AMD EPYC 74F3 24-Core testing of Ubuntu Linux versions by Michael Larabel for a future article.
Ubuntu 20.04 LTS Processor: AMD EPYC 74F3 24-Core @ 3.20GHz (24 Cores / 48 Threads), Motherboard: ASRockRack ROME2D16-2T (P3.10 BIOS), Chipset: AMD Starship/Matisse, Memory: 64GB, Disk: 1000GB Western Digital WD_BLACK SN850 1TB, Graphics: ASPEED, Audio: AMD Starship/Matisse, Monitor: VE228, Network: 2 x Intel 10G X550T
OS: Ubuntu 20.04, Kernel: 5.4.0-88-generic (x86_64), Vulkan: 1.0.2, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0xa001114Java Notes: OpenJDK Runtime Environment (build 11.0.11+9-Ubuntu-0ubuntu2.20.04)Python Notes: Python 3.8.10Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Ubuntu 21.04 OS: Ubuntu 21.04, Kernel: 5.11.0-37-generic (x86_64), Display Server: X Server, Vulkan: 1.0.2, Compiler: GCC 10.3.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --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 -vProcessor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001114Java Notes: OpenJDK Runtime Environment (build 11.0.11+9-Ubuntu-0ubuntu2)Python Notes: Python 3.9.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Ubuntu 21.10 OS: Ubuntu 21.10, Kernel: 5.13.0-16-generic (x86_64), Desktop: GNOME Shell 40.5, Display Server: X Server, Vulkan: 1.1.182, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001114Java Notes: OpenJDK Runtime Environment (build 11.0.12+7-Ubuntu-0ubuntu3)Python Notes: Python 3.9.7Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Ubuntu 21.10 + Linux 5.15 OS: Ubuntu 21.10, Kernel: 5.15.0-051500rc5daily20211011-generic (x86_64) 20211010, Desktop: GNOME Shell 40.5, Display Server: X Server, Vulkan: 1.1.182, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 1920x1080
Ubuntu 21.04 LTS To Ubuntu 21.10 AMD EPYC Milan Benchmarks Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Vulkan Compiler File-System Screen Resolution Display Server Desktop Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 AMD EPYC 74F3 24-Core @ 3.20GHz (24 Cores / 48 Threads) ASRockRack ROME2D16-2T (P3.10 BIOS) AMD Starship/Matisse 64GB 1000GB Western Digital WD_BLACK SN850 1TB ASPEED AMD Starship/Matisse VE228 2 x Intel 10G X550T Ubuntu 20.04 5.4.0-88-generic (x86_64) 1.0.2 GCC 9.3.0 ext4 1920x1080 Ubuntu 21.04 5.11.0-37-generic (x86_64) X Server GCC 10.3.0 Ubuntu 21.10 5.13.0-16-generic (x86_64) GNOME Shell 40.5 1.1.182 GCC 11.2.0 5.15.0-051500rc5daily20211011-generic (x86_64) 20211010 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - Ubuntu 20.04 LTS: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - 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 21.10: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Ubuntu 21.10 + Linux 5.15: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details - Ubuntu 20.04 LTS: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0xa001114 - Ubuntu 21.04: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001114 - Ubuntu 21.10: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001114 - Ubuntu 21.10 + Linux 5.15: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001114 Java Details - Ubuntu 20.04 LTS: OpenJDK Runtime Environment (build 11.0.11+9-Ubuntu-0ubuntu2.20.04) - Ubuntu 21.04: OpenJDK Runtime Environment (build 11.0.11+9-Ubuntu-0ubuntu2) - Ubuntu 21.10: OpenJDK Runtime Environment (build 11.0.12+7-Ubuntu-0ubuntu3) - Ubuntu 21.10 + Linux 5.15: OpenJDK Runtime Environment (build 11.0.12+7-Ubuntu-0ubuntu3) Python Details - Ubuntu 20.04 LTS: Python 3.8.10 - Ubuntu 21.04: Python 3.9.5 - Ubuntu 21.10: Python 3.9.7 - Ubuntu 21.10 + Linux 5.15: Python 3.9.7 Security Details - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 Result Overview Phoronix Test Suite 100% 108% 116% 124% LeelaChessZero MariaDB Redis VP9 libvpx Encoding Timed LLVM Compilation Timed Linux Kernel Compilation Timed Godot Game Engine Compilation Timed Node.js Compilation Stress-NG Apache Cassandra Mobile Neural Network SVT-VP9 JPEG XL libjxl NCNN libavif avifenc SVT-HEVC Rodinia PlaidML Stockfish NAS Parallel Benchmarks Intel Open Image Denoise Xcompact3d Incompact3d simdjson Chaos Group V-RAY AOM AV1 OpenFOAM ASTC Encoder ONNX Runtime 7-Zip Compression OSPray Appleseed Natron LuxCoreRender Xmrig Blender Sysbench NAMD
Ubuntu 21.04 LTS To Ubuntu 21.10 AMD EPYC Milan Benchmarks lczero: BLAS stress-ng: Socket Activity vpxenc: Speed 5 - Bosphorus 4K mysqlslap: 512 avifenc: 10 vpxenc: Speed 0 - Bosphorus 4K build-llvm: Unix Makefiles build-llvm: Ninja build-linux-kernel: Time To Compile build-godot: Time To Compile npb: IS.D ncnn: CPU - regnety_400m build-nodejs: Time To Compile stress-ng: Vector Math rodinia: OpenMP Leukocyte jpegxl: PNG - 5 mnn: MobileNetV2_224 stress-ng: CPU Stress cassandra: Writes mnn: SqueezeNetV1.0 plaidml: No - Inference - VGG16 - CPU ncnn: CPU - vgg16 plaidml: No - Inference - VGG19 - CPU npb: CG.C svt-vp9: VMAF Optimized - Bosphorus 1080p svt-hevc: 10 - Bosphorus 1080p mnn: squeezenetv1.1 avifenc: 6 ncnn: CPU - efficientnet-b0 ncnn: CPU - resnet18 ncnn: CPU - mnasnet ncnn: CPU - resnet50 ncnn: CPU - mobilenet npb: FT.C ncnn: CPU - squeezenet_ssd incompact3d: input.i3d 129 Cells Per Direction stockfish: Total Time ncnn: CPU-v2-v2 - mobilenet-v2 simdjson: LargeRand npb: MG.C svt-hevc: 7 - Bosphorus 1080p npb: LU.C jpegxl: PNG - 8 astcenc: Thorough ospray: NASA Streamlines - SciVis openfoam: Motorbike 30M oidn: RT.ldr_alb_nrm.3840x2160 v-ray: CPU simdjson: DistinctUserID aom-av1: Speed 9 Realtime - Bosphorus 4K npb: SP.C npb: SP.B incompact3d: input.i3d 193 Cells Per Direction avifenc: 6, Lossless avifenc: 0 stress-ng: Matrix Math onnx: fcn-resnet101-11 - OpenMP CPU plaidml: No - Inference - ResNet 50 - CPU compress-7zip: Compress Speed Test luxcorerender: LuxCore Benchmark - CPU simdjson: Kostya luxcorerender: Danish Mood - CPU appleseed: Material Tester natron: Spaceship openfoam: Motorbike 60M ospray: San Miguel - SciVis xmrig: Monero - 1M sysbench: RAM / Memory luxcorerender: Orange Juice - CPU astcenc: Exhaustive luxcorerender: DLSC - CPU xmrig: Wownero - 1M blender: Barbershop - CPU-Only namd: ATPase Simulation - 327,506 Atoms sysbench: CPU redis: SET rodinia: OpenMP Streamcluster Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 1101 15654.88 13.83 562 3.311 6.51 312.650 266.603 40.411 63.477 1782.03 16.31 171.825 127389.21 48.547 67.14 3.834 63169.41 210683 6.211 26.99 26.71 23.28 24987.15 415.51 517.77 4.724 9.760 7.25 9.30 5.33 16.30 13.33 41384.74 16.55 6.74854708 71806266 5.89 1.08 50231.27 271.43 81482.77 0.96 6.8227 50.53 25.15 0.83 27377 4.79 45.69 35978.09 63676.15 30.7172693 29.119 46.039 102782.01 167 10.34 172416 3.94 3.18 3.64 149.61541 5.0 243.43 37.04 18153.2 10190.97 7.03 24.2063 4.74 19031.1 228.67 0.77668 114401.77 1771810.56 6.708 1442 14625.69 16.15 660 3.677 6.94 278.383 238.515 35.659 57.898 1790.31 15.43 157.057 127352.28 49.579 72.78 4.018 66584.16 229507 6.529 26.53 26.24 22.47 25140.10 436.86 545.96 4.771 10.051 7.02 8.91 5.19 16.07 13.12 43707.66 16.33 6.85141821 75316326 5.72 1.06 50207.13 279.49 81382.28 0.94 6.7181 50 25.15 0.86 27781 4.78 47.13 35627.71 63522.54 30.2943401 29.031 46.226 103521.20 171 10.21 171152 4.03 3.14 3.67 146.602235 5.1 242.99 37.51 18245.2 10283.19 7.03 24.0834 4.76 19125.8 227.98 0.77608 114490.11 2070185.38 6.292 1457 14982.11 17.51 703 3.497 7.46 274.264 235.750 36.731 56.360 1993.83 14.94 153.714 142582.12 44.601 72.00 3.837 69408.59 230318 6.249 27.13 25.51 22.20 24114.11 446.62 553.02 4.726 9.722 7.07 9.26 5.13 16.43 13.59 42915.03 16.17 6.90810013 75631071 5.73 1.11 50332.64 281.48 82765.18 0.96 6.5677 50.53 24.22 0.86 27825 4.93 46.80 35556.44 63598.14 30.3851414 28.860 45.120 102691.89 167 10.10 172117 3.94 3.21 3.61 147.897295 5.1 243.11 37.51 18217.5 10278.23 7.05 24.0608 4.74 19059.6 229.14 0.77725 114579.76 2148023.02 6.558 1340 19318.77 16.97 647 3.197 7.42 275.492 234.950 36.466 56.081 2013.11 14.50 153.044 142690.55 44.354 74.92 3.604 69941.34 231554 5.962 28.99 24.70 23.92 25960.11 444.46 556.42 4.441 9.418 6.81 8.74 5.01 15.45 12.84 43590.57 15.69 6.55719979 75304369 5.61 1.11 52547.88 283.51 84921.35 0.98 6.5450 52.11 24.21 0.85 28305 4.94 46.73 36599.60 65350.97 29.8944200 28.358 45.073 105285.85 171 10.29 175165 3.99 3.21 3.69 147.981773 5.1 239.68 37.51 18333.4 10249.84 7.09 24.0457 4.77 19138.5 227.94 0.77730 114562.03 2195897.79 6.695 OpenBenchmarking.org
LeelaChessZero LeelaChessZero (lc0 / lczero) is a chess engine automated vian neural networks. This test profile can be used for OpenCL, CUDA + cuDNN, and BLAS (CPU-based) benchmarking. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.28 Backend: BLAS Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 300 600 900 1200 1500 SE +/- 11.79, N = 3 SE +/- 8.33, N = 3 SE +/- 12.03, N = 3 SE +/- 14.18, N = 9 1101 1442 1457 1340 1. (CXX) g++ options: -flto -pthread
Stress-NG Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Socket Activity Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 4K 8K 12K 16K 20K SE +/- 40.55, N = 3 SE +/- 0.85, N = 3 SE +/- 20.77, N = 3 SE +/- 66.97, N = 3 15654.88 14625.69 14982.11 19318.77 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic
VP9 libvpx Encoding This is a standard video encoding performance test of Google's libvpx library and the vpxenc command for the VP9 video format. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.10.0 Speed: Speed 5 - Input: Bosphorus 4K Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 4 8 12 16 20 SE +/- 0.09, N = 3 SE +/- 0.11, N = 3 SE +/- 0.15, N = 3 SE +/- 0.07, N = 3 13.83 16.15 17.51 16.97 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
MariaDB This is a MariaDB MySQL database server benchmark making use of mysqlslap. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.6.4 Clients: 512 Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 150 300 450 600 750 SE +/- 1.28, N = 3 SE +/- 2.61, N = 3 SE +/- 1.91, N = 3 SE +/- 6.28, N = 3 562 660 703 647 -pthread -pthread 1. (CXX) g++ options: -pie -fPIC -fstack-protector -O3 -llzma -lbz2 -lsnappy -lnuma -lpcre2-8 -lcrypt -laio -lz -lm -lssl -lcrypto -lpthread -ldl
libavif avifenc This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.9.0 Encoder Speed: 10 Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 0.8273 1.6546 2.4819 3.3092 4.1365 SE +/- 0.002, N = 3 SE +/- 0.010, N = 3 SE +/- 0.004, N = 3 SE +/- 0.008, N = 3 3.311 3.677 3.497 3.197 1. (CXX) g++ options: -O3 -fPIC -lm
VP9 libvpx Encoding This is a standard video encoding performance test of Google's libvpx library and the vpxenc command for the VP9 video format. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.10.0 Speed: Speed 0 - Input: Bosphorus 4K Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 2 4 6 8 10 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.08, N = 3 6.51 6.94 7.46 7.42 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 13.0 Build System: Ninja Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 60 120 180 240 300 SE +/- 0.12, N = 3 SE +/- 0.21, N = 3 SE +/- 0.59, N = 3 SE +/- 0.32, N = 3 266.60 238.52 235.75 234.95
Timed Godot Game Engine Compilation This test times how long it takes to compile the Godot Game Engine. Godot is a popular, open-source, cross-platform 2D/3D game engine and is built using the SCons build system and targeting the X11 platform. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Timed Godot Game Engine Compilation 3.2.3 Time To Compile Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 14 28 42 56 70 SE +/- 0.13, N = 3 SE +/- 0.03, N = 3 SE +/- 0.15, N = 3 SE +/- 0.12, N = 3 63.48 57.90 56.36 56.08
NAS Parallel Benchmarks NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: IS.D Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 400 800 1200 1600 2000 SE +/- 1.92, N = 3 SE +/- 6.56, N = 3 SE +/- 6.66, N = 3 SE +/- 3.59, N = 3 1782.03 1790.31 1993.83 2013.11 -pthread -pthread -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Ubuntu 20.04 LTS: Open MPI 4.0.3 3. Ubuntu 21.04: Open MPI 4.1.0 4. Ubuntu 21.10: Open MPI 4.1.0 5. Ubuntu 21.10 + Linux 5.15: Open MPI 4.1.0
NCNN NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: regnety_400m Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.06, N = 3 SE +/- 0.18, N = 3 SE +/- 0.04, N = 3 16.31 15.43 14.94 14.50 -pthread - MIN: 16.17 / MAX: 18.83 -pthread - MIN: 15.28 / MAX: 17.87 MIN: 14.42 / MAX: 114.45 MIN: 14.35 / MAX: 17.97 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Timed Node.js Compilation This test profile times how long it takes to build/compile Node.js itself from source. Node.js is a JavaScript run-time built from the Chrome V8 JavaScript engine while itself is written in C/C++. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Timed Node.js Compilation 15.11 Time To Compile Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 40 80 120 160 200 SE +/- 0.30, N = 3 SE +/- 0.16, N = 3 SE +/- 0.14, N = 3 SE +/- 0.20, N = 3 171.83 157.06 153.71 153.04
Stress-NG Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Vector Math Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 30K 60K 90K 120K 150K SE +/- 12.36, N = 3 SE +/- 13.25, N = 3 SE +/- 12.72, N = 3 SE +/- 16.18, N = 3 127389.21 127352.28 142582.12 142690.55 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic
Rodinia Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP Leukocyte Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 11 22 33 44 55 SE +/- 0.17, N = 3 SE +/- 0.30, N = 3 SE +/- 0.11, N = 3 SE +/- 0.22, N = 3 48.55 49.58 44.60 44.35 1. (CXX) g++ options: -O2 -lOpenCL
JPEG XL libjxl The JPEG XL Image Coding System is designed to provide next-generation JPEG image capabilities with JPEG XL offering better image quality and compression over legacy JPEG. This test profile is currently focused on the multi-threaded JPEG XL image encode performance using the reference libjxl library. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.5 Input: PNG - Encode Speed: 5 Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 20 40 60 80 100 SE +/- 0.13, N = 3 SE +/- 0.15, N = 3 SE +/- 0.17, N = 3 SE +/- 0.06, N = 3 67.14 72.78 72.00 74.92 -pthread -pthread 1. (CXX) g++ options: -funwind-tables -O3 -O2 -fPIE -pie
Mobile Neural Network MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by Alibaba. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: MobileNetV2_224 Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 0.9041 1.8082 2.7123 3.6164 4.5205 SE +/- 0.051, N = 3 SE +/- 0.022, N = 15 SE +/- 0.032, N = 15 SE +/- 0.032, N = 14 3.834 4.018 3.837 3.604 MIN: 3.66 / MAX: 4.12 MIN: 3.82 / MAX: 4.55 MIN: 3.58 / MAX: 4.5 MIN: 3.38 / MAX: 7.24 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Stress-NG Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: CPU Stress Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 15K 30K 45K 60K 75K SE +/- 124.09, N = 3 SE +/- 73.09, N = 3 SE +/- 64.21, N = 3 SE +/- 15.37, N = 3 63169.41 66584.16 69408.59 69941.34 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic
Mobile Neural Network MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by Alibaba. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: SqueezeNetV1.0 Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 2 4 6 8 10 SE +/- 0.046, N = 3 SE +/- 0.048, N = 15 SE +/- 0.054, N = 15 SE +/- 0.044, N = 14 6.211 6.529 6.249 5.962 MIN: 5.89 / MAX: 6.94 MIN: 6.09 / MAX: 7.56 MIN: 5.67 / MAX: 11.64 MIN: 5.6 / MAX: 9.22 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
PlaidML This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: VGG16 - Device: CPU Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 7 14 21 28 35 SE +/- 0.08, N = 3 SE +/- 0.30, N = 3 SE +/- 0.09, N = 3 SE +/- 0.23, N = 3 26.99 26.53 27.13 28.99
NCNN NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: vgg16 Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 6 12 18 24 30 SE +/- 0.05, N = 3 SE +/- 0.09, N = 3 SE +/- 0.16, N = 3 SE +/- 0.57, N = 3 26.71 26.24 25.51 24.70 -pthread - MIN: 26.25 / MAX: 28.9 -pthread - MIN: 25.85 / MAX: 59.93 MIN: 24.52 / MAX: 94.79 MIN: 23.74 / MAX: 37.55 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
PlaidML This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: VGG19 - Device: CPU Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 6 12 18 24 30 SE +/- 0.09, N = 3 SE +/- 0.12, N = 3 SE +/- 0.12, N = 3 SE +/- 0.30, N = 3 23.28 22.47 22.20 23.92
NAS Parallel Benchmarks NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: CG.C Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 6K 12K 18K 24K 30K SE +/- 127.06, N = 3 SE +/- 24.29, N = 3 SE +/- 158.46, N = 3 SE +/- 235.98, N = 3 24987.15 25140.10 24114.11 25960.11 -pthread -pthread -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Ubuntu 20.04 LTS: Open MPI 4.0.3 3. Ubuntu 21.04: Open MPI 4.1.0 4. Ubuntu 21.10: Open MPI 4.1.0 5. Ubuntu 21.10 + Linux 5.15: Open MPI 4.1.0
SVT-VP9 This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample YUV input video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: VMAF Optimized - Input: Bosphorus 1080p Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 100 200 300 400 500 SE +/- 3.12, N = 14 SE +/- 3.59, N = 14 SE +/- 3.38, N = 13 SE +/- 5.09, N = 14 415.51 436.86 446.62 444.46 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
SVT-HEVC This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 10 - Input: Bosphorus 1080p Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 120 240 360 480 600 SE +/- 4.50, N = 3 SE +/- 1.52, N = 3 SE +/- 2.56, N = 3 SE +/- 0.62, N = 3 517.77 545.96 553.02 556.42 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
Mobile Neural Network MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by Alibaba. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: squeezenetv1.1 Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 1.0735 2.147 3.2205 4.294 5.3675 SE +/- 0.038, N = 3 SE +/- 0.050, N = 15 SE +/- 0.054, N = 15 SE +/- 0.054, N = 14 4.724 4.771 4.726 4.441 MIN: 4.5 / MAX: 5.27 MIN: 4.19 / MAX: 5.5 MIN: 4.13 / MAX: 8.49 MIN: 3.94 / MAX: 7.88 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
libavif avifenc This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.9.0 Encoder Speed: 6 Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 3 6 9 12 15 SE +/- 0.047, N = 3 SE +/- 0.063, N = 3 SE +/- 0.018, N = 3 SE +/- 0.024, N = 3 9.760 10.051 9.722 9.418 1. (CXX) g++ options: -O3 -fPIC -lm
NCNN NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: efficientnet-b0 Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 2 4 6 8 10 SE +/- 0.05, N = 3 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 SE +/- 0.00, N = 3 7.25 7.02 7.07 6.81 -pthread - MIN: 7.11 / MAX: 9.7 -pthread - MIN: 6.94 / MAX: 7.29 MIN: 6.84 / MAX: 61.76 MIN: 6.74 / MAX: 10.45 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: resnet18 Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 SE +/- 0.22, N = 3 9.30 8.91 9.26 8.74 -pthread - MIN: 9.05 / MAX: 10.67 -pthread - MIN: 8.62 / MAX: 10.75 MIN: 8.7 / MAX: 58.92 MIN: 8.38 / MAX: 10.87 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: mnasnet Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 1.1993 2.3986 3.5979 4.7972 5.9965 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 5.33 5.19 5.13 5.01 -pthread - MIN: 5.27 / MAX: 7.62 -pthread - MIN: 5.1 / MAX: 7.63 MIN: 5 / MAX: 20.79 MIN: 4.91 / MAX: 15.1 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: resnet50 Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 4 8 12 16 20 SE +/- 0.07, N = 3 SE +/- 0.06, N = 3 SE +/- 0.31, N = 3 SE +/- 0.24, N = 3 16.30 16.07 16.43 15.45 -pthread - MIN: 16.02 / MAX: 18.19 -pthread - MIN: 15.82 / MAX: 18.83 MIN: 15.63 / MAX: 176.4 MIN: 14.99 / MAX: 19.35 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: mobilenet Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 3 6 9 12 15 SE +/- 0.07, N = 3 SE +/- 0.04, N = 3 SE +/- 0.12, N = 3 SE +/- 0.18, N = 3 13.33 13.12 13.59 12.84 -pthread - MIN: 13.05 / MAX: 15.05 -pthread - MIN: 12.84 / MAX: 15.23 MIN: 12.98 / MAX: 71.45 MIN: 12.4 / MAX: 14.89 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NAS Parallel Benchmarks NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: FT.C Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 9K 18K 27K 36K 45K SE +/- 49.05, N = 3 SE +/- 94.87, N = 3 SE +/- 131.14, N = 3 SE +/- 29.98, N = 3 41384.74 43707.66 42915.03 43590.57 -pthread -pthread -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Ubuntu 20.04 LTS: Open MPI 4.0.3 3. Ubuntu 21.04: Open MPI 4.1.0 4. Ubuntu 21.10: Open MPI 4.1.0 5. Ubuntu 21.10 + Linux 5.15: Open MPI 4.1.0
NCNN NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: squeezenet_ssd Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 4 8 12 16 20 SE +/- 0.10, N = 3 SE +/- 0.01, N = 3 SE +/- 0.11, N = 3 SE +/- 0.11, N = 3 16.55 16.33 16.17 15.69 -pthread - MIN: 16.09 / MAX: 18.49 -pthread - MIN: 16.02 / MAX: 17.24 MIN: 15.43 / MAX: 158.11 MIN: 15.28 / MAX: 19.14 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Xcompact3d Incompact3d Xcompact3d Incompact3d is a Fortran-MPI based, finite difference high-performance code for solving the incompressible Navier-Stokes equation and as many as you need scalar transport equations. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 Input: input.i3d 129 Cells Per Direction Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 2 4 6 8 10 SE +/- 0.02637687, N = 3 SE +/- 0.07087910, N = 5 SE +/- 0.02220467, N = 3 SE +/- 0.05267586, N = 3 6.74854708 6.85141821 6.90810013 6.55719979 -pthread -pthread -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 1. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi
Stockfish This is a test of Stockfish, an advanced open-source C++11 chess benchmark that can scale up to 512 CPU threads. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 13 Total Time Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 16M 32M 48M 64M 80M SE +/- 226764.09, N = 3 SE +/- 461786.73, N = 15 SE +/- 716479.64, N = 3 SE +/- 552677.79, N = 15 71806266 75316326 75631071 75304369 -mbmi2 -mbmi2 -mbmi2 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 -msse4.1 -mssse3 -msse2 -flto -flto=jobserver
NCNN NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU-v2-v2 - Model: mobilenet-v2 Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 1.3253 2.6506 3.9759 5.3012 6.6265 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 5.89 5.72 5.73 5.61 -pthread - MIN: 5.75 / MAX: 8.25 -pthread - MIN: 5.58 / MAX: 6.05 MIN: 5.52 / MAX: 15.08 MIN: 5.46 / MAX: 9.47 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
simdjson This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org GB/s, More Is Better simdjson 1.0 Throughput Test: LargeRandom Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 0.2498 0.4996 0.7494 0.9992 1.249 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 1.08 1.06 1.11 1.11 -pthread -pthread 1. (CXX) g++ options: -O3
NAS Parallel Benchmarks NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: MG.C Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 11K 22K 33K 44K 55K SE +/- 19.57, N = 3 SE +/- 67.20, N = 3 SE +/- 39.41, N = 3 SE +/- 55.76, N = 3 50231.27 50207.13 50332.64 52547.88 -pthread -pthread -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Ubuntu 20.04 LTS: Open MPI 4.0.3 3. Ubuntu 21.04: Open MPI 4.1.0 4. Ubuntu 21.10: Open MPI 4.1.0 5. Ubuntu 21.10 + Linux 5.15: Open MPI 4.1.0
SVT-HEVC This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 7 - Input: Bosphorus 1080p Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 60 120 180 240 300 SE +/- 3.68, N = 3 SE +/- 2.36, N = 8 SE +/- 3.36, N = 4 SE +/- 2.41, N = 8 271.43 279.49 281.48 283.51 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
NAS Parallel Benchmarks NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: LU.C Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 20K 40K 60K 80K 100K SE +/- 120.17, N = 3 SE +/- 271.58, N = 3 SE +/- 302.50, N = 3 SE +/- 115.55, N = 3 81482.77 81382.28 82765.18 84921.35 -pthread -pthread -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Ubuntu 20.04 LTS: Open MPI 4.0.3 3. Ubuntu 21.04: Open MPI 4.1.0 4. Ubuntu 21.10: Open MPI 4.1.0 5. Ubuntu 21.10 + Linux 5.15: Open MPI 4.1.0
JPEG XL libjxl The JPEG XL Image Coding System is designed to provide next-generation JPEG image capabilities with JPEG XL offering better image quality and compression over legacy JPEG. This test profile is currently focused on the multi-threaded JPEG XL image encode performance using the reference libjxl library. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.5 Input: PNG - Encode Speed: 8 Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 0.2205 0.441 0.6615 0.882 1.1025 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.96 0.94 0.96 0.98 -pthread -pthread 1. (CXX) g++ options: -funwind-tables -O3 -O2 -fPIE -pie
ASTC Encoder ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 3.2 Preset: Thorough Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 2 4 6 8 10 SE +/- 0.0388, N = 3 SE +/- 0.0094, N = 3 SE +/- 0.0094, N = 3 SE +/- 0.0028, N = 3 6.8227 6.7181 6.5677 6.5450 1. (CXX) g++ options: -O3 -flto -pthread
OSPray Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity scientific visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: NASA Streamlines - Renderer: SciVis Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 12 24 36 48 60 SE +/- 0.53, N = 5 SE +/- 0.53, N = 5 SE +/- 0.53, N = 5 50.53 50.00 50.53 52.11 MIN: 47.62 / MAX: 52.63 MIN: 47.62 / MAX: 52.63 MIN: 35.71 / MAX: 52.63 MIN: 47.62 / MAX: 52.63
OpenFOAM OpenFOAM is the leading free, open source software for computational fluid dynamics (CFD). Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 8 Input: Motorbike 30M Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 6 12 18 24 30 SE +/- 0.19, N = 3 SE +/- 0.15, N = 3 SE +/- 0.07, N = 3 SE +/- 0.06, N = 3 25.15 25.15 24.22 24.21 1. (CXX) g++ options: -std=c++11 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm
Chaos Group V-RAY This is a test of Chaos Group's V-RAY benchmark. V-RAY is a commercial renderer that can integrate with various creator software products like SketchUp and 3ds Max. The V-RAY benchmark is standalone and supports CPU and NVIDIA CUDA/RTX based rendering. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org vsamples, More Is Better Chaos Group V-RAY 5 Mode: CPU Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 6K 12K 18K 24K 30K SE +/- 206.68, N = 3 SE +/- 317.32, N = 4 SE +/- 357.24, N = 3 SE +/- 262.43, N = 3 27377 27781 27825 28305
simdjson This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org GB/s, More Is Better simdjson 1.0 Throughput Test: DistinctUserID Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 1.1115 2.223 3.3345 4.446 5.5575 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 4.79 4.78 4.93 4.94 -pthread -pthread 1. (CXX) g++ options: -O3
AOM AV1 This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.1 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 11 22 33 44 55 SE +/- 0.09, N = 3 SE +/- 0.47, N = 3 SE +/- 0.15, N = 3 SE +/- 0.19, N = 3 45.69 47.13 46.80 46.73 -lpthread -lpthread 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
NAS Parallel Benchmarks NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.C Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 8K 16K 24K 32K 40K SE +/- 81.55, N = 3 SE +/- 62.61, N = 3 SE +/- 27.26, N = 3 SE +/- 24.90, N = 3 35978.09 35627.71 35556.44 36599.60 -pthread -pthread -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Ubuntu 20.04 LTS: Open MPI 4.0.3 3. Ubuntu 21.04: Open MPI 4.1.0 4. Ubuntu 21.10: Open MPI 4.1.0 5. Ubuntu 21.10 + Linux 5.15: Open MPI 4.1.0
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.B Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 14K 28K 42K 56K 70K SE +/- 174.33, N = 3 SE +/- 199.94, N = 3 SE +/- 123.88, N = 3 SE +/- 150.74, N = 3 63676.15 63522.54 63598.14 65350.97 -pthread -pthread -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Ubuntu 20.04 LTS: Open MPI 4.0.3 3. Ubuntu 21.04: Open MPI 4.1.0 4. Ubuntu 21.10: Open MPI 4.1.0 5. Ubuntu 21.10 + Linux 5.15: Open MPI 4.1.0
Xcompact3d Incompact3d Xcompact3d Incompact3d is a Fortran-MPI based, finite difference high-performance code for solving the incompressible Navier-Stokes equation and as many as you need scalar transport equations. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 Input: input.i3d 193 Cells Per Direction Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 7 14 21 28 35 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.15, N = 3 SE +/- 0.18, N = 3 30.72 30.29 30.39 29.89 -pthread -pthread -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 1. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi
libavif avifenc This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.9.0 Encoder Speed: 6, Lossless Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 7 14 21 28 35 SE +/- 0.20, N = 3 SE +/- 0.05, N = 3 SE +/- 0.18, N = 3 SE +/- 0.12, N = 3 29.12 29.03 28.86 28.36 1. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.9.0 Encoder Speed: 0 Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 10 20 30 40 50 SE +/- 0.10, N = 3 SE +/- 0.14, N = 3 SE +/- 0.04, N = 3 SE +/- 0.14, N = 3 46.04 46.23 45.12 45.07 1. (CXX) g++ options: -O3 -fPIC -lm
Stress-NG Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Matrix Math Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 20K 40K 60K 80K 100K SE +/- 92.57, N = 3 SE +/- 17.49, N = 3 SE +/- 452.67, N = 3 SE +/- 87.63, N = 3 102782.01 103521.20 102691.89 105285.85 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic
ONNX Runtime ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Zoo. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.8.2 Model: fcn-resnet101-11 - Device: OpenMP CPU Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 40 80 120 160 200 SE +/- 0.50, N = 3 SE +/- 2.02, N = 3 SE +/- 0.60, N = 3 SE +/- 1.00, N = 3 167 171 167 171 1. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
PlaidML This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 3 6 9 12 15 SE +/- 0.07, N = 3 SE +/- 0.02, N = 3 SE +/- 0.09, N = 3 SE +/- 0.02, N = 3 10.34 10.21 10.10 10.29
7-Zip Compression This is a test of 7-Zip using p7zip with its integrated benchmark feature or upstream 7-Zip for the Windows x64 build. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 16.02 Compress Speed Test Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 40K 80K 120K 160K 200K SE +/- 686.96, N = 3 SE +/- 539.21, N = 3 SE +/- 363.33, N = 3 SE +/- 240.00, N = 3 172416 171152 172117 175165 1. (CXX) g++ options: -pipe -lpthread
LuxCoreRender LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.5 Scene: LuxCore Benchmark - Acceleration: CPU Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 0.9068 1.8136 2.7204 3.6272 4.534 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 3.94 4.03 3.94 3.99 MIN: 1.47 / MAX: 4.62 MIN: 1.51 / MAX: 4.68 MIN: 1.48 / MAX: 4.61 MIN: 1.52 / MAX: 4.63
simdjson This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org GB/s, More Is Better simdjson 1.0 Throughput Test: Kostya Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 0.7223 1.4446 2.1669 2.8892 3.6115 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 3.18 3.14 3.21 3.21 -pthread -pthread 1. (CXX) g++ options: -O3
LuxCoreRender LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.5 Scene: Danish Mood - Acceleration: CPU Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 0.8303 1.6606 2.4909 3.3212 4.1515 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 3.64 3.67 3.61 3.69 MIN: 1.35 / MAX: 4.26 MIN: 1.38 / MAX: 4.29 MIN: 1.38 / MAX: 4.2 MIN: 1.43 / MAX: 4.3
Natron Natron is an open-source, cross-platform compositing software for visual effects (VFX) and motion graphics. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better Natron 2.4 Input: Spaceship Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 1.1475 2.295 3.4425 4.59 5.7375 SE +/- 0.03, N = 3 SE +/- 0.05, N = 5 SE +/- 0.07, N = 3 SE +/- 0.00, N = 3 5.0 5.1 5.1 5.1
OpenFOAM OpenFOAM is the leading free, open source software for computational fluid dynamics (CFD). Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 8 Input: Motorbike 60M Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 50 100 150 200 250 SE +/- 0.17, N = 3 SE +/- 0.38, N = 3 SE +/- 0.49, N = 3 SE +/- 0.24, N = 3 243.43 242.99 243.11 239.68 1. (CXX) g++ options: -std=c++11 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm
OSPray Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity scientific visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: San Miguel - Renderer: SciVis Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 9 18 27 36 45 SE +/- 0.00, N = 3 SE +/- 0.47, N = 3 SE +/- 0.47, N = 3 SE +/- 0.47, N = 3 37.04 37.51 37.51 37.51 MIN: 34.48 / MAX: 40 MIN: 35.71 / MAX: 40 MIN: 35.71 / MAX: 40 MIN: 34.48 / MAX: 40
Xmrig Xmrig is an open-source cross-platform CPU/GPU miner for RandomX, KawPow, CryptoNight and AstroBWT. This test profile is setup to measure the Xmlrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org H/s, More Is Better Xmrig 6.12.1 Variant: Monero - Hash Count: 1M Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 4K 8K 12K 16K 20K SE +/- 32.46, N = 3 SE +/- 22.27, N = 3 SE +/- 22.84, N = 3 SE +/- 44.27, N = 3 18153.2 18245.2 18217.5 18333.4 1. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
Sysbench This is a benchmark of Sysbench with the built-in CPU and memory sub-tests. Sysbench is a scriptable multi-threaded benchmark tool based on LuaJIT. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MiB/sec, More Is Better Sysbench 1.0.20 Test: RAM / Memory Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 2K 4K 6K 8K 10K SE +/- 1.94, N = 3 SE +/- 19.16, N = 3 SE +/- 12.34, N = 3 SE +/- 29.24, N = 3 10190.97 10283.19 10278.23 10249.84 -pthread -pthread 1. (CC) gcc options: -O2 -funroll-loops -rdynamic -ldl -laio -lm
LuxCoreRender LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.5 Scene: Orange Juice - Acceleration: CPU Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 2 4 6 8 10 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 7.03 7.03 7.05 7.09 MIN: 6.22 / MAX: 7.4 MIN: 6.25 / MAX: 7.39 MIN: 6.32 / MAX: 7.44 MIN: 6.35 / MAX: 7.47
ASTC Encoder ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 3.2 Preset: Exhaustive Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 6 12 18 24 30 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 24.21 24.08 24.06 24.05 1. (CXX) g++ options: -O3 -flto -pthread
LuxCoreRender LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.5 Scene: DLSC - Acceleration: CPU Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 1.0733 2.1466 3.2199 4.2932 5.3665 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 4.74 4.76 4.74 4.77 MIN: 4.55 / MAX: 5.03 MIN: 4.64 / MAX: 5.03 MIN: 4.6 / MAX: 5.11 MIN: 4.56 / MAX: 5.2
Xmrig Xmrig is an open-source cross-platform CPU/GPU miner for RandomX, KawPow, CryptoNight and AstroBWT. This test profile is setup to measure the Xmlrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org H/s, More Is Better Xmrig 6.12.1 Variant: Wownero - Hash Count: 1M Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 4K 8K 12K 16K 20K SE +/- 5.70, N = 3 SE +/- 11.01, N = 3 SE +/- 14.16, N = 3 SE +/- 6.03, N = 3 19031.1 19125.8 19059.6 19138.5 1. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
Blender Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL, NVIDIA OptiX, and NVIDIA CUDA is supported. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Barbershop - Compute: CPU-Only Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 50 100 150 200 250 SE +/- 0.20, N = 3 SE +/- 0.23, N = 3 SE +/- 0.51, N = 3 SE +/- 0.53, N = 3 228.67 227.98 229.14 227.94
NAMD NAMD is a parallel molecular dynamics code designed for high-performance simulation of large biomolecular systems. NAMD was developed by the Theoretical and Computational Biophysics Group in the Beckman Institute for Advanced Science and Technology at the University of Illinois at Urbana-Champaign. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org days/ns, Fewer Is Better NAMD 2.14 ATPase Simulation - 327,506 Atoms Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 0.1749 0.3498 0.5247 0.6996 0.8745 SE +/- 0.00057, N = 3 SE +/- 0.00019, N = 3 SE +/- 0.00109, N = 3 SE +/- 0.00218, N = 3 0.77668 0.77608 0.77725 0.77730
Sysbench This is a benchmark of Sysbench with the built-in CPU and memory sub-tests. Sysbench is a scriptable multi-threaded benchmark tool based on LuaJIT. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Events Per Second, More Is Better Sysbench 1.0.20 Test: CPU Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 20K 40K 60K 80K 100K SE +/- 2.43, N = 3 SE +/- 20.32, N = 3 SE +/- 5.29, N = 3 SE +/- 6.02, N = 3 114401.77 114490.11 114579.76 114562.03 -pthread -pthread 1. (CC) gcc options: -O2 -funroll-loops -rdynamic -ldl -laio -lm
Redis Redis is an open-source in-memory data structure store, used as a database, cache, and message broker. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Requests Per Second, More Is Better Redis 6.0.9 Test: SET Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 500K 1000K 1500K 2000K 2500K SE +/- 21556.91, N = 4 SE +/- 27973.62, N = 15 SE +/- 45756.31, N = 15 SE +/- 39012.54, N = 15 1771810.56 2070185.38 2148023.02 2195897.79 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Rodinia Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP Streamcluster Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 2 4 6 8 10 SE +/- 0.023, N = 3 SE +/- 0.110, N = 15 SE +/- 0.086, N = 15 SE +/- 0.032, N = 3 6.708 6.292 6.558 6.695 1. (CXX) g++ options: -O2 -lOpenCL
Geometric Mean Of All Test Results OpenBenchmarking.org Geometric Mean, More Is Better Geometric Mean Of All Test Results Result Composite - Ubuntu 21.04 LTS To Ubuntu 21.10 AMD EPYC Milan Benchmarks Ubuntu 20.04 LTS Ubuntu 21.04 Ubuntu 21.10 Ubuntu 21.10 + Linux 5.15 20 40 60 80 100 93.71 96.02 97.20 99.04
Hide Result
Ubuntu 20.04 LTS Processor: AMD EPYC 74F3 24-Core @ 3.20GHz (24 Cores / 48 Threads), Motherboard: ASRockRack ROME2D16-2T (P3.10 BIOS), Chipset: AMD Starship/Matisse, Memory: 64GB, Disk: 1000GB Western Digital WD_BLACK SN850 1TB, Graphics: ASPEED, Audio: AMD Starship/Matisse, Monitor: VE228, Network: 2 x Intel 10G X550T
OS: Ubuntu 20.04, Kernel: 5.4.0-88-generic (x86_64), Vulkan: 1.0.2, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0xa001114Java Notes: OpenJDK Runtime Environment (build 11.0.11+9-Ubuntu-0ubuntu2.20.04)Python Notes: Python 3.8.10Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 13 October 2021 11:01 by user phoronix.
Ubuntu 21.04 Processor: AMD EPYC 74F3 24-Core @ 3.20GHz (24 Cores / 48 Threads), Motherboard: ASRockRack ROME2D16-2T (P3.10 BIOS), Chipset: AMD Starship/Matisse, Memory: 64GB, Disk: 1000GB Western Digital WD_BLACK SN850 1TB, Graphics: ASPEED, Audio: AMD Starship/Matisse, Monitor: VE228, Network: 2 x Intel 10G X550T
OS: Ubuntu 21.04, Kernel: 5.11.0-37-generic (x86_64), Display Server: X Server, Vulkan: 1.0.2, Compiler: GCC 10.3.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --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 -vProcessor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001114Java Notes: OpenJDK Runtime Environment (build 11.0.11+9-Ubuntu-0ubuntu2)Python Notes: Python 3.9.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 12 October 2021 06:52 by user phoronix.
Ubuntu 21.10 Processor: AMD EPYC 74F3 24-Core @ 3.20GHz (24 Cores / 48 Threads), Motherboard: ASRockRack ROME2D16-2T (P3.10 BIOS), Chipset: AMD Starship/Matisse, Memory: 64GB, Disk: 1000GB Western Digital WD_BLACK SN850 1TB, Graphics: ASPEED, Audio: AMD Starship/Matisse, Monitor: VE228, Network: 2 x Intel 10G X550T
OS: Ubuntu 21.10, Kernel: 5.13.0-16-generic (x86_64), Desktop: GNOME Shell 40.5, Display Server: X Server, Vulkan: 1.1.182, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001114Java Notes: OpenJDK Runtime Environment (build 11.0.12+7-Ubuntu-0ubuntu3)Python Notes: Python 3.9.7Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 10 October 2021 20:29 by user phoronix.
Ubuntu 21.10 + Linux 5.15 Processor: AMD EPYC 74F3 24-Core @ 3.20GHz (24 Cores / 48 Threads), Motherboard: ASRockRack ROME2D16-2T (P3.10 BIOS), Chipset: AMD Starship/Matisse, Memory: 64GB, Disk: 1000GB Western Digital WD_BLACK SN850 1TB, Graphics: ASPEED, Audio: AMD Starship/Matisse, Monitor: VE228, Network: 2 x Intel 10G X550T
OS: Ubuntu 21.10, Kernel: 5.15.0-051500rc5daily20211011-generic (x86_64) 20211010, Desktop: GNOME Shell 40.5, Display Server: X Server, Vulkan: 1.1.182, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001114Java Notes: OpenJDK Runtime Environment (build 11.0.12+7-Ubuntu-0ubuntu3)Python Notes: Python 3.9.7Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 11 October 2021 13:34 by user phoronix.