ampere-altra-aa Tests for a future article. Ampere Altra ARMv8 Neoverse-N1 testing with a WIWYNN Mt.Jade (1.1.20201019 BIOS) and ASPEED on Ubuntu 20.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2105053-IB-AMPEREALT48&grs .
ampere-altra-aa Processor Motherboard Chipset Memory Disk Graphics Monitor Network OS Kernel Desktop Display Server Compiler File-System Screen Resolution 1 1a 2 Ampere Altra ARMv8 Neoverse-N1 @ 3.00GHz (160 Cores) WIWYNN Mt.Jade (1.1.20201019 BIOS) Ampere Computing LLC Device e100 16 x 32 GB DDR4-3200MT/s Samsung M393A4K40DB3-CWE 3841GB Micron_9300_MTFDHAL3T8TDP + 960GB SAMSUNG MZ1LB960HAJQ-00007 ASPEED VE228 Mellanox MT28908 + Intel I210 Ubuntu 20.04 5.11.0-051100-generic-64k (aarch64) GNOME Shell 3.36.4 X Server 1.20.9 GCC 9.3.0 ext4 1920x1080 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - --build=aarch64-linux-gnu --disable-libquadmath --disable-libquadmath-support --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-fix-cortex-a53-843419 --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-objc-gc=auto --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --program-prefix=aarch64-linux-gnu- --target=aarch64-linux-gnu --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-target-system-zlib=auto -v Processor Details - Scaling Governor: cppc_cpufreq ondemand (Boost: Enabled) Python Details - Python 3.8.5 Security Details - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Not affected + srbds: Not affected + tsx_async_abort: Not affected
ampere-altra-aa mnn: SqueezeNetV1.0 onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPU onednn: Recurrent Neural Network Training - bf16bf16bf16 - CPU onednn: Recurrent Neural Network Training - f32 - CPU onednn: Recurrent Neural Network Inference - u8s8f32 - CPU onednn: Deconvolution Batch shapes_3d - u8s8f32 - CPU mnn: inception-v3 onednn: Deconvolution Batch shapes_3d - f32 - CPU onednn: Recurrent Neural Network Training - u8s8f32 - CPU onednn: Recurrent Neural Network Inference - f32 - CPU gnuradio: Five Back to Back FIR Filters aom-av1: Speed 8 Realtime - Bosphorus 4K avifenc: 10 basis: UASTC Level 3 mnn: mobilenet-v1-1.0 build-llvm: Ninja aom-av1: Speed 6 Two-Pass - Bosphorus 4K onednn: Matrix Multiply Batch Shapes Transformer - f32 - CPU luaradio: Five Back to Back FIR Filters onednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU aom-av1: Speed 4 Two-Pass - Bosphorus 4K mnn: MobileNetV2_224 aom-av1: Speed 9 Realtime - Bosphorus 4K onednn: Deconvolution Batch shapes_1d - u8s8f32 - CPU compress-zstd: 3 - Compression Speed basis: UASTC Level 0 aom-av1: Speed 6 Two-Pass - Bosphorus 1080p onednn: IP Shapes 1D - u8s8f32 - CPU gnuradio: IIR Filter gnuradio: FM Deemphasis Filter draco: Lion srslte: PHY_DL_Test mnn: resnet-v2-50 onednn: IP Shapes 3D - u8s8f32 - CPU onednn: Deconvolution Batch shapes_1d - f32 - CPU aom-av1: Speed 4 Two-Pass - Bosphorus 1080p draco: Church Facade gnuradio: Signal Source (Cosine) viennacl: CPU BLAS - sAXPY viennacl: CPU BLAS - dGEMV-T gnuradio: FIR Filter viennacl: CPU BLAS - dGEMM-NT onednn: IP Shapes 1D - f32 - CPU build-mesa: Time To Compile avifenc: 6 avifenc: 6, Lossless basis: ETC1S viennacl: CPU BLAS - sDOT viennacl: CPU BLAS - dGEMM-NN aom-av1: Speed 8 Realtime - Bosphorus 1080p viennacl: CPU BLAS - dAXPY build-linux-kernel: Time To Compile build-nodejs: Time To Compile avifenc: 10, Lossless sysbench: RAM / Memory compress-zstd: 19 - Decompression Speed compress-zstd: 3, Long Mode - Decompression Speed viennacl: CPU BLAS - dGEMM-TN compress-zstd: 8, Long Mode - Decompression Speed viennacl: CPU BLAS - sCOPY aom-av1: Speed 9 Realtime - Bosphorus 1080p luaradio: FM Deemphasis Filter basis: UASTC Level 2 onednn: IP Shapes 3D - f32 - CPU avifenc: 0 viennacl: CPU BLAS - dGEMV-N build-llvm: Unix Makefiles aom-av1: Speed 6 Realtime - Bosphorus 4K gnuradio: Hilbert Transform compress-zstd: 8 - Decompression Speed luaradio: Hilbert Transform stockfish: Total Time srslte: OFDM_Test botan: AES-256 onednn: Convolution Batch Shapes Auto - f32 - CPU build-erlang: Time To Compile liquid-dsp: 1 - 256 - 57 liquid-dsp: 160 - 256 - 57 gmpbench: Total Time botan: AES-256 - Decrypt incompact3d: input.i3d 193 Cells Per Direction onednn: Convolution Batch Shapes Auto - u8s8f32 - CPU avifenc: 2 compress-zstd: 19, Long Mode - Decompression Speed sysbench: CPU viennacl: CPU BLAS - dDOT liquid-dsp: 4 - 256 - 57 liquid-dsp: 32 - 256 - 57 incompact3d: X3D-benchmarking input.i3d aom-av1: Speed 6 Realtime - Bosphorus 1080p botan: Twofish liquid-dsp: 16 - 256 - 57 srslte: PHY_DL_Test tjbench: Decompression Throughput botan: Blowfish - Decrypt liquid-dsp: 64 - 256 - 57 botan: CAST-256 - Decrypt botan: CAST-256 liquid-dsp: 8 - 256 - 57 securemark: SecureMark-TLS botan: Blowfish botan: ChaCha20Poly1305 - Decrypt botan: Twofish - Decrypt liquid-dsp: 2 - 256 - 57 liquid-dsp: 128 - 256 - 57 botan: KASUMI botan: KASUMI - Decrypt botan: ChaCha20Poly1305 viennacl: CPU BLAS - dGEMM-TT viennacl: CPU BLAS - dCOPY aom-av1: Speed 0 Two-Pass - Bosphorus 1080p aom-av1: Speed 0 Two-Pass - Bosphorus 4K luaradio: Complex Phase compress-zstd: 19, Long Mode - Compression Speed compress-zstd: 8, Long Mode - Compression Speed compress-zstd: 3, Long Mode - Compression Speed compress-zstd: 19 - Compression Speed compress-zstd: 8 - Compression Speed compress-zstd: 3 - Decompression Speed incompact3d: input.i3d 129 Cells Per Direction 1 1a 2 2464.1 9.934515 239.84964 2.66801906 9.449 11378.5 13553.8 15052.9 15125.7 35.318 48.227 37.5645 20154.4 12802.7 432.4 16.39 4.024 24.281 6.494 152.984 2.31 24.8967 399.8 5.62849 1.16 5.525 19.58 18.0682 2298 24.135 6.96 42.683 630 522.8 7414 53.6 34.024 46.627 43.916 1.71 9142 1706.5 55.9 74.7 370.2 51.4 58.5014 21.722 20.883 32.753 37.811 27.7 63.7 41.33 105 59.338 117.941 5.733 1301.39 2639.6 3261 82.1 3318.2 53.7 46.95 370 25.719 125.089 134.099 45 263.382 4.48 220.5 3200.4 8.3 133808173 46000000 2920.531 209.464 261.795 22033000 3501000000 2454.1 2914.75 9.94751263 98.2669 73.647 2757.9 612114.56 48.8 87774000 702870000 239.498199 7.13 265.647 351440000 134.8 143.035381 317.255 1402500000 124.135 124.64 175480000 160409 313.14 314.533 271.415 43878000 2802200000 71.451 69.56 316.867 98.2 0.06 0.03 8.5 25.4 300.2 357.1 39.6 346.2 3091.7 2.51974607 14.351 16831.2 19171 20882.6 20936.6 46.9958 63.48 29.8678 16199.6 15658.8 356.6 13.54 3.38 28.645 5.56 132.666 2.65 21.7565 352 4.97049 1.03 6.194 21.55 19.7728 2116.4 26.2 6.42 45.9797 675.3 560.2 6927 50.4 31.998 49.5431 46.6474 1.61 9704 1805.6 59.1 71 387.5 53.7 60.9242 22.6 20.104 34.019 39.153 26.8 65.8 40.16 108 60.939 114.844 5.585 1270.79 2699.0 3333.0 80.4 3387.4 52.7 46.08 363.9 25.351 126.894 132.295 44.4 266.938 4.54 223.4 3160.7 8.2 132503840 45700000 2901.819 208.283 260.569 21934000 3486600000 2463.5 2903.463 9.97241412 97.9454 73.855 2751.3 613461.54 48.9 87603000 701630000 239.520584 7.12 265.331 351170000 134.9 142.936983 317.11 1403100000 124.18 124.597 175520000 160378 313.19 314.499 271.39 43882000 2802400000 71.446 69.563 316.863 63.8 98.2 0.06 0.03 8.5 25.0 290.0 344.0 42.7 368.4 3000.3 2.65654607 OpenBenchmarking.org
Mobile Neural Network Model: SqueezeNetV1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.1.3 Model: SqueezeNetV1.0 1a 2 4 8 12 16 20 9.449 14.351 MIN: 9.24 / MAX: 13.75 MIN: 13.88 / MAX: 17.67 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
oneDNN Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU 1a 2 4K 8K 12K 16K 20K 11378.5 16831.2 MIN: 10878.4 MIN: 13382.4 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -mcpu=native -fPIC -pie -lpthread -ldl
oneDNN Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU 1a 2 4K 8K 12K 16K 20K 13553.8 19171.0 MIN: 12741.7 MIN: 17095.5 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -mcpu=native -fPIC -pie -lpthread -ldl
oneDNN Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU 1a 2 4K 8K 12K 16K 20K 15052.9 20882.6 MIN: 13642.1 MIN: 20639.3 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -mcpu=native -fPIC -pie -lpthread -ldl
oneDNN Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU 1a 2 4K 8K 12K 16K 20K 15125.7 20936.6 MIN: 10636.8 MIN: 18217.7 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -mcpu=native -fPIC -pie -lpthread -ldl
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU 1a 2 11 22 33 44 55 35.32 47.00 MIN: 30.81 MIN: 38.06 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -mcpu=native -fPIC -pie -lpthread -ldl
Mobile Neural Network Model: inception-v3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.1.3 Model: inception-v3 1a 2 14 28 42 56 70 48.23 63.48 MIN: 46.63 / MAX: 62.25 MIN: 62.64 / MAX: 68.99 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
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU 1a 2 9 18 27 36 45 37.56 29.87 MIN: 28.64 MIN: 25.42 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -mcpu=native -fPIC -pie -lpthread -ldl
oneDNN Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU 1a 2 4K 8K 12K 16K 20K 20154.4 16199.6 MIN: 19134.1 MIN: 14658.6 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -mcpu=native -fPIC -pie -lpthread -ldl
oneDNN Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU 1a 2 3K 6K 9K 12K 15K 12802.7 15658.8 MIN: 10310.2 MIN: 11083.5 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -mcpu=native -fPIC -pie -lpthread -ldl
GNU Radio Test: Five Back to Back FIR Filters OpenBenchmarking.org MiB/s, More Is Better GNU Radio Test: Five Back to Back FIR Filters 1a 2 90 180 270 360 450 432.4 356.6 1. 3.8.1.0
AOM AV1 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.0 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K 1a 2 4 8 12 16 20 16.39 13.54 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
libavif avifenc Encoder Speed: 10 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.9.0 Encoder Speed: 10 1a 2 0.9054 1.8108 2.7162 3.6216 4.527 4.024 3.380 1. (CXX) g++ options: -O3 -fPIC -lm
Basis Universal Settings: UASTC Level 3 OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.13 Settings: UASTC Level 3 1a 2 7 14 21 28 35 24.28 28.65 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
Mobile Neural Network Model: mobilenet-v1-1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.1.3 Model: mobilenet-v1-1.0 1a 2 2 4 6 8 10 6.494 5.560 MIN: 5.8 / MAX: 9.49 MIN: 5.23 / MAX: 5.99 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
Timed LLVM Compilation Build System: Ninja OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 12.0 Build System: Ninja 1a 2 30 60 90 120 150 152.98 132.67
AOM AV1 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.0 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K 1a 2 0.5963 1.1926 1.7889 2.3852 2.9815 2.31 2.65 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
oneDNN Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU 1a 2 6 12 18 24 30 24.90 21.76 MIN: 18.69 MIN: 16.85 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -mcpu=native -fPIC -pie -lpthread -ldl
LuaRadio Test: Five Back to Back FIR Filters OpenBenchmarking.org MiB/s, More Is Better LuaRadio 0.9.1 Test: Five Back to Back FIR Filters 1a 2 90 180 270 360 450 399.8 352.0
oneDNN Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU 1a 2 1.2664 2.5328 3.7992 5.0656 6.332 5.62849 4.97049 MIN: 4.57 MIN: 4.07 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -mcpu=native -fPIC -pie -lpthread -ldl
AOM AV1 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.0 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4K 1a 2 0.261 0.522 0.783 1.044 1.305 1.16 1.03 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
Mobile Neural Network Model: MobileNetV2_224 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.1.3 Model: MobileNetV2_224 1a 2 2 4 6 8 10 5.525 6.194 MIN: 5.31 / MAX: 5.73 MIN: 5.5 / MAX: 9.59 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
AOM AV1 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.0 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K 1a 2 5 10 15 20 25 19.58 21.55 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU 1a 2 5 10 15 20 25 18.07 19.77 MIN: 13.9 MIN: 13.89 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -mcpu=native -fPIC -pie -lpthread -ldl
Zstd Compression Compression Level: 3 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 3 - Compression Speed 1a 2 500 1000 1500 2000 2500 SE +/- 27.70, N = 15 2298.0 2116.4 1. (CC) gcc options: -O3 -pthread -lz -llzma
Basis Universal Settings: UASTC Level 0 OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.13 Settings: UASTC Level 0 1a 2 6 12 18 24 30 24.14 26.20 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
AOM AV1 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.0 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080p 1a 2 2 4 6 8 10 6.96 6.42 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
oneDNN Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU 1a 2 10 20 30 40 50 42.68 45.98 MIN: 34.27 MIN: 37.38 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -mcpu=native -fPIC -pie -lpthread -ldl
GNU Radio Test: IIR Filter OpenBenchmarking.org MiB/s, More Is Better GNU Radio Test: IIR Filter 1a 2 150 300 450 600 750 630.0 675.3 1. 3.8.1.0
GNU Radio Test: FM Deemphasis Filter OpenBenchmarking.org MiB/s, More Is Better GNU Radio Test: FM Deemphasis Filter 1a 2 120 240 360 480 600 522.8 560.2 1. 3.8.1.0
Google Draco Model: Lion OpenBenchmarking.org ms, Fewer Is Better Google Draco 1.4.1 Model: Lion 1a 2 1600 3200 4800 6400 8000 7414 6927 1. (CXX) g++ options: -O3
srsLTE Test: PHY_DL_Test OpenBenchmarking.org UE Mb/s, More Is Better srsLTE 20.10.1 Test: PHY_DL_Test 1a 2 12 24 36 48 60 53.6 50.4 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lm -lfftw3f
Mobile Neural Network Model: resnet-v2-50 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.1.3 Model: resnet-v2-50 1a 2 8 16 24 32 40 34.02 32.00 MIN: 32.86 / MAX: 41.11 MIN: 26.31 / MAX: 53.88 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
oneDNN Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU 1a 2 11 22 33 44 55 46.63 49.54 MIN: 43.67 MIN: 42.65 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -mcpu=native -fPIC -pie -lpthread -ldl
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU 1a 2 11 22 33 44 55 43.92 46.65 MIN: 35.23 MIN: 36.81 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -mcpu=native -fPIC -pie -lpthread -ldl
AOM AV1 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.0 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080p 1a 2 0.3848 0.7696 1.1544 1.5392 1.924 1.71 1.61 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
Google Draco Model: Church Facade OpenBenchmarking.org ms, Fewer Is Better Google Draco 1.4.1 Model: Church Facade 1a 2 2K 4K 6K 8K 10K 9142 9704 1. (CXX) g++ options: -O3
GNU Radio Test: Signal Source (Cosine) OpenBenchmarking.org MiB/s, More Is Better GNU Radio Test: Signal Source (Cosine) 1a 2 400 800 1200 1600 2000 1706.5 1805.6 1. 3.8.1.0
ViennaCL Test: CPU BLAS - sAXPY OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - sAXPY 1a 2 13 26 39 52 65 55.9 59.1 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: CPU BLAS - dGEMV-T OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dGEMV-T 1a 2 20 40 60 80 100 74.7 71.0 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
GNU Radio Test: FIR Filter OpenBenchmarking.org MiB/s, More Is Better GNU Radio Test: FIR Filter 1a 2 80 160 240 320 400 370.2 387.5 1. 3.8.1.0
ViennaCL Test: CPU BLAS - dGEMM-NT OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-NT 1a 2 12 24 36 48 60 51.4 53.7 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
oneDNN Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU 1a 2 14 28 42 56 70 58.50 60.92 MIN: 52.2 MIN: 49.82 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -mcpu=native -fPIC -pie -lpthread -ldl
Timed Mesa Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Mesa Compilation 21.0 Time To Compile 1a 2 5 10 15 20 25 21.72 22.60
libavif avifenc Encoder Speed: 6 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.9.0 Encoder Speed: 6 1a 2 5 10 15 20 25 20.88 20.10 1. (CXX) g++ options: -O3 -fPIC -lm
libavif avifenc Encoder Speed: 6, Lossless OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.9.0 Encoder Speed: 6, Lossless 1a 2 8 16 24 32 40 32.75 34.02 1. (CXX) g++ options: -O3 -fPIC -lm
Basis Universal Settings: ETC1S OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.13 Settings: ETC1S 1a 2 9 18 27 36 45 37.81 39.15 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
ViennaCL Test: CPU BLAS - sDOT OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - sDOT 1a 2 7 14 21 28 35 27.7 26.8 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: CPU BLAS - dGEMM-NN OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-NN 1a 2 15 30 45 60 75 63.7 65.8 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
AOM AV1 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.0 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080p 1a 2 9 18 27 36 45 41.33 40.16 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
ViennaCL Test: CPU BLAS - dAXPY OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dAXPY 1a 2 20 40 60 80 100 105 108 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
Timed Linux Kernel Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 5.10.20 Time To Compile 1a 2 14 28 42 56 70 59.34 60.94
Timed Node.js Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Node.js Compilation 15.11 Time To Compile 1a 2 30 60 90 120 150 117.94 114.84
libavif avifenc Encoder Speed: 10, Lossless OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.9.0 Encoder Speed: 10, Lossless 1a 2 1.2899 2.5798 3.8697 5.1596 6.4495 5.733 5.585 1. (CXX) g++ options: -O3 -fPIC -lm
Sysbench Test: RAM / Memory OpenBenchmarking.org MiB/sec, More Is Better Sysbench 1.0.20 Test: RAM / Memory 1a 2 300 600 900 1200 1500 1301.39 1270.79 1. (CC) gcc options: -pthread -O2 -funroll-loops -rdynamic -ldl -laio -lm
Zstd Compression Compression Level: 19 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 19 - Decompression Speed 1a 2 600 1200 1800 2400 3000 SE +/- 11.95, N = 15 2639.6 2699.0 1. (CC) gcc options: -O3 -pthread -lz -llzma
Zstd Compression Compression Level: 3, Long Mode - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 3, Long Mode - Decompression Speed 1a 2 700 1400 2100 2800 3500 SE +/- 17.60, N = 15 3261.0 3333.0 1. (CC) gcc options: -O3 -pthread -lz -llzma
ViennaCL Test: CPU BLAS - dGEMM-TN OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-TN 1a 2 20 40 60 80 100 82.1 80.4 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
Zstd Compression Compression Level: 8, Long Mode - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 8, Long Mode - Decompression Speed 1a 2 700 1400 2100 2800 3500 SE +/- 25.49, N = 12 3318.2 3387.4 1. (CC) gcc options: -O3 -pthread -lz -llzma
ViennaCL Test: CPU BLAS - sCOPY OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - sCOPY 1a 2 12 24 36 48 60 53.7 52.7 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
AOM AV1 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.0 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080p 1a 2 11 22 33 44 55 46.95 46.08 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
LuaRadio Test: FM Deemphasis Filter OpenBenchmarking.org MiB/s, More Is Better LuaRadio 0.9.1 Test: FM Deemphasis Filter 1a 2 80 160 240 320 400 370.0 363.9
Basis Universal Settings: UASTC Level 2 OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.13 Settings: UASTC Level 2 1a 2 6 12 18 24 30 25.72 25.35 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
oneDNN Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU 1a 2 30 60 90 120 150 125.09 126.89 MIN: 122.58 MIN: 121.46 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -mcpu=native -fPIC -pie -lpthread -ldl
libavif avifenc Encoder Speed: 0 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.9.0 Encoder Speed: 0 1a 2 30 60 90 120 150 134.10 132.30 1. (CXX) g++ options: -O3 -fPIC -lm
ViennaCL Test: CPU BLAS - dGEMV-N OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dGEMV-N 1a 2 10 20 30 40 50 45.0 44.4 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
Timed LLVM Compilation Build System: Unix Makefiles OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 12.0 Build System: Unix Makefiles 1a 2 60 120 180 240 300 263.38 266.94
AOM AV1 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.0 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K 1a 2 1.0215 2.043 3.0645 4.086 5.1075 4.48 4.54 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
GNU Radio Test: Hilbert Transform OpenBenchmarking.org MiB/s, More Is Better GNU Radio Test: Hilbert Transform 1a 2 50 100 150 200 250 220.5 223.4 1. 3.8.1.0
Zstd Compression Compression Level: 8 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 8 - Decompression Speed 1a 2 700 1400 2100 2800 3500 SE +/- 17.08, N = 15 3200.4 3160.7 1. (CC) gcc options: -O3 -pthread -lz -llzma
LuaRadio Test: Hilbert Transform OpenBenchmarking.org MiB/s, More Is Better LuaRadio 0.9.1 Test: Hilbert Transform 1a 2 2 4 6 8 10 8.3 8.2
Stockfish Total Time OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 13 Total Time 1a 2 30M 60M 90M 120M 150M 133808173 132503840 1. (CXX) g++ options: -lgcov -lpthread -fno-exceptions -std=c++17 -fprofile-use -fno-peel-loops -fno-tracer -pedantic -O3 -flto -flto=jobserver
srsLTE Test: OFDM_Test OpenBenchmarking.org Samples / Second, More Is Better srsLTE 20.10.1 Test: OFDM_Test 1a 2 10M 20M 30M 40M 50M SE +/- 57735.03, N = 3 46000000 45700000 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lm -lfftw3f
Botan Test: AES-256 OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: AES-256 1a 2 600 1200 1800 2400 3000 2920.53 2901.82 1. (CXX) g++ options: -fstack-protector -pthread -lbotan-2 -ldl -lrt
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU 1a 2 50 100 150 200 250 209.46 208.28 MIN: 203.67 MIN: 204.22 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -mcpu=native -fPIC -pie -lpthread -ldl
Timed Erlang/OTP Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Erlang/OTP Compilation 23.2 Time To Compile 1a 2 60 120 180 240 300 261.80 260.57
Liquid-DSP Threads: 1 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 1 - Buffer Length: 256 - Filter Length: 57 1a 2 5M 10M 15M 20M 25M 22033000 21934000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Liquid-DSP Threads: 160 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 160 - Buffer Length: 256 - Filter Length: 57 1a 2 700M 1400M 2100M 2800M 3500M 3501000000 3486600000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
GNU GMP GMPbench Total Time OpenBenchmarking.org GMPbench Score, More Is Better GNU GMP GMPbench 6.2.1 Total Time 1 1a 2 500 1000 1500 2000 2500 2464.1 2454.1 2463.5 1. (CC) gcc options: -O3 -fomit-frame-pointer -lm
Botan Test: AES-256 - Decrypt OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: AES-256 - Decrypt 1a 2 600 1200 1800 2400 3000 2914.75 2903.46 1. (CXX) g++ options: -fstack-protector -pthread -lbotan-2 -ldl -lrt
Xcompact3d Incompact3d Input: input.i3d 193 Cells Per Direction OpenBenchmarking.org Seconds, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 Input: input.i3d 193 Cells Per Direction 1 1a 2 3 6 9 12 15 SE +/- 0.08153142, N = 9 9.93451500 9.94751263 9.97241412 1. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU 1a 2 20 40 60 80 100 98.27 97.95 MIN: 94.33 MIN: 93.95 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -mcpu=native -fPIC -pie -lpthread -ldl
libavif avifenc Encoder Speed: 2 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.9.0 Encoder Speed: 2 1a 2 16 32 48 64 80 73.65 73.86 1. (CXX) g++ options: -O3 -fPIC -lm
Zstd Compression Compression Level: 19, Long Mode - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 19, Long Mode - Decompression Speed 1a 2 600 1200 1800 2400 3000 SE +/- 4.99, N = 15 2757.9 2751.3 1. (CC) gcc options: -O3 -pthread -lz -llzma
Sysbench Test: CPU OpenBenchmarking.org Events Per Second, More Is Better Sysbench 1.0.20 Test: CPU 1a 2 130K 260K 390K 520K 650K 612114.56 613461.54 1. (CC) gcc options: -pthread -O2 -funroll-loops -rdynamic -ldl -laio -lm
ViennaCL Test: CPU BLAS - dDOT OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dDOT 1a 2 11 22 33 44 55 48.8 48.9 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
Liquid-DSP Threads: 4 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 4 - Buffer Length: 256 - Filter Length: 57 1a 2 20M 40M 60M 80M 100M 87774000 87603000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Liquid-DSP Threads: 32 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 32 - Buffer Length: 256 - Filter Length: 57 1a 2 150M 300M 450M 600M 750M 702870000 701630000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Xcompact3d Incompact3d Input: X3D-benchmarking input.i3d OpenBenchmarking.org Seconds, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 Input: X3D-benchmarking input.i3d 1 1a 2 50 100 150 200 250 SE +/- 0.07, N = 3 239.85 239.50 239.52 1. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
AOM AV1 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.0 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080p 1a 2 2 4 6 8 10 7.13 7.12 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
Botan Test: Twofish OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: Twofish 1a 2 60 120 180 240 300 265.65 265.33 1. (CXX) g++ options: -fstack-protector -pthread -lbotan-2 -ldl -lrt
Liquid-DSP Threads: 16 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 16 - Buffer Length: 256 - Filter Length: 57 1a 2 80M 160M 240M 320M 400M 351440000 351170000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
srsLTE Test: PHY_DL_Test OpenBenchmarking.org eNb Mb/s, More Is Better srsLTE 20.10.1 Test: PHY_DL_Test 1a 2 30 60 90 120 150 134.8 134.9 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lm -lfftw3f
libjpeg-turbo tjbench Test: Decompression Throughput OpenBenchmarking.org Megapixels/sec, More Is Better libjpeg-turbo tjbench 2.1.0 Test: Decompression Throughput 1a 2 30 60 90 120 150 143.04 142.94 1. (CC) gcc options: -O3 -rdynamic
Botan Test: Blowfish - Decrypt OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: Blowfish - Decrypt 1a 2 70 140 210 280 350 317.26 317.11 1. (CXX) g++ options: -fstack-protector -pthread -lbotan-2 -ldl -lrt
Liquid-DSP Threads: 64 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 64 - Buffer Length: 256 - Filter Length: 57 1a 2 300M 600M 900M 1200M 1500M 1402500000 1403100000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Botan Test: CAST-256 - Decrypt OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: CAST-256 - Decrypt 1a 2 30 60 90 120 150 124.14 124.18 1. (CXX) g++ options: -fstack-protector -pthread -lbotan-2 -ldl -lrt
Botan Test: CAST-256 OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: CAST-256 1a 2 30 60 90 120 150 124.64 124.60 1. (CXX) g++ options: -fstack-protector -pthread -lbotan-2 -ldl -lrt
Liquid-DSP Threads: 8 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 8 - Buffer Length: 256 - Filter Length: 57 1a 2 40M 80M 120M 160M 200M 175480000 175520000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
SecureMark Benchmark: SecureMark-TLS OpenBenchmarking.org marks, More Is Better SecureMark 1.0.4 Benchmark: SecureMark-TLS 1a 2 30K 60K 90K 120K 150K 160409 160378 1. (CC) gcc options: -pedantic -O3
Botan Test: Blowfish OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: Blowfish 1a 2 70 140 210 280 350 313.14 313.19 1. (CXX) g++ options: -fstack-protector -pthread -lbotan-2 -ldl -lrt
Botan Test: ChaCha20Poly1305 - Decrypt OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: ChaCha20Poly1305 - Decrypt 1a 2 70 140 210 280 350 314.53 314.50 1. (CXX) g++ options: -fstack-protector -pthread -lbotan-2 -ldl -lrt
Botan Test: Twofish - Decrypt OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: Twofish - Decrypt 1a 2 60 120 180 240 300 271.42 271.39 1. (CXX) g++ options: -fstack-protector -pthread -lbotan-2 -ldl -lrt
Liquid-DSP Threads: 2 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 2 - Buffer Length: 256 - Filter Length: 57 1a 2 9M 18M 27M 36M 45M 43878000 43882000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Liquid-DSP Threads: 128 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 128 - Buffer Length: 256 - Filter Length: 57 1a 2 600M 1200M 1800M 2400M 3000M 2802200000 2802400000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Botan Test: KASUMI OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: KASUMI 1a 2 16 32 48 64 80 71.45 71.45 1. (CXX) g++ options: -fstack-protector -pthread -lbotan-2 -ldl -lrt
Botan Test: KASUMI - Decrypt OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: KASUMI - Decrypt 1a 2 15 30 45 60 75 69.56 69.56 1. (CXX) g++ options: -fstack-protector -pthread -lbotan-2 -ldl -lrt
Botan Test: ChaCha20Poly1305 OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: ChaCha20Poly1305 1a 2 70 140 210 280 350 316.87 316.86 1. (CXX) g++ options: -fstack-protector -pthread -lbotan-2 -ldl -lrt
ViennaCL Test: CPU BLAS - dGEMM-TT OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-TT 2 14 28 42 56 70 63.8 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: CPU BLAS - dCOPY OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dCOPY 1a 2 20 40 60 80 100 98.2 98.2 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
AOM AV1 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.0 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080p 1a 2 0.0135 0.027 0.0405 0.054 0.0675 0.06 0.06 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 3.0 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4K 1a 2 0.0068 0.0136 0.0204 0.0272 0.034 0.03 0.03 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
LuaRadio Test: Complex Phase OpenBenchmarking.org MiB/s, More Is Better LuaRadio 0.9.1 Test: Complex Phase 1a 2 2 4 6 8 10 8.5 8.5
Zstd Compression Compression Level: 19, Long Mode - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 19, Long Mode - Compression Speed 1a 2 6 12 18 24 30 SE +/- 0.58, N = 15 25.4 25.0 1. (CC) gcc options: -O3 -pthread -lz -llzma
Zstd Compression Compression Level: 8, Long Mode - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 8, Long Mode - Compression Speed 1a 2 70 140 210 280 350 SE +/- 5.59, N = 12 300.2 290.0 1. (CC) gcc options: -O3 -pthread -lz -llzma
Zstd Compression Compression Level: 3, Long Mode - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 3, Long Mode - Compression Speed 1a 2 80 160 240 320 400 SE +/- 7.47, N = 15 357.1 344.0 1. (CC) gcc options: -O3 -pthread -lz -llzma
Zstd Compression Compression Level: 19 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 19 - Compression Speed 1a 2 10 20 30 40 50 SE +/- 1.49, N = 15 39.6 42.7 1. (CC) gcc options: -O3 -pthread -lz -llzma
Zstd Compression Compression Level: 8 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 8 - Compression Speed 1a 2 80 160 240 320 400 SE +/- 27.55, N = 15 346.2 368.4 1. (CC) gcc options: -O3 -pthread -lz -llzma
Zstd Compression Compression Level: 3 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 3 - Decompression Speed 1a 2 700 1400 2100 2800 3500 SE +/- 112.73, N = 6 3091.7 3000.3 1. (CC) gcc options: -O3 -pthread -lz -llzma
Xcompact3d Incompact3d Input: input.i3d 129 Cells Per Direction OpenBenchmarking.org Seconds, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 Input: input.i3d 129 Cells Per Direction 1 1a 2 0.6003 1.2006 1.8009 2.4012 3.0015 SE +/- 0.05362470, N = 15 2.66801906 2.51974607 2.65654607 1. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
Phoronix Test Suite v10.8.4