 4.6465 4.05 4.06 4.13 MIN: 4.01 / MAX: 4.2 MIN: 4.01 / MAX: 4.23 MIN: 3.99 / MAX: 4.37 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Renaissance Test: Akka Unbalanced Cobwebbed Tree OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Akka Unbalanced Cobwebbed Tree 3 4 2 1 3K 6K 9K 12K 15K 11573.8 11683.1 11706.0 11785.7 MIN: 8805.09 MIN: 9175.98 MIN: 9030.07 MIN: 9230.09 / MAX: 11785.72
Renaissance Test: Finagle HTTP Requests OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Finagle HTTP Requests 3 1 4 2 500 1000 1500 2000 2500 2252.0 2263.3 2267.9 2292.6 MIN: 2087.63 / MAX: 2255.64 MIN: 2101.74 / MAX: 2301.08 MIN: 2120.25 / MAX: 2267.92 MIN: 2130.42 / MAX: 2292.63
Zstd Compression Compression Level: 3 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 3 - Compression Speed 2 4 1 3 400 800 1200 1600 2000 1980.4 1978.2 1956.6 1947.9 1. (CC) gcc options: -O3 -pthread -lz -llzma
Mobile Neural Network Model: squeezenetv1.1 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: squeezenetv1.1 1 2 3 0.8381 1.6762 2.5143 3.3524 4.1905 3.664 3.679 3.725 MIN: 3.59 / MAX: 4.6 MIN: 3.6 / MAX: 3.81 MIN: 3.68 / MAX: 3.84 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
Zstd Compression Compression Level: 8 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 8 - Compression Speed 3 2 4 1 50 100 150 200 250 220.5 219.3 218.6 217.0 1. (CC) gcc options: -O3 -pthread -lz -llzma
Renaissance Test: Savina Reactors.IO OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Savina Reactors.IO 3 2 1 4 2K 4K 6K 8K 10K 10001.7 10112.3 10119.0 10156.9 MAX: 14205.21 MAX: 14389.21 MAX: 14229.78 MAX: 14525.95
Renaissance Test: ALS Movie Lens OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: ALS Movie Lens 4 3 2 1 1500 3000 4500 6000 7500 6826.2 6891.1 6901.3 6931.0 MAX: 7516 MIN: 6891.09 / MAX: 7639.17 MIN: 6901.27 / MAX: 7633.19 MAX: 7698.11
NAS Parallel Benchmarks Test / Class: LU.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: LU.C 2 4 3 1 4K 8K 12K 16K 20K 19423.32 19394.41 19390.39 19134.00 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.3
NCNN Target: Vulkan GPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: shufflenet-v2 2 3 1 4 8 12 16 20 16.72 16.72 16.97 MIN: 15.45 / MAX: 17.43 MIN: 16.08 / MAX: 17.76 MIN: 16.32 / MAX: 18.27 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Stress-NG Test: Forking OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Forking 3 2 1 9K 18K 27K 36K 45K 41476.37 41030.42 40882.32 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
yquake2 Renderer: OpenGL 3.x - Resolution: 1920 x 1080 OpenBenchmarking.org Frames Per Second, More Is Better yquake2 8.0 Renderer: OpenGL 3.x - Resolution: 1920 x 1080 4 3 2 1 50 100 150 200 250 230.9 230.6 230.2 227.8 1. (CC) gcc options: -lm -ldl -rdynamic -shared -lSDL2 -O2 -pipe -fomit-frame-pointer -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC
NCNN Target: Vulkan GPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: regnety_400m 3 1 2 4 8 12 16 20 17.17 17.24 17.40 MIN: 16.8 / MAX: 17.53 MIN: 16.9 / MAX: 17.7 MIN: 16.85 / MAX: 17.98 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Stress-NG Test: Glibc Qsort Data Sorting OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Glibc Qsort Data Sorting 1 3 2 20 40 60 80 100 106.60 106.37 105.23 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
Facebook RocksDB Test: Update Random OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Update Random 1 2 3 80K 160K 240K 320K 400K 356642 355812 352203 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Stress-NG Test: Socket Activity OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Socket Activity 1 3 2 1300 2600 3900 5200 6500 6244.83 6191.15 6167.73 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
srsRAN Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM 2 3 1 60 120 180 240 300 269.6 269.4 266.3 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lm -lfftw3f
VP9 libvpx Encoding Speed: Speed 5 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.10.0 Speed: Speed 5 - Input: Bosphorus 1080p 1 3 2 6 12 18 24 30 27.06 26.88 26.73 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
JPEG XL Decoding libjxl CPU Threads: 1 OpenBenchmarking.org MP/s, More Is Better JPEG XL Decoding libjxl 0.5 CPU Threads: 1 2 3 1 13 26 39 52 65 55.81 55.57 55.14
Stress-NG Test: Semaphores OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Semaphores 2 3 1 200K 400K 600K 800K 1000K 846677.12 836974.47 836841.96 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
yquake2 Renderer: OpenGL 1.x - Resolution: 1920 x 1080 OpenBenchmarking.org Frames Per Second, More Is Better yquake2 8.0 Renderer: OpenGL 1.x - Resolution: 1920 x 1080 4 2 3 1 40 80 120 160 200 167.7 166.4 166.3 165.8 1. (CC) gcc options: -lm -ldl -rdynamic -shared -lSDL2 -O2 -pipe -fomit-frame-pointer -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC
GLmark2 Resolution: 1920 x 1080 OpenBenchmarking.org Score, More Is Better GLmark2 2021.08.30 Resolution: 1920 x 1080 3 4 1 2 150 300 450 600 750 718 715 713 710
Zstd Compression Compression Level: 19 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19 - Compression Speed 1 3 2 4 6 12 18 24 30 27.2 27.1 27.0 26.9 1. (CC) gcc options: -O3 -pthread -lz -llzma
NCNN Target: Vulkan GPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: vgg16 2 1 3 40 80 120 160 200 187.06 187.81 188.22 MIN: 185.46 / MAX: 189 MIN: 186.31 / MAX: 190.16 MIN: 186.7 / MAX: 189.79 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
JPEG XL libjxl Input: JPEG - Encode Speed: 8 OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.5 Input: JPEG - Encode Speed: 8 3 2 1 7 14 21 28 35 28.46 28.36 28.17 1. (CXX) g++ options: -funwind-tables -O3 -O2 -fPIE -pie -pthread
SVT-AV1 Encoder Mode: Preset 4 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.8.7 Encoder Mode: Preset 4 - Input: Bosphorus 1080p 2 3 1 0.709 1.418 2.127 2.836 3.545 3.151 3.141 3.119 1. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
NCNN Target: Vulkan GPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: yolov4-tiny 3 1 2 20 40 60 80 100 74.61 74.98 75.37 MIN: 66.91 / MAX: 78.55 MIN: 67.54 / MAX: 81.06 MIN: 60.66 / MAX: 108.78 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
simdjson Throughput Test: Kostya OpenBenchmarking.org GB/s, More Is Better simdjson 1.0 Throughput Test: Kostya 3 4 1 2 0.6728 1.3456 2.0184 2.6912 3.364 2.99 2.98 2.97 2.96 1. (CXX) g++ options: -O3 -pthread
srsRAN Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM 2 1 3 30 60 90 120 150 140.5 140.4 139.1 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lm -lfftw3f
Mobile Neural Network Model: inception-v3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: inception-v3 1 2 3 9 18 27 36 45 37.15 37.27 37.53 MIN: 36.99 / MAX: 51.7 MIN: 37.14 / MAX: 37.9 MIN: 37.38 / MAX: 53.06 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
simdjson Throughput Test: LargeRandom OpenBenchmarking.org GB/s, More Is Better simdjson 1.0 Throughput Test: LargeRandom 3 4 2 1 0.2273 0.4546 0.6819 0.9092 1.1365 1.01 1.00 1.00 1.00 1. (CXX) g++ options: -O3 -pthread
srsRAN Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM 1 2 3 90 180 270 360 450 426.5 426.1 422.4 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lm -lfftw3f
GLmark2 Resolution: 1024 x 768 OpenBenchmarking.org Score, More Is Better GLmark2 2021.08.30 Resolution: 1024 x 768 2 4 1 3 500 1000 1500 2000 2500 2114 2102 2095 2094
dav1d Video Input: Summer Nature 1080p OpenBenchmarking.org FPS, More Is Better dav1d 0.9.2 Video Input: Summer Nature 1080p 3 2 1 110 220 330 440 550 504.84 502.74 500.20 MIN: 465.42 / MAX: 549.28 MIN: 455.71 / MAX: 549.04 MIN: 436.95 / MAX: 546.86 1. (CC) gcc options: -pthread -lm
Mobile Neural Network Model: MobileNetV2_224 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: MobileNetV2_224 3 2 1 0.7119 1.4238 2.1357 2.8476 3.5595 3.135 3.142 3.164 MIN: 3.06 / MAX: 3.61 MIN: 3.07 / MAX: 3.58 MIN: 3.11 / MAX: 3.27 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
yquake2 Renderer: Software CPU - Resolution: 1920 x 1080 OpenBenchmarking.org Frames Per Second, More Is Better yquake2 8.0 Renderer: Software CPU - Resolution: 1920 x 1080 1 3 4 2 30 60 90 120 150 121.5 121.3 120.8 120.4 1. (CC) gcc options: -lm -ldl -rdynamic -shared -lSDL2 -O2 -pipe -fomit-frame-pointer -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC
ASTC Encoder Preset: Medium OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 3.0 Preset: Medium 1 2 3 1.2007 2.4014 3.6021 4.8028 6.0035 5.2883 5.3328 5.3364 1. (CXX) g++ options: -O3 -flto -pthread
Zstd Compression Compression Level: 19, Long Mode - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19, Long Mode - Compression Speed 3 2 1 4 5 10 15 20 25 22.2 22.2 22.2 22.0 1. (CC) gcc options: -O3 -pthread -lz -llzma
Embree Binary: Pathtracer ISPC - Model: Crown OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Crown 3 1 2 2 4 6 8 10 8.6429 8.6217 8.5676 MIN: 8.57 / MAX: 8.79 MIN: 8.57 / MAX: 8.76 MIN: 8.48 / MAX: 8.71
Embree Binary: Pathtracer ISPC - Model: Asian Dragon Obj OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Asian Dragon Obj 1 2 3 3 6 9 12 15 9.3601 9.2938 9.2822 MIN: 9.32 / MAX: 9.49 MIN: 9.25 / MAX: 9.4 MIN: 9.24 / MAX: 9.39
Timed GCC Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed GCC Compilation 11.2.0 Time To Compile 1 2 3 300 600 900 1200 1500 1246.31 1255.03 1256.56
simdjson Throughput Test: DistinctUserID OpenBenchmarking.org GB/s, More Is Better simdjson 1.0 Throughput Test: DistinctUserID 2 4 1 3 1.1138 2.2276 3.3414 4.4552 5.569 4.95 4.94 4.94 4.91 1. (CXX) g++ options: -O3 -pthread
Stress-NG Test: System V Message Passing OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: System V Message Passing 3 1 2 1.1M 2.2M 3.3M 4.4M 5.5M 5072092.35 5045343.65 5031152.84 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
NAS Parallel Benchmarks Test / Class: BT.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: BT.C 2 4 1 3 4K 8K 12K 16K 20K 18533.07 18485.52 18433.22 18384.85 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.3
dav1d Video Input: Chimera 1080p OpenBenchmarking.org FPS, More Is Better dav1d 0.9.2 Video Input: Chimera 1080p 1 2 3 120 240 360 480 600 547.92 546.20 543.56 MIN: 405.96 / MAX: 832.49 MIN: 404.97 / MAX: 803.92 MIN: 404.33 / MAX: 817.25 1. (CC) gcc options: -pthread -lm
Stress-NG Test: Glibc C String Functions OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Glibc C String Functions 2 1 3 200K 400K 600K 800K 1000K 854447.49 854399.50 847660.01 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
Zstd Compression Compression Level: 19, Long Mode - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19, Long Mode - Decompression Speed 2 1 3 4 700 1400 2100 2800 3500 3485.8 3466.8 3461.0 3458.7 1. (CC) gcc options: -O3 -pthread -lz -llzma
Mobile Neural Network Model: mobilenetV3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: mobilenetV3 1 3 2 0.4361 0.8722 1.3083 1.7444 2.1805 1.923 1.930 1.938 MIN: 1.88 / MAX: 3.98 MIN: 1.88 / MAX: 3.12 MIN: 1.91 / MAX: 3.15 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
GROMACS Implementation: MPI CPU - Input: water_GMX50_bare OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2021.2 Implementation: MPI CPU - Input: water_GMX50_bare 2 1 3 0.1751 0.3502 0.5253 0.7004 0.8755 0.778 0.778 0.772 1. (CXX) g++ options: -O3 -pthread
GLmark2 Resolution: 1280 x 1024 OpenBenchmarking.org Score, More Is Better GLmark2 2021.08.30 Resolution: 1280 x 1024 4 2 3 1 300 600 900 1200 1500 1179 1179 1173 1170
NCNN Target: CPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: mnasnet 1 3 2 0.8865 1.773 2.6595 3.546 4.4325 3.91 3.91 3.94 MIN: 3.88 / MAX: 4.17 MIN: 3.88 / MAX: 4.09 MIN: 3.91 / MAX: 4.1 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: regnety_400m 1 3 2 3 6 9 12 15 9.62 9.64 9.69 MIN: 9.57 / MAX: 9.68 MIN: 9.6 / MAX: 9.69 MIN: 9.65 / MAX: 9.95 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
srsRAN Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM 2 1 3 30 60 90 120 150 128.5 128.4 127.6 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lm -lfftw3f
BRL-CAD VGR Performance Metric OpenBenchmarking.org VGR Performance Metric, More Is Better BRL-CAD 7.32.2 VGR Performance Metric 2 1 20K 40K 60K 80K 100K 86546 85965 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 -pthread -ldl -lm
TNN Target: CPU - Model: DenseNet OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: DenseNet 3 1 2 700 1400 2100 2800 3500 3467.12 3470.26 3488.81 MIN: 3461.83 / MAX: 3475.19 MIN: 3462.7 / MAX: 3660.27 MIN: 3483.75 / MAX: 3527.85 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
srsRAN Test: 5G PHY_DL_NR Test 270 PRB SISO 256-QAM OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 21.04 Test: 5G PHY_DL_NR Test 270 PRB SISO 256-QAM 1 3 2 30 60 90 120 150 148.6 148.4 147.7 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lm -lfftw3f
Timed FFmpeg Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed FFmpeg Compilation 4.4 Time To Compile 1 3 2 20 40 60 80 100 80.92 81.22 81.39
Stress-NG Test: RdRand OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: RdRand 1 3 2 1200 2400 3600 4800 6000 5756.81 5746.08 5723.69 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
NCNN Target: Vulkan GPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: efficientnet-b0 3 2 1 6 12 18 24 30 24.58 24.60 24.63 MIN: 24.23 / MAX: 24.66 MIN: 24.2 / MAX: 24.66 MIN: 23.26 / MAX: 24.85 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Stress-NG Test: NUMA OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: NUMA 2 3 1 30 60 90 120 150 138.46 138.40 137.69 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
srsRAN Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM 2 3 1 80 160 240 320 400 387.2 386.6 385.1 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lm -lfftw3f
Zstd Compression Compression Level: 8 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 8 - Decompression Speed 2 4 3 1 800 1600 2400 3200 4000 3961.1 3948.3 3946.2 3941.1 1. (CC) gcc options: -O3 -pthread -lz -llzma
JPEG XL Decoding libjxl CPU Threads: All OpenBenchmarking.org MP/s, More Is Better JPEG XL Decoding libjxl 0.5 CPU Threads: All 2 3 1 50 100 150 200 250 243.18 242.65 241.96
srsRAN Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 21.04 Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM 1 3 2 14 28 42 56 70 60.4 60.1 60.1 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lm -lfftw3f
JPEG XL libjxl Input: PNG - Encode Speed: 7 OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.5 Input: PNG - Encode Speed: 7 4 1 3 2 2 4 6 8 10 8.21 8.20 8.17 8.17 1. (CXX) g++ options: -funwind-tables -O3 -O2 -fPIE -pie -pthread
TNN Target: CPU - Model: MobileNet v2 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: MobileNet v2 2 1 3 70 140 210 280 350 329.11 330.70 330.73 MIN: 328.76 / MAX: 329.51 MIN: 330.31 / MAX: 331.08 MIN: 330.35 / MAX: 331.29 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
YafaRay Total Time For Sample Scene OpenBenchmarking.org Seconds, Fewer Is Better YafaRay 3.5.1 Total Time For Sample Scene 3 2 1 50 100 150 200 250 207.63 208.01 208.64 1. (CXX) g++ options: -std=c++11 -pthread -O3 -ffast-math -rdynamic -ldl -lImath -lIlmImf -lIex -lHalf -lz -lIlmThread -lxml2 -lfreetype
nginx Concurrent Requests: 500 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.21.1 Concurrent Requests: 500 2 1 3 70K 140K 210K 280K 350K 339409.53 338833.88 337779.64 1. (CC) gcc options: -ldl -lpthread -lcrypt -lz -O3 -march=native
Timed GDB GNU Debugger Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed GDB GNU Debugger Compilation 10.2 Time To Compile 3 1 2 20 40 60 80 100 89.51 89.74 89.93
yquake2 Renderer: Vulkan - Resolution: 1920 x 1080 OpenBenchmarking.org Frames Per Second, More Is Better yquake2 8.0 Renderer: Vulkan - Resolution: 1920 x 1080 3 2 4 1 15 30 45 60 75 65.4 65.4 65.3 65.1 1. (CC) gcc options: -lm -ldl -rdynamic -shared -lSDL2 -O2 -pipe -fomit-frame-pointer -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC
Zstd Compression Compression Level: 8, Long Mode - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 8, Long Mode - Decompression Speed 3 1 4 2 900 1800 2700 3600 4500 4225.1 4224.8 4210.5 4205.8 1. (CC) gcc options: -O3 -pthread -lz -llzma
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.8.7 Encoder Mode: Preset 8 - Input: Bosphorus 4K 1 3 2 3 6 9 12 15 11.88 11.86 11.83 1. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
Embree Binary: Pathtracer - Model: Asian Dragon OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer - Model: Asian Dragon 3 1 2 2 4 6 8 10 8.9140 8.8994 8.8749 MIN: 8.88 / MAX: 9 MIN: 8.87 / MAX: 9 MIN: 8.85 / MAX: 8.96
JPEG XL libjxl Input: PNG - Encode Speed: 5 OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.5 Input: PNG - Encode Speed: 5 3 1 2 4 7 14 21 28 35 31.96 31.96 31.87 31.82 1. (CXX) g++ options: -funwind-tables -O3 -O2 -fPIE -pie -pthread
Stress-NG Test: MEMFD OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: MEMFD 1 2 3 130 260 390 520 650 587.49 584.95 584.92 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
NCNN Target: CPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: resnet50 1 2 3 7 14 21 28 35 28.16 28.16 28.28 MIN: 28 / MAX: 28.36 MIN: 28.01 / MAX: 28.6 MIN: 28.06 / MAX: 28.44 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Mobile Neural Network Model: SqueezeNetV1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: SqueezeNetV1.0 3 1 2 1.1507 2.3014 3.4521 4.6028 5.7535 5.093 5.110 5.114 MIN: 4.98 / MAX: 5.62 MIN: 5.06 / MAX: 5.24 MIN: 5.02 / MAX: 7.45 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
C-Blosc Compressor: blosclz OpenBenchmarking.org MB/s, More Is Better C-Blosc 2.0 Compressor: blosclz 4 2 3 1 3K 6K 9K 12K 15K 13334.5 13323.9 13292.1 13281.3 1. (CC) gcc options: -std=gnu99 -O3 -pthread -lrt -lm
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.8.7 Encoder Mode: Preset 8 - Input: Bosphorus 1080p 3 1 2 9 18 27 36 45 38.16 38.15 38.01 1. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
Mobile Neural Network Model: resnet-v2-50 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: resnet-v2-50 2 1 3 8 16 24 32 40 36.38 36.47 36.53 MIN: 36.26 / MAX: 51.83 MIN: 36.25 / MAX: 36.6 MIN: 36.4 / MAX: 51.07 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
Zstd Compression Compression Level: 19 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19 - Decompression Speed 2 4 1 3 700 1400 2100 2800 3500 3440.9 3434.8 3432.1 3427.7 1. (CC) gcc options: -O3 -pthread -lz -llzma
GLmark2 Resolution: 800 x 600 OpenBenchmarking.org Score, More Is Better GLmark2 2021.08.30 Resolution: 800 x 600 4 2 1 3 700 1400 2100 2800 3500 3210 3206 3204 3198
KeyDB OpenBenchmarking.org Ops/sec, More Is Better KeyDB 6.2.0 1 3 2 130K 260K 390K 520K 650K 604573.44 603560.52 602322.29 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
NCNN Target: CPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: alexnet 2 3 1 4 8 12 16 20 13.77 13.78 13.82 MIN: 13.72 / MAX: 13.83 MIN: 13.72 / MAX: 14.03 MIN: 13.73 / MAX: 22.67 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Embree Binary: Pathtracer ISPC - Model: Asian Dragon OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Asian Dragon 2 3 1 3 6 9 12 15 10.37 10.36 10.33 MIN: 10.32 / MAX: 10.5 MIN: 10.31 / MAX: 10.49 MIN: 10.28 / MAX: 10.45
nginx Concurrent Requests: 1000 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.21.1 Concurrent Requests: 1000 1 3 2 70K 140K 210K 280K 350K 324545.20 323869.57 323378.31 1. (CC) gcc options: -ldl -lpthread -lcrypt -lz -O3 -march=native
srsRAN Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM 3 2 1 50 100 150 200 250 224.6 224.4 223.8 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lm -lfftw3f
Stress-NG Test: CPU Stress OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: CPU Stress 3 2 1 3K 6K 9K 12K 15K 12753.63 12739.37 12709.69 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
JPEG XL libjxl Input: JPEG - Encode Speed: 7 OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.5 Input: JPEG - Encode Speed: 7 3 2 1 16 32 48 64 80 72.65 72.59 72.40 1. (CXX) g++ options: -funwind-tables -O3 -O2 -fPIE -pie -pthread
Google SynthMark Test: VoiceMark_100 OpenBenchmarking.org Voices, More Is Better Google SynthMark 20201109 Test: VoiceMark_100 1 3 2 160 320 480 640 800 737.08 735.63 734.61 1. (CXX) g++ options: -lm -lpthread -std=c++11 -Ofast
NCNN Target: CPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: googlenet 1 3 2 4 8 12 16 20 15.00 15.04 15.05 MIN: 14.9 / MAX: 15.37 MIN: 14.87 / MAX: 15.66 MIN: 14.86 / MAX: 15.14 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Mobile Neural Network Model: mobilenet-v1-1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: mobilenet-v1-1.0 1 3 2 0.9533 1.9066 2.8599 3.8132 4.7665 4.223 4.236 4.237 MIN: 4.19 / MAX: 4.27 MIN: 4.2 / MAX: 4.27 MIN: 4.18 / MAX: 20.33 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
JPEG XL libjxl Input: JPEG - Encode Speed: 5 OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.5 Input: JPEG - Encode Speed: 5 3 2 1 16 32 48 64 80 72.58 72.56 72.35 1. (CXX) g++ options: -funwind-tables -O3 -O2 -fPIE -pie -pthread
ECP-CANDLE Benchmark: P3B2 OpenBenchmarking.org Seconds, Fewer Is Better ECP-CANDLE 0.4 Benchmark: P3B2 1 2 3 100 200 300 400 500 482.08 482.33 483.60
srsRAN Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 21.04 Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM 1 3 2 30 60 90 120 150 132.0 131.6 131.6 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lm -lfftw3f
Zstd Compression Compression Level: 3, Long Mode - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 3, Long Mode - Decompression Speed 2 3 1 4 900 1800 2700 3600 4500 4102.3 4099.0 4097.8 4091.0 1. (CC) gcc options: -O3 -pthread -lz -llzma
SVT-AV1 Encoder Mode: Preset 4 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.8.7 Encoder Mode: Preset 4 - Input: Bosphorus 4K 3 2 1 0.2529 0.5058 0.7587 1.0116 1.2645 1.124 1.122 1.121 1. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
srsRAN Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM 3 1 2 90 180 270 360 450 424.0 423.9 422.9 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lm -lfftw3f
srsRAN Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM 1 2 3 80 160 240 320 400 390.4 389.7 389.4 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lm -lfftw3f
NCNN Target: CPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: resnet18 1 2 3 4 8 12 16 20 16.08 16.11 16.12 MIN: 15.99 / MAX: 17 MIN: 16.02 / MAX: 16.27 MIN: 16.02 / MAX: 16.51 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: googlenet 3 2 1 8 16 24 32 40 33.16 33.17 33.24 MIN: 32.27 / MAX: 33.31 MIN: 32.78 / MAX: 33.25 MIN: 32.82 / MAX: 33.34 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Embree Binary: Pathtracer - Model: Asian Dragon Obj OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer - Model: Asian Dragon Obj 2 3 1 2 4 6 8 10 8.3322 8.3320 8.3126 MIN: 8.3 / MAX: 8.42 MIN: 8.3 / MAX: 8.4 MIN: 8.28 / MAX: 8.39
simdjson Throughput Test: PartialTweets OpenBenchmarking.org GB/s, More Is Better simdjson 1.0 Throughput Test: PartialTweets 4 3 2 1 0.9585 1.917 2.8755 3.834 4.7925 4.26 4.26 4.25 4.25 1. (CXX) g++ options: -O3 -pthread
NCNN Target: CPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: mobilenet 2 1 3 4 8 12 16 20 17.55 17.58 17.59 MIN: 17.46 / MAX: 17.73 MIN: 17.49 / MAX: 18.15 MIN: 17.52 / MAX: 17.67 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Stress-NG Test: Vector Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Vector Math 2 1 3 5K 10K 15K 20K 25K 22983.35 22943.85 22932.66 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
NAS Parallel Benchmarks Test / Class: MG.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: MG.C 4 3 2 1 2K 4K 6K 8K 10K 9846.21 9844.16 9831.50 9824.50 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.3
Tachyon Total Time OpenBenchmarking.org Seconds, Fewer Is Better Tachyon 0.99b6 Total Time 1 2 3 30 60 90 120 150 125.29 125.51 125.56 1. (CC) gcc options: -m64 -O3 -fomit-frame-pointer -ffast-math -ltachyon -lm -lpthread
ASTC Encoder Preset: Thorough OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 3.0 Preset: Thorough 1 3 2 3 6 9 12 15 10.10 10.12 10.12 1. (CXX) g++ options: -O3 -flto -pthread
NCNN Target: CPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU-v2-v2 - Model: mobilenet-v2 2 1 3 1.125 2.25 3.375 4.5 5.625 4.99 5.00 5.00 MIN: 4.92 / MAX: 5.22 MIN: 4.92 / MAX: 5.2 MIN: 4.92 / MAX: 5.26 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: squeezenet_ssd 1 2 3 9 18 27 36 45 40.34 40.35 40.42 MIN: 39.78 / MAX: 41.81 MIN: 40.08 / MAX: 40.46 MIN: 40.05 / MAX: 40.54 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: yolov4-tiny 2 1 3 6 12 18 24 30 26.84 26.87 26.89 MIN: 26.73 / MAX: 27.17 MIN: 26.74 / MAX: 27.23 MIN: 26.76 / MAX: 27.56 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Stress-NG Test: Malloc OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Malloc 1 3 2 9M 18M 27M 36M 45M 44237988.76 44174105.62 44158669.27 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
dav1d Video Input: Summer Nature 4K OpenBenchmarking.org FPS, More Is Better dav1d 0.9.2 Video Input: Summer Nature 4K 2 3 1 30 60 90 120 150 142.89 142.72 142.64 MIN: 134.86 / MAX: 160.39 MIN: 134.63 / MAX: 159.58 MIN: 134.64 / MAX: 159.26 1. (CC) gcc options: -pthread -lm
Stress-NG Test: SENDFILE OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: SENDFILE 2 3 1 20K 40K 60K 80K 100K 89742.16 89689.69 89585.63 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
NCNN Target: Vulkan GPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: resnet18 3 2 1 7 14 21 28 35 29.28 29.31 29.33 MIN: 28.2 / MAX: 29.4 MIN: 28.97 / MAX: 29.41 MIN: 29.03 / MAX: 29.43 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: vgg16 1 2 3 14 28 42 56 70 64.69 64.71 64.80 MIN: 64.58 / MAX: 64.84 MIN: 64.59 / MAX: 65.04 MIN: 64.66 / MAX: 73.88 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
TNN Target: CPU - Model: SqueezeNet v2 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v2 3 2 1 15 30 45 60 75 68.13 68.19 68.24 MIN: 68.09 / MAX: 68.25 MIN: 68.1 / MAX: 68.48 MIN: 68.13 / MAX: 68.48 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
TNN Target: CPU - Model: SqueezeNet v1.1 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v1.1 2 1 3 60 120 180 240 300 287.92 288.05 288.33 MIN: 287.44 / MAX: 288.62 MIN: 287.67 / MAX: 288.79 MIN: 287.62 / MAX: 288.91 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
OpenSSL Algorithm: RSA4096 OpenBenchmarking.org verify/s, More Is Better OpenSSL 3.0 Algorithm: RSA4096 3 2 1 30K 60K 90K 120K 150K 130379.6 130221.2 130208.3 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
nginx Concurrent Requests: 20 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.21.1 Concurrent Requests: 20 1 2 3 80K 160K 240K 320K 400K 351418.03 351021.37 350959.64 1. (CC) gcc options: -ldl -lpthread -lcrypt -lz -O3 -march=native
NAS Parallel Benchmarks Test / Class: SP.B OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.B 2 3 4 1 1300 2600 3900 5200 6500 5911.75 5908.31 5904.69 5904.07 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.3
Timed Linux Kernel Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 5.14 Time To Compile 2 3 1 30 60 90 120 150 131.80 131.90 131.96
srsRAN Test: 5G PHY_DL_NR Test 270 PRB SISO 256-QAM OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 21.04 Test: 5G PHY_DL_NR Test 270 PRB SISO 256-QAM 1 3 2 20 40 60 80 100 82.0 81.9 81.9 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lm -lfftw3f
nginx Concurrent Requests: 200 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.21.1 Concurrent Requests: 200 2 3 1 70K 140K 210K 280K 350K 344929.75 344691.30 344510.80 1. (CC) gcc options: -ldl -lpthread -lcrypt -lz -O3 -march=native
nginx Concurrent Requests: 100 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.21.1 Concurrent Requests: 100 1 3 2 70K 140K 210K 280K 350K 343249.44 343172.13 342834.35 1. (CC) gcc options: -ldl -lpthread -lcrypt -lz -O3 -march=native
NCNN Target: Vulkan GPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: resnet50 3 1 2 16 32 48 64 80 69.60 69.61 69.67 MIN: 69.18 / MAX: 69.8 MIN: 68.93 / MAX: 69.89 MIN: 69.23 / MAX: 70.1 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
dav1d Video Input: Chimera 1080p 10-bit OpenBenchmarking.org FPS, More Is Better dav1d 0.9.2 Video Input: Chimera 1080p 10-bit 1 2 3 90 180 270 360 450 408.18 407.88 407.79 MIN: 319.05 / MAX: 619.92 MIN: 318.96 / MAX: 618.37 MIN: 318.96 / MAX: 623.31 1. (CC) gcc options: -pthread -lm
OpenSSL Algorithm: RSA4096 OpenBenchmarking.org sign/s, More Is Better OpenSSL 3.0 Algorithm: RSA4096 1 2 3 400 800 1200 1600 2000 1982.4 1981.6 1980.6 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
ASTC Encoder Preset: Exhaustive OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 3.0 Preset: Exhaustive 3 1 2 20 40 60 80 100 93.69 93.73 93.78 1. (CXX) g++ options: -O3 -flto -pthread
Stress-NG Test: Crypto OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Crypto 1 2 3 300 600 900 1200 1500 1405.32 1404.25 1404.06 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
ECP-CANDLE Benchmark: P3B1 OpenBenchmarking.org Seconds, Fewer Is Better ECP-CANDLE 0.4 Benchmark: P3B1 1 3 2 200 400 600 800 1000 886.95 887.23 887.70
NAS Parallel Benchmarks Test / Class: SP.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.C 3 2 4 1 1300 2600 3900 5200 6500 5980.76 5979.89 5977.62 5975.89 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.3
NCNN Target: CPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: squeezenet_ssd 1 3 2 5 10 15 20 25 20.36 20.36 20.37 MIN: 20.15 / MAX: 20.5 MIN: 20.19 / MAX: 20.78 MIN: 20.15 / MAX: 20.73 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenSSL Algorithm: SHA256 OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.0 Algorithm: SHA256 2 1 3 500M 1000M 1500M 2000M 2500M 2253807270 2253793670 2253767030 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
NCNN Target: CPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: efficientnet-b0 1 2 3 2 4 6 8 10 6.64 6.64 6.64 MIN: 6.6 / MAX: 7.22 MIN: 6.6 / MAX: 6.82 MIN: 6.59 / MAX: 6.84 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenVKL Benchmark: vklBenchmark ISPC OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 1.0 Benchmark: vklBenchmark ISPC 3 2 1 12 24 36 48 60 54 54 54 MIN: 4 / MAX: 618 MIN: 4 / MAX: 618 MIN: 4 / MAX: 620
Intel Open Image Denoise Run: RTLightmap.hdr.4096x4096 OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 1.4.0 Run: RTLightmap.hdr.4096x4096 3 2 1 0.0315 0.063 0.0945 0.126 0.1575 0.14 0.14 0.14
Intel Open Image Denoise Run: RT.ldr_alb_nrm.3840x2160 OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 1.4.0 Run: RT.ldr_alb_nrm.3840x2160 3 2 1 0.0653 0.1306 0.1959 0.2612 0.3265 0.29 0.29 0.29
Intel Open Image Denoise Run: RT.hdr_alb_nrm.3840x2160 OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 1.4.0 Run: RT.hdr_alb_nrm.3840x2160 3 2 1 0.0653 0.1306 0.1959 0.2612 0.3265 0.29 0.29 0.29
VP9 libvpx Encoding Speed: Speed 0 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.10.0 Speed: Speed 0 - Input: Bosphorus 4K 3 2 1 0.9945 1.989 2.9835 3.978 4.9725 4.42 4.42 4.42 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
JPEG XL libjxl Input: PNG - Encode Speed: 8 OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.5 Input: PNG - Encode Speed: 8 4 3 2 1 0.18 0.36 0.54 0.72 0.9 0.8 0.8 0.8 0.8 1. (CXX) g++ options: -funwind-tables -O3 -O2 -fPIE -pie -pthread
Phoronix Test Suite v10.8.4