2990wx-december AMD Ryzen Threadripper 2990WX 32-Core testing with a ASUS ROG ZENITH EXTREME (1701 BIOS) and Gigabyte AMD Radeon RX 470/480/570/570X/580/580X/590 4GB on Ubuntu 20.10 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2112065-TJ-2990WXDEC10&grs&sor .
2990wx-december Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server OpenGL Vulkan Compiler File-System Screen Resolution A AA B AMD Ryzen Threadripper 2990WX 32-Core @ 3.00GHz (32 Cores / 64 Threads) ASUS ROG ZENITH EXTREME (1701 BIOS) AMD 17h 32GB Samsung SSD 970 EVO 500GB + 250GB Western Digital WDS250G2X0C-00L350 Gigabyte AMD Radeon RX 470/480/570/570X/580/580X/590 4GB (1244/1750MHz) Realtek ALC1220 MX279 Intel I211 + Qualcomm Atheros QCA6174 802.11ac + Wilocity Wil6200 802.11ad Ubuntu 20.10 5.8.0-50-generic (x86_64) GNOME Shell 3.38.1 X Server 1.20.9 4.6 Mesa 20.2.1 (LLVM 11.0.0) 1.2.131 GCC 10.2.0 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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-gcn/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: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x800820d Graphics Details - BAR1 / Visible vRAM Size: 4096 MB Java Details - OpenJDK Runtime Environment (build 11.0.11+9-Ubuntu-0ubuntu2.20.10) Python Details - Python 3.8.6 Security Details - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: 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 Full AMD retpoline IBPB: conditional STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected
2990wx-december cpuminer-opt: Ringcoin npb: CG.C npb: BT.C npb: FT.C rocksdb: Read Rand Write Rand cpuminer-opt: Deepcoin ncnn: CPU - resnet18 compress-zstd: 19 - Compression Speed ncnn: CPU - mobilenet ncnn: CPU-v2-v2 - mobilenet-v2 npb: SP.C gromacs: MPI CPU - water_GMX50_bare ncnn: CPU - vgg16 renaissance: Scala Dotty lczero: Eigen stargate: 44100 - 1024 ncnn: CPU - yolov4-tiny ncnn: CPU - alexnet nginx: Short Connection - 1000 ncnn: CPU - resnet50 cpuminer-opt: Garlicoin compress-zstd: 8 - Compression Speed stress-ng: NUMA compress-zstd: 19, Long Mode - Compression Speed lczero: BLAS aom-av1: Speed 9 Realtime - Bosphorus 1080p blosc: blosclz compress-zstd: 19 - Compression Speed ncnn: CPU - mnasnet opencv: DNN - Deep Neural Network opencv: Features 2D compress-zstd: 3 - Compression Speed aom-av1: Speed 10 Realtime - Bosphorus 1080p ncnn: CPU - googlenet rocksdb: Rand Fill cpuminer-opt: Blake-2 S stress-ng: Memory Copying compress-zstd: 3 - Compression Speed npb: SP.B cassandra: Reads ncnn: CPU - blazeface natron: Spaceship ncnn: CPU - regnety_400m nginx: Short Connection - 100 nginx: Long Connection - 100 mnn: SqueezeNetV1.0 nginx: Short Connection - 500 npb: MG.C stargate: 480000 - 512 mnn: MobileNetV2_224 stargate: 96000 - 512 stargate: 192000 - 512 rocksdb: Seq Fill npb: IS.D stargate: 44100 - 512 ncnn: CPU - shufflenet-v2 cpuminer-opt: Skeincoin stargate: 480000 - 1024 jpegxl-decode: All compress-zstd: 8, Long Mode - Compression Speed oidn: RTLightmap.hdr.4096x4096 oidn: RT.ldr_alb_nrm.3840x2160 renaissance: In-Memory Database Shootout yquake2: Software CPU - 1920 x 1080 ncnn: Vulkan GPU - alexnet ncnn: Vulkan GPU - regnety_400m jpegxl: JPEG - 5 dav1d: Summer Nature 4K stress-ng: IO_uring renaissance: ALS Movie Lens compress-zstd: 3, Long Mode - Compression Speed compress-rar: Linux Source Tree Archiving To RAR ncnn: Vulkan GPU - efficientnet-b0 renaissance: Rand Forest compress-zstd: 19, Long Mode - Compression Speed stress-ng: Forking renaissance: Apache Spark PageRank opencv: Object Detection sockperf: Throughput ncnn: Vulkan GPU - mobilenet vpxenc: Speed 5 - Bosphorus 1080p renaissance: Genetic Algorithm Using Jenetics + Futures renaissance: Savina Reactors.IO yquake2: OpenGL 3.x - 1920 x 1080 mnn: resnet-v2-50 stress-ng: CPU Cache compress-zstd: 3 - Decompression Speed aom-av1: Speed 9 Realtime - Bosphorus 4K ncnn: Vulkan GPU - squeezenet_ssd aom-av1: Speed 8 Realtime - Bosphorus 4K aom-av1: Speed 4 Two-Pass - Bosphorus 4K ncnn: Vulkan GPU - vgg16 ncnn: CPU - efficientnet-b0 aom-av1: Speed 6 Two-Pass - Bosphorus 1080p cpuminer-opt: Quad SHA-256, Pyrite sockperf: Latency Ping Pong yquake2: Vulkan - 1920 x 1080 stress-ng: Glibc C String Functions jpegxl: JPEG - 7 vpxenc: Speed 0 - Bosphorus 4K oidn: RT.hdr_alb_nrm.3840x2160 cpuminer-opt: LBC, LBRY Credits nginx: Long Connection - 1000 dav1d: Chimera 1080p compress-zstd: 8 - Compression Speed ncnn: CPU - squeezenet_ssd ncnn: Vulkan GPU - googlenet build-llvm: Unix Makefiles aom-av1: Speed 8 Realtime - Bosphorus 1080p dav1d: Chimera 1080p 10-bit mnn: inception-v3 compress-zstd: 3, Long Mode - Decompression Speed compress-zstd: 19 - Decompression Speed compress-7zip: Compression Rating openssl: SHA256 aom-av1: Speed 6 Realtime - Bosphorus 4K vpxenc: Speed 0 - Bosphorus 1080p ncnn: Vulkan GPU - resnet18 stress-ng: Socket Activity jpegxl: PNG - 8 ncnn: Vulkan GPU - shufflenet-v2 renaissance: Akka Unbalanced Cobwebbed Tree ecp-candle: P1B2 kvazaar: Bosphorus 1080p - Very Fast srsran: 4G PHY_DL_Test 100 PRB SISO 256-QAM aom-av1: Speed 6 Two-Pass - Bosphorus 4K tnn: CPU - SqueezeNet v2 aom-av1: Speed 4 Two-Pass - Bosphorus 1080p couchdb: 100 - 1000 - 24 yafaray: Total Time For Sample Scene mnn: mobilenet-v1-1.0 compress-zstd: 8 - Decompression Speed srsran: 4G PHY_DL_Test 100 PRB MIMO 64-QAM kvazaar: Bosphorus 1080p - Slow srsran: 4G PHY_DL_Test 100 PRB MIMO 64-QAM jpegxl: PNG - 7 rocksdb: Rand Fill Sync compress-zstd: 8 - Decompression Speed aom-av1: Speed 10 Realtime - Bosphorus 4K jpegxl: JPEG - 8 tachyon: Total Time mnn: squeezenetv1.1 stargate: 192000 - 1024 ncnn: CPU-v3-v3 - mobilenet-v3 stress-ng: Context Switching compress-zstd: 19, Long Mode - Decompression Speed encode-flac: WAV To FLAC kvazaar: Bosphorus 1080p - Ultra Fast synthmark: VoiceMark_100 ncnn: Vulkan GPU - blazeface stress-ng: MEMFD npb: LU.C jpegxl-decode: 1 compress-zstd: 8, Long Mode - Decompression Speed ncnn: Vulkan GPU - mnasnet mnn: mobilenetV3 qe: AUSURF112 kvazaar: Bosphorus 4K - Very Fast tnn: CPU - DenseNet tnn: CPU - MobileNet v2 blender: Pabellon Barcelona - CPU-Only ncnn: Vulkan GPU - yolov4-tiny srsran: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM astcenc: Medium vpxenc: Speed 5 - Bosphorus 4K srsran: 4G PHY_DL_Test 100 PRB SISO 64-QAM kvazaar: Bosphorus 4K - Medium simdjson: Kostya stress-ng: Crypto compress-zstd: 8, Long Mode - Decompression Speed srsran: OFDM_Test aom-av1: Speed 6 Realtime - Bosphorus 1080p kvazaar: Bosphorus 1080p - Medium stress-ng: CPU Stress nginx: Long Connection - 500 cpuminer-opt: x25x kvazaar: Bosphorus 4K - Slow simdjson: PartialTweets blender: Classroom - CPU-Only stress-ng: Semaphores srsran: 5G PHY_DL_NR Test 270 PRB SISO 256-QAM build-gdb: Time To Compile simdjson: DistinctUserID astcenc: Exhaustive build-linux-kernel: Time To Compile brl-cad: VGR Performance Metric primesieve: 1e12 Prime Number Generation stress-ng: Malloc rocksdb: Rand Read kvazaar: Bosphorus 4K - Ultra Fast renaissance: Apache Spark Bayes srsran: 4G PHY_DL_Test 100 PRB SISO 256-QAM renaissance: Finagle HTTP Requests compress-zstd: 3, Long Mode - Decompression Speed srsran: 4G PHY_DL_Test 100 PRB SISO 64-QAM stress-ng: Vector Math srsran: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM astcenc: Thorough build-ffmpeg: Time To Compile dav1d: Summer Nature 1080p stress-ng: SENDFILE cpuminer-opt: Magi ncnn: Vulkan GPU-v2-v2 - mobilenet-v2 openssl: RSA4096 compress-zstd: 19, Long Mode - Decompression Speed srsran: 5G PHY_DL_NR Test 270 PRB SISO 256-QAM renaissance: Apache Spark ALS ncnn: Vulkan GPU-v3-v3 - mobilenet-v3 blender: BMW27 - CPU-Only blender: Fishy Cat - CPU-Only stress-ng: System V Message Passing jpegxl: PNG - 5 stargate: 96000 - 1024 cpuminer-opt: Myriad-Groestl openssl: RSA4096 blender: Barbershop - CPU-Only ncnn: Vulkan GPU - resnet50 srsran: 4G PHY_DL_Test 100 PRB MIMO 256-QAM openssl: compress-7zip: Decompression Rating npb: EP.C compress-zstd: 19 - Decompression Speed stress-ng: MMAP npb: EP.D stress-ng: Matrix Math tnn: CPU - SqueezeNet v1.1 compress-zstd: 3, Long Mode - Compression Speed srsran: 4G PHY_DL_Test 100 PRB MIMO 256-QAM stress-ng: Glibc Qsort Data Sorting stress-ng: Atomic openssl: compress-zstd: 3 - Decompression Speed rocksdb: Read While Writing cassandra: Mixed 1:3 cassandra: Mixed 1:1 cassandra: Writes cpuminer-opt: Triple SHA-256, Onecoin build-llvm: Ninja build-gcc: Time To Compile openvkl: vklBenchmark Scalar openvkl: vklBenchmark ISPC aom-av1: Speed 0 Two-Pass - Bosphorus 1080p aom-av1: Speed 0 Two-Pass - Bosphorus 4K compress-zstd: 8, Long Mode - Compression Speed simdjson: LargeRand blake2: sockperf: Latency Under Load yquake2: OpenGL 1.x - 1920 x 1080 A AA B 104.8 612458 951.8 5.653 382.3 70.384 649.4 226.19 3352.88 21934.13 12671.13 1309509 7527.57 45.86 52.5 31.03 20.19 11732.49 1.411 108.18 1137.2 497 3.055921 52.34 35.53 93226.33 72.75 4801.58 627.7 443.26 12.9 500 73.07 14183.9 50.8 15.69 44723 322937 3373.8 79.35 33.57 293341 269790 2125.93 3251.3 16588.24 154656 7.14 3.1 45.56 38192.34 147038.04 9.737 83537.34 16295.39 2.872219 6.072 1.941293 1.437551 318668 741.1 2.980126 14.9 105330 2.90154 181.74 336.6 0.27 0.55 6700.4 103.5 8.72 12.76 66.97 210.97 96527.73 10082.8 675.1 115.34 16.18 951.1 26.3 18580.61 4693.7 129354 602275 11.39 18.1 2611.9 11517.9 969.3 37.627 322.09 3158.4 31.8 11.1 26.37 3.24 19.56 19.92 15.81 62750 5.607 382.8 1721460.67 67.52 4.17 0.53 39700 132522.05 566.04 408.8 41.65 10.57 428.412 67.88 382.14 42.115 3456.5 3086.1 107251 36802112140 7.22 9.31 5.61 16318.27 0.73 5.22 21464.9 45.472 65.36 352.4 6.55 67.26 6.03 119.315 79.247 4.453 3351.5 321 31.85 113.3 8.32 10379 3345.7 33.99 23.8 32.2071 7.523 1.515152 15.43 10178763.82 2997.3 17.185 125.49 588.248 3.06 1789.09 43987.67 42.18 3569.8 5.88 3.942 540.19 21.97 2918.398 294.812 189.32 15.27 87.7 4.5256 9.1 327.8 12.37 2.5 6620.43 3601.4 82000000 5.47 33.25 69913.83 135958.27 802.96 12.25 3.09 147.72 4705038.25 97.3 65.844 3.41 31.2861 50.272 300804 8.086 319416181.16 141073292 35.26 1159.4 210.2 4196.7 3474.6 175.6 117428.81 47.3 8.3396 32.762 578.08 457950.37 1155.44 5.67 376708.4 3114.3 63 2109.3 7.63 53.95 78.69 8604238.16 52.47 2.213074 10180 5851.5 635.52 12.05 121 375075.2 173519 1736.13 2949 896.44 1737.94 135023.34 250.935 339.5 350.4 458.2 184198.75 5849.4 149882 128000 947.374 56 89 0.23 0.12 560.5 4.47 28.734 548.1 52.63 7946.23 42972.01 20808.6 1969467 11250 65.25 37.2 40.87 15.37 8947.81 1.786 86.61 944.9 593 2.572506 62 30 80350.13 62.81 4292.58 561.7 402.14 14.2 456 79.71 15418.5 46.9 14.51 41365 298984 3533 85.68 36.18 315885 290190 2286.51 3496.2 17801.43 165930 6.67 3.3 42.8 35904.17 138651.12 9.207 87990.53 17140.13 2.735496 5.789 2.035179 1.506787 333854 707.86 2.855051 15.52 101240 3.017824 188.84 349.6 0.26 0.53 6460.0 107.3 9.04 12.31 64.61 218.63 99948.02 10427.3 652.9 119.224 15.68 922.1 25.5 18015.66 4554.8 125639 619257 11.71 17.62 2542.9 11220.9 976.8 38.574 330.17 3234.4 32.52 11.35 26.96 3.31 19.98 19.52 15.5 64000 5.545 375.5 1754742.63 66.24 4.25 0.54 38970 130095.57 555.78 416.3 42.4 10.76 436.064 66.73 388.65 42.825 3399.8 3035.6 108998 37378019350 7.11 9.17 5.69 16548.52 0.72 5.15 21754.1 44.87 64.52 356.9 6.47 68.053 5.96 120.697 78.395 4.406 3317 317.8 32.17 112.2 8.24 10280 3316.1 34.29 24.01 32.4741 7.585 1.503322 15.55 10101278.83 2975.3 17.309 124.66 592.156 3.08 1777.53 43717.86 41.95 3550.9 5.91 3.922 542.93 22.08 2904.19 296.227 188.42 15.34 88.1 4.5057 9.06 326.4 12.42 2.51 6646.34 3588 82300000 5.49 33.13 70164.47 136435.64 800.21 12.21 3.08 147.25 4690182.85 97 65.641 3.42 31.3776 50.416 299956 8.064 318555456.11 141450130 35.35 1162.3 210.7 4206.6 3466.5 176 117178.8 47.2 8.3224 32.826 579.16 457100.94 1153.33 5.66 376078.8 3109.1 62.9 2112.1 7.64 54.02 78.79 8594247.31 52.41 2.215502 10190 5845.9 634.97 12.04 121.1 375362.3 173641 1734.99 2950.9 896.92 1738.63 134983.16 251.009 339.4 350.3 458.07 184185.78 5849.1 3229.1 4472075 150860 175440 128000 381.16 56 89 0.23 0.12 560.5 0.84 4.47 112.556 569.4 OpenBenchmarking.org
Cpuminer-Opt Algorithm: Ringcoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.18 Algorithm: Ringcoin AA B 50 100 150 200 250 226.19 52.63 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
NAS Parallel Benchmarks Test / Class: CG.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: CG.C B AA 2K 4K 6K 8K 10K 7946.23 3352.88 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.0.3
NAS Parallel Benchmarks Test / Class: BT.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: BT.C B AA 9K 18K 27K 36K 45K 42972.01 21934.13 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.0.3
NAS Parallel Benchmarks Test / Class: FT.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: FT.C B AA 4K 8K 12K 16K 20K 20808.60 12671.13 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.0.3
Facebook RocksDB Test: Read Random Write Random OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Read Random Write Random B AA 400K 800K 1200K 1600K 2000K 1969467 1309509 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Cpuminer-Opt Algorithm: Deepcoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.18 Algorithm: Deepcoin B AA 2K 4K 6K 8K 10K 11250.00 7527.57 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
NCNN Target: CPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: resnet18 AA B 15 30 45 60 75 45.86 65.25 MIN: 25.38 / MAX: 196.67 MIN: 23.16 / MAX: 211.77 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Zstd Compression Compression Level: 19 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19 - Compression Speed AA B 12 24 36 48 60 52.5 37.2 1. (CC) gcc options: -O3 -pthread -lz -llzma
NCNN Target: CPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: mobilenet AA B 9 18 27 36 45 31.03 40.87 MIN: 29.44 / MAX: 77.93 MIN: 30.3 / MAX: 442.58 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU-v2-v2 - Model: mobilenet-v2 B AA 5 10 15 20 25 15.37 20.19 MIN: 14.73 / MAX: 55.17 MIN: 14.09 / MAX: 349.17 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NAS Parallel Benchmarks Test / Class: SP.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.C AA B 3K 6K 9K 12K 15K 11732.49 8947.81 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.0.3
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 B AA 0.4019 0.8038 1.2057 1.6076 2.0095 1.786 1.411 1. (CXX) g++ options: -O3 -pthread
NCNN Target: CPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: vgg16 B AA 20 40 60 80 100 86.61 108.18 MIN: 63.18 / MAX: 184.99 MIN: 70.12 / MAX: 199.37 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Renaissance Test: Scala Dotty OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Scala Dotty B AA 200 400 600 800 1000 944.9 1137.2 MIN: 801.18 / MAX: 1665.45 MIN: 876.85 / MAX: 1645.52
LeelaChessZero Backend: Eigen OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.28 Backend: Eigen B AA 130 260 390 520 650 593 497 1. (CXX) g++ options: -flto -pthread
Stargate Digital Audio Workstation Sample Rate: 44100 - Buffer Size: 1024 OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 21.10.9 Sample Rate: 44100 - Buffer Size: 1024 AA B 0.6876 1.3752 2.0628 2.7504 3.438 3.055921 2.572506 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
NCNN Target: CPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: yolov4-tiny AA B 14 28 42 56 70 52.34 62.00 MIN: 43.78 / MAX: 209.33 MIN: 43.29 / MAX: 216 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: alexnet B AA 8 16 24 32 40 30.00 35.53 MIN: 19.66 / MAX: 93.41 MIN: 20.52 / MAX: 92.88 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Nginx Test: Short Connection - Connections: 1000 OpenBenchmarking.org Requests Per Second, More Is Better Nginx Test: Short Connection - Connections: 1000 AA B 20K 40K 60K 80K 100K 93226.33 80350.13 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2 2. nginx version: nginx/1.18.0 (Ubuntu)
NCNN Target: CPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: resnet50 B AA 16 32 48 64 80 62.81 72.75 MIN: 37.55 / MAX: 544.84 MIN: 38.13 / MAX: 512.36 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Cpuminer-Opt Algorithm: Garlicoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.18 Algorithm: Garlicoin AA B 1000 2000 3000 4000 5000 4801.58 4292.58 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Zstd Compression Compression Level: 8 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 8 - Compression Speed AA B 140 280 420 560 700 627.7 561.7 1. (CC) gcc options: -O3 -pthread -lz -llzma
Stress-NG Test: NUMA OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: NUMA AA B 100 200 300 400 500 443.26 402.14 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
Zstd Compression Compression Level: 19, Long Mode - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 19, Long Mode - Compression Speed B AA 4 8 12 16 20 14.2 12.9 1. *** zstd command line interface 64-bits v1.4.5, by Yann Collet ***
LeelaChessZero Backend: BLAS OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.28 Backend: BLAS AA B 110 220 330 440 550 500 456 1. (CXX) g++ options: -flto -pthread
AOM AV1 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.2 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080p B AA 20 40 60 80 100 79.71 73.07 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
C-Blosc Compressor: blosclz OpenBenchmarking.org MB/s, More Is Better C-Blosc 2.0 Compressor: blosclz B AA 3K 6K 9K 12K 15K 15418.5 14183.9 1. (CC) gcc options: -std=gnu99 -O3 -pthread -lrt -lm
Zstd Compression Compression Level: 19 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 19 - Compression Speed AA B 11 22 33 44 55 50.8 46.9 1. *** zstd command line interface 64-bits v1.4.5, by Yann Collet ***
NCNN Target: CPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: mnasnet B AA 4 8 12 16 20 14.51 15.69 MIN: 13.1 / MAX: 119.13 MIN: 13.31 / MAX: 371.2 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenCV Test: DNN - Deep Neural Network OpenBenchmarking.org ms, Fewer Is Better OpenCV 4.5.4 Test: DNN - Deep Neural Network B AA 10K 20K 30K 40K 50K 41365 44723 1. (CXX) g++ options: -fPIC -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -shared
OpenCV Test: Features 2D OpenBenchmarking.org ms, Fewer Is Better OpenCV 4.5.4 Test: Features 2D B AA 70K 140K 210K 280K 350K 298984 322937 1. (CXX) g++ options: -fPIC -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -shared
Zstd Compression Compression Level: 3 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 3 - Compression Speed B AA 800 1600 2400 3200 4000 3533.0 3373.8 1. (CC) gcc options: -O3 -pthread -lz -llzma
AOM AV1 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.2 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 1080p B AA 20 40 60 80 100 85.68 79.35 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
NCNN Target: CPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: googlenet AA B 8 16 24 32 40 33.57 36.18 MIN: 28.43 / MAX: 398.62 MIN: 28.07 / MAX: 494.43 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Facebook RocksDB Test: Random Fill OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Random Fill B AA 70K 140K 210K 280K 350K 315885 293341 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Cpuminer-Opt Algorithm: Blake-2 S OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.18 Algorithm: Blake-2 S B AA 60K 120K 180K 240K 300K 290190 269790 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Stress-NG Test: Memory Copying OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Memory Copying B AA 500 1000 1500 2000 2500 2286.51 2125.93 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
Zstd Compression Compression Level: 3 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 3 - Compression Speed B AA 700 1400 2100 2800 3500 3496.2 3251.3 1. *** zstd command line interface 64-bits v1.4.5, by Yann Collet ***
NAS Parallel Benchmarks Test / Class: SP.B OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.B B AA 4K 8K 12K 16K 20K 17801.43 16588.24 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.0.3
Apache Cassandra Test: Reads OpenBenchmarking.org Op/s, More Is Better Apache Cassandra 4.0 Test: Reads B AA 40K 80K 120K 160K 200K 165930 154656
NCNN Target: CPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: blazeface B AA 2 4 6 8 10 6.67 7.14 MIN: 6.32 / MAX: 60.3 MIN: 6.53 / MAX: 87.06 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Natron Input: Spaceship OpenBenchmarking.org FPS, More Is Better Natron 2.4 Input: Spaceship B AA 0.7425 1.485 2.2275 2.97 3.7125 3.3 3.1
NCNN Target: CPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: regnety_400m B AA 10 20 30 40 50 42.80 45.56 MIN: 42.25 / MAX: 57.06 MIN: 43.43 / MAX: 228.28 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Nginx Test: Short Connection - Connections: 100 OpenBenchmarking.org Requests Per Second, More Is Better Nginx Test: Short Connection - Connections: 100 AA B 8K 16K 24K 32K 40K 38192.34 35904.17 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2 2. nginx version: nginx/1.18.0 (Ubuntu)
Nginx Test: Long Connection - Connections: 100 OpenBenchmarking.org Requests Per Second, More Is Better Nginx Test: Long Connection - Connections: 100 AA B 30K 60K 90K 120K 150K 147038.04 138651.12 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2 2. nginx version: nginx/1.18.0 (Ubuntu)
Mobile Neural Network Model: SqueezeNetV1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: SqueezeNetV1.0 B AA 3 6 9 12 15 9.207 9.737 MIN: 9.12 / MAX: 15.46 MIN: 9.63 / MAX: 16.75 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
Nginx Test: Short Connection - Connections: 500 OpenBenchmarking.org Requests Per Second, More Is Better Nginx Test: Short Connection - Connections: 500 B AA 20K 40K 60K 80K 100K 87990.53 83537.34 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2 2. nginx version: nginx/1.18.0 (Ubuntu)
NAS Parallel Benchmarks Test / Class: MG.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: MG.C B AA 4K 8K 12K 16K 20K 17140.13 16295.39 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.0.3
Stargate Digital Audio Workstation Sample Rate: 480000 - Buffer Size: 512 OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 21.10.9 Sample Rate: 480000 - Buffer Size: 512 AA B 0.6462 1.2924 1.9386 2.5848 3.231 2.872219 2.735496 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
Mobile Neural Network Model: MobileNetV2_224 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: MobileNetV2_224 B AA 2 4 6 8 10 5.789 6.072 MIN: 5.74 / MAX: 6.44 MIN: 6.03 / MAX: 6.21 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
Stargate Digital Audio Workstation Sample Rate: 96000 - Buffer Size: 512 OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 21.10.9 Sample Rate: 96000 - Buffer Size: 512 B AA 0.4579 0.9158 1.3737 1.8316 2.2895 2.035179 1.941293 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
Stargate Digital Audio Workstation Sample Rate: 192000 - Buffer Size: 512 OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 21.10.9 Sample Rate: 192000 - Buffer Size: 512 B AA 0.339 0.678 1.017 1.356 1.695 1.506787 1.437551 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
Facebook RocksDB Test: Sequential Fill OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Sequential Fill B AA 70K 140K 210K 280K 350K 333854 318668 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
NAS Parallel Benchmarks Test / Class: IS.D OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: IS.D AA B 160 320 480 640 800 741.10 707.86 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.0.3
Stargate Digital Audio Workstation Sample Rate: 44100 - Buffer Size: 512 OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 21.10.9 Sample Rate: 44100 - Buffer Size: 512 AA B 0.6705 1.341 2.0115 2.682 3.3525 2.980126 2.855051 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
NCNN Target: CPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: shufflenet-v2 AA B 4 8 12 16 20 14.90 15.52 MIN: 14.76 / MAX: 21.86 MIN: 15.23 / MAX: 21.93 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Cpuminer-Opt Algorithm: Skeincoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.18 Algorithm: Skeincoin AA B 20K 40K 60K 80K 100K 105330 101240 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Stargate Digital Audio Workstation Sample Rate: 480000 - Buffer Size: 1024 OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 21.10.9 Sample Rate: 480000 - Buffer Size: 1024 B AA 0.679 1.358 2.037 2.716 3.395 3.017824 2.901540 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
JPEG XL Decoding libjxl CPU Threads: All OpenBenchmarking.org MP/s, More Is Better JPEG XL Decoding libjxl 0.6.1 CPU Threads: All B AA 40 80 120 160 200 188.84 181.74
Zstd Compression Compression Level: 8, Long Mode - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 8, Long Mode - Compression Speed B AA 80 160 240 320 400 349.6 336.6 1. *** zstd command line interface 64-bits v1.4.5, by Yann Collet ***
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 AA B 0.0608 0.1216 0.1824 0.2432 0.304 0.27 0.26
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 AA B 0.1238 0.2476 0.3714 0.4952 0.619 0.55 0.53
Renaissance Test: In-Memory Database Shootout OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: In-Memory Database Shootout B AA 1400 2800 4200 5600 7000 6460.0 6700.4 MIN: 6317.66 / MAX: 7320.27 MIN: 6495.23 / MAX: 7775.6
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 B A AA 20 40 60 80 100 SE +/- 0.41, N = 3 107.3 104.8 103.5 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: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: alexnet AA B 3 6 9 12 15 8.72 9.04 MIN: 8.15 / MAX: 10.14 MIN: 8.09 / MAX: 10.67 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: regnety_400m B AA 3 6 9 12 15 12.31 12.76 MIN: 10.5 / MAX: 15.04 MIN: 11.47 / MAX: 14.21 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
JPEG XL libjxl Input: JPEG - Encode Speed: 5 OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.6.1 Input: JPEG - Encode Speed: 5 AA B 15 30 45 60 75 66.97 64.61 1. (CXX) g++ options: -funwind-tables -O3 -O2 -pthread -fPIE -pie
dav1d Video Input: Summer Nature 4K OpenBenchmarking.org FPS, More Is Better dav1d 0.9.2 Video Input: Summer Nature 4K B AA 50 100 150 200 250 218.63 210.97 MIN: 148.28 / MAX: 230.99 MIN: 148.02 / MAX: 223.23 1. (CC) gcc options: -pthread -lm
Stress-NG Test: IO_uring OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: IO_uring B AA 20K 40K 60K 80K 100K 99948.02 96527.73 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
Renaissance Test: ALS Movie Lens OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: ALS Movie Lens AA B 2K 4K 6K 8K 10K 10082.8 10427.3 MAX: 10972.53 MIN: 10427.25 / MAX: 11373.16
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 AA B 150 300 450 600 750 675.1 652.9 1. (CC) gcc options: -O3 -pthread -lz -llzma
RAR Compression Linux Source Tree Archiving To RAR OpenBenchmarking.org Seconds, Fewer Is Better RAR Compression 6.0.2 Linux Source Tree Archiving To RAR AA B 30 60 90 120 150 115.34 119.22
NCNN Target: Vulkan GPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: efficientnet-b0 B AA 4 8 12 16 20 15.68 16.18 MIN: 14.17 / MAX: 21.93 MIN: 14.51 / MAX: 24.04 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 B AA 200 400 600 800 1000 922.1 951.1 MIN: 847.54 / MAX: 1114.66 MIN: 879.34 / MAX: 1049.53
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 AA B 6 12 18 24 30 26.3 25.5 1. (CC) gcc options: -O3 -pthread -lz -llzma
Stress-NG Test: Forking OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Forking AA B 4K 8K 12K 16K 20K 18580.61 18015.66 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
Renaissance Test: Apache Spark PageRank OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Apache Spark PageRank B AA 1000 2000 3000 4000 5000 4554.8 4693.7 MIN: 4071.82 / MAX: 4635.27 MIN: 4223.52 / MAX: 5207.25
OpenCV Test: Object Detection OpenBenchmarking.org ms, Fewer Is Better OpenCV 4.5.4 Test: Object Detection B AA 30K 60K 90K 120K 150K 125639 129354 1. (CXX) g++ options: -fPIC -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -shared
Sockperf Test: Throughput OpenBenchmarking.org Messages Per Second, More Is Better Sockperf 3.7 Test: Throughput B A AA 130K 260K 390K 520K 650K SE +/- 5789.85, N = 5 619257 612458 602275 1. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread
NCNN Target: Vulkan GPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: mobilenet AA B 3 6 9 12 15 11.39 11.71 MIN: 10.08 / MAX: 18.02 MIN: 10.33 / MAX: 16.42 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
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 AA B 4 8 12 16 20 18.10 17.62 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
Renaissance Test: Genetic Algorithm Using Jenetics + Futures OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Genetic Algorithm Using Jenetics + Futures B AA 600 1200 1800 2400 3000 2542.9 2611.9 MIN: 2432.26 / MAX: 2647.9 MIN: 2518.12 / MAX: 2673.66
Renaissance Test: Savina Reactors.IO OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Savina Reactors.IO B AA 2K 4K 6K 8K 10K 11220.9 11517.9 MIN: 11220.89 / MAX: 17814.55 MAX: 17487.35
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 B AA A 200 400 600 800 1000 SE +/- 5.18, N = 3 976.8 969.3 951.8 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
Mobile Neural Network Model: resnet-v2-50 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: resnet-v2-50 AA B 9 18 27 36 45 37.63 38.57 MIN: 37.2 / MAX: 77.83 MIN: 36.41 / MAX: 104.02 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
Stress-NG Test: CPU Cache OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: CPU Cache B AA 70 140 210 280 350 330.17 322.09 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
Zstd Compression Compression Level: 3 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 3 - Decompression Speed B AA 700 1400 2100 2800 3500 3234.4 3158.4 1. (CC) gcc options: -O3 -pthread -lz -llzma
AOM AV1 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.2 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K B AA 8 16 24 32 40 32.52 31.80 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
NCNN Target: Vulkan GPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: squeezenet_ssd AA B 3 6 9 12 15 11.10 11.35 MIN: 10.31 / MAX: 16.18 MIN: 10.39 / MAX: 18.33 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
AOM AV1 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.2 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K B AA 6 12 18 24 30 26.96 26.37 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
AOM AV1 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.2 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4K B AA 0.7448 1.4896 2.2344 2.9792 3.724 3.31 3.24 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
NCNN Target: Vulkan GPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: vgg16 AA B 5 10 15 20 25 19.56 19.98 MIN: 19.1 / MAX: 24.46 MIN: 19.14 / MAX: 26.09 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: efficientnet-b0 B AA 5 10 15 20 25 19.52 19.92 MIN: 18.77 / MAX: 78.26 MIN: 19.12 / MAX: 81.87 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
AOM AV1 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.2 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080p AA B 4 8 12 16 20 15.81 15.50 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
Cpuminer-Opt Algorithm: Quad SHA-256, Pyrite OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.18 Algorithm: Quad SHA-256, Pyrite B AA 14K 28K 42K 56K 70K 64000 62750 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Sockperf Test: Latency Ping Pong OpenBenchmarking.org usec, Fewer Is Better Sockperf 3.7 Test: Latency Ping Pong B AA A 1.2719 2.5438 3.8157 5.0876 6.3595 SE +/- 0.013, N = 5 5.545 5.607 5.653 1. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread
yquake2 Renderer: Vulkan - Resolution: 1920 x 1080 OpenBenchmarking.org Frames Per Second, More Is Better yquake2 8.0 Renderer: Vulkan - Resolution: 1920 x 1080 AA A B 80 160 240 320 400 SE +/- 0.27, N = 3 382.8 382.3 375.5 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
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 B AA 400K 800K 1200K 1600K 2000K 1754742.63 1721460.67 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -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 0.6.1 Input: JPEG - Encode Speed: 7 AA B 15 30 45 60 75 67.52 66.24 1. (CXX) g++ options: -funwind-tables -O3 -O2 -pthread -fPIE -pie
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 B AA 0.9563 1.9126 2.8689 3.8252 4.7815 4.25 4.17 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
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 B AA 0.1215 0.243 0.3645 0.486 0.6075 0.54 0.53
Cpuminer-Opt Algorithm: LBC, LBRY Credits OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.18 Algorithm: LBC, LBRY Credits AA B 9K 18K 27K 36K 45K 39700 38970 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Nginx Test: Long Connection - Connections: 1000 OpenBenchmarking.org Requests Per Second, More Is Better Nginx Test: Long Connection - Connections: 1000 AA B 30K 60K 90K 120K 150K 132522.05 130095.57 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2 2. nginx version: nginx/1.18.0 (Ubuntu)
dav1d Video Input: Chimera 1080p OpenBenchmarking.org FPS, More Is Better dav1d 0.9.2 Video Input: Chimera 1080p AA B 120 240 360 480 600 566.04 555.78 MIN: 437.5 / MAX: 716.24 MIN: 432.12 / MAX: 699.97 1. (CC) gcc options: -pthread -lm
Zstd Compression Compression Level: 8 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 8 - Compression Speed B AA 90 180 270 360 450 416.3 408.8 1. *** zstd command line interface 64-bits v1.4.5, by Yann Collet ***
NCNN Target: CPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: squeezenet_ssd AA B 10 20 30 40 50 41.65 42.40 MIN: 32.09 / MAX: 415.56 MIN: 33.15 / MAX: 419.98 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 AA B 3 6 9 12 15 10.57 10.76 MIN: 9.94 / MAX: 11.16 MIN: 9.92 / MAX: 12.3 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Timed LLVM Compilation Build System: Unix Makefiles OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 13.0 Build System: Unix Makefiles AA B 90 180 270 360 450 428.41 436.06
AOM AV1 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.2 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080p AA B 15 30 45 60 75 67.88 66.73 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
dav1d Video Input: Chimera 1080p 10-bit OpenBenchmarking.org FPS, More Is Better dav1d 0.9.2 Video Input: Chimera 1080p 10-bit B AA 80 160 240 320 400 388.65 382.14 MIN: 306.7 / MAX: 517.94 MIN: 303.66 / MAX: 510.51 1. (CC) gcc options: -pthread -lm
Mobile Neural Network Model: inception-v3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: inception-v3 AA B 10 20 30 40 50 42.12 42.83 MIN: 41.83 / MAX: 47.67 MIN: 40.5 / MAX: 112.3 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: 3, Long Mode - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 3, Long Mode - Decompression Speed AA B 700 1400 2100 2800 3500 3456.5 3399.8 1. *** zstd command line interface 64-bits v1.4.5, by Yann Collet ***
Zstd Compression Compression Level: 19 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 19 - Decompression Speed AA B 700 1400 2100 2800 3500 3086.1 3035.6 1. *** zstd command line interface 64-bits v1.4.5, by Yann Collet ***
7-Zip Compression Test: Compression Rating OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 21.06 Test: Compression Rating B AA 20K 40K 60K 80K 100K 108998 107251 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
OpenSSL Algorithm: SHA256 OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.0 Algorithm: SHA256 B AA 8000M 16000M 24000M 32000M 40000M 37378019350 36802112140 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
AOM AV1 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.2 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K AA B 2 4 6 8 10 7.22 7.11 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
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 AA B 3 6 9 12 15 9.31 9.17 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
NCNN Target: Vulkan GPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: resnet18 AA B 1.2803 2.5606 3.8409 5.1212 6.4015 5.61 5.69 MIN: 5.07 / MAX: 7.19 MIN: 5.07 / MAX: 7.06 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Stress-NG Test: Socket Activity OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Socket Activity B AA 4K 8K 12K 16K 20K 16548.52 16318.27 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
JPEG XL libjxl Input: PNG - Encode Speed: 8 OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.6.1 Input: PNG - Encode Speed: 8 AA B 0.1643 0.3286 0.4929 0.6572 0.8215 0.73 0.72 1. (CXX) g++ options: -funwind-tables -O3 -O2 -pthread -fPIE -pie
NCNN Target: Vulkan GPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: shufflenet-v2 B AA 1.1745 2.349 3.5235 4.698 5.8725 5.15 5.22 MIN: 4.66 / MAX: 6.72 MIN: 4.68 / MAX: 7.64 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 AA B 5K 10K 15K 20K 25K 21464.9 21754.1 MIN: 16997.03 MIN: 17550.77 / MAX: 21754.14
ECP-CANDLE Benchmark: P1B2 OpenBenchmarking.org Seconds, Fewer Is Better ECP-CANDLE 0.4 Benchmark: P1B2 B AA 10 20 30 40 50 44.87 45.47
Kvazaar Video Input: Bosphorus 1080p - Video Preset: Very Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.1 Video Input: Bosphorus 1080p - Video Preset: Very Fast AA B 15 30 45 60 75 65.36 64.52 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
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 B AA 80 160 240 320 400 356.9 352.4 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 -lbladeRF -lm -lfftw3f -lmbedcrypto
AOM AV1 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.2 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K AA B 2 4 6 8 10 6.55 6.47 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
TNN Target: CPU - Model: SqueezeNet v2 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v2 AA B 15 30 45 60 75 67.26 68.05 MIN: 66.79 / MAX: 67.68 MIN: 67.83 / MAX: 69.38 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
AOM AV1 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.2 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080p AA B 2 4 6 8 10 6.03 5.96 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
Apache CouchDB Bulk Size: 100 - Inserts: 1000 - Rounds: 24 OpenBenchmarking.org Seconds, Fewer Is Better Apache CouchDB 3.2.1 Bulk Size: 100 - Inserts: 1000 - Rounds: 24 AA B 30 60 90 120 150 119.32 120.70 1. (CXX) g++ options: -std=c++14 -lmozjs-68 -lm -lei -fPIC -MMD
YafaRay Total Time For Sample Scene OpenBenchmarking.org Seconds, Fewer Is Better YafaRay 3.5.1 Total Time For Sample Scene B AA 20 40 60 80 100 78.40 79.25 1. (CXX) g++ options: -std=c++11 -pthread -O3 -ffast-math -rdynamic -ldl -lImath -lIlmImf -lIex -lHalf -lz -lIlmThread -lxml2 -lfreetype
Mobile Neural Network Model: mobilenet-v1-1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: mobilenet-v1-1.0 B AA 1.0019 2.0038 3.0057 4.0076 5.0095 4.406 4.453 MIN: 4 / MAX: 23.02 MIN: 4.02 / MAX: 22.31 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 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 8 - Decompression Speed AA B 700 1400 2100 2800 3500 3351.5 3317.0 1. (CC) gcc options: -O3 -pthread -lz -llzma
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 AA B 70 140 210 280 350 321.0 317.8 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 -lbladeRF -lm -lfftw3f -lmbedcrypto
Kvazaar Video Input: Bosphorus 1080p - Video Preset: Slow OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.1 Video Input: Bosphorus 1080p - Video Preset: Slow B AA 7 14 21 28 35 32.17 31.85 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
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 AA B 30 60 90 120 150 113.3 112.2 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 -lbladeRF -lm -lfftw3f -lmbedcrypto
JPEG XL libjxl Input: PNG - Encode Speed: 7 OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.6.1 Input: PNG - Encode Speed: 7 AA B 2 4 6 8 10 8.32 8.24 1. (CXX) g++ options: -funwind-tables -O3 -O2 -pthread -fPIE -pie
Facebook RocksDB Test: Random Fill Sync OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Random Fill Sync AA B 2K 4K 6K 8K 10K 10379 10280 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Zstd Compression Compression Level: 8 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 8 - Decompression Speed AA B 700 1400 2100 2800 3500 3345.7 3316.1 1. *** zstd command line interface 64-bits v1.4.5, by Yann Collet ***
AOM AV1 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.2 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4K B AA 8 16 24 32 40 34.29 33.99 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
JPEG XL libjxl Input: JPEG - Encode Speed: 8 OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.6.1 Input: JPEG - Encode Speed: 8 B AA 6 12 18 24 30 24.01 23.80 1. (CXX) g++ options: -funwind-tables -O3 -O2 -pthread -fPIE -pie
Tachyon Total Time OpenBenchmarking.org Seconds, Fewer Is Better Tachyon 0.99b6 Total Time AA B 8 16 24 32 40 32.21 32.47 1. (CC) gcc options: -m64 -O3 -fomit-frame-pointer -ffast-math -ltachyon -lm -lpthread
Mobile Neural Network Model: squeezenetv1.1 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: squeezenetv1.1 AA B 2 4 6 8 10 7.523 7.585 MIN: 7.37 / MAX: 8.45 MIN: 7.26 / MAX: 9.89 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
Stargate Digital Audio Workstation Sample Rate: 192000 - Buffer Size: 1024 OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 21.10.9 Sample Rate: 192000 - Buffer Size: 1024 AA B 0.3409 0.6818 1.0227 1.3636 1.7045 1.515152 1.503322 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
NCNN Target: CPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU-v3-v3 - Model: mobilenet-v3 AA B 4 8 12 16 20 15.43 15.55 MIN: 14.03 / MAX: 182.16 MIN: 13.85 / MAX: 201.51 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Stress-NG Test: Context Switching OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Context Switching AA B 2M 4M 6M 8M 10M 10178763.82 10101278.83 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -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 AA B 600 1200 1800 2400 3000 2997.3 2975.3 1. (CC) gcc options: -O3 -pthread -lz -llzma
FLAC Audio Encoding WAV To FLAC OpenBenchmarking.org Seconds, Fewer Is Better FLAC Audio Encoding 1.3.3 WAV To FLAC AA B 4 8 12 16 20 17.19 17.31 1. (CXX) g++ options: -fvisibility=hidden -logg -lm
Kvazaar Video Input: Bosphorus 1080p - Video Preset: Ultra Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.1 Video Input: Bosphorus 1080p - Video Preset: Ultra Fast AA B 30 60 90 120 150 125.49 124.66 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Google SynthMark Test: VoiceMark_100 OpenBenchmarking.org Voices, More Is Better Google SynthMark 20201109 Test: VoiceMark_100 B AA 130 260 390 520 650 592.16 588.25 1. (CXX) g++ options: -lm -lpthread -std=c++11 -Ofast
NCNN Target: Vulkan GPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: blazeface AA B 0.693 1.386 2.079 2.772 3.465 3.06 3.08 MIN: 2.63 / MAX: 3.7 MIN: 2.66 / MAX: 3.7 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Stress-NG Test: MEMFD OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: MEMFD AA B 400 800 1200 1600 2000 1789.09 1777.53 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
NAS Parallel Benchmarks Test / Class: LU.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: LU.C AA B 9K 18K 27K 36K 45K 43987.67 43717.86 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.0.3
JPEG XL Decoding libjxl CPU Threads: 1 OpenBenchmarking.org MP/s, More Is Better JPEG XL Decoding libjxl 0.6.1 CPU Threads: 1 AA B 10 20 30 40 50 42.18 41.95
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 AA B 800 1600 2400 3200 4000 3569.8 3550.9 1. (CC) gcc options: -O3 -pthread -lz -llzma
NCNN Target: Vulkan GPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: mnasnet AA B 1.3298 2.6596 3.9894 5.3192 6.649 5.88 5.91 MIN: 5.22 / MAX: 8.6 MIN: 5.11 / MAX: 8.37 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Mobile Neural Network Model: mobilenetV3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: mobilenetV3 B AA 0.887 1.774 2.661 3.548 4.435 3.922 3.942 MIN: 3.87 / MAX: 4.14 MIN: 3.87 / MAX: 4.1 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
Quantum ESPRESSO Input: AUSURF112 OpenBenchmarking.org Seconds, Fewer Is Better Quantum ESPRESSO 6.8 Input: AUSURF112 AA B 120 240 360 480 600 540.19 542.93 1. (F9X) gfortran options: -ldevXlib -lopenblas -lFoX_dom -lFoX_sax -lFoX_wxml -lFoX_common -lFoX_utils -lFoX_fsys -lfftw3 -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz
Kvazaar Video Input: Bosphorus 4K - Video Preset: Very Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.1 Video Input: Bosphorus 4K - Video Preset: Very Fast B AA 5 10 15 20 25 22.08 21.97 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
TNN Target: CPU - Model: DenseNet OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: DenseNet B AA 600 1200 1800 2400 3000 2904.19 2918.40 MIN: 2809.41 / MAX: 2990.57 MIN: 2821.05 / MAX: 3026.23 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
TNN Target: CPU - Model: MobileNet v2 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: MobileNet v2 AA B 60 120 180 240 300 294.81 296.23 MIN: 279.31 / MAX: 315.98 MIN: 271.31 / MAX: 318.79 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
Blender Blend File: Pabellon Barcelona - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.0 Blend File: Pabellon Barcelona - Compute: CPU-Only B AA 40 80 120 160 200 188.42 189.32
NCNN Target: Vulkan GPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: yolov4-tiny AA B 4 8 12 16 20 15.27 15.34 MIN: 13.4 / MAX: 19.61 MIN: 13.48 / MAX: 20.04 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
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 B AA 20 40 60 80 100 88.1 87.7 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 -lbladeRF -lm -lfftw3f -lmbedcrypto
ASTC Encoder Preset: Medium OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 3.2 Preset: Medium B AA 1.0183 2.0366 3.0549 4.0732 5.0915 4.5057 4.5256 1. (CXX) g++ options: -O3 -flto -pthread
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 AA B 3 6 9 12 15 9.10 9.06 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
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 AA B 70 140 210 280 350 327.8 326.4 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 -lbladeRF -lm -lfftw3f -lmbedcrypto
Kvazaar Video Input: Bosphorus 4K - Video Preset: Medium OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.1 Video Input: Bosphorus 4K - Video Preset: Medium B AA 3 6 9 12 15 12.42 12.37 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
simdjson Throughput Test: Kostya OpenBenchmarking.org GB/s, More Is Better simdjson 1.0 Throughput Test: Kostya B AA 0.5648 1.1296 1.6944 2.2592 2.824 2.51 2.50 1. (CXX) g++ options: -O3 -pthread
Stress-NG Test: Crypto OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Crypto B AA 1400 2800 4200 5600 7000 6646.34 6620.43 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
Zstd Compression Compression Level: 8, Long Mode - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 8, Long Mode - Decompression Speed AA B 800 1600 2400 3200 4000 3601.4 3588.0 1. *** zstd command line interface 64-bits v1.4.5, by Yann Collet ***
srsRAN Test: OFDM_Test OpenBenchmarking.org Samples / Second, More Is Better srsRAN 21.04 Test: OFDM_Test B AA 20M 40M 60M 80M 100M 82300000 82000000 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 -lbladeRF -lm -lfftw3f -lmbedcrypto
AOM AV1 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.2 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080p B AA 1.2353 2.4706 3.7059 4.9412 6.1765 5.49 5.47 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
Kvazaar Video Input: Bosphorus 1080p - Video Preset: Medium OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.1 Video Input: Bosphorus 1080p - Video Preset: Medium AA B 8 16 24 32 40 33.25 33.13 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Stress-NG Test: CPU Stress OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: CPU Stress B AA 15K 30K 45K 60K 75K 70164.47 69913.83 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
Nginx Test: Long Connection - Connections: 500 OpenBenchmarking.org Requests Per Second, More Is Better Nginx Test: Long Connection - Connections: 500 B AA 30K 60K 90K 120K 150K 136435.64 135958.27 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2 2. nginx version: nginx/1.18.0 (Ubuntu)
Cpuminer-Opt Algorithm: x25x OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.18 Algorithm: x25x AA B 200 400 600 800 1000 802.96 800.21 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Kvazaar Video Input: Bosphorus 4K - Video Preset: Slow OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.1 Video Input: Bosphorus 4K - Video Preset: Slow AA B 3 6 9 12 15 12.25 12.21 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
simdjson Throughput Test: PartialTweets OpenBenchmarking.org GB/s, More Is Better simdjson 1.0 Throughput Test: PartialTweets AA B 0.6953 1.3906 2.0859 2.7812 3.4765 3.09 3.08 1. (CXX) g++ options: -O3 -pthread
Blender Blend File: Classroom - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.0 Blend File: Classroom - Compute: CPU-Only B AA 30 60 90 120 150 147.25 147.72
Stress-NG Test: Semaphores OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Semaphores AA B 1000K 2000K 3000K 4000K 5000K 4705038.25 4690182.85 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
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 AA B 20 40 60 80 100 97.3 97.0 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 -lbladeRF -lm -lfftw3f -lmbedcrypto
Timed GDB GNU Debugger Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed GDB GNU Debugger Compilation 10.2 Time To Compile B AA 15 30 45 60 75 65.64 65.84
simdjson Throughput Test: DistinctUserID OpenBenchmarking.org GB/s, More Is Better simdjson 1.0 Throughput Test: DistinctUserID B AA 0.7695 1.539 2.3085 3.078 3.8475 3.42 3.41 1. (CXX) g++ options: -O3 -pthread
ASTC Encoder Preset: Exhaustive OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 3.2 Preset: Exhaustive AA B 7 14 21 28 35 31.29 31.38 1. (CXX) g++ options: -O3 -flto -pthread
Timed Linux Kernel Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 5.14 Time To Compile AA B 11 22 33 44 55 50.27 50.42
BRL-CAD VGR Performance Metric OpenBenchmarking.org VGR Performance Metric, More Is Better BRL-CAD 7.32.2 VGR Performance Metric AA B 60K 120K 180K 240K 300K 300804 299956 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
Primesieve 1e12 Prime Number Generation OpenBenchmarking.org Seconds, Fewer Is Better Primesieve 7.7 1e12 Prime Number Generation B AA 2 4 6 8 10 8.064 8.086 1. (CXX) g++ options: -O3 -lpthread
Stress-NG Test: Malloc OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Malloc AA B 70M 140M 210M 280M 350M 319416181.16 318555456.11 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
Facebook RocksDB Test: Random Read OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Random Read B AA 30M 60M 90M 120M 150M 141450130 141073292 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Kvazaar Video Input: Bosphorus 4K - Video Preset: Ultra Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.1 Video Input: Bosphorus 4K - Video Preset: Ultra Fast B AA 8 16 24 32 40 35.35 35.26 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Renaissance Test: Apache Spark Bayes OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Apache Spark Bayes AA B 300 600 900 1200 1500 1159.4 1162.3 MIN: 833.69 / MAX: 1209.29 MIN: 837.65
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 B AA 50 100 150 200 250 210.7 210.2 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 -lbladeRF -lm -lfftw3f -lmbedcrypto
Renaissance Test: Finagle HTTP Requests OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Finagle HTTP Requests AA B 900 1800 2700 3600 4500 4196.7 4206.6 MIN: 3824.45 / MAX: 4204.8 MIN: 3861.51 / MAX: 4484.94
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 AA B 700 1400 2100 2800 3500 3474.6 3466.5 1. (CC) gcc options: -O3 -pthread -lz -llzma
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 B AA 40 80 120 160 200 176.0 175.6 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 -lbladeRF -lm -lfftw3f -lmbedcrypto
Stress-NG Test: Vector Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Vector Math AA B 30K 60K 90K 120K 150K 117428.81 117178.80 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
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 AA B 11 22 33 44 55 47.3 47.2 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 -lbladeRF -lm -lfftw3f -lmbedcrypto
ASTC Encoder Preset: Thorough OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 3.2 Preset: Thorough B AA 2 4 6 8 10 8.3224 8.3396 1. (CXX) g++ options: -O3 -flto -pthread
Timed FFmpeg Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed FFmpeg Compilation 4.4 Time To Compile AA B 8 16 24 32 40 32.76 32.83
dav1d Video Input: Summer Nature 1080p OpenBenchmarking.org FPS, More Is Better dav1d 0.9.2 Video Input: Summer Nature 1080p B AA 130 260 390 520 650 579.16 578.08 MIN: 346.11 / MAX: 632.83 MIN: 343.91 / MAX: 631 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 AA B 100K 200K 300K 400K 500K 457950.37 457100.94 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
Cpuminer-Opt Algorithm: Magi OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.18 Algorithm: Magi AA B 200 400 600 800 1000 1155.44 1153.33 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
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 B AA 1.2758 2.5516 3.8274 5.1032 6.379 5.66 5.67 MIN: 5 / MAX: 8.84 MIN: 4.91 / MAX: 8.18 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenSSL Algorithm: RSA4096 OpenBenchmarking.org verify/s, More Is Better OpenSSL 3.0 Algorithm: RSA4096 AA B 80K 160K 240K 320K 400K 376708.4 376078.8 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
Zstd Compression Compression Level: 19, Long Mode - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 19, Long Mode - Decompression Speed AA B 700 1400 2100 2800 3500 3114.3 3109.1 1. *** zstd command line interface 64-bits v1.4.5, by Yann Collet ***
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 AA B 14 28 42 56 70 63.0 62.9 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 -lbladeRF -lm -lfftw3f -lmbedcrypto
Renaissance Test: Apache Spark ALS OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Apache Spark ALS AA B 500 1000 1500 2000 2500 2109.3 2112.1 MIN: 1919.48 / MAX: 2302.92 MIN: 1933.98 / MAX: 2598.69
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 AA B 2 4 6 8 10 7.63 7.64 MIN: 6.44 / MAX: 14.46 MIN: 6.45 / MAX: 13.29 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Blender Blend File: BMW27 - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.0 Blend File: BMW27 - Compute: CPU-Only AA B 12 24 36 48 60 53.95 54.02
Blender Blend File: Fishy Cat - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.0 Blend File: Fishy Cat - Compute: CPU-Only AA B 20 40 60 80 100 78.69 78.79
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 AA B 2M 4M 6M 8M 10M 8604238.16 8594247.31 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
JPEG XL libjxl Input: PNG - Encode Speed: 5 OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.6.1 Input: PNG - Encode Speed: 5 AA B 12 24 36 48 60 52.47 52.41 1. (CXX) g++ options: -funwind-tables -O3 -O2 -pthread -fPIE -pie
Stargate Digital Audio Workstation Sample Rate: 96000 - Buffer Size: 1024 OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 21.10.9 Sample Rate: 96000 - Buffer Size: 1024 B AA 0.4985 0.997 1.4955 1.994 2.4925 2.215502 2.213074 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
Cpuminer-Opt Algorithm: Myriad-Groestl OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.18 Algorithm: Myriad-Groestl B AA 2K 4K 6K 8K 10K 10190 10180 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenSSL Algorithm: RSA4096 OpenBenchmarking.org sign/s, More Is Better OpenSSL 3.0 Algorithm: RSA4096 AA B 1300 2600 3900 5200 6500 5851.5 5845.9 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
Blender Blend File: Barbershop - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.0 Blend File: Barbershop - Compute: CPU-Only B AA 140 280 420 560 700 634.97 635.52
NCNN Target: Vulkan GPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: resnet50 B AA 3 6 9 12 15 12.04 12.05 MIN: 11.44 / MAX: 13.28 MIN: 11.6 / MAX: 15.22 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -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 B AA 30 60 90 120 150 121.1 121.0 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 -lbladeRF -lm -lfftw3f -lmbedcrypto
OpenSSL OpenBenchmarking.org verify/s, More Is Better OpenSSL B AA 80K 160K 240K 320K 400K 375362.3 375075.2 1. OpenSSL 1.1.1f 31 Mar 2020
7-Zip Compression Test: Decompression Rating OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 21.06 Test: Decompression Rating B AA 40K 80K 120K 160K 200K 173641 173519 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
NAS Parallel Benchmarks Test / Class: EP.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.C AA B 400 800 1200 1600 2000 1736.13 1734.99 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.0.3
Zstd Compression Compression Level: 19 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19 - Decompression Speed B AA 600 1200 1800 2400 3000 2950.9 2949.0 1. (CC) gcc options: -O3 -pthread -lz -llzma
Stress-NG Test: MMAP OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: MMAP B AA 200 400 600 800 1000 896.92 896.44 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
NAS Parallel Benchmarks Test / Class: EP.D OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.D B AA 400 800 1200 1600 2000 1738.63 1737.94 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.0.3
Stress-NG Test: Matrix Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Matrix Math AA B 30K 60K 90K 120K 150K 135023.34 134983.16 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
TNN Target: CPU - Model: SqueezeNet v1.1 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v1.1 AA B 50 100 150 200 250 250.94 251.01 MIN: 250.45 / MAX: 251.59 MIN: 250.45 / MAX: 252.56 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
Zstd Compression Compression Level: 3, Long Mode - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 3, Long Mode - Compression Speed AA B 70 140 210 280 350 339.5 339.4 1. *** zstd command line interface 64-bits v1.4.5, by Yann Collet ***
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 AA B 80 160 240 320 400 350.4 350.3 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 -lbladeRF -lm -lfftw3f -lmbedcrypto
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 AA B 100 200 300 400 500 458.20 458.07 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
Stress-NG Test: Atomic OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Atomic AA B 40K 80K 120K 160K 200K 184198.75 184185.78 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
OpenSSL OpenBenchmarking.org sign/s, More Is Better OpenSSL AA B 1300 2600 3900 5200 6500 5849.4 5849.1 1. OpenSSL 1.1.1f 31 Mar 2020
Zstd Compression Compression Level: 3 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 3 - Decompression Speed B 700 1400 2100 2800 3500 3229.1 1. *** zstd command line interface 64-bits v1.4.5, by Yann Collet ***
Facebook RocksDB Test: Read While Writing OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Read While Writing B 1000K 2000K 3000K 4000K 5000K 4472075 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Apache Cassandra Test: Mixed 1:3 OpenBenchmarking.org Op/s, More Is Better Apache Cassandra 4.0 Test: Mixed 1:3 AA 30K 60K 90K 120K 150K 149882
Apache Cassandra Test: Mixed 1:1 OpenBenchmarking.org Op/s, More Is Better Apache Cassandra 4.0 Test: Mixed 1:1 B 30K 60K 90K 120K 150K 150860
Apache Cassandra Test: Writes OpenBenchmarking.org Op/s, More Is Better Apache Cassandra 4.0 Test: Writes B 40K 80K 120K 160K 200K 175440
Cpuminer-Opt Algorithm: Triple SHA-256, Onecoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.18 Algorithm: Triple SHA-256, Onecoin B AA 30K 60K 90K 120K 150K 128000 128000 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Timed LLVM Compilation Build System: Ninja OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 13.0 Build System: Ninja B 80 160 240 320 400 381.16
Timed GCC Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed GCC Compilation 11.2.0 Time To Compile AA 200 400 600 800 1000 947.37
OpenVKL Benchmark: vklBenchmark Scalar OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 1.0 Benchmark: vklBenchmark Scalar B AA 13 26 39 52 65 56 56 MIN: 5 / MAX: 918 MIN: 5 / MAX: 932
OpenVKL Benchmark: vklBenchmark ISPC OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 1.0 Benchmark: vklBenchmark ISPC B AA 20 40 60 80 100 89 89 MIN: 11 / MAX: 875 MIN: 11 / MAX: 877
AOM AV1 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.2 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080p B AA 0.0518 0.1036 0.1554 0.2072 0.259 0.23 0.23 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
AOM AV1 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.2 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4K B AA 0.027 0.054 0.081 0.108 0.135 0.12 0.12 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
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 B AA 120 240 360 480 600 560.5 560.5 1. (CC) gcc options: -O3 -pthread -lz -llzma
simdjson Throughput Test: LargeRandom OpenBenchmarking.org GB/s, More Is Better simdjson 1.0 Throughput Test: LargeRandom B 0.189 0.378 0.567 0.756 0.945 0.84 1. (CXX) g++ options: -O3 -pthread
BLAKE2 OpenBenchmarking.org Cycles Per Byte, Fewer Is Better BLAKE2 20170307 AA B 1.0058 2.0116 3.0174 4.0232 5.029 4.47 4.47 1. (CC) gcc options: -O3 -march=native -lcrypto -lz
Sockperf Test: Latency Under Load OpenBenchmarking.org usec, Fewer Is Better Sockperf 3.7 Test: Latency Under Load AA A B 30 60 90 120 150 SE +/- 6.08, N = 25 28.73 70.38 112.56 1. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread
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 A B AA 140 280 420 560 700 SE +/- 18.30, N = 15 649.4 569.4 548.1 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
Phoronix Test Suite v10.8.5