AMD EPYC 7543 32-Core testing with a TYAN S8036GM2NE-LE (V2.00.B21 BIOS) and llvmpipe on CentOS Stream 8 via the Phoronix Test Suite.
Ubuntu 20.04.2 LTS Processor: AMD EPYC 7543 32-Core @ 2.80GHz (32 Cores / 64 Threads), Motherboard: TYAN S8036GM2NE-LE (V2.00.B21 BIOS), Chipset: AMD Starship/Matisse, Memory: 64GB, Disk: 1000GB Western Digital WD_BLACK SN850 1TB, Graphics: ASPEED, Monitor: VE228, Network: 2 x Broadcom NetXtreme BCM5720 2-port PCIe
OS: Ubuntu 20.04, Kernel: 5.8.0-55-generic (x86_64), Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.9, OpenGL: 4.5 Mesa 20.2.6 (LLVM 11.0.0 256 bits), 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: 0xa001119Python Notes: Python 3.8.5Security 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
Fedora Server 34 Processor: AMD EPYC 7543 32-Core @ 2.80GHz (32 Cores / 64 Threads), Motherboard: TYAN S8036GM2NE-LE (V2.00.B21 BIOS), Chipset: AMD Starship/Matisse, Memory: 64GB, Disk: 1000GB Western Digital WD_BLACK SN850 1TB, Graphics: ASPEED, Monitor: VE228, Network: 2 x Broadcom NetXtreme BCM5720 PCIe
OS: Fedora 34, Kernel: 5.12.11-300.fc34.x86_64 (x86_64), Compiler: GCC 11.1.1 20210531, File-System: xfs, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,fortran,objc,obj-c++,ada,go,d,lto --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=i686 --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driverProcessor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001119Python Notes: Python 3.9.5Security Notes: SELinux + 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
Debian 10.10 OS: Debian 10, Kernel: 4.19.0-17-amd64 (x86_64), Desktop: GNOME Shell 3.30.2, Display Server: X Server, Compiler: GCC 8.3.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: alwaysCompiler 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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0xa001119Python Notes: Python 2.7.16 + Python 3.7.3Security 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
Debian Bullseye Processor: AMD EPYC 7543 32-Core @ 2.80GHz (32 Cores / 64 Threads), Motherboard: TYAN S8036GM2NE-LE (V2.00.B21 BIOS), Chipset: AMD Starship/Matisse, Memory: 64GB, Disk: 1000GB Western Digital WD_BLACK SN850 1TB, Graphics: ASPEED, Monitor: VE228, Network: 2 x Broadcom NetXtreme BCM5720 2-port PCIe
OS: Debian 11, Kernel: 5.10.0-7-amd64 (x86_64), Desktop: GNOME Shell 3.38.4, Display Server: X Server, Vulkan: 1.0.2, Compiler: GCC 10.2.1 20210110, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: alwaysCompiler 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-Km9U7s/gcc-10-10.2.1/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-Km9U7s/gcc-10-10.2.1/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: 0xa001119Python Notes: Python 3.9.2Security 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
CentOS Stream Processor: AMD EPYC 7543 32-Core @ 2.80GHz (32 Cores / 64 Threads), Motherboard: TYAN S8036GM2NE-LE (V2.00.B21 BIOS), Chipset: AMD Starship/Matisse, Memory: 64GB, Disk: 1000GB Western Digital WD_BLACK SN850 1TB, Graphics: llvmpipe , Monitor: VE228, Network: 2 x Broadcom NetXtreme BCM5720 2-port PCIe
OS: CentOS Stream 8, Kernel: 4.18.0-310.el8.x86_64 (x86_64), Desktop: GNOME Shell 3.32.2, Display Server: X Server + Wayland, OpenGL: 4.5 Mesa 21.1.1 (LLVM 11.0.0 256 bits), Compiler: GCC 8.5.0 20210514, File-System: xfs, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --build=x86_64-redhat-linux --disable-libmpx --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-gcc-major-version-only --with-isl --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driverProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001119Python Notes: Python 3.6.8Security Notes: SELinux + 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
EPYC Tyan Server Processor Motherboard Chipset Memory Disk Graphics Monitor Network OS Kernel Desktop Display Server OpenGL Compiler File-System Screen Resolution Vulkan Ubuntu 20.04.2 LTS Fedora Server 34 Debian 10.10 Debian Bullseye CentOS Stream AMD EPYC 7543 32-Core @ 2.80GHz (32 Cores / 64 Threads) TYAN S8036GM2NE-LE (V2.00.B21 BIOS) AMD Starship/Matisse 64GB 1000GB Western Digital WD_BLACK SN850 1TB ASPEED VE228 2 x Broadcom NetXtreme BCM5720 2-port PCIe Ubuntu 20.04 5.8.0-55-generic (x86_64) GNOME Shell 3.36.4 X Server 1.20.9 4.5 Mesa 20.2.6 (LLVM 11.0.0 256 bits) GCC 9.3.0 ext4 1920x1080 2 x Broadcom NetXtreme BCM5720 PCIe Fedora 34 5.12.11-300.fc34.x86_64 (x86_64) GCC 11.1.1 20210531 xfs Debian 10 4.19.0-17-amd64 (x86_64) GNOME Shell 3.30.2 X Server GCC 8.3.0 ext4 2 x Broadcom NetXtreme BCM5720 2-port PCIe Debian 11 5.10.0-7-amd64 (x86_64) GNOME Shell 3.38.4 1.0.2 GCC 10.2.1 20210110 llvmpipe CentOS Stream 8 4.18.0-310.el8.x86_64 (x86_64) GNOME Shell 3.32.2 X Server + Wayland 4.5 Mesa 21.1.1 (LLVM 11.0.0 256 bits) GCC 8.5.0 20210514 xfs OpenBenchmarking.org Kernel Details - Ubuntu 20.04.2 LTS: Transparent Huge Pages: madvise - Fedora Server 34: Transparent Huge Pages: madvise - Debian 10.10: Transparent Huge Pages: always - Debian Bullseye: Transparent Huge Pages: always - CentOS Stream: Transparent Huge Pages: always Compiler Details - Ubuntu 20.04.2 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 - Fedora Server 34: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,fortran,objc,obj-c++,ada,go,d,lto --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=i686 --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver - Debian 10.10: --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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -v - Debian Bullseye: --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-Km9U7s/gcc-10-10.2.1/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-Km9U7s/gcc-10-10.2.1/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 - CentOS Stream: --build=x86_64-redhat-linux --disable-libmpx --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-gcc-major-version-only --with-isl --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver Processor Details - Ubuntu 20.04.2 LTS: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0xa001119 - Fedora Server 34: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001119 - Debian 10.10: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0xa001119 - Debian Bullseye: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001119 - CentOS Stream: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001119 Python Details - Ubuntu 20.04.2 LTS: Python 3.8.5 - Fedora Server 34: Python 3.9.5 - Debian 10.10: Python 2.7.16 + Python 3.7.3 - Debian Bullseye: Python 3.9.2 - CentOS Stream: Python 3.6.8 Security Details - Ubuntu 20.04.2 LTS: 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 - Fedora Server 34: SELinux + 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 - Debian 10.10: 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 - Debian Bullseye: 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 - CentOS Stream: SELinux + 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 20.04.2 LTS Fedora Server 34 Debian 10.10 Debian Bullseye CentOS Stream Result Overview Phoronix Test Suite 100% 170% 240% 310% NAS Parallel Benchmarks miniFE VP9 libvpx Encoding SVT-VP9 SVT-AV1 Timed LLVM Compilation Timed Node.js Compilation libavif avifenc PlaidML Timed Linux Kernel Compilation Mobile Neural Network ONNX Runtime SVT-HEVC Intel Open Image Denoise Embree OpenVKL TNN BRL-CAD OSPray Blender LuxCoreRender Kripke NAMD TensorFlow Lite
EPYC Tyan Server npb: LU.C npb: SP.C npb: FT.C npb: CG.C npb: IS.D vpxenc: Speed 5 - Bosphorus 4K svt-av1: Preset 8 - Bosphorus 4K build-wasmer: Time To Compile avifenc: 10 svt-vp9: PSNR/SSIM Optimized - Bosphorus 1080p svt-vp9: VMAF Optimized - Bosphorus 1080p numenta-nab: Bayesian Changepoint build-llvm: Unix Makefiles plaidml: No - Inference - VGG16 - CPU plaidml: No - Inference - ResNet 50 - CPU plaidml: No - Inference - VGG19 - CPU svt-vp9: Visual Quality Optimized - Bosphorus 1080p build-llvm: Ninja build-nodejs: Time To Compile mnn: inception-v3 avifenc: 10, Lossless build-linux-kernel: Time To Compile build-godot: Time To Compile mnn: SqueezeNetV1.0 mnn: squeezenetv1.1 onnx: shufflenet-v2-10 - OpenMP CPU numenta-nab: Earthgecko Skyline svt-av1: Preset 4 - Bosphorus 4K vpxenc: Speed 0 - Bosphorus 4K build-mesa: Time To Compile numenta-nab: Relative Entropy avifenc: 6, Lossless oidn: RT.ldr_alb_nrm.3840x2160 oidn: RT.hdr_alb_nrm.3840x2160 tnn: CPU - DenseNet oidn: RTLightmap.hdr.4096x4096 svt-hevc: 7 - Bosphorus 1080p numenta-nab: Windowed Gaussian xmrig: Monero - 1M tnn: CPU - MobileNet v2 xmrig: Wownero - 1M openvkl: vklBenchmark onnx: bertsquad-10 - OpenMP CPU incompact3d: input.i3d 193 Cells Per Direction gromacs: MPI CPU - water_GMX50_bare tnn: CPU - SqueezeNet v2 brl-cad: VGR Performance Metric blender: Barbershop - CPU-Only embree: Pathtracer ISPC - Crown ospray: NASA Streamlines - Path Tracer luxcorerender: LuxCore Benchmark - CPU luxcorerender: Danish Mood - CPU tensorflow-lite: Mobilenet Quant svt-hevc: 1 - Bosphorus 1080p ospray: San Miguel - Path Tracer openfoam: Motorbike 30M astcenc: Exhaustive luxcorerender: Orange Juice - CPU blender: BMW27 - CPU-Only tensorflow-lite: Inception V4 tnn: CPU - SqueezeNet v1.1 tensorflow-lite: Inception ResNet V2 ospray: XFrog Forest - Path Tracer blender: Classroom - CPU-Only nwchem: C240 Buckyball namd: ATPase Simulation - 327,506 Atoms luxcorerender: DLSC - CPU openfoam: Motorbike 60M openvino: Age Gender Recognition Retail 0013 FP32 - CPU openvino: Age Gender Recognition Retail 0013 FP32 - CPU openvino: Age Gender Recognition Retail 0013 FP16 - CPU openvino: Age Gender Recognition Retail 0013 FP16 - CPU openvino: Person Detection 0106 FP32 - CPU openvino: Person Detection 0106 FP32 - CPU openvino: Person Detection 0106 FP16 - CPU openvino: Person Detection 0106 FP16 - CPU openvino: Face Detection 0106 FP32 - CPU openvino: Face Detection 0106 FP32 - CPU openvino: Face Detection 0106 FP16 - CPU openvino: Face Detection 0106 FP16 - CPU gpaw: Carbon Nanotube kripke: numenta-nab: EXPoSE onnx: super-resolution-10 - OpenMP CPU onnx: fcn-resnet101-11 - OpenMP CPU onnx: yolov4 - OpenMP CPU mnn: mobilenet-v1-1.0 mnn: MobileNetV2_224 mnn: resnet-v2-50 mnn: mobilenetV3 tensorflow-lite: Mobilenet Float tensorflow-lite: NASNet Mobile tensorflow-lite: SqueezeNet svt-hevc: 10 - Bosphorus 1080p embree: Pathtracer ISPC - Asian Dragon ospray: Magnetic Reconnection - Path Tracer luxcorerender: Rainbow Colors and Prism - CPU minife: Small npb: MG.C npb: EP.D npb: BT.C hpcg: Ubuntu 20.04.2 LTS Fedora Server 34 Debian 10.10 Debian Bullseye CentOS Stream 102552.84 33234.28 47059.68 29891.71 1786.82 13.63 20.851 61.241 3.817 353.98 349.16 26.842 286.375 26.73 9.04 22.49 264.89 232.758 151.647 24.361 6.287 35.137 57.907 6.094 4.144 10866 76.414 1.931 6.16 22.747 13.047 30.222 0.90 0.90 2907.266 0.45 282.38 6.805 21914.9 290.337 23123.1 297 445 27.8769480 3.639 62.597 422481 195.79 33.3187 12.35 4.73 4.32 46472.9 24.65 3.72 22.24 23.6779 8.29 52.85 936694 269.182 835539 4.47 146.51 3116.9 0.67252 5.45 237.38 0.76 20458.87 0.76 20273.78 3448.71 4.58 3486.44 4.57 2551.27 6.25 2548.12 6.25 114.896 78658979 1397.776 4775 93 291 2.849 3.947 21.954 2.572 43688.4 88673.1 69192.6 458.18 37.1865 500 16.38 11203.04 49265.36 2934.26 87954.98 12.8778 21406.45 10058.28 17996.09 13587.61 1092.18 16.23 18.345 41.498 3.620 305.14 291.76 257.168 26.96 8.59 22.13 272.55 209.690 137.588 22.603 6.185 34.019 54.948 5.767 4.042 10911 1.913 6.89 27.881 0.96 0.96 3042.861 0.48 281.37 296.547 296 440 29.0366478 3.640 64.811 417781 196.64 33.3893 12.35 4.68 4.39 46557.7 24.71 3.70 23.5167 8.29 53.13 941892 271.391 837065 4.46 146.65 0.67355 5.46 78470519 4884 84 277 2.894 3.975 18.933 2.535 43885.7 111782.4 70453.9 434.07 37.3838 500 16.11 10017.79 23154.54 1601.22 20507.55 11.7130 33843.85 13.03 20.716 2.785 353.73 344.93 35.812 223.264 33.54 9.60 27.95 297.41 185.201 123.139 26.471 5.323 29.492 63.293 6.326 4.720 11064 75.368 1.852 6.05 12.321 27.237 0.87 0.87 2822.380 0.44 296.57 6.671 22334.5 286.254 23003.3 282 432 62.217 409125 192.55 32.5872 12.5 4.74 4.36 46650.1 25.19 3.73 8.33 52.44 942408 268.003 834724 4.48 146.09 0.67193 5.47 78433118 1120.730 5018 75 233 3.482 4.242 23.736 2.906 44222.9 75742.3 69846.2 537.01 32.4410 444.44 17.14 10918.40 87888.38 105456.95 33101.40 49076.24 30352.21 1731.34 9.31 14.875 60.641 2.873 259.56 256.35 250.573 33.87 9.61 27.67 236.32 202.013 134.407 27.651 5.298 32.031 53.426 6.204 4.676 11283 1.707 6.52 20.273 27.395 0.94 0.89 3098.333 0.46 273.70 23576.3 307.534 24478.3 287 424 27.7018650 3.756 62.165 420156 189.90 33.5204 12.66 4.79 4.42 46349.8 24.96 3.78 21.77 23.4605 8.39 52.55 932251 269.358 834703 4.50 145.38 3101.2 0.67131 5.45 236.58 78112133 4597 73 282 3.796 4.034 22.520 2.616 43711.5 84817.3 69107.3 429.71 37.3153 422.22 16.75 13355.4 50128.60 2965.21 89192.77 11.7941 21087.26 10303.96 18869.87 12924.77 958.16 14.89 22.402 45.007 2.817 303.00 303.33 36.140 227.741 33.59 7.59 27.92 274.02 192.197 127.498 27.519 5.188 31.134 6.776 4.355 9699 66.497 1.959 6.48 20.082 11.637 27.000 0.95 0.94 2957.066 0.47 285.20 6.293 301.637 293 427 28.6477426 3.801 62.620 406823 190.76 33.2960 12.5 4.74 4.40 47417.3 24.76 3.74 23.9299 8.25 52.25 944105 269.467 843780 4.46 146.29 0.67415 5.46 77631927 1014.364 4475 74 242 2.932 4.275 22.034 2.584 45933.1 186658 87580.8 467.20 37.2281 500 17.01 7928.40 23036.93 1006.08 21314.04 12.4586 OpenBenchmarking.org
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 CentOS Stream Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 20K 40K 60K 80K 100K SE +/- 94.10, N = 3 SE +/- 824.08, N = 3 SE +/- 42.83, N = 3 SE +/- 609.71, N = 3 21087.26 105456.95 21406.45 102552.84 -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Debian Bullseye: Open MPI 4.1.0 3. Ubuntu 20.04.2 LTS: Open MPI 4.0.3
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.C CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 7K 14K 21K 28K 35K SE +/- 5.32, N = 3 SE +/- 79.00, N = 3 SE +/- 72.73, N = 3 SE +/- 44.59, N = 3 SE +/- 59.03, N = 3 10303.96 33843.85 33101.40 10058.28 33234.28 -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Debian 10.10: Open MPI 3.1.3 3. Debian Bullseye: Open MPI 4.1.0 4. Ubuntu 20.04.2 LTS: Open MPI 4.0.3
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: FT.C CentOS Stream Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 11K 22K 33K 44K 55K SE +/- 49.69, N = 3 SE +/- 134.89, N = 3 SE +/- 43.58, N = 3 SE +/- 40.78, N = 3 18869.87 49076.24 17996.09 47059.68 -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Debian Bullseye: Open MPI 4.1.0 3. Ubuntu 20.04.2 LTS: Open MPI 4.0.3
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: CG.C CentOS Stream Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 7K 14K 21K 28K 35K SE +/- 138.23, N = 4 SE +/- 246.35, N = 3 SE +/- 10.91, N = 3 SE +/- 271.73, N = 3 12924.77 30352.21 13587.61 29891.71 -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Debian Bullseye: Open MPI 4.1.0 3. Ubuntu 20.04.2 LTS: Open MPI 4.0.3
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: IS.D CentOS Stream Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 400 800 1200 1600 2000 SE +/- 6.10, N = 3 SE +/- 10.78, N = 3 SE +/- 11.91, N = 4 SE +/- 8.29, N = 3 958.16 1731.34 1092.18 1786.82 -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Debian Bullseye: Open MPI 4.1.0 3. Ubuntu 20.04.2 LTS: Open MPI 4.0.3
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 CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 4 8 12 16 20 SE +/- 0.10, N = 15 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 SE +/- 0.13, N = 3 SE +/- 0.07, N = 3 14.89 13.03 9.31 16.23 13.63 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
SVT-AV1 This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.8.7 Encoder Mode: Preset 8 - Input: Bosphorus 4K CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 5 10 15 20 25 SE +/- 0.07, N = 3 SE +/- 0.11, N = 3 SE +/- 0.12, N = 3 SE +/- 0.11, N = 3 SE +/- 0.12, N = 3 22.40 20.72 14.88 18.35 20.85 1. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
Timed Wasmer Compilation This test times how long it takes to compile Wasmer. Wasmer is written in the Rust programming language and is a WebAssembly runtime implementation that supports WASI and EmScripten. This test profile builds Wasmer with the Cranelift and Singlepast compiler features enabled. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Timed Wasmer Compilation 1.0.2 Time To Compile CentOS Stream Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 14 28 42 56 70 SE +/- 0.63, N = 3 SE +/- 0.57, N = 3 SE +/- 0.19, N = 3 SE +/- 0.35, N = 3 45.01 60.64 41.50 61.24 1. (CC) gcc options: -m64 -pie -nodefaultlibs -ldl -lgcc_s -lutil -lrt -lpthread -lm -lc
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 CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 0.8588 1.7176 2.5764 3.4352 4.294 SE +/- 0.024, N = 15 SE +/- 0.037, N = 3 SE +/- 0.021, N = 15 SE +/- 0.030, N = 9 SE +/- 0.018, N = 3 2.817 2.785 2.873 3.620 3.817 1. (CXX) g++ options: -O3 -fPIC -lm
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: PSNR/SSIM Optimized - Input: Bosphorus 1080p CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 80 160 240 320 400 SE +/- 2.40, N = 3 SE +/- 1.49, N = 3 SE +/- 0.27, N = 3 SE +/- 2.17, N = 15 SE +/- 2.18, N = 3 303.00 353.73 259.56 305.14 353.98 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: VMAF Optimized - Input: Bosphorus 1080p CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 80 160 240 320 400 SE +/- 3.44, N = 15 SE +/- 2.58, N = 15 SE +/- 2.14, N = 3 SE +/- 1.79, N = 3 SE +/- 4.22, N = 12 303.33 344.93 256.35 291.76 349.16 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
Numenta Anomaly Benchmark Numenta Anomaly Benchmark (NAB) is a benchmark for evaluating algorithms for anomaly detection in streaming, real-time applications. It is comprised of over 50 labeled real-world and artificial timeseries data files plus a novel scoring mechanism designed for real-time applications. This test profile currently measures the time to run various detectors. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Numenta Anomaly Benchmark 1.1 Detector: Bayesian Changepoint CentOS Stream Debian 10.10 Ubuntu 20.04.2 LTS 8 16 24 32 40 SE +/- 0.23, N = 3 SE +/- 0.29, N = 3 SE +/- 0.15, N = 3 36.14 35.81 26.84
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 CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 8 16 24 32 40 SE +/- 0.27, N = 3 SE +/- 0.25, N = 3 SE +/- 0.46, N = 3 SE +/- 0.19, N = 3 SE +/- 0.23, N = 3 33.59 33.54 33.87 26.96 26.73
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 3 6 9 12 15 SE +/- 0.02, N = 3 SE +/- 0.10, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 7.59 9.60 9.61 8.59 9.04
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: VGG19 - Device: CPU CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 7 14 21 28 35 SE +/- 0.25, N = 3 SE +/- 0.32, N = 3 SE +/- 0.24, N = 3 SE +/- 0.23, N = 5 SE +/- 0.19, N = 3 27.92 27.95 27.67 22.13 22.49
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: Visual Quality Optimized - Input: Bosphorus 1080p CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 60 120 180 240 300 SE +/- 2.06, N = 3 SE +/- 2.94, N = 3 SE +/- 2.63, N = 5 SE +/- 2.18, N = 3 SE +/- 2.34, N = 3 274.02 297.41 236.32 272.55 264.89 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
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 CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 30 60 90 120 150 SE +/- 0.15, N = 3 SE +/- 0.17, N = 3 SE +/- 0.16, N = 3 SE +/- 0.21, N = 3 SE +/- 0.10, N = 3 127.50 123.14 134.41 137.59 151.65
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: inception-v3 CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 7 14 21 28 35 SE +/- 0.33, N = 3 SE +/- 0.23, N = 12 SE +/- 0.10, N = 15 SE +/- 0.14, N = 15 SE +/- 0.22, N = 5 27.52 26.47 27.65 22.60 24.36 MIN: 26.2 / MAX: 115.35 MIN: 23.92 / MAX: 128.7 MIN: 25.83 / MAX: 133.2 MIN: 21.09 / MAX: 293.57 MIN: 23.32 / MAX: 78.89 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
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, Lossless CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 2 4 6 8 10 SE +/- 0.064, N = 3 SE +/- 0.079, N = 15 SE +/- 0.015, N = 3 SE +/- 0.006, N = 3 SE +/- 0.060, N = 6 5.188 5.323 5.298 6.185 6.287 1. (CXX) g++ options: -O3 -fPIC -lm
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 Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 14 28 42 56 70 SE +/- 0.36, N = 3 SE +/- 0.17, N = 3 SE +/- 0.09, N = 3 SE +/- 0.28, N = 3 63.29 53.43 54.95 57.91
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 CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 2 4 6 8 10 SE +/- 0.088, N = 3 SE +/- 0.099, N = 12 SE +/- 0.094, N = 15 SE +/- 0.049, N = 15 SE +/- 0.096, N = 5 6.776 6.326 6.204 5.767 6.094 MIN: 6.24 / MAX: 13.86 MIN: 5.64 / MAX: 13.73 MIN: 5.43 / MAX: 24.5 MIN: 5.34 / MAX: 18.22 MIN: 5.73 / MAX: 12.28 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
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: squeezenetv1.1 CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 1.062 2.124 3.186 4.248 5.31 SE +/- 0.084, N = 3 SE +/- 0.046, N = 12 SE +/- 0.029, N = 15 SE +/- 0.035, N = 15 SE +/- 0.037, N = 5 4.355 4.720 4.676 4.042 4.144 MIN: 4.13 / MAX: 5.15 MIN: 4.17 / MAX: 23.32 MIN: 4.15 / MAX: 20.3 MIN: 3.75 / MAX: 13.49 MIN: 4.02 / MAX: 6.05 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
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 1.6 Model: shufflenet-v2-10 - Device: OpenMP CPU CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 2K 4K 6K 8K 10K SE +/- 110.43, N = 4 SE +/- 108.89, N = 3 SE +/- 51.39, N = 3 SE +/- 78.91, N = 3 SE +/- 51.37, N = 3 9699 11064 11283 10911 10866 1. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
Numenta Anomaly Benchmark Numenta Anomaly Benchmark (NAB) is a benchmark for evaluating algorithms for anomaly detection in streaming, real-time applications. It is comprised of over 50 labeled real-world and artificial timeseries data files plus a novel scoring mechanism designed for real-time applications. This test profile currently measures the time to run various detectors. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Numenta Anomaly Benchmark 1.1 Detector: Earthgecko Skyline CentOS Stream Debian 10.10 Ubuntu 20.04.2 LTS 20 40 60 80 100 SE +/- 0.57, N = 3 SE +/- 0.44, N = 3 SE +/- 0.34, N = 3 66.50 75.37 76.41
SVT-AV1 This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.8.7 Encoder Mode: Preset 4 - Input: Bosphorus 4K CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 0.4408 0.8816 1.3224 1.7632 2.204 SE +/- 0.008, N = 3 SE +/- 0.003, N = 3 SE +/- 0.005, N = 3 SE +/- 0.004, N = 3 SE +/- 0.001, N = 3 1.959 1.852 1.707 1.913 1.931 1. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
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 CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 2 4 6 8 10 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 6.48 6.05 6.52 6.89 6.16 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
Timed Mesa Compilation This test profile times how long it takes to compile Mesa with Meson/Ninja. For minimizing build dependencies and avoid versioning conflicts, test this is just the core Mesa build without LLVM or the extra Gallium3D/Mesa drivers enabled. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Timed Mesa Compilation 21.0 Time To Compile CentOS Stream Debian Bullseye Ubuntu 20.04.2 LTS 5 10 15 20 25 SE +/- 0.05, N = 3 SE +/- 0.10, N = 3 SE +/- 0.32, N = 3 20.08 20.27 22.75
Numenta Anomaly Benchmark Numenta Anomaly Benchmark (NAB) is a benchmark for evaluating algorithms for anomaly detection in streaming, real-time applications. It is comprised of over 50 labeled real-world and artificial timeseries data files plus a novel scoring mechanism designed for real-time applications. This test profile currently measures the time to run various detectors. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Numenta Anomaly Benchmark 1.1 Detector: Relative Entropy CentOS Stream Debian 10.10 Ubuntu 20.04.2 LTS 3 6 9 12 15 SE +/- 0.09, N = 3 SE +/- 0.03, N = 3 SE +/- 0.14, N = 3 11.64 12.32 13.05
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 CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 7 14 21 28 35 SE +/- 0.11, N = 3 SE +/- 0.31, N = 3 SE +/- 0.09, N = 3 SE +/- 0.02, N = 3 SE +/- 0.20, N = 3 27.00 27.24 27.40 27.88 30.22 1. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 1.4.0 Run: RT.hdr_alb_nrm.3840x2160 CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 0.216 0.432 0.648 0.864 1.08 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.94 0.87 0.89 0.96 0.90
TNN TNN is an open-source deep learning reasoning framework developed by Tencent. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: DenseNet CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 700 1400 2100 2800 3500 SE +/- 3.26, N = 3 SE +/- 3.53, N = 3 SE +/- 9.62, N = 3 SE +/- 20.85, N = 3 SE +/- 0.81, N = 3 2957.07 2822.38 3098.33 3042.86 2907.27 MIN: 2883.16 / MAX: 3348.08 MIN: 2717.84 / MAX: 3264.89 MIN: 2905.58 / MAX: 3528.68 MIN: 2872.4 / MAX: 3417.28 MIN: 2834.03 / MAX: 3318.39 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
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 CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 60 120 180 240 300 SE +/- 1.92, N = 3 SE +/- 3.39, N = 3 SE +/- 3.08, N = 4 SE +/- 2.22, N = 3 SE +/- 3.95, N = 3 285.20 296.57 273.70 281.37 282.38 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
Numenta Anomaly Benchmark Numenta Anomaly Benchmark (NAB) is a benchmark for evaluating algorithms for anomaly detection in streaming, real-time applications. It is comprised of over 50 labeled real-world and artificial timeseries data files plus a novel scoring mechanism designed for real-time applications. This test profile currently measures the time to run various detectors. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Numenta Anomaly Benchmark 1.1 Detector: Windowed Gaussian CentOS Stream Debian 10.10 Ubuntu 20.04.2 LTS 2 4 6 8 10 SE +/- 0.071, N = 3 SE +/- 0.035, N = 3 SE +/- 0.070, N = 3 6.293 6.671 6.805
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 Debian 10.10 Debian Bullseye Ubuntu 20.04.2 LTS 5K 10K 15K 20K 25K SE +/- 52.41, N = 3 SE +/- 32.24, N = 3 SE +/- 33.78, N = 3 22334.5 23576.3 21914.9 1. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
TNN TNN is an open-source deep learning reasoning framework developed by Tencent. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: MobileNet v2 CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 70 140 210 280 350 SE +/- 0.46, N = 3 SE +/- 2.75, N = 3 SE +/- 3.50, N = 4 SE +/- 2.56, N = 3 SE +/- 0.71, N = 3 301.64 286.25 307.53 296.55 290.34 MIN: 299.49 / MAX: 336.37 MIN: 280.64 / MAX: 370.21 MIN: 283.29 / MAX: 381.19 MIN: 285.14 / MAX: 355.51 MIN: 286.82 / MAX: 344.05 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
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 Debian 10.10 Debian Bullseye Ubuntu 20.04.2 LTS 5K 10K 15K 20K 25K SE +/- 79.23, N = 3 SE +/- 30.16, N = 3 SE +/- 36.32, N = 3 23003.3 24478.3 23123.1 1. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenVKL OpenVKL is the Intel Open Volume Kernel Library that offers high-performance volume computation kernels and part of the Intel oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 0.9 Benchmark: vklBenchmark CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 60 120 180 240 300 SE +/- 4.35, N = 9 SE +/- 2.31, N = 3 SE +/- 3.51, N = 3 SE +/- 1.45, N = 3 SE +/- 4.05, N = 9 293 282 287 296 297 MIN: 1 / MAX: 1453 MIN: 1 / MAX: 852 MIN: 1 / MAX: 1036 MIN: 1 / MAX: 896 MIN: 1 / MAX: 1469
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 1.6 Model: bertsquad-10 - Device: OpenMP CPU CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 100 200 300 400 500 SE +/- 4.86, N = 3 SE +/- 6.36, N = 12 SE +/- 4.24, N = 12 SE +/- 4.15, N = 12 SE +/- 3.78, N = 12 427 432 424 440 445 1. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
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 CentOS Stream Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 7 14 21 28 35 SE +/- 0.18, N = 3 SE +/- 0.20, N = 15 SE +/- 0.09, N = 3 SE +/- 0.28, N = 6 28.65 27.70 29.04 27.88 -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 1. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
GROMACS The GROMACS (GROningen MAchine for Chemical Simulations) molecular dynamics package testing with the water_GMX50 data. This test profile allows selecting between CPU and GPU-based GROMACS builds. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2021.2 Implementation: MPI CPU - Input: water_GMX50_bare CentOS Stream Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 0.8552 1.7104 2.5656 3.4208 4.276 SE +/- 0.003, N = 3 SE +/- 0.005, N = 3 SE +/- 0.007, N = 3 SE +/- 0.010, N = 3 3.801 3.756 3.640 3.639 1. (CXX) g++ options: -O3 -pthread
TNN TNN is an open-source deep learning reasoning framework developed by Tencent. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v2 CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 14 28 42 56 70 SE +/- 0.16, N = 3 SE +/- 0.67, N = 5 SE +/- 0.47, N = 3 SE +/- 0.06, N = 3 SE +/- 0.31, N = 3 62.62 62.22 62.17 64.81 62.60 MIN: 62.33 / MAX: 63.1 MIN: 60.94 / MAX: 65.02 MIN: 61.16 / MAX: 62.91 MIN: 64.62 / MAX: 65.08 MIN: 61.94 / MAX: 63.37 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
BRL-CAD BRL-CAD is a cross-platform, open-source solid modeling system with built-in benchmark mode. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org VGR Performance Metric, More Is Better BRL-CAD 7.32.2 VGR Performance Metric CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 90K 180K 270K 360K 450K 406823 409125 420156 417781 422481 1. (CXX) g++ options: -std=c++11 -pipe -fvisibility=hidden -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -pedantic -pthread -ldl -lm
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 CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 40 80 120 160 200 SE +/- 0.07, N = 3 SE +/- 0.98, N = 3 SE +/- 0.28, N = 3 SE +/- 0.29, N = 3 SE +/- 0.05, N = 3 190.76 192.55 189.90 196.64 195.79
Embree Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Crown CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 8 16 24 32 40 SE +/- 0.07, N = 3 SE +/- 0.12, N = 3 SE +/- 0.07, N = 3 SE +/- 0.05, N = 3 SE +/- 0.01, N = 3 33.30 32.59 33.52 33.39 33.32 MIN: 32.81 / MAX: 34.03 MIN: 32.08 / MAX: 33.4 MIN: 33.02 / MAX: 34.41 MIN: 32.92 / MAX: 34.19 MIN: 32.96 / MAX: 33.96
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: Path Tracer CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 3 6 9 12 15 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 12.50 12.50 12.66 12.35 12.35 MIN: 9.71 / MAX: 12.66 MIN: 9.8 / MAX: 12.66 MIN: 9.8 / MAX: 12.82 MIN: 9.26 / MAX: 12.5 MIN: 9.26 / MAX: 12.5
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 CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 1.0778 2.1556 3.2334 4.3112 5.389 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 4.74 4.74 4.79 4.68 4.73 MIN: 1.79 / MAX: 5.53 MIN: 1.76 / MAX: 5.58 MIN: 1.84 / MAX: 5.61 MIN: 1.77 / MAX: 5.48 MIN: 1.81 / MAX: 5.53
OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.5 Scene: Danish Mood - Acceleration: CPU CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 0.9945 1.989 2.9835 3.978 4.9725 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 4.40 4.36 4.42 4.39 4.32 MIN: 1.78 / MAX: 5.12 MIN: 1.73 / MAX: 5.08 MIN: 1.72 / MAX: 5.11 MIN: 1.77 / MAX: 5.1 MIN: 1.72 / MAX: 5.09
TensorFlow Lite This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Mobilenet Quant CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 10K 20K 30K 40K 50K SE +/- 461.80, N = 3 SE +/- 94.70, N = 3 SE +/- 25.57, N = 3 SE +/- 170.17, N = 3 SE +/- 88.51, N = 3 47417.3 46650.1 46349.8 46557.7 46472.9
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: 1 - Input: Bosphorus 1080p CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 6 12 18 24 30 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 SE +/- 0.08, N = 3 SE +/- 0.10, N = 3 SE +/- 0.09, N = 3 24.76 25.19 24.96 24.71 24.65 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
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: Path Tracer CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 0.8505 1.701 2.5515 3.402 4.2525 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 3.74 3.73 3.78 3.70 3.72 MIN: 3.23 / MAX: 3.79 MIN: 2.99 / MAX: 3.75 MIN: 2.73 / MAX: 3.8 MIN: 3.01 / MAX: 3.73 MIN: 2.87 / MAX: 3.75
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 Debian Bullseye Ubuntu 20.04.2 LTS 5 10 15 20 25 SE +/- 0.07, N = 3 SE +/- 0.05, N = 3 21.77 22.24 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
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 3.0 Preset: Exhaustive CentOS Stream Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 6 12 18 24 30 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 23.93 23.46 23.52 23.68 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: Orange Juice - Acceleration: CPU CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 2 4 6 8 10 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 8.25 8.33 8.39 8.29 8.29 MIN: 7.37 / MAX: 8.69 MIN: 7.33 / MAX: 8.83 MIN: 7.42 / MAX: 8.88 MIN: 7.33 / MAX: 8.74 MIN: 7.33 / MAX: 8.75
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: BMW27 - Compute: CPU-Only CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 12 24 36 48 60 SE +/- 0.07, N = 3 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 SE +/- 0.09, N = 3 SE +/- 0.06, N = 3 52.25 52.44 52.55 53.13 52.85
TensorFlow Lite This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Inception V4 CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 200K 400K 600K 800K 1000K SE +/- 4791.59, N = 3 SE +/- 4599.44, N = 3 SE +/- 1376.88, N = 3 SE +/- 6145.17, N = 3 SE +/- 2093.15, N = 3 944105 942408 932251 941892 936694
TNN TNN is an open-source deep learning reasoning framework developed by Tencent. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v1.1 CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 60 120 180 240 300 SE +/- 0.12, N = 3 SE +/- 0.36, N = 3 SE +/- 0.57, N = 3 SE +/- 0.09, N = 3 SE +/- 0.08, N = 3 269.47 268.00 269.36 271.39 269.18 MIN: 269.22 / MAX: 269.91 MIN: 267.47 / MAX: 295.77 MIN: 268.62 / MAX: 270.75 MIN: 271.08 / MAX: 271.69 MIN: 268.98 / MAX: 269.45 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
TensorFlow Lite This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Inception ResNet V2 CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 200K 400K 600K 800K 1000K SE +/- 2990.07, N = 3 SE +/- 156.42, N = 3 SE +/- 1598.54, N = 3 SE +/- 1783.60, N = 3 SE +/- 1339.58, N = 3 843780 834724 834703 837065 835539
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: XFrog Forest - Renderer: Path Tracer CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 1.0125 2.025 3.0375 4.05 5.0625 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 4.46 4.48 4.50 4.46 4.47 MIN: 4.03 / MAX: 4.5 MIN: 4.37 / MAX: 4.5 MIN: 3.82 / MAX: 4.52 MIN: 4.05 / MAX: 4.5 MIN: 4.24 / MAX: 4.5
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: Classroom - Compute: CPU-Only CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 30 60 90 120 150 SE +/- 0.15, N = 3 SE +/- 0.27, N = 3 SE +/- 0.13, N = 3 SE +/- 0.10, N = 3 SE +/- 0.13, N = 3 146.29 146.09 145.38 146.65 146.51
NWChem NWChem is an open-source high performance computational chemistry package. Per NWChem's documentation, "NWChem aims to provide its users with computational chemistry tools that are scalable both in their ability to treat large scientific computational chemistry problems efficiently, and in their use of available parallel computing resources from high-performance parallel supercomputers to conventional workstation clusters." Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better NWChem 7.0.2 Input: C240 Buckyball Debian Bullseye Ubuntu 20.04.2 LTS 700 1400 2100 2800 3500 3101.2 3116.9 -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lz 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 -lm -lcomex -m64 -ffast-math -std=legacy -fdefault-integer-8 -finline-functions -O2
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 CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 0.1517 0.3034 0.4551 0.6068 0.7585 SE +/- 0.00027, N = 3 SE +/- 0.00019, N = 3 SE +/- 0.00045, N = 3 SE +/- 0.00051, N = 3 SE +/- 0.00041, N = 3 0.67415 0.67193 0.67131 0.67355 0.67252
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 CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 1.2308 2.4616 3.6924 4.9232 6.154 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 5.46 5.47 5.45 5.46 5.45 MIN: 5.27 / MAX: 5.81 MIN: 5.25 / MAX: 5.85 MIN: 5.34 / MAX: 5.91 MIN: 5.31 / MAX: 5.8 MIN: 5.34 / MAX: 5.8
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 Debian Bullseye Ubuntu 20.04.2 LTS 50 100 150 200 250 SE +/- 0.08, N = 3 SE +/- 0.07, N = 3 236.58 237.38 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
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2021.1 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU Ubuntu 20.04.2 LTS 0.171 0.342 0.513 0.684 0.855 SE +/- 0.00, N = 3 0.76
GPAW GPAW is a density-functional theory (DFT) Python code based on the projector-augmented wave (PAW) method and the atomic simulation environment (ASE). Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better GPAW 20.1 Input: Carbon Nanotube Ubuntu 20.04.2 LTS 30 60 90 120 150 SE +/- 0.64, N = 3 114.90 1. (CC) gcc options: -pthread -shared -fwrapv -O2 -lxc -lblas -lmpi
Kripke Kripke is a simple, scalable, 3D Sn deterministic particle transport code. Its primary purpose is to research how data layout, programming paradigms and architectures effect the implementation and performance of Sn transport. Kripke is developed by LLNL. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Throughput FoM, More Is Better Kripke 1.2.4 CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 20M 40M 60M 80M 100M SE +/- 1319329.81, N = 12 SE +/- 2823751.60, N = 12 SE +/- 1339128.86, N = 12 SE +/- 2249941.31, N = 15 SE +/- 1927474.75, N = 15 77631927 78433118 78112133 78470519 78658979 1. (CXX) g++ options: -O3 -fopenmp
Numenta Anomaly Benchmark Numenta Anomaly Benchmark (NAB) is a benchmark for evaluating algorithms for anomaly detection in streaming, real-time applications. It is comprised of over 50 labeled real-world and artificial timeseries data files plus a novel scoring mechanism designed for real-time applications. This test profile currently measures the time to run various detectors. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Numenta Anomaly Benchmark 1.1 Detector: EXPoSE CentOS Stream Debian 10.10 Ubuntu 20.04.2 LTS 300 600 900 1200 1500 SE +/- 26.90, N = 9 SE +/- 6.56, N = 3 SE +/- 15.40, N = 3 1014.36 1120.73 1397.78
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 1.6 Model: super-resolution-10 - Device: OpenMP CPU CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 1100 2200 3300 4400 5500 SE +/- 55.13, N = 12 SE +/- 96.24, N = 12 SE +/- 22.65, N = 3 SE +/- 26.74, N = 3 SE +/- 34.58, N = 3 4475 5018 4597 4884 4775 1. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.6 Model: fcn-resnet101-11 - Device: OpenMP CPU CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 20 40 60 80 100 SE +/- 2.25, N = 12 SE +/- 1.93, N = 12 SE +/- 3.37, N = 9 SE +/- 3.41, N = 12 SE +/- 4.09, N = 9 74 75 73 84 93 1. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.6 Model: yolov4 - Device: OpenMP CPU CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 60 120 180 240 300 SE +/- 2.69, N = 12 SE +/- 4.62, N = 12 SE +/- 4.80, N = 9 SE +/- 1.96, N = 3 SE +/- 4.38, N = 12 242 233 282 277 291 1. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -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: mobilenet-v1-1.0 CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 0.8541 1.7082 2.5623 3.4164 4.2705 SE +/- 0.195, N = 3 SE +/- 0.086, N = 12 SE +/- 0.083, N = 15 SE +/- 0.057, N = 15 SE +/- 0.077, N = 5 2.932 3.482 3.796 2.894 2.849 MIN: 2.63 / MAX: 4.03 MIN: 2.98 / MAX: 5.1 MIN: 2.99 / MAX: 6.12 MIN: 2.55 / MAX: 7.14 MIN: 2.57 / MAX: 7.42 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
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: MobileNetV2_224 CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 0.9619 1.9238 2.8857 3.8476 4.8095 SE +/- 0.051, N = 3 SE +/- 0.072, N = 12 SE +/- 0.107, N = 15 SE +/- 0.046, N = 14 SE +/- 0.095, N = 5 4.275 4.242 4.034 3.975 3.947 MIN: 3.78 / MAX: 21.47 MIN: 3.8 / MAX: 6.21 MIN: 3.48 / MAX: 7.15 MIN: 3.37 / MAX: 43.2 MIN: 3.62 / MAX: 5.86 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
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: resnet-v2-50 CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 6 12 18 24 30 SE +/- 0.43, N = 3 SE +/- 0.28, N = 12 SE +/- 0.38, N = 15 SE +/- 0.28, N = 15 SE +/- 0.08, N = 5 22.03 23.74 22.52 18.93 21.95 MIN: 20.86 / MAX: 39.15 MIN: 22.27 / MAX: 64.14 MIN: 20.6 / MAX: 109.28 MIN: 17.69 / MAX: 159.34 MIN: 20.25 / MAX: 89.25 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
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: mobilenetV3 CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 0.6539 1.3078 1.9617 2.6156 3.2695 SE +/- 0.018, N = 3 SE +/- 0.055, N = 12 SE +/- 0.033, N = 15 SE +/- 0.029, N = 15 SE +/- 0.027, N = 5 2.584 2.906 2.616 2.535 2.572 MIN: 2.51 / MAX: 2.98 MIN: 2.52 / MAX: 6.63 MIN: 2.33 / MAX: 5.48 MIN: 2.28 / MAX: 3.47 MIN: 2.44 / MAX: 4.26 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
TensorFlow Lite This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Mobilenet Float CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 10K 20K 30K 40K 50K SE +/- 897.43, N = 13 SE +/- 96.21, N = 3 SE +/- 101.03, N = 3 SE +/- 107.46, N = 3 SE +/- 161.47, N = 3 45933.1 44222.9 43711.5 43885.7 43688.4
OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: NASNet Mobile CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 40K 80K 120K 160K 200K SE +/- 12526.20, N = 15 SE +/- 362.65, N = 3 SE +/- 2109.59, N = 15 SE +/- 3807.02, N = 15 SE +/- 1510.00, N = 15 186658.0 75742.3 84817.3 111782.4 88673.1
OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: SqueezeNet CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 20K 40K 60K 80K 100K SE +/- 2095.69, N = 15 SE +/- 372.87, N = 3 SE +/- 292.33, N = 3 SE +/- 521.49, N = 3 SE +/- 188.81, N = 3 87580.8 69846.2 69107.3 70453.9 69192.6
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 CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 120 240 360 480 600 SE +/- 12.08, N = 12 SE +/- 6.17, N = 4 SE +/- 8.24, N = 15 SE +/- 6.12, N = 15 SE +/- 12.16, N = 15 467.20 537.01 429.71 434.07 458.18 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
Embree Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Asian Dragon CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 9 18 27 36 45 SE +/- 0.10, N = 3 SE +/- 0.64, N = 15 SE +/- 0.22, N = 3 SE +/- 0.15, N = 3 SE +/- 0.26, N = 3 37.23 32.44 37.32 37.38 37.19 MIN: 36.83 / MAX: 37.88 MIN: 29.11 / MAX: 37.15 MIN: 36.86 / MAX: 38.33 MIN: 36.85 / MAX: 38.17 MIN: 36.46 / MAX: 37.99
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: Magnetic Reconnection - Renderer: Path Tracer CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 110 220 330 440 550 SE +/- 21.00, N = 15 SE +/- 22.22, N = 15 500.00 444.44 422.22 500.00 500.00 MIN: 333.33 MIN: 250 / MAX: 500 MIN: 200 / MAX: 500 MIN: 250 MIN: 250
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: Rainbow Colors and Prism - Acceleration: CPU CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 4 8 12 16 20 SE +/- 0.29, N = 15 SE +/- 0.30, N = 15 SE +/- 0.26, N = 15 SE +/- 0.10, N = 3 SE +/- 0.19, N = 15 17.01 17.14 16.75 16.11 16.38 MIN: 14.75 / MAX: 19.11 MIN: 14.81 / MAX: 19.08 MIN: 14.5 / MAX: 18.42 MIN: 14.68 / MAX: 16.32 MIN: 14.52 / MAX: 18.74
miniFE MiniFE Finite Element is an application for unstructured implicit finite element codes. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org CG Mflops, More Is Better miniFE 2.2 Problem Size: Small CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 3K 6K 9K 12K 15K SE +/- 381.69, N = 12 SE +/- 241.94, N = 15 SE +/- 374.12, N = 12 SE +/- 203.18, N = 12 SE +/- 260.75, N = 15 7928.40 10918.40 13355.40 10017.79 11203.04 1. (CXX) g++ options: -O3 -fopenmp -pthread -lmpi_cxx -lmpi
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 CentOS Stream Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 11K 22K 33K 44K 55K SE +/- 231.31, N = 15 SE +/- 60.07, N = 3 SE +/- 467.47, N = 15 SE +/- 83.51, N = 3 23036.93 50128.60 23154.54 49265.36 -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Debian Bullseye: Open MPI 4.1.0 3. Ubuntu 20.04.2 LTS: Open MPI 4.0.3
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.D CentOS Stream Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 600 1200 1800 2400 3000 SE +/- 15.88, N = 12 SE +/- 8.37, N = 3 SE +/- 28.47, N = 14 SE +/- 21.45, N = 13 1006.08 2965.21 1601.22 2934.26 -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Debian Bullseye: Open MPI 4.1.0 3. Ubuntu 20.04.2 LTS: Open MPI 4.0.3
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: BT.C CentOS Stream Debian 10.10 Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 20K 40K 60K 80K 100K SE +/- 4.57, N = 3 SE +/- 319.12, N = 3 SE +/- 44.18, N = 3 SE +/- 482.34, N = 9 SE +/- 203.96, N = 3 21314.04 87888.38 89192.77 20507.55 87954.98 -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Debian 10.10: Open MPI 3.1.3 3. Debian Bullseye: Open MPI 4.1.0 4. Ubuntu 20.04.2 LTS: Open MPI 4.0.3
High Performance Conjugate Gradient HPCG is the High Performance Conjugate Gradient and is a new scientific benchmark from Sandia National Lans focused for super-computer testing with modern real-world workloads compared to HPCC. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org GFLOP/s, More Is Better High Performance Conjugate Gradient 3.1 CentOS Stream Debian Bullseye Fedora Server 34 Ubuntu 20.04.2 LTS 3 6 9 12 15 SE +/- 0.13, N = 12 SE +/- 0.64, N = 9 SE +/- 0.60, N = 12 SE +/- 0.01, N = 3 12.46 11.79 11.71 12.88 1. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -pthread -lmpi_cxx -lmpi
Ubuntu 20.04.2 LTS Processor: AMD EPYC 7543 32-Core @ 2.80GHz (32 Cores / 64 Threads), Motherboard: TYAN S8036GM2NE-LE (V2.00.B21 BIOS), Chipset: AMD Starship/Matisse, Memory: 64GB, Disk: 1000GB Western Digital WD_BLACK SN850 1TB, Graphics: ASPEED, Monitor: VE228, Network: 2 x Broadcom NetXtreme BCM5720 2-port PCIe
OS: Ubuntu 20.04, Kernel: 5.8.0-55-generic (x86_64), Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.9, OpenGL: 4.5 Mesa 20.2.6 (LLVM 11.0.0 256 bits), 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: 0xa001119Python Notes: Python 3.8.5Security 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 20 June 2021 15:52 by user phoronix.
Fedora Server 34 Processor: AMD EPYC 7543 32-Core @ 2.80GHz (32 Cores / 64 Threads), Motherboard: TYAN S8036GM2NE-LE (V2.00.B21 BIOS), Chipset: AMD Starship/Matisse, Memory: 64GB, Disk: 1000GB Western Digital WD_BLACK SN850 1TB, Graphics: ASPEED, Monitor: VE228, Network: 2 x Broadcom NetXtreme BCM5720 PCIe
OS: Fedora 34, Kernel: 5.12.11-300.fc34.x86_64 (x86_64), Compiler: GCC 11.1.1 20210531, File-System: xfs, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,fortran,objc,obj-c++,ada,go,d,lto --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=i686 --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driverProcessor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001119Python Notes: Python 3.9.5Security Notes: SELinux + 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 21 June 2021 07:45 by user .
Debian 10.10 Processor: AMD EPYC 7543 32-Core @ 2.80GHz (32 Cores / 64 Threads), Motherboard: TYAN S8036GM2NE-LE (V2.00.B21 BIOS), Chipset: AMD Starship/Matisse, Memory: 64GB, Disk: 1000GB Western Digital WD_BLACK SN850 1TB, Graphics: ASPEED, Monitor: VE228, Network: 2 x Broadcom NetXtreme BCM5720 PCIe
OS: Debian 10, Kernel: 4.19.0-17-amd64 (x86_64), Desktop: GNOME Shell 3.30.2, Display Server: X Server, Compiler: GCC 8.3.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: alwaysCompiler 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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0xa001119Python Notes: Python 2.7.16 + Python 3.7.3Security 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 21 June 2021 20:11 by user phoronix.
Debian Bullseye Processor: AMD EPYC 7543 32-Core @ 2.80GHz (32 Cores / 64 Threads), Motherboard: TYAN S8036GM2NE-LE (V2.00.B21 BIOS), Chipset: AMD Starship/Matisse, Memory: 64GB, Disk: 1000GB Western Digital WD_BLACK SN850 1TB, Graphics: ASPEED, Monitor: VE228, Network: 2 x Broadcom NetXtreme BCM5720 2-port PCIe
OS: Debian 11, Kernel: 5.10.0-7-amd64 (x86_64), Desktop: GNOME Shell 3.38.4, Display Server: X Server, Vulkan: 1.0.2, Compiler: GCC 10.2.1 20210110, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: alwaysCompiler 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-Km9U7s/gcc-10-10.2.1/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-Km9U7s/gcc-10-10.2.1/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: 0xa001119Python Notes: Python 3.9.2Security 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 22 June 2021 06:29 by user phoronix.
CentOS Stream Processor: AMD EPYC 7543 32-Core @ 2.80GHz (32 Cores / 64 Threads), Motherboard: TYAN S8036GM2NE-LE (V2.00.B21 BIOS), Chipset: AMD Starship/Matisse, Memory: 64GB, Disk: 1000GB Western Digital WD_BLACK SN850 1TB, Graphics: llvmpipe, Monitor: VE228, Network: 2 x Broadcom NetXtreme BCM5720 2-port PCIe
OS: CentOS Stream 8, Kernel: 4.18.0-310.el8.x86_64 (x86_64), Desktop: GNOME Shell 3.32.2, Display Server: X Server + Wayland, OpenGL: 4.5 Mesa 21.1.1 (LLVM 11.0.0 256 bits), Compiler: GCC 8.5.0 20210514, File-System: xfs, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --build=x86_64-redhat-linux --disable-libmpx --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-gcc-major-version-only --with-isl --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driverProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001119Python Notes: Python 3.6.8Security Notes: SELinux + 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 22 June 2021 19:03 by user phoronix.