ice-lake-ubuntu 2 x Intel Xeon Platinum 8380 testing with a Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS) and ASPEED on Ubuntu 20.10 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2105170-IB-2105155IB65&sro&grr .
ice-lake-ubuntu Processor Motherboard Chipset Memory Disk Graphics Monitor Network OS Kernel Desktop Display Server Compiler File-System Screen Resolution Ubuntu 21.04 Ubuntu 20.10 2 x Intel Xeon Platinum 8380 @ 3.40GHz (80 Cores / 160 Threads) Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS) Intel Device 0998 504GB 800GB INTEL SSDPF21Q800GB ASPEED VE228 2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP Ubuntu 21.04 5.11.0-17-generic (x86_64) GNOME Shell 3.38.4 X Server GCC 10.3.0 ext4 1920x1080 Ubuntu 20.10 5.8.0-53-generic (x86_64) GNOME Shell 3.38.1 X Server 1.20.9 GCC 10.2.0 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - Ubuntu 21.04: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/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-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Ubuntu 20.10: --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 Disk Details - NONE / errors=remount-ro,relatime,rw / Block Size: 4096 Processor Details - Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd000270 Java Details - Ubuntu 21.04: OpenJDK Runtime Environment (build 11.0.11+9-Ubuntu-0ubuntu2) - Ubuntu 20.10: OpenJDK Runtime Environment (build 11.0.11+9-Ubuntu-0ubuntu2.20.10) Python Details - Ubuntu 21.04: Python 3.9.4 - Ubuntu 20.10: 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 Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
ice-lake-ubuntu wrf: conus 2.5km java-gradle-perf: Reactor openvkl: vklBenchmarkUnstructuredVolume numpy: openvkl: vklBenchmark wireguard: nwchem: C240 Buckyball onnx: super-resolution-10 - OpenMP CPU blogbench: Read onednn: Recurrent Neural Network Training - u8s8f32 - CPU yafaray: Total Time For Sample Scene relion: Basic - CPU tensorflow-lite: NASNet Mobile onnx: bertsquad-10 - OpenMP CPU tensorflow-lite: Mobilenet Quant tensorflow-lite: Mobilenet Float incompact3d: X3D-benchmarking input.i3d securemark: SecureMark-TLS pjsip: INVITE cassandra: Writes libgav1: Chimera 1080p node-web-tooling: helsing: 14 digit lammps: 20k Atoms onednn: Recurrent Neural Network Training - f32 - CPU onednn: Recurrent Neural Network Inference - u8s8f32 - CPU build-llvm: Unix Makefiles aom-av1: Speed 6 Two-Pass - Bosphorus 4K hpcg: onednn: Recurrent Neural Network Training - bf16bf16bf16 - CPU libgav1: Summer Nature 4K tnn: CPU - MobileNet v2 build-erlang: Time To Compile keydb: openfoam: Motorbike 60M mrbayes: Primate Phylogeny Analysis compress-zstd: 3, Long Mode - Decompression Speed cpuminer-opt: Blake-2 S cpuminer-opt: Skeincoin cpuminer-opt: Ringcoin cpuminer-opt: Myriad-Groestl tensorflow-lite: Inception ResNet V2 tensorflow-lite: SqueezeNet asmfish: 1024 Hash Memory, 26 Depth cpuminer-opt: Quad SHA-256, Pyrite compress-zstd: 19 - Decompression Speed compress-zstd: 19 - Compression Speed cpuminer-opt: Deepcoin cpuminer-opt: LBC, LBRY Credits build-llvm: Ninja compress-zstd: 19, Long Mode - Decompression Speed compress-zstd: 19, Long Mode - Compression Speed openvkl: vklBenchmarkStructuredVolume compress-zstd: 19, Long Mode - Decompression Speed compress-zstd: 19, Long Mode - Compression Speed compress-zstd: 8 - Decompression Speed compress-zstd: 8 - Compression Speed cpuminer-opt: Garlicoin onnx: fcn-resnet101-11 - OpenMP CPU onnx: yolov4 - OpenMP CPU compress-zstd: 8, Long Mode - Decompression Speed compress-zstd: 8, Long Mode - Compression Speed onnx: shufflenet-v2-10 - OpenMP CPU build-linux-kernel: Time To Compile blender: Barbershop - CPU-Only onednn: Deconvolution Batch shapes_1d - f32 - CPU build-nodejs: Time To Compile rodinia: OpenMP HotSpot3D compress-zstd: 3 - Decompression Speed compress-zstd: 3 - Compression Speed compress-zstd: 3, Long Mode - Compression Speed pgbench: 100 - 250 - Read Only - Average Latency pgbench: 100 - 250 - Read Only svt-av1: Preset 8 - Bosphorus 4K sysbench: CPU blender: Pabellon Barcelona - CPU-Only kvazaar: Bosphorus 4K - Medium build-php: Time To Compile libgav1: Summer Nature 1080p aom-av1: Speed 6 Realtime - Bosphorus 4K build-eigen: Time To Compile node-express-loadtest: tensorflow-lite: Inception V4 cpuminer-opt: Triple SHA-256, Onecoin cpuminer-opt: Magi build-godot: Time To Compile onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPU onednn: Recurrent Neural Network Inference - f32 - CPU stockfish: Total Time rodinia: OpenMP Leukocyte blender: Classroom - CPU-Only build2: Time To Compile tungsten: Volumetric Caustic openvkl: vklBenchmarkVdbVolume svt-av1: Preset 4 - Bosphorus 4K pjsip: OPTIONS, Stateful john-the-ripper: MD5 compress-zstd: 19 - Decompression Speed compress-zstd: 19 - Compression Speed build-wasmer: Time To Compile pjsip: OPTIONS, Stateless dacapobench: Jython neat: blender: Fishy Cat - CPU-Only x265: Bosphorus 4K ospray: San Miguel - Path Tracer onednn: IP Shapes 1D - u8s8f32 - CPU chia-vdf: Square Assembly Optimized kvazaar: Bosphorus 4K - Very Fast srsran: OFDM_Test tungsten: Water Caustic srslte: OFDM_Test rodinia: OpenMP LavaMD compress-zstd: 8, Long Mode - Decompression Speed compress-zstd: 8, Long Mode - Compression Speed aom-av1: Speed 8 Realtime - Bosphorus 4K srslte: PHY_DL_Test srslte: PHY_DL_Test sysbench: RAM / Memory onednn: IP Shapes 1D - bf16bf16bf16 - CPU avifenc: 6, Lossless srsran: PHY_DL_Test srsran: PHY_DL_Test dacapobench: Tradebeans build-apache: Time To Compile cpuminer-opt: x25x chia-vdf: Square Plain C++ onednn: IP Shapes 3D - bf16bf16bf16 - CPU toybrot: TBB pgbench: 100 - 250 - Read Write - Average Latency pgbench: 100 - 250 - Read Write namd: ATPase Simulation - 327,506 Atoms onednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU avifenc: 10, Lossless onednn: IP Shapes 3D - u8s8f32 - CPU coremark: CoreMark Size 666 - Iterations Per Second gromacs: MPI CPU - water_GMX50_bare blender: BMW27 - CPU-Only john-the-ripper: Blowfish aircrack-ng: x265: Bosphorus 1080p aom-av1: Speed 9 Realtime - Bosphorus 4K phpbench: PHP Benchmark Suite onednn: IP Shapes 1D - f32 - CPU avifenc: 10 ospray: San Miguel - SciVis openfoam: Motorbike 30M kvazaar: Bosphorus 4K - Ultra Fast tnn: CPU - SqueezeNet v1.1 ospray: XFrog Forest - Path Tracer kvazaar: Bosphorus 1080p - Medium dacapobench: H2 liquid-dsp: 64 - 256 - 57 pybench: Total For Average Test Times svt-hevc: 1 - Bosphorus 1080p rodinia: OpenMP CFD Solver tungsten: Hair onednn: Deconvolution Batch shapes_1d - bf16bf16bf16 - CPU onednn: Deconvolution Batch shapes_1d - u8s8f32 - CPU liquid-dsp: 160 - 256 - 57 liquid-dsp: 128 - 256 - 57 liquid-dsp: 32 - 256 - 57 liquid-dsp: 16 - 256 - 57 onednn: Convolution Batch Shapes Auto - bf16bf16bf16 - CPU svt-vp9: PSNR/SSIM Optimized - Bosphorus 1080p swet: Average svt-vp9: VMAF Optimized - Bosphorus 1080p avifenc: 6 oidn: Memorial npb: EP.D toybrot: C++ Tasks ospray: XFrog Forest - SciVis povray: Trace Time embree: Pathtracer ISPC - Asian Dragon onednn: Matrix Multiply Batch Shapes Transformer - f32 - CPU onednn: Deconvolution Batch shapes_3d - u8s8f32 - CPU onednn: Deconvolution Batch shapes_3d - bf16bf16bf16 - CPU ospray: Magnetic Reconnection - Path Tracer incompact3d: input.i3d 193 Cells Per Direction onednn: Matrix Multiply Batch Shapes Transformer - bf16bf16bf16 - CPU kvazaar: Bosphorus 1080p - Very Fast ospray: Magnetic Reconnection - SciVis npb: EP.C embree: Pathtracer - Asian Dragon npb: LU.C embree: Pathtracer - Crown build-mplayer: Time To Compile embree: Pathtracer ISPC - Crown ospray: NASA Streamlines - Path Tracer onednn: IP Shapes 3D - f32 - CPU toybrot: C++ Threads rodinia: OpenMP Streamcluster toybrot: OpenMP kvazaar: Bosphorus 1080p - Ultra Fast svt-hevc: 10 - Bosphorus 1080p svt-vp9: Visual Quality Optimized - Bosphorus 1080p lammps: Rhodopsin Protein onednn: Convolution Batch Shapes Auto - f32 - CPU onednn: Convolution Batch Shapes Auto - u8s8f32 - CPU onednn: Deconvolution Batch shapes_3d - f32 - CPU svt-hevc: 7 - Bosphorus 1080p tungsten: Non-Exponential ospray: NASA Streamlines - SciVis blogbench: Write Ubuntu 21.04 Ubuntu 20.10 9903.05 366.363 1776457 332.22 669 681.119 1875.8 6967 2253810 684.271 86.283 348.838 81319.3 500 43074.5 41555.1 291.993968 230272 2531 106863 34.39 10.79 82.465 35.725 672.646 439.677 198.538 4.05 39.8231 671.541 19.39 443.547 180.485 524178.09 105.35 170.019 1395127 277683 3487.91 40753 569303 47808.3 172711481 317291 2615.9 82.2 29191 163627 129.152 2708.5 46.0 73429487 2719.4 47.2 3073.3 2096.7 29473 193 479 3193.9 296.3 8217 24.813 108.31 28.7517 102.136 105.650 2985.6 6148.4 266.9 0.266 946634 29.809 213870.87 88.36 6.90 40.207 41.83 7.36 87.461 5554 687019 422680 2735.74 75.951 437.972 437.866 180493580 62.044 72.28 70.057 13.4481 21915837 2.845 3815 10077667 2727.6 82.3 44.607 40082 5320 45.569 45.72 12.92 10.42 1.25869 147240 13.38 120766667 31.2739 121500000 40.406 3283.9 300.2 16.97 86.6 210.9 12176.80 3.03516 36.764 85.1 206.8 16729 35.187 2221.97 138967 1.82051 6999 8.739 28712 0.27128 0.231483 8.522 0.445171 2347453.567360 9.004 29.61 118366 211170.458 28.33 23.59 715587 0.945450 5.050 90.91 15.05 22.78 366.729 10.38 25.42 10740 3044966667 995 29.57 4.807 6.52538 3.27051 0.362841 3080633333 3290766667 1631166667 826756667 2.10597 204.86 639155887 210.15 15.383 57.59 8659.20 8015 18.87 9.476 106.6858 0.256555 0.193198 3.60538 477.78 11.3305505 0.615331 49.20 109.63 6259.88 81.2911 187807.08 64.3015 10.109 67.0395 27.78 1.37903 7118 7.696 7438 85.41 260.88 170.47 23.866 1.41084 0.924756 0.846330 172.02 5.23912 125 60768 9897.119 401.780 1493294 387.62 604 657.468 1873.7 5673 2245366 730.825 83.265 348.747 157434 435 58977.6 55489.8 299.195353 226588 1866 104506 34.93 10.37 83.525 35.506 732.235 506.972 226.852 3.89 39.6266 754.982 19.20 606.052 183.275 355593.18 104.92 171.388 3131.9 1360453 268467 3954.42 46086 725870 66836.4 167218420 322628 2607.2 81.8 28568 151978 144.787 2685.6 41.0 80648255 2736.3 45.1 3022.1 2004.3 26183 161 356 3192.5 300.1 7470 26.529 109.65 35.4561 108.602 104.849 2969.1 4516.9 265.2 0.271 927066 27.160 213970.43 89.25 6.93 44.011 42.30 7.34 81.774 5765 892083 402686 2731.13 76.879 472.245 468.050 177624409 85.284 72.53 74.317 13.7613 22032745 2.796 3716 9267667 2713.8 81.7 68.800 40166 5614 55.921 46.91 12.66 10.42 1.40323 147100 13.20 121300000 31.1264 120333333 39.838 3235.7 297.4 17.02 84.4 207.6 12184.78 3.30961 38.676 85.3 205.4 17609 37.074 2253.80 139033 1.96166 6946 12.100 20742 0.28452 0.247260 9.451 0.471052 2316974.822459 8.851 29.56 111351 211559.000 28.26 23.69 717063 1.018895 5.855 90.91 15.01 22.74 366.201 10.31 25.26 11377 2157125000 984 28.63 4.941 6.75881 3.50505 0.386794 3086966667 3292133333 1569933333 812776667 2.27008 198.24 627367473 201.11 15.356 50.81 9183.40 7963 18.87 9.365 101.8558 0.270802 0.206919 11.68014 466.67 11.8795649 0.659638 48.57 111.11 5881.04 80.2191 188751.17 64.4236 11.098 66.1552 27.78 1.54442 7165 8.563 7806 86.46 237.32 164.77 21.646 1.57954 1.03102 0.902751 161.78 5.25085 125 62517 OpenBenchmarking.org
WRF Input: conus 2.5km OpenBenchmarking.org Seconds, Fewer Is Better WRF 4.2.2 Input: conus 2.5km Ubuntu 20.10 Ubuntu 21.04 2K 4K 6K 8K 10K 9897.12 9903.05 -levent -levent_core 1. (F9X) gfortran options: -O2 -ftree-vectorize -funroll-loops -ffree-form -fconvert=big-endian -frecord-marker=4 -fallow-invalid-boz -lesmf_time -lwrfio_nf -lnetcdff -lnetcdf -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_pthreads -lutil -lm -lrt -lz
Java Gradle Build Gradle Build: Reactor OpenBenchmarking.org Seconds, Fewer Is Better Java Gradle Build Gradle Build: Reactor Ubuntu 20.10 Ubuntu 21.04 90 180 270 360 450 SE +/- 11.03, N = 9 SE +/- 5.06, N = 9 401.78 366.36
OpenVKL Benchmark: vklBenchmarkUnstructuredVolume OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 0.9 Benchmark: vklBenchmarkUnstructuredVolume Ubuntu 20.10 Ubuntu 21.04 400K 800K 1200K 1600K 2000K SE +/- 5996.30, N = 3 SE +/- 7183.20, N = 3 1493294 1776457 MIN: 18361 / MAX: 5191710 MIN: 24424 / MAX: 5906521
Numpy Benchmark OpenBenchmarking.org Score, More Is Better Numpy Benchmark Ubuntu 20.10 Ubuntu 21.04 80 160 240 320 400 SE +/- 2.90, N = 12 SE +/- 2.48, N = 12 387.62 332.22
OpenVKL Benchmark: vklBenchmark OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 0.9 Benchmark: vklBenchmark Ubuntu 20.10 Ubuntu 21.04 140 280 420 560 700 SE +/- 7.42, N = 3 SE +/- 2.40, N = 3 604 669 MIN: 1 / MAX: 2606 MIN: 1 / MAX: 2821
WireGuard + Linux Networking Stack Stress Test OpenBenchmarking.org Seconds, Fewer Is Better WireGuard + Linux Networking Stack Stress Test Ubuntu 20.10 Ubuntu 21.04 150 300 450 600 750 SE +/- 7.37, N = 3 SE +/- 8.55, N = 3 657.47 681.12
NWChem Input: C240 Buckyball OpenBenchmarking.org Seconds, Fewer Is Better NWChem 7.0.2 Input: C240 Buckyball Ubuntu 20.10 Ubuntu 21.04 400 800 1200 1600 2000 1873.7 1875.8 -levent -levent_core 1. (F9X) gfortran options: -lnwctask -lccsd -lmcscf -lselci -lmp2 -lmoints -lstepper -ldriver -loptim -lnwdft -lgradients -lcphf -lesp -lddscf -ldangchang -lguess -lhessian -lvib -lnwcutil -lrimp2 -lproperty -lsolvation -lnwints -lprepar -lnwmd -lnwpw -lofpw -lpaw -lpspw -lband -lnwpwlib -lcafe -lspace -lanalyze -lqhop -lpfft -ldplot -ldrdy -lvscf -lqmmm -lqmd -letrans -ltce -lbq -lmm -lcons -lperfm -ldntmc -lccca -ldimqm -lga -larmci -lpeigs -l64to32 -lopenblas -lpthread -lrt -llapack -lnwcblas -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_pthreads -lutil -lm -lz -lcomex -m64 -ffast-math -std=legacy -fdefault-integer-8 -finline-functions -O2
ONNX Runtime Model: super-resolution-10 - Device: OpenMP CPU OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.6 Model: super-resolution-10 - Device: OpenMP CPU Ubuntu 20.10 Ubuntu 21.04 1500 3000 4500 6000 7500 SE +/- 158.31, N = 12 SE +/- 204.88, N = 12 5673 6967 1. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
BlogBench Test: Read OpenBenchmarking.org Final Score, More Is Better BlogBench 1.1 Test: Read Ubuntu 20.10 Ubuntu 21.04 500K 1000K 1500K 2000K 2500K SE +/- 19991.91, N = 3 SE +/- 30037.66, N = 3 2245366 2253810 1. (CC) gcc options: -O2 -pthread
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 Ubuntu 20.10 Ubuntu 21.04 160 320 480 640 800 SE +/- 6.32, N = 15 SE +/- 5.64, N = 15 730.83 684.27 MIN: 671.61 MIN: 645.4 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
YafaRay Total Time For Sample Scene OpenBenchmarking.org Seconds, Fewer Is Better YafaRay 3.4.1 Total Time For Sample Scene Ubuntu 20.10 Ubuntu 21.04 20 40 60 80 100 SE +/- 2.54, N = 12 SE +/- 2.26, N = 15 83.27 86.28 1. (CXX) g++ options: -std=c++11 -O3 -ffast-math -rdynamic -ldl -lImath -lIlmImf -lIex -lHalf -lz -lIlmThread -lxml2 -lfreetype -lpthread
RELION Test: Basic - Device: CPU OpenBenchmarking.org Seconds, Fewer Is Better RELION 3.1.1 Test: Basic - Device: CPU Ubuntu 20.10 Ubuntu 21.04 80 160 240 320 400 SE +/- 0.44, N = 3 SE +/- 1.61, N = 3 348.75 348.84 1. (CXX) g++ options: -fopenmp -std=c++0x -O3 -rdynamic -ldl -ltiff -lfftw3f -lfftw3 -lpng -pthread -lmpi_cxx -lmpi
TensorFlow Lite Model: NASNet Mobile OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: NASNet Mobile Ubuntu 20.10 Ubuntu 21.04 30K 60K 90K 120K 150K SE +/- 5683.05, N = 15 SE +/- 768.19, N = 15 157434.0 81319.3
ONNX Runtime Model: bertsquad-10 - Device: OpenMP CPU OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.6 Model: bertsquad-10 - Device: OpenMP CPU Ubuntu 20.10 Ubuntu 21.04 110 220 330 440 550 SE +/- 4.21, N = 3 SE +/- 6.29, N = 12 435 500 1. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
TensorFlow Lite Model: Mobilenet Quant OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Mobilenet Quant Ubuntu 20.10 Ubuntu 21.04 13K 26K 39K 52K 65K SE +/- 573.26, N = 15 SE +/- 601.06, N = 15 58977.6 43074.5
TensorFlow Lite Model: Mobilenet Float OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Mobilenet Float Ubuntu 20.10 Ubuntu 21.04 12K 24K 36K 48K 60K SE +/- 733.25, N = 15 SE +/- 612.15, N = 15 55489.8 41555.1
Xcompact3d Incompact3d Input: X3D-benchmarking input.i3d OpenBenchmarking.org Seconds, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 Input: X3D-benchmarking input.i3d Ubuntu 20.10 Ubuntu 21.04 70 140 210 280 350 SE +/- 1.73, N = 3 SE +/- 1.18, N = 3 299.20 291.99 -levent -levent_core 1. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_pthreads -lutil -lm -lrt -lz
SecureMark Benchmark: SecureMark-TLS OpenBenchmarking.org marks, More Is Better SecureMark 1.0.4 Benchmark: SecureMark-TLS Ubuntu 20.10 Ubuntu 21.04 50K 100K 150K 200K 250K SE +/- 530.29, N = 3 SE +/- 178.37, N = 3 226588 230272 1. (CC) gcc options: -pedantic -O3
PJSIP Method: INVITE OpenBenchmarking.org Responses Per Second, More Is Better PJSIP 2.11 Method: INVITE Ubuntu 20.10 Ubuntu 21.04 500 1000 1500 2000 2500 SE +/- 14.40, N = 10 SE +/- 22.31, N = 15 1866 2531 1. (CC) gcc options: -lSDL2 -lavformat -lavcodec -lswscale -lavutil -lstdc++ -lssl -lcrypto -luuid -lm -lrt -lpthread -lasound -O2
Apache Cassandra Test: Writes OpenBenchmarking.org Op/s, More Is Better Apache Cassandra 3.11.4 Test: Writes Ubuntu 20.10 Ubuntu 21.04 20K 40K 60K 80K 100K SE +/- 1429.17, N = 3 SE +/- 2263.61, N = 15 104506 106863
libgav1 Video Input: Chimera 1080p OpenBenchmarking.org FPS, More Is Better libgav1 0.16.3 Video Input: Chimera 1080p Ubuntu 20.10 Ubuntu 21.04 8 16 24 32 40 SE +/- 0.10, N = 3 SE +/- 0.19, N = 3 34.93 34.39 1. (CXX) g++ options: -O3 -lpthread -lrt
Node.js V8 Web Tooling Benchmark OpenBenchmarking.org runs/s, More Is Better Node.js V8 Web Tooling Benchmark Ubuntu 20.10 Ubuntu 21.04 3 6 9 12 15 SE +/- 0.13, N = 15 SE +/- 0.07, N = 3 10.37 10.79 1. Ubuntu 20.10: Nodejs
v12.18.2 2. Ubuntu 21.04: Nodejs
v12.21.0
Helsing Digit Range: 14 digit OpenBenchmarking.org Seconds, Fewer Is Better Helsing 1.0-beta Digit Range: 14 digit Ubuntu 20.10 Ubuntu 21.04 20 40 60 80 100 SE +/- 0.21, N = 3 SE +/- 0.73, N = 15 83.53 82.47 1. (CC) gcc options: -O2 -pthread
LAMMPS Molecular Dynamics Simulator Model: 20k Atoms OpenBenchmarking.org ns/day, More Is Better LAMMPS Molecular Dynamics Simulator 29Oct2020 Model: 20k Atoms Ubuntu 20.10 Ubuntu 21.04 8 16 24 32 40 SE +/- 0.19, N = 3 SE +/- 0.03, N = 3 35.51 35.73 1. (CXX) g++ options: -O3 -pthread -lm
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 Ubuntu 20.10 Ubuntu 21.04 160 320 480 640 800 SE +/- 5.22, N = 15 SE +/- 1.73, N = 3 732.24 672.65 MIN: 674.53 MIN: 646.15 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -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 Ubuntu 20.10 Ubuntu 21.04 110 220 330 440 550 SE +/- 33.83, N = 15 SE +/- 0.53, N = 3 506.97 439.68 MIN: 435.95 MIN: 424.75 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
Timed LLVM Compilation Build System: Unix Makefiles OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 12.0 Build System: Unix Makefiles Ubuntu 20.10 Ubuntu 21.04 50 100 150 200 250 SE +/- 0.98, N = 3 SE +/- 1.40, N = 3 226.85 198.54
AOM AV1 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.1 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K Ubuntu 20.10 Ubuntu 21.04 0.9113 1.8226 2.7339 3.6452 4.5565 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 3.89 4.05 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
High Performance Conjugate Gradient OpenBenchmarking.org GFLOP/s, More Is Better High Performance Conjugate Gradient 3.1 Ubuntu 20.10 Ubuntu 21.04 9 18 27 36 45 SE +/- 0.15, N = 3 SE +/- 0.03, N = 3 39.63 39.82 1. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -pthread -lmpi_cxx -lmpi
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 Ubuntu 20.10 Ubuntu 21.04 160 320 480 640 800 SE +/- 19.97, N = 12 SE +/- 0.16, N = 3 754.98 671.54 MIN: 673.86 MIN: 647.67 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
libgav1 Video Input: Summer Nature 4K OpenBenchmarking.org FPS, More Is Better libgav1 0.16.3 Video Input: Summer Nature 4K Ubuntu 20.10 Ubuntu 21.04 5 10 15 20 25 SE +/- 0.05, N = 3 SE +/- 0.15, N = 3 19.20 19.39 1. (CXX) g++ options: -O3 -lpthread -lrt
TNN Target: CPU - Model: MobileNet v2 OpenBenchmarking.org ms, Fewer Is Better TNN 0.2.3 Target: CPU - Model: MobileNet v2 Ubuntu 20.10 Ubuntu 21.04 130 260 390 520 650 SE +/- 12.21, N = 15 SE +/- 9.40, N = 15 606.05 443.55 MIN: 372.96 / MAX: 843.9 MIN: 367.81 / MAX: 808.75 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl
Timed Erlang/OTP Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Erlang/OTP Compilation 23.2 Time To Compile Ubuntu 20.10 Ubuntu 21.04 40 80 120 160 200 SE +/- 1.20, N = 3 SE +/- 0.85, N = 3 183.28 180.49
KeyDB OpenBenchmarking.org Ops/sec, More Is Better KeyDB 6.0.16 Ubuntu 20.10 Ubuntu 21.04 110K 220K 330K 440K 550K SE +/- 13586.63, N = 12 SE +/- 4128.37, N = 3 355593.18 524178.09 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenFOAM Input: Motorbike 60M OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 8 Input: Motorbike 60M Ubuntu 20.10 Ubuntu 21.04 20 40 60 80 100 SE +/- 0.07, N = 3 SE +/- 0.46, N = 3 104.92 105.35 1. (CXX) g++ options: -std=c++11 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -ldynamicMesh -ldecompose -lgenericPatchFields -lmetisDecomp -lscotchDecomp -llagrangian -lregionModels -lOpenFOAM -ldl -lm
Timed MrBayes Analysis Primate Phylogeny Analysis OpenBenchmarking.org Seconds, Fewer Is Better Timed MrBayes Analysis 3.2.7 Primate Phylogeny Analysis Ubuntu 20.10 Ubuntu 21.04 40 80 120 160 200 SE +/- 0.41, N = 3 SE +/- 0.83, N = 3 171.39 170.02 1. (CC) gcc options: -mmmx -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msha -maes -mavx -mfma -mavx2 -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi -mrdrnd -mbmi -mbmi2 -madx -mabm -O3 -std=c99 -pedantic -lm
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 Ubuntu 20.10 700 1400 2100 2800 3500 SE +/- 31.17, N = 12 3131.9 1. (CC) gcc options: -O3 -pthread -lz -llzma
Cpuminer-Opt Algorithm: Blake-2 S OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.15.5 Algorithm: Blake-2 S Ubuntu 20.10 Ubuntu 21.04 300K 600K 900K 1200K 1500K SE +/- 14563.41, N = 15 SE +/- 21571.08, N = 15 1360453 1395127 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Cpuminer-Opt Algorithm: Skeincoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.15.5 Algorithm: Skeincoin Ubuntu 20.10 Ubuntu 21.04 60K 120K 180K 240K 300K SE +/- 3496.83, N = 15 SE +/- 2421.06, N = 15 268467 277683 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Cpuminer-Opt Algorithm: Ringcoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.15.5 Algorithm: Ringcoin Ubuntu 20.10 Ubuntu 21.04 800 1600 2400 3200 4000 SE +/- 168.93, N = 15 SE +/- 99.60, N = 15 3954.42 3487.91 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Cpuminer-Opt Algorithm: Myriad-Groestl OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.15.5 Algorithm: Myriad-Groestl Ubuntu 20.10 Ubuntu 21.04 10K 20K 30K 40K 50K SE +/- 1259.45, N = 15 SE +/- 1514.24, N = 15 46086 40753 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
TensorFlow Lite Model: Inception ResNet V2 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Inception ResNet V2 Ubuntu 20.10 Ubuntu 21.04 160K 320K 480K 640K 800K SE +/- 13732.96, N = 12 SE +/- 790.57, N = 3 725870 569303
TensorFlow Lite Model: SqueezeNet OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: SqueezeNet Ubuntu 20.10 Ubuntu 21.04 14K 28K 42K 56K 70K SE +/- 1725.85, N = 12 SE +/- 35.00, N = 3 66836.4 47808.3
asmFish 1024 Hash Memory, 26 Depth OpenBenchmarking.org Nodes/second, More Is Better asmFish 2018-07-23 1024 Hash Memory, 26 Depth Ubuntu 20.10 Ubuntu 21.04 40M 80M 120M 160M 200M SE +/- 748824.48, N = 3 SE +/- 1805964.50, N = 3 167218420 172711481
Cpuminer-Opt Algorithm: Quad SHA-256, Pyrite OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.15.5 Algorithm: Quad SHA-256, Pyrite Ubuntu 20.10 Ubuntu 21.04 70K 140K 210K 280K 350K SE +/- 9923.95, N = 13 SE +/- 3914.38, N = 15 322628 317291 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Zstd Compression Compression Level: 19 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19 - Decompression Speed Ubuntu 20.10 Ubuntu 21.04 600 1200 1800 2400 3000 SE +/- 9.81, N = 3 SE +/- 3.01, N = 15 2607.2 2615.9 1. (CC) gcc options: -O3 -pthread -lz -llzma
Zstd Compression Compression Level: 19 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19 - Compression Speed Ubuntu 20.10 Ubuntu 21.04 20 40 60 80 100 SE +/- 0.46, N = 3 SE +/- 1.03, N = 15 81.8 82.2 1. (CC) gcc options: -O3 -pthread -lz -llzma
Cpuminer-Opt Algorithm: Deepcoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.15.5 Algorithm: Deepcoin Ubuntu 20.10 Ubuntu 21.04 6K 12K 18K 24K 30K SE +/- 615.22, N = 12 SE +/- 326.37, N = 15 28568 29191 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Cpuminer-Opt Algorithm: LBC, LBRY Credits OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.15.5 Algorithm: LBC, LBRY Credits Ubuntu 20.10 Ubuntu 21.04 40K 80K 120K 160K 200K SE +/- 3093.55, N = 12 SE +/- 2699.74, N = 15 151978 163627 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 12.0 Build System: Ninja Ubuntu 20.10 Ubuntu 21.04 30 60 90 120 150 SE +/- 1.55, N = 3 SE +/- 0.36, N = 3 144.79 129.15
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 Ubuntu 20.10 Ubuntu 21.04 600 1200 1800 2400 3000 SE +/- 3.89, N = 3 SE +/- 5.02, N = 15 2685.6 2708.5 1. (CC) gcc options: -O3 -pthread -lz -llzma
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 Ubuntu 20.10 Ubuntu 21.04 10 20 30 40 50 SE +/- 0.27, N = 3 SE +/- 0.54, N = 15 41.0 46.0 1. (CC) gcc options: -O3 -pthread -lz -llzma
OpenVKL Benchmark: vklBenchmarkStructuredVolume OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 0.9 Benchmark: vklBenchmarkStructuredVolume Ubuntu 20.10 Ubuntu 21.04 20M 40M 60M 80M 100M SE +/- 2593649.80, N = 12 SE +/- 65330.82, N = 3 80648255 73429487 MIN: 1000000 / MAX: 1324247328 MIN: 1371963 / MAX: 676014012
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 Ubuntu 20.10 Ubuntu 21.04 600 1200 1800 2400 3000 SE +/- 5.79, N = 15 SE +/- 1.06, N = 3 2736.3 2719.4 1. (CC) gcc options: -O3 -pthread -lz -llzma
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 Ubuntu 20.10 Ubuntu 21.04 11 22 33 44 55 SE +/- 0.39, N = 15 SE +/- 0.33, N = 3 45.1 47.2 1. (CC) gcc options: -O3 -pthread -lz -llzma
Zstd Compression Compression Level: 8 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 8 - Decompression Speed Ubuntu 20.10 Ubuntu 21.04 700 1400 2100 2800 3500 SE +/- 6.44, N = 13 SE +/- 2.77, N = 3 3022.1 3073.3 1. (CC) gcc options: -O3 -pthread -lz -llzma
Zstd Compression Compression Level: 8 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 8 - Compression Speed Ubuntu 20.10 Ubuntu 21.04 500 1000 1500 2000 2500 SE +/- 42.14, N = 15 SE +/- 24.65, N = 3 2004.3 2096.7 1. (CC) gcc options: -O3 -pthread -lz -llzma
Cpuminer-Opt Algorithm: Garlicoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.15.5 Algorithm: Garlicoin Ubuntu 20.10 Ubuntu 21.04 6K 12K 18K 24K 30K SE +/- 1085.72, N = 12 SE +/- 1184.13, N = 12 26183 29473 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
ONNX Runtime Model: fcn-resnet101-11 - Device: OpenMP CPU OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.6 Model: fcn-resnet101-11 - Device: OpenMP CPU Ubuntu 20.10 Ubuntu 21.04 40 80 120 160 200 SE +/- 1.04, N = 3 SE +/- 1.20, N = 3 161 193 1. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
ONNX Runtime Model: yolov4 - Device: OpenMP CPU OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.6 Model: yolov4 - Device: OpenMP CPU Ubuntu 20.10 Ubuntu 21.04 100 200 300 400 500 SE +/- 1.67, N = 3 SE +/- 1.17, N = 3 356 479 1. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
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 Ubuntu 20.10 Ubuntu 21.04 700 1400 2100 2800 3500 SE +/- 5.83, N = 14 SE +/- 6.74, N = 4 3192.5 3193.9 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 Ubuntu 20.10 Ubuntu 21.04 70 140 210 280 350 SE +/- 8.82, N = 14 SE +/- 3.49, N = 4 300.1 296.3 1. (CC) gcc options: -O3 -pthread -lz -llzma
ONNX Runtime Model: shufflenet-v2-10 - Device: OpenMP CPU OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.6 Model: shufflenet-v2-10 - Device: OpenMP CPU Ubuntu 20.10 Ubuntu 21.04 2K 4K 6K 8K 10K SE +/- 35.85, N = 3 SE +/- 106.53, N = 3 7470 8217 1. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
Timed Linux Kernel Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 5.10.20 Time To Compile Ubuntu 20.10 Ubuntu 21.04 6 12 18 24 30 SE +/- 0.39, N = 14 SE +/- 0.35, N = 13 26.53 24.81
Blender Blend File: Barbershop - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Barbershop - Compute: CPU-Only Ubuntu 20.10 Ubuntu 21.04 20 40 60 80 100 SE +/- 0.41, N = 3 SE +/- 0.26, N = 3 109.65 108.31
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 Ubuntu 20.10 Ubuntu 21.04 8 16 24 32 40 SE +/- 0.37, N = 15 SE +/- 0.29, N = 15 35.46 28.75 MIN: 14.26 MIN: 15.46 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
Timed Node.js Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Node.js Compilation 15.11 Time To Compile Ubuntu 20.10 Ubuntu 21.04 20 40 60 80 100 SE +/- 1.42, N = 3 SE +/- 0.97, N = 3 108.60 102.14
Rodinia Test: OpenMP HotSpot3D OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP HotSpot3D Ubuntu 20.10 Ubuntu 21.04 20 40 60 80 100 SE +/- 0.02, N = 3 SE +/- 0.57, N = 3 104.85 105.65 1. (CXX) g++ options: -O2 -lOpenCL
Zstd Compression Compression Level: 3 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 3 - Decompression Speed Ubuntu 20.10 Ubuntu 21.04 600 1200 1800 2400 3000 SE +/- 7.67, N = 5 SE +/- 9.20, N = 2 2969.1 2985.6 1. (CC) gcc options: -O3 -pthread -lz -llzma
Zstd Compression Compression Level: 3 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 3 - Compression Speed Ubuntu 20.10 Ubuntu 21.04 1300 2600 3900 5200 6500 SE +/- 43.45, N = 13 SE +/- 53.61, N = 3 4516.9 6148.4 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 1.5.0 Compression Level: 3, Long Mode - Compression Speed Ubuntu 20.10 Ubuntu 21.04 60 120 180 240 300 SE +/- 8.38, N = 12 SE +/- 1.99, N = 3 265.2 266.9 1. (CC) gcc options: -O3 -pthread -lz -llzma
PostgreSQL pgbench Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average Latency Ubuntu 20.10 Ubuntu 21.04 0.061 0.122 0.183 0.244 0.305 SE +/- 0.004, N = 3 SE +/- 0.003, N = 15 0.271 0.266 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 250 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Only Ubuntu 20.10 Ubuntu 21.04 200K 400K 600K 800K 1000K SE +/- 12775.84, N = 3 SE +/- 10755.01, N = 15 927066 946634 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.8.7 Encoder Mode: Preset 8 - Input: Bosphorus 4K Ubuntu 20.10 Ubuntu 21.04 7 14 21 28 35 SE +/- 0.37, N = 15 SE +/- 0.34, N = 3 27.16 29.81 1. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
Sysbench Test: CPU OpenBenchmarking.org Events Per Second, More Is Better Sysbench 1.0.20 Test: CPU Ubuntu 20.10 Ubuntu 21.04 50K 100K 150K 200K 250K SE +/- 253.78, N = 3 SE +/- 275.74, N = 3 213970.43 213870.87 1. (CC) gcc options: -pthread -O2 -funroll-loops -rdynamic -ldl -laio -lm
Blender Blend File: Pabellon Barcelona - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Pabellon Barcelona - Compute: CPU-Only Ubuntu 20.10 Ubuntu 21.04 20 40 60 80 100 SE +/- 0.26, N = 3 SE +/- 0.24, N = 3 89.25 88.36
Kvazaar Video Input: Bosphorus 4K - Video Preset: Medium OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 4K - Video Preset: Medium Ubuntu 20.10 Ubuntu 21.04 2 4 6 8 10 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 6.93 6.90 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Timed PHP Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed PHP Compilation 7.4.2 Time To Compile Ubuntu 20.10 Ubuntu 21.04 10 20 30 40 50 SE +/- 0.37, N = 9 SE +/- 0.52, N = 3 44.01 40.21
libgav1 Video Input: Summer Nature 1080p OpenBenchmarking.org FPS, More Is Better libgav1 0.16.3 Video Input: Summer Nature 1080p Ubuntu 20.10 Ubuntu 21.04 10 20 30 40 50 SE +/- 0.04, N = 3 SE +/- 0.43, N = 3 42.30 41.83 1. (CXX) g++ options: -O3 -lpthread -lrt
AOM AV1 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.1 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K Ubuntu 20.10 Ubuntu 21.04 2 4 6 8 10 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 7.34 7.36 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
Timed Eigen Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Eigen Compilation 3.3.9 Time To Compile Ubuntu 20.10 Ubuntu 21.04 20 40 60 80 100 SE +/- 0.34, N = 3 SE +/- 0.84, N = 3 81.77 87.46
Node.js Express HTTP Load Test OpenBenchmarking.org Requests Per Second, More Is Better Node.js Express HTTP Load Test Ubuntu 20.10 Ubuntu 21.04 1200 2400 3600 4800 6000 SE +/- 203.22, N = 12 SE +/- 161.00, N = 15 5765 5554 1. Ubuntu 20.10: Nodejs
v12.18.2 2. Ubuntu 21.04: Nodejs
v12.21.0
TensorFlow Lite Model: Inception V4 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Inception V4 Ubuntu 20.10 Ubuntu 21.04 200K 400K 600K 800K 1000K SE +/- 7218.89, N = 3 SE +/- 7233.85, N = 5 892083 687019
Cpuminer-Opt Algorithm: Triple SHA-256, Onecoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.15.5 Algorithm: Triple SHA-256, Onecoin Ubuntu 20.10 Ubuntu 21.04 90K 180K 270K 360K 450K SE +/- 11124.39, N = 12 SE +/- 1250.96, N = 3 402686 422680 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Cpuminer-Opt Algorithm: Magi OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.15.5 Algorithm: Magi Ubuntu 20.10 Ubuntu 21.04 600 1200 1800 2400 3000 SE +/- 5.62, N = 3 SE +/- 50.25, N = 12 2731.13 2735.74 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Timed Godot Game Engine Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Godot Game Engine Compilation 3.2.3 Time To Compile Ubuntu 20.10 Ubuntu 21.04 20 40 60 80 100 SE +/- 0.33, N = 3 SE +/- 0.13, N = 3 76.88 75.95
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 Ubuntu 20.10 Ubuntu 21.04 100 200 300 400 500 SE +/- 1.27, N = 3 SE +/- 0.96, N = 3 472.25 437.97 MIN: 442.59 MIN: 422.42 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -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 Ubuntu 20.10 Ubuntu 21.04 100 200 300 400 500 SE +/- 2.30, N = 3 SE +/- 0.63, N = 3 468.05 437.87 MIN: 438.61 MIN: 422.67 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
Stockfish Total Time OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 13 Total Time Ubuntu 20.10 Ubuntu 21.04 40M 80M 120M 160M 200M SE +/- 1600302.62, N = 3 SE +/- 2129761.70, N = 15 177624409 180493580 1. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fprofile-use -fno-peel-loops -fno-tracer -pedantic -O3 -msse -msse3 -mpopcnt -mavx2 -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto=jobserver
Rodinia Test: OpenMP Leukocyte OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP Leukocyte Ubuntu 20.10 Ubuntu 21.04 20 40 60 80 100 SE +/- 0.59, N = 3 SE +/- 0.67, N = 3 85.28 62.04 1. (CXX) g++ options: -O2 -lOpenCL
Blender Blend File: Classroom - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Classroom - Compute: CPU-Only Ubuntu 20.10 Ubuntu 21.04 16 32 48 64 80 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 72.53 72.28
Build2 Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Build2 0.13 Time To Compile Ubuntu 20.10 Ubuntu 21.04 16 32 48 64 80 SE +/- 0.57, N = 3 SE +/- 0.48, N = 3 74.32 70.06
Tungsten Renderer Scene: Volumetric Caustic OpenBenchmarking.org Seconds, Fewer Is Better Tungsten Renderer 0.2.2 Scene: Volumetric Caustic Ubuntu 20.10 Ubuntu 21.04 4 8 12 16 20 SE +/- 0.44, N = 15 SE +/- 0.44, N = 15 13.76 13.45 1. (CXX) g++ options: -std=c++0x -march=core2 -msse2 -msse3 -mssse3 -mno-sse4.1 -mno-sse4.2 -mno-sse4a -mno-avx -mno-fma -mno-bmi2 -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz -ljpeg -lpthread -ldl
OpenVKL Benchmark: vklBenchmarkVdbVolume OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 0.9 Benchmark: vklBenchmarkVdbVolume Ubuntu 20.10 Ubuntu 21.04 5M 10M 15M 20M 25M SE +/- 181382.68, N = 3 SE +/- 58341.71, N = 3 22032745 21915837 MIN: 1023660 / MAX: 161438904 MIN: 1062215 / MAX: 153704880
SVT-AV1 Encoder Mode: Preset 4 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.8.7 Encoder Mode: Preset 4 - Input: Bosphorus 4K Ubuntu 20.10 Ubuntu 21.04 0.6401 1.2802 1.9203 2.5604 3.2005 SE +/- 0.002, N = 3 SE +/- 0.037, N = 3 2.796 2.845 1. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
PJSIP Method: OPTIONS, Stateful OpenBenchmarking.org Responses Per Second, More Is Better PJSIP 2.11 Method: OPTIONS, Stateful Ubuntu 20.10 Ubuntu 21.04 800 1600 2400 3200 4000 SE +/- 7.67, N = 3 SE +/- 6.89, N = 3 3716 3815 1. (CC) gcc options: -lSDL2 -lavformat -lavcodec -lswscale -lavutil -lstdc++ -lssl -lcrypto -luuid -lm -lrt -lpthread -lasound -O2
John The Ripper Test: MD5 OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.9.0-jumbo-1 Test: MD5 Ubuntu 20.10 Ubuntu 21.04 2M 4M 6M 8M 10M SE +/- 118341.78, N = 3 SE +/- 137751.39, N = 3 9267667 10077667 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2
Zstd Compression Compression Level: 19 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 19 - Decompression Speed Ubuntu 20.10 Ubuntu 21.04 600 1200 1800 2400 3000 SE +/- 15.59, N = 4 SE +/- 12.48, N = 3 2713.8 2727.6 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 Ubuntu 20.10 Ubuntu 21.04 20 40 60 80 100 SE +/- 0.92, N = 4 SE +/- 0.81, N = 3 81.7 82.3 1. (CC) gcc options: -O3 -pthread -lz -llzma
Timed Wasmer Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Wasmer Compilation 1.0.2 Time To Compile Ubuntu 20.10 Ubuntu 21.04 15 30 45 60 75 SE +/- 0.19, N = 3 SE +/- 0.37, N = 3 68.80 44.61 1. (CC) gcc options: -m64 -pie -nodefaultlibs -ldl -lrt -lpthread -lgcc_s -lc -lm -lutil
PJSIP Method: OPTIONS, Stateless OpenBenchmarking.org Responses Per Second, More Is Better PJSIP 2.11 Method: OPTIONS, Stateless Ubuntu 20.10 Ubuntu 21.04 9K 18K 27K 36K 45K SE +/- 217.12, N = 3 SE +/- 533.56, N = 3 40166 40082 1. (CC) gcc options: -lSDL2 -lavformat -lavcodec -lswscale -lavutil -lstdc++ -lssl -lcrypto -luuid -lm -lrt -lpthread -lasound -O2
DaCapo Benchmark Java Test: Jython OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: Jython Ubuntu 20.10 Ubuntu 21.04 1200 2400 3600 4800 6000 SE +/- 174.19, N = 20 SE +/- 153.92, N = 20 5614 5320
Nebular Empirical Analysis Tool OpenBenchmarking.org Seconds, Fewer Is Better Nebular Empirical Analysis Tool 2.3 Ubuntu 20.10 Ubuntu 21.04 13 26 39 52 65 SE +/- 0.44, N = 3 SE +/- 0.19, N = 3 55.92 45.57 1. (F9X) gfortran options: -O3 -cpp -ffree-line-length-0 -Jsource/ -fopenmp -fno-backtrace -lcfitsio
Blender Blend File: Fishy Cat - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Fishy Cat - Compute: CPU-Only Ubuntu 20.10 Ubuntu 21.04 11 22 33 44 55 SE +/- 0.44, N = 3 SE +/- 0.15, N = 3 46.91 45.72
x265 Video Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better x265 3.4 Video Input: Bosphorus 4K Ubuntu 20.10 Ubuntu 21.04 3 6 9 12 15 SE +/- 0.07, N = 3 SE +/- 0.09, N = 3 12.66 12.92 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OSPray Demo: San Miguel - Renderer: Path Tracer OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: San Miguel - Renderer: Path Tracer Ubuntu 20.10 Ubuntu 21.04 3 6 9 12 15 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 10.42 10.42 MIN: 7.25 / MAX: 10.53 MIN: 7.87 / MAX: 10.64
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 Ubuntu 20.10 Ubuntu 21.04 0.3157 0.6314 0.9471 1.2628 1.5785 SE +/- 0.01231, N = 3 SE +/- 0.00905, N = 15 1.40323 1.25869 MIN: 0.82 MIN: 0.86 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
Chia Blockchain VDF Test: Square Assembly Optimized OpenBenchmarking.org IPS, More Is Better Chia Blockchain VDF 1.0.1 Test: Square Assembly Optimized Ubuntu 20.10 Ubuntu 21.04 30K 60K 90K 120K 150K SE +/- 900.00, N = 3 SE +/- 1568.63, N = 5 147100 147240 1. (CXX) g++ options: -flto -no-pie -lgmpxx -lgmp -lboost_system -pthread
Kvazaar Video Input: Bosphorus 4K - Video Preset: Very Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 4K - Video Preset: Very Fast Ubuntu 20.10 Ubuntu 21.04 3 6 9 12 15 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 13.20 13.38 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
srsRAN Test: OFDM_Test OpenBenchmarking.org Samples / Second, More Is Better srsRAN 21.04 Test: OFDM_Test Ubuntu 20.10 Ubuntu 21.04 30M 60M 90M 120M 150M SE +/- 305505.05, N = 3 SE +/- 284800.12, N = 3 121300000 120766667 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
Tungsten Renderer Scene: Water Caustic OpenBenchmarking.org Seconds, Fewer Is Better Tungsten Renderer 0.2.2 Scene: Water Caustic Ubuntu 20.10 Ubuntu 21.04 7 14 21 28 35 SE +/- 0.06, N = 3 SE +/- 0.27, N = 3 31.13 31.27 1. (CXX) g++ options: -std=c++0x -march=core2 -msse2 -msse3 -mssse3 -mno-sse4.1 -mno-sse4.2 -mno-sse4a -mno-avx -mno-fma -mno-bmi2 -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz -ljpeg -lpthread -ldl
srsLTE Test: OFDM_Test OpenBenchmarking.org Samples / Second, More Is Better srsLTE 20.10.1 Test: OFDM_Test Ubuntu 20.10 Ubuntu 21.04 30M 60M 90M 120M 150M SE +/- 260341.66, N = 3 SE +/- 650640.71, N = 3 120333333 121500000 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lm -lfftw3f
Rodinia Test: OpenMP LavaMD OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP LavaMD Ubuntu 20.10 Ubuntu 21.04 9 18 27 36 45 SE +/- 0.11, N = 3 SE +/- 0.15, N = 3 39.84 40.41 1. (CXX) g++ options: -O2 -lOpenCL
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 Ubuntu 20.10 Ubuntu 21.04 700 1400 2100 2800 3500 SE +/- 15.05, N = 3 SE +/- 8.34, N = 3 3235.7 3283.9 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 1.5.0 Compression Level: 8, Long Mode - Compression Speed Ubuntu 20.10 Ubuntu 21.04 70 140 210 280 350 SE +/- 1.00, N = 3 SE +/- 3.33, N = 3 297.4 300.2 1. (CC) gcc options: -O3 -pthread -lz -llzma
AOM AV1 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.1 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K Ubuntu 20.10 Ubuntu 21.04 4 8 12 16 20 SE +/- 0.17, N = 3 SE +/- 0.02, N = 3 17.02 16.97 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
srsLTE Test: PHY_DL_Test OpenBenchmarking.org UE Mb/s, More Is Better srsLTE 20.10.1 Test: PHY_DL_Test Ubuntu 20.10 Ubuntu 21.04 20 40 60 80 100 SE +/- 0.90, N = 3 SE +/- 0.30, N = 3 84.4 86.6 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lm -lfftw3f
srsLTE Test: PHY_DL_Test OpenBenchmarking.org eNb Mb/s, More Is Better srsLTE 20.10.1 Test: PHY_DL_Test Ubuntu 20.10 Ubuntu 21.04 50 100 150 200 250 SE +/- 1.35, N = 3 SE +/- 0.84, N = 3 207.6 210.9 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lm -lfftw3f
Sysbench Test: RAM / Memory OpenBenchmarking.org MiB/sec, More Is Better Sysbench 1.0.20 Test: RAM / Memory Ubuntu 20.10 Ubuntu 21.04 3K 6K 9K 12K 15K SE +/- 151.11, N = 12 SE +/- 145.91, N = 15 12184.78 12176.80 1. (CC) gcc options: -pthread -O2 -funroll-loops -rdynamic -ldl -laio -lm
oneDNN Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU Ubuntu 20.10 Ubuntu 21.04 0.7447 1.4894 2.2341 2.9788 3.7235 SE +/- 0.03870, N = 3 SE +/- 0.02675, N = 12 3.30961 3.03516 MIN: 2.85 MIN: 2.86 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
libavif avifenc Encoder Speed: 6, Lossless OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.9.0 Encoder Speed: 6, Lossless Ubuntu 20.10 Ubuntu 21.04 9 18 27 36 45 SE +/- 0.05, N = 3 SE +/- 0.47, N = 3 38.68 36.76 1. (CXX) g++ options: -O3 -fPIC -lm
srsRAN Test: PHY_DL_Test OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 21.04 Test: PHY_DL_Test Ubuntu 20.10 Ubuntu 21.04 20 40 60 80 100 SE +/- 0.23, N = 3 SE +/- 0.78, N = 3 85.3 85.1 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
srsRAN Test: PHY_DL_Test OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 21.04 Test: PHY_DL_Test Ubuntu 20.10 Ubuntu 21.04 50 100 150 200 250 SE +/- 0.64, N = 3 SE +/- 0.78, N = 3 205.4 206.8 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
DaCapo Benchmark Java Test: Tradebeans OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: Tradebeans Ubuntu 20.10 Ubuntu 21.04 4K 8K 12K 16K 20K SE +/- 203.85, N = 4 SE +/- 82.67, N = 4 17609 16729
Timed Apache Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Apache Compilation 2.4.41 Time To Compile Ubuntu 20.10 Ubuntu 21.04 9 18 27 36 45 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 37.07 35.19
Cpuminer-Opt Algorithm: x25x OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.15.5 Algorithm: x25x Ubuntu 20.10 Ubuntu 21.04 500 1000 1500 2000 2500 SE +/- 25.12, N = 4 SE +/- 24.82, N = 3 2253.80 2221.97 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Chia Blockchain VDF Test: Square Plain C++ OpenBenchmarking.org IPS, More Is Better Chia Blockchain VDF 1.0.1 Test: Square Plain C++ Ubuntu 20.10 Ubuntu 21.04 30K 60K 90K 120K 150K SE +/- 484.19, N = 3 SE +/- 88.19, N = 3 139033 138967 1. (CXX) g++ options: -flto -no-pie -lgmpxx -lgmp -lboost_system -pthread
oneDNN Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU Ubuntu 20.10 Ubuntu 21.04 0.4414 0.8828 1.3242 1.7656 2.207 SE +/- 0.01622, N = 9 SE +/- 0.01169, N = 14 1.96166 1.82051 MIN: 1.66 MIN: 1.67 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
toyBrot Fractal Generator Implementation: TBB OpenBenchmarking.org ms, Fewer Is Better toyBrot Fractal Generator 2020-11-18 Implementation: TBB Ubuntu 20.10 Ubuntu 21.04 1500 3000 4500 6000 7500 SE +/- 68.57, N = 15 SE +/- 91.17, N = 15 6946 6999 1. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc
PostgreSQL pgbench Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average Latency Ubuntu 20.10 Ubuntu 21.04 3 6 9 12 15 SE +/- 0.030, N = 3 SE +/- 0.010, N = 3 12.100 8.739 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 250 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Write Ubuntu 20.10 Ubuntu 21.04 6K 12K 18K 24K 30K SE +/- 45.12, N = 3 SE +/- 43.42, N = 3 20742 28712 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
NAMD ATPase Simulation - 327,506 Atoms OpenBenchmarking.org days/ns, Fewer Is Better NAMD 2.14 ATPase Simulation - 327,506 Atoms Ubuntu 20.10 Ubuntu 21.04 0.064 0.128 0.192 0.256 0.32 SE +/- 0.00359, N = 3 SE +/- 0.00049, N = 3 0.28452 0.27128
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 Ubuntu 20.10 Ubuntu 21.04 0.0556 0.1112 0.1668 0.2224 0.278 SE +/- 0.001954, N = 10 SE +/- 0.002322, N = 6 0.247260 0.231483 MIN: 0.2 MIN: 0.2 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
libavif avifenc Encoder Speed: 10, Lossless OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.9.0 Encoder Speed: 10, Lossless Ubuntu 20.10 Ubuntu 21.04 3 6 9 12 15 SE +/- 0.088, N = 7 SE +/- 0.146, N = 15 9.451 8.522 1. (CXX) g++ options: -O3 -fPIC -lm
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 Ubuntu 20.10 Ubuntu 21.04 0.106 0.212 0.318 0.424 0.53 SE +/- 0.003416, N = 15 SE +/- 0.004513, N = 6 0.471052 0.445171 MIN: 0.39 MIN: 0.4 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
Coremark CoreMark Size 666 - Iterations Per Second OpenBenchmarking.org Iterations/Sec, More Is Better Coremark 1.0 CoreMark Size 666 - Iterations Per Second Ubuntu 20.10 Ubuntu 21.04 500K 1000K 1500K 2000K 2500K SE +/- 3242.58, N = 3 SE +/- 2872.35, N = 3 2316974.82 2347453.57 1. (CC) gcc options: -O2 -lrt" -lrt
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 Ubuntu 20.10 Ubuntu 21.04 3 6 9 12 15 SE +/- 0.014, N = 3 SE +/- 0.058, N = 3 8.851 9.004 1. (CXX) g++ options: -O3 -pthread
Blender Blend File: BMW27 - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: BMW27 - Compute: CPU-Only Ubuntu 20.10 Ubuntu 21.04 7 14 21 28 35 SE +/- 0.14, N = 3 SE +/- 0.04, N = 3 29.56 29.61
John The Ripper Test: Blowfish OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.9.0-jumbo-1 Test: Blowfish Ubuntu 20.10 Ubuntu 21.04 30K 60K 90K 120K 150K SE +/- 877.45, N = 3 SE +/- 160.48, N = 3 111351 118366 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2
Aircrack-ng OpenBenchmarking.org k/s, More Is Better Aircrack-ng 1.5.2 Ubuntu 20.10 Ubuntu 21.04 50K 100K 150K 200K 250K SE +/- 149.68, N = 3 SE +/- 66.66, N = 3 211559.00 211170.46 1. (CXX) g++ options: -O3 -fvisibility=hidden -masm=intel -fcommon -rdynamic -lpthread -lz -lcrypto -lhwloc -ldl -lm -pthread
x265 Video Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better x265 3.4 Video Input: Bosphorus 1080p Ubuntu 20.10 Ubuntu 21.04 7 14 21 28 35 SE +/- 0.29, N = 5 SE +/- 0.34, N = 3 28.26 28.33 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
AOM AV1 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.1 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K Ubuntu 20.10 Ubuntu 21.04 6 12 18 24 30 SE +/- 0.15, N = 3 SE +/- 0.28, N = 3 23.69 23.59 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
PHPBench PHP Benchmark Suite OpenBenchmarking.org Score, More Is Better PHPBench 0.8.1 PHP Benchmark Suite Ubuntu 20.10 Ubuntu 21.04 150K 300K 450K 600K 750K SE +/- 4029.73, N = 3 SE +/- 3328.66, N = 3 717063 715587
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 Ubuntu 20.10 Ubuntu 21.04 0.2293 0.4586 0.6879 0.9172 1.1465 SE +/- 0.009311, N = 7 SE +/- 0.010679, N = 4 1.018895 0.945450 MIN: 0.84 MIN: 0.86 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
libavif avifenc Encoder Speed: 10 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.9.0 Encoder Speed: 10 Ubuntu 20.10 Ubuntu 21.04 1.3174 2.6348 3.9522 5.2696 6.587 SE +/- 0.084, N = 15 SE +/- 0.074, N = 15 5.855 5.050 1. (CXX) g++ options: -O3 -fPIC -lm
OSPray Demo: San Miguel - Renderer: SciVis OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: San Miguel - Renderer: SciVis Ubuntu 20.10 Ubuntu 21.04 20 40 60 80 100 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 90.91 90.91 MIN: 43.48 / MAX: 100 MIN: 55.56 / MAX: 100
OpenFOAM Input: Motorbike 30M OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 8 Input: Motorbike 30M Ubuntu 20.10 Ubuntu 21.04 4 8 12 16 20 SE +/- 0.06, N = 3 SE +/- 0.11, N = 3 15.01 15.05 1. (CXX) g++ options: -std=c++11 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -ldynamicMesh -ldecompose -lgenericPatchFields -lmetisDecomp -lscotchDecomp -llagrangian -lregionModels -lOpenFOAM -ldl -lm
Kvazaar Video Input: Bosphorus 4K - Video Preset: Ultra Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 4K - Video Preset: Ultra Fast Ubuntu 20.10 Ubuntu 21.04 5 10 15 20 25 SE +/- 0.02, N = 3 SE +/- 0.11, N = 3 22.74 22.78 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
TNN Target: CPU - Model: SqueezeNet v1.1 OpenBenchmarking.org ms, Fewer Is Better TNN 0.2.3 Target: CPU - Model: SqueezeNet v1.1 Ubuntu 20.10 Ubuntu 21.04 80 160 240 320 400 SE +/- 0.02, N = 3 SE +/- 0.08, N = 3 366.20 366.73 MIN: 366.01 / MAX: 367.51 MIN: 365.95 / MAX: 373.2 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl
OSPray Demo: XFrog Forest - Renderer: Path Tracer OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: XFrog Forest - Renderer: Path Tracer Ubuntu 20.10 Ubuntu 21.04 3 6 9 12 15 SE +/- 0.00, N = 3 SE +/- 0.04, N = 3 10.31 10.38 MIN: 7.46 / MAX: 10.75 MIN: 7.58 / MAX: 10.75
Kvazaar Video Input: Bosphorus 1080p - Video Preset: Medium OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 1080p - Video Preset: Medium Ubuntu 20.10 Ubuntu 21.04 6 12 18 24 30 SE +/- 0.04, N = 3 SE +/- 0.07, N = 3 25.26 25.42 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
DaCapo Benchmark Java Test: H2 OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: H2 Ubuntu 20.10 Ubuntu 21.04 2K 4K 6K 8K 10K SE +/- 129.08, N = 4 SE +/- 133.93, N = 4 11377 10740
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 Ubuntu 20.10 Ubuntu 21.04 700M 1400M 2100M 2800M 3500M SE +/- 24378623.66, N = 4 SE +/- 19853994.84, N = 3 2157125000 3044966667 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
PyBench Total For Average Test Times OpenBenchmarking.org Milliseconds, Fewer Is Better PyBench 2018-02-16 Total For Average Test Times Ubuntu 20.10 Ubuntu 21.04 200 400 600 800 1000 SE +/- 2.67, N = 3 SE +/- 1.86, N = 3 984 995
SVT-HEVC Tuning: 1 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 1 - Input: Bosphorus 1080p Ubuntu 20.10 Ubuntu 21.04 7 14 21 28 35 SE +/- 0.18, N = 3 SE +/- 0.09, N = 3 28.63 29.57 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
Rodinia Test: OpenMP CFD Solver OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP CFD Solver Ubuntu 20.10 Ubuntu 21.04 1.1117 2.2234 3.3351 4.4468 5.5585 SE +/- 0.065, N = 15 SE +/- 0.071, N = 12 4.941 4.807 1. (CXX) g++ options: -O2 -lOpenCL
Tungsten Renderer Scene: Hair OpenBenchmarking.org Seconds, Fewer Is Better Tungsten Renderer 0.2.2 Scene: Hair Ubuntu 20.10 Ubuntu 21.04 2 4 6 8 10 SE +/- 0.07152, N = 15 SE +/- 0.07388, N = 3 6.75881 6.52538 1. (CXX) g++ options: -std=c++0x -march=core2 -msse2 -msse3 -mssse3 -mno-sse4.1 -mno-sse4.2 -mno-sse4a -mno-avx -mno-fma -mno-bmi2 -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz -ljpeg -lpthread -ldl
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU Ubuntu 20.10 Ubuntu 21.04 0.7886 1.5772 2.3658 3.1544 3.943 SE +/- 0.02670, N = 3 SE +/- 0.00929, N = 3 3.50505 3.27051 MIN: 3.07 MIN: 3.09 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
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 Ubuntu 20.10 Ubuntu 21.04 0.087 0.174 0.261 0.348 0.435 SE +/- 0.003521, N = 3 SE +/- 0.004351, N = 3 0.386794 0.362841 MIN: 0.31 MIN: 0.32 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
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 Ubuntu 20.10 Ubuntu 21.04 700M 1400M 2100M 2800M 3500M SE +/- 10305392.33, N = 3 SE +/- 15087448.79, N = 3 3086966667 3080633333 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 Ubuntu 20.10 Ubuntu 21.04 700M 1400M 2100M 2800M 3500M SE +/- 13475203.56, N = 3 SE +/- 9583724.63, N = 3 3292133333 3290766667 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 Ubuntu 20.10 Ubuntu 21.04 300M 600M 900M 1200M 1500M SE +/- 11623730.52, N = 3 SE +/- 768837.51, N = 3 1569933333 1631166667 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
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 Ubuntu 20.10 Ubuntu 21.04 200M 400M 600M 800M 1000M SE +/- 2859827.11, N = 3 SE +/- 702242.44, N = 3 812776667 826756667 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU Ubuntu 20.10 Ubuntu 21.04 0.5108 1.0216 1.5324 2.0432 2.554 SE +/- 0.02930, N = 15 SE +/- 0.01823, N = 3 2.27008 2.10597 MIN: 2.03 MIN: 2.03 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
SVT-VP9 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p Ubuntu 20.10 Ubuntu 21.04 40 80 120 160 200 SE +/- 1.24, N = 3 SE +/- 2.00, N = 15 198.24 204.86 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
Swet Average OpenBenchmarking.org Operations Per Second, More Is Better Swet 1.5.16 Average Ubuntu 20.10 Ubuntu 21.04 140M 280M 420M 560M 700M SE +/- 7650995.20, N = 3 SE +/- 1889606.21, N = 3 627367473 639155887 1. (CC) gcc options: -lm -lpthread -lcurses -lrt
SVT-VP9 Tuning: VMAF Optimized - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: VMAF Optimized - Input: Bosphorus 1080p Ubuntu 20.10 Ubuntu 21.04 50 100 150 200 250 SE +/- 2.23, N = 3 SE +/- 2.00, N = 15 201.11 210.15 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
libavif avifenc Encoder Speed: 6 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.9.0 Encoder Speed: 6 Ubuntu 20.10 Ubuntu 21.04 4 8 12 16 20 SE +/- 0.11, N = 3 SE +/- 0.19, N = 4 15.36 15.38 1. (CXX) g++ options: -O3 -fPIC -lm
Intel Open Image Denoise Scene: Memorial OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 1.2.0 Scene: Memorial Ubuntu 20.10 Ubuntu 21.04 13 26 39 52 65 SE +/- 2.62, N = 12 SE +/- 2.57, N = 12 50.81 57.59
NAS Parallel Benchmarks Test / Class: EP.D OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.D Ubuntu 20.10 Ubuntu 21.04 2K 4K 6K 8K 10K SE +/- 121.01, N = 3 SE +/- 33.68, N = 3 9183.40 8659.20 -levent -levent_core 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_pthreads -lutil -lm -lrt -lz 2. Ubuntu 20.10: Open MPI 4.0.3 3. Ubuntu 21.04: Open MPI 4.1.0
toyBrot Fractal Generator Implementation: C++ Tasks OpenBenchmarking.org ms, Fewer Is Better toyBrot Fractal Generator 2020-11-18 Implementation: C++ Tasks Ubuntu 20.10 Ubuntu 21.04 2K 4K 6K 8K 10K SE +/- 78.83, N = 6 SE +/- 77.75, N = 6 7963 8015 1. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc
OSPray Demo: XFrog Forest - Renderer: SciVis OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: XFrog Forest - Renderer: SciVis Ubuntu 20.10 Ubuntu 21.04 5 10 15 20 25 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 18.87 18.87 MIN: 12.05 / MAX: 19.23 MIN: 13.33 / MAX: 19.23
POV-Ray Trace Time OpenBenchmarking.org Seconds, Fewer Is Better POV-Ray 3.7.0.7 Trace Time Ubuntu 20.10 Ubuntu 21.04 3 6 9 12 15 SE +/- 0.063, N = 3 SE +/- 0.097, N = 5 9.365 9.476 1. (CXX) g++ options: -pipe -O3 -ffast-math -march=native -pthread -lSM -lICE -lX11 -lIlmImf -lIlmImf-2_5 -lImath-2_5 -lHalf-2_5 -lIex-2_5 -lIexMath-2_5 -lIlmThread-2_5 -lIlmThread -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system
Embree Binary: Pathtracer ISPC - Model: Asian Dragon OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Asian Dragon Ubuntu 20.10 Ubuntu 21.04 20 40 60 80 100 SE +/- 0.47, N = 3 SE +/- 0.84, N = 10 101.86 106.69 MIN: 80.69 / MAX: 111.15 MIN: 85.33 / MAX: 112.78
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 Ubuntu 20.10 Ubuntu 21.04 0.0609 0.1218 0.1827 0.2436 0.3045 SE +/- 0.003157, N = 4 SE +/- 0.002948, N = 3 0.270802 0.256555 MIN: 0.23 MIN: 0.23 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -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 Ubuntu 20.10 Ubuntu 21.04 0.0466 0.0932 0.1398 0.1864 0.233 SE +/- 0.001494, N = 14 SE +/- 0.001836, N = 13 0.206919 0.193198 MIN: 0.18 MIN: 0.18 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU Ubuntu 20.10 Ubuntu 21.04 3 6 9 12 15 SE +/- 3.41513, N = 12 SE +/- 0.03296, N = 14 11.68014 3.60538 MIN: 3.48 MIN: 3.48 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OSPray Demo: Magnetic Reconnection - Renderer: Path Tracer OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: Magnetic Reconnection - Renderer: Path Tracer Ubuntu 20.10 Ubuntu 21.04 100 200 300 400 500 SE +/- 17.82, N = 15 SE +/- 15.14, N = 15 466.67 477.78 MIN: 142.86 / MAX: 1000 MIN: 142.86 / MAX: 1000
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 Ubuntu 20.10 Ubuntu 21.04 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 11.88 11.33 -levent -levent_core 1. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_pthreads -lutil -lm -lrt -lz
oneDNN Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU Ubuntu 20.10 Ubuntu 21.04 0.1484 0.2968 0.4452 0.5936 0.742 SE +/- 0.004580, N = 3 SE +/- 0.004554, N = 3 0.659638 0.615331 MIN: 0.56 MIN: 0.57 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
Kvazaar Video Input: Bosphorus 1080p - Video Preset: Very Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 1080p - Video Preset: Very Fast Ubuntu 20.10 Ubuntu 21.04 11 22 33 44 55 SE +/- 0.20, N = 3 SE +/- 0.45, N = 3 48.57 49.20 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OSPray Demo: Magnetic Reconnection - Renderer: SciVis OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: Magnetic Reconnection - Renderer: SciVis Ubuntu 20.10 Ubuntu 21.04 20 40 60 80 100 SE +/- 0.00, N = 3 SE +/- 1.01, N = 15 111.11 109.63 MIN: 23.26 MIN: 20.83 / MAX: 125
NAS Parallel Benchmarks Test / Class: EP.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.C Ubuntu 20.10 Ubuntu 21.04 1300 2600 3900 5200 6500 SE +/- 92.04, N = 15 SE +/- 51.84, N = 15 5881.04 6259.88 -levent -levent_core 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_pthreads -lutil -lm -lrt -lz 2. Ubuntu 20.10: Open MPI 4.0.3 3. Ubuntu 21.04: Open MPI 4.1.0
Embree Binary: Pathtracer - Model: Asian Dragon OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer - Model: Asian Dragon Ubuntu 20.10 Ubuntu 21.04 20 40 60 80 100 SE +/- 0.89, N = 5 SE +/- 0.58, N = 3 80.22 81.29 MIN: 64.42 / MAX: 92.94 MIN: 67.06 / MAX: 91.79
NAS Parallel Benchmarks Test / Class: LU.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: LU.C Ubuntu 20.10 Ubuntu 21.04 40K 80K 120K 160K 200K SE +/- 579.11, N = 3 SE +/- 419.66, N = 3 188751.17 187807.08 -levent -levent_core 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_pthreads -lutil -lm -lrt -lz 2. Ubuntu 20.10: Open MPI 4.0.3 3. Ubuntu 21.04: Open MPI 4.1.0
Embree Binary: Pathtracer - Model: Crown OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer - Model: Crown Ubuntu 20.10 Ubuntu 21.04 14 28 42 56 70 SE +/- 0.77, N = 3 SE +/- 0.70, N = 3 64.42 64.30 MIN: 56.4 / MAX: 82.25 MIN: 55.83 / MAX: 81.77
Timed MPlayer Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed MPlayer Compilation 1.4 Time To Compile Ubuntu 20.10 Ubuntu 21.04 3 6 9 12 15 SE +/- 0.06, N = 3 SE +/- 0.06, N = 3 11.10 10.11
Embree Binary: Pathtracer ISPC - Model: Crown OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Crown Ubuntu 20.10 Ubuntu 21.04 15 30 45 60 75 SE +/- 0.47, N = 3 SE +/- 0.30, N = 3 66.16 67.04 MIN: 57.81 / MAX: 87.38 MIN: 59.72 / MAX: 87.99
OSPray Demo: NASA Streamlines - Renderer: Path Tracer OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: NASA Streamlines - Renderer: Path Tracer Ubuntu 20.10 Ubuntu 21.04 7 14 21 28 35 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 27.78 27.78 MIN: 16.67 / MAX: 29.41 MIN: 17.24 / MAX: 29.41
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 Ubuntu 20.10 Ubuntu 21.04 0.3475 0.695 1.0425 1.39 1.7375 SE +/- 0.02039, N = 3 SE +/- 0.01131, N = 3 1.54442 1.37903 MIN: 1.31 MIN: 1.33 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
toyBrot Fractal Generator Implementation: C++ Threads OpenBenchmarking.org ms, Fewer Is Better toyBrot Fractal Generator 2020-11-18 Implementation: C++ Threads Ubuntu 20.10 Ubuntu 21.04 1500 3000 4500 6000 7500 SE +/- 61.67, N = 3 SE +/- 85.39, N = 4 7165 7118 1. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc
Rodinia Test: OpenMP Streamcluster OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP Streamcluster Ubuntu 20.10 Ubuntu 21.04 2 4 6 8 10 SE +/- 0.089, N = 3 SE +/- 0.081, N = 3 8.563 7.696 1. (CXX) g++ options: -O2 -lOpenCL
toyBrot Fractal Generator Implementation: OpenMP OpenBenchmarking.org ms, Fewer Is Better toyBrot Fractal Generator 2020-11-18 Implementation: OpenMP Ubuntu 20.10 Ubuntu 21.04 2K 4K 6K 8K 10K SE +/- 108.03, N = 3 SE +/- 105.33, N = 3 7806 7438 1. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc
Kvazaar Video Input: Bosphorus 1080p - Video Preset: Ultra Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 1080p - Video Preset: Ultra Fast Ubuntu 20.10 Ubuntu 21.04 20 40 60 80 100 SE +/- 0.21, N = 3 SE +/- 0.67, N = 3 86.46 85.41 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
SVT-HEVC Tuning: 10 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 10 - Input: Bosphorus 1080p Ubuntu 20.10 Ubuntu 21.04 60 120 180 240 300 SE +/- 2.36, N = 6 SE +/- 2.49, N = 3 237.32 260.88 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
SVT-VP9 Tuning: Visual Quality Optimized - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: Visual Quality Optimized - Input: Bosphorus 1080p Ubuntu 20.10 Ubuntu 21.04 40 80 120 160 200 SE +/- 0.47, N = 3 SE +/- 2.03, N = 3 164.77 170.47 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
LAMMPS Molecular Dynamics Simulator Model: Rhodopsin Protein OpenBenchmarking.org ns/day, More Is Better LAMMPS Molecular Dynamics Simulator 29Oct2020 Model: Rhodopsin Protein Ubuntu 20.10 Ubuntu 21.04 6 12 18 24 30 SE +/- 0.26, N = 15 SE +/- 0.02, N = 3 21.65 23.87 1. (CXX) g++ options: -O3 -pthread -lm
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 Ubuntu 20.10 Ubuntu 21.04 0.3554 0.7108 1.0662 1.4216 1.777 SE +/- 0.01111, N = 3 SE +/- 0.00589, N = 3 1.57954 1.41084 MIN: 1.24 MIN: 1.27 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
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 Ubuntu 20.10 Ubuntu 21.04 0.232 0.464 0.696 0.928 1.16 SE +/- 0.004578, N = 3 SE +/- 0.005014, N = 3 1.031020 0.924756 MIN: 0.84 MIN: 0.86 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -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 Ubuntu 20.10 Ubuntu 21.04 0.2031 0.4062 0.6093 0.8124 1.0155 SE +/- 0.008637, N = 6 SE +/- 0.008374, N = 6 0.902751 0.846330 MIN: 0.8 MIN: 0.8 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
SVT-HEVC Tuning: 7 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 7 - Input: Bosphorus 1080p Ubuntu 20.10 Ubuntu 21.04 40 80 120 160 200 SE +/- 1.13, N = 3 SE +/- 1.72, N = 3 161.78 172.02 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
Tungsten Renderer Scene: Non-Exponential OpenBenchmarking.org Seconds, Fewer Is Better Tungsten Renderer 0.2.2 Scene: Non-Exponential Ubuntu 20.10 Ubuntu 21.04 1.1814 2.3628 3.5442 4.7256 5.907 SE +/- 0.04628, N = 3 SE +/- 0.07466, N = 3 5.25085 5.23912 1. (CXX) g++ options: -std=c++0x -march=core2 -msse2 -msse3 -mssse3 -mno-sse4.1 -mno-sse4.2 -mno-sse4a -mno-avx -mno-fma -mno-bmi2 -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz -ljpeg -lpthread -ldl
OSPray Demo: NASA Streamlines - Renderer: SciVis OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: NASA Streamlines - Renderer: SciVis Ubuntu 20.10 Ubuntu 21.04 30 60 90 120 150 125 125 MIN: 28.57 / MAX: 142.86 MIN: 31.25 / MAX: 142.86
BlogBench Test: Write OpenBenchmarking.org Final Score, More Is Better BlogBench 1.1 Test: Write Ubuntu 20.10 Ubuntu 21.04 13K 26K 39K 52K 65K SE +/- 419.01, N = 3 SE +/- 717.36, N = 3 62517 60768 1. (CC) gcc options: -O2 -pthread
Phoronix Test Suite v10.8.4