2 x Intel Xeon Platinum 8380 testing with a Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS) and ASPEED on Fedora 34 via the Phoronix Test Suite.
Ubuntu 21.04 Processor: 2 x Intel Xeon Platinum 8380 @ 3.40GHz (80 Cores / 160 Threads), Motherboard: Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS), Chipset: Intel Device 0998, Memory: 504GB, Disk: 800GB INTEL SSDPF21Q800GB, Graphics: ASPEED, Monitor: VE228, Network: 2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP
OS: Ubuntu 21.04, Kernel: 5.11.0-17-generic (x86_64), Desktop: GNOME Shell 3.38.4, Display Server: X Server, 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 -vDisk Notes: NONE / errors=remount-ro,relatime,rw / Block Size: 4096Processor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd000270Java Notes: OpenJDK Runtime Environment (build 11.0.11+9-Ubuntu-0ubuntu2)Python Notes: Python 3.9.4Security 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 Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Ubuntu 20.04.2 LTS OS: Ubuntu 20.04, Kernel: 5.8.0-53-generic (x86_64), Desktop: GNOME Shell 3.36.7, Display Server: X Server 1.20.9, 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 -vDisk Notes: NONE / errors=remount-ro,relatime,rw / Block Size: 4096Processor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd000270Java Notes: OpenJDK Runtime Environment (build 11.0.11+9-Ubuntu-0ubuntu2.20.04)Python 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 Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Clear Linux 34630 OS: Clear Linux OS 34630, Kernel: 5.10.19-1032.native (x86_64), Desktop: GNOME Shell 40.0, Display Server: X Server, Compiler: GCC 11.1.1 20210517 releases/gcc-11.1.0-132-g7d91dd2efb + Clang 11.1.0 + LLVM 11.1.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: alwaysEnvironment Notes: FFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -fstack-protector --param=ssp-buffer-size=32 -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z -Wl,now -Wl,-z -Wl,relro -malign-data=abi -fno-semantic-interposition -ftree-vectorize -ftree-loop-vectorize -Wl,--enable-new-dtags -Wa,-mbranches-within-32B-boundaries" CXXFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -fstack-protector --param=ssp-buffer-size=32 -Wformat -Wformat-security -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z -Wl,now -Wl,-z -Wl,relro -fno-semantic-interposition -ffat-lto-objects -fno-trapping-math -Wl,-sort-common -Wl,--enable-new-dtags -mtune=skylake -Wa,-mbranches-within-32B-boundaries -fvisibility-inlines-hidden -Wl,--enable-new-dtags" FCFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -fstack-protector --param=ssp-buffer-size=32 -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z -Wl,now -Wl,-z -Wl,relro -malign-data=abi -fno-semantic-interposition -ftree-vectorize -ftree-loop-vectorize -Wl,-sort-common -Wl,--enable-new-dtags" CFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -fstack-protector --param=ssp-buffer-size=32 -Wformat -Wformat-security -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z -Wl,now -Wl,-z -Wl,relro -fno-semantic-interposition -ffat-lto-objects -fno-trapping-math -Wl,-sort-common -Wl,--enable-new-dtags -mtune=skylake -Wa,-mbranches-within-32B-boundaries" THEANO_FLAGS="floatX=float32,openmp=true,gcc.cxxflags="-ftree-vectorize -mavx""Compiler Notes: --build=x86_64-generic-linux --disable-libmpx --disable-libunwind-exceptions --disable-multiarch --disable-vtable-verify --disable-werror --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-clocale=gnu --enable-default-pie --enable-gnu-indirect-function --enable-languages=c,c++,fortran,go --enable-ld=default --enable-libstdcxx-pch --enable-lto --enable-multilib --enable-plugin --enable-shared --enable-threads=posix --exec-prefix=/usr --includedir=/usr/include --target=x86_64-generic-linux --with-arch=westmere --with-gcc-major-version-only --with-glibc-version=2.19 --with-gnu-ld --with-isl --with-ppl=yes --with-tune=skylake-avx512Disk Notes: MQ-DEADLINE / relatime,rw,stripe=256 / Block Size: 4096Processor Notes: Scaling Governor: intel_pstate performance - CPU Microcode: 0xd000270Java Notes: OpenJDK Runtime Environment (build 1.8.0-u252-ga-b00)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 Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Fedora Server 34 OS: Fedora 34, Kernel: 5.11.20-300.fc34.x86_64 (x86_64), Compiler: GCC 11.1.1 20210428, 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-driverDisk Notes: NONE / attr2,inode64,logbsize=32k,logbufs=8,noquota,relatime,rw,seclabel / Block Size: 4096Processor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd000270Java Notes: OpenJDK Runtime Environment 18.9 (build 11.0.11+9)Python 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 Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Ice Lake Ubuntu 20.04.2 / 20.10 / 21.04 Linux Benchmarks Processor Motherboard Chipset Memory Disk Graphics Monitor Network OS Kernel Desktop Display Server Compiler File-System Screen Resolution Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 2 x Intel Xeon Platinum 8380 @ 3.40GHz (80 Cores / 160 Threads) Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS) Intel Device 0998 504GB 800GB INTEL SSDPF21Q800GB ASPEED VE228 2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP Ubuntu 21.04 5.11.0-17-generic (x86_64) GNOME Shell 3.38.4 X Server GCC 10.3.0 ext4 1920x1080 Ubuntu 20.04 5.8.0-53-generic (x86_64) GNOME Shell 3.36.7 X Server 1.20.9 GCC 9.3.0 Clear Linux OS 34630 5.10.19-1032.native (x86_64) GNOME Shell 40.0 X Server GCC 11.1.1 20210517 releases/gcc-11.1.0-132-g7d91dd2efb + Clang 11.1.0 + LLVM 11.1.0 Fedora 34 5.11.20-300.fc34.x86_64 (x86_64) GCC 11.1.1 20210428 xfs OpenBenchmarking.org Kernel Details - Ubuntu 21.04: Transparent Huge Pages: madvise - Ubuntu 20.04.2 LTS: Transparent Huge Pages: madvise - Clear Linux 34630: Transparent Huge Pages: always - Fedora Server 34: Transparent Huge Pages: madvise Compiler Details - Ubuntu 21.04: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Ubuntu 20.04.2 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 - Clear Linux 34630: --build=x86_64-generic-linux --disable-libmpx --disable-libunwind-exceptions --disable-multiarch --disable-vtable-verify --disable-werror --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-clocale=gnu --enable-default-pie --enable-gnu-indirect-function --enable-languages=c,c++,fortran,go --enable-ld=default --enable-libstdcxx-pch --enable-lto --enable-multilib --enable-plugin --enable-shared --enable-threads=posix --exec-prefix=/usr --includedir=/usr/include --target=x86_64-generic-linux --with-arch=westmere --with-gcc-major-version-only --with-glibc-version=2.19 --with-gnu-ld --with-isl --with-ppl=yes --with-tune=skylake-avx512 - 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 Disk Details - Ubuntu 21.04: NONE / errors=remount-ro,relatime,rw / Block Size: 4096 - Ubuntu 20.04.2 LTS: NONE / errors=remount-ro,relatime,rw / Block Size: 4096 - Clear Linux 34630: MQ-DEADLINE / relatime,rw,stripe=256 / Block Size: 4096 - Fedora Server 34: NONE / attr2,inode64,logbsize=32k,logbufs=8,noquota,relatime,rw,seclabel / Block Size: 4096 Processor Details - Ubuntu 21.04: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd000270 - Ubuntu 20.04.2 LTS: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd000270 - Clear Linux 34630: Scaling Governor: intel_pstate performance - CPU Microcode: 0xd000270 - Fedora Server 34: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd000270 Java Details - Ubuntu 21.04: OpenJDK Runtime Environment (build 11.0.11+9-Ubuntu-0ubuntu2) - Ubuntu 20.04.2 LTS: OpenJDK Runtime Environment (build 11.0.11+9-Ubuntu-0ubuntu2.20.04) - Clear Linux 34630: OpenJDK Runtime Environment (build 1.8.0-u252-ga-b00) - Fedora Server 34: OpenJDK Runtime Environment 18.9 (build 11.0.11+9) Python Details - Ubuntu 21.04: Python 3.9.4 - Ubuntu 20.04.2 LTS: Python 3.8.5 - Clear Linux 34630: Python 3.9.5 - Fedora Server 34: Python 3.9.5 Security Details - Ubuntu 21.04: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected - 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 Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected - Clear Linux 34630: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected - 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 Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected Environment Details - Clear Linux 34630: FFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -fstack-protector --param=ssp-buffer-size=32 -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z -Wl,now -Wl,-z -Wl,relro -malign-data=abi -fno-semantic-interposition -ftree-vectorize -ftree-loop-vectorize -Wl,--enable-new-dtags -Wa,-mbranches-within-32B-boundaries" CXXFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -fstack-protector --param=ssp-buffer-size=32 -Wformat -Wformat-security -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z -Wl,now -Wl,-z -Wl,relro -fno-semantic-interposition -ffat-lto-objects -fno-trapping-math -Wl,-sort-common -Wl,--enable-new-dtags -mtune=skylake -Wa,-mbranches-within-32B-boundaries -fvisibility-inlines-hidden -Wl,--enable-new-dtags" FCFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -fstack-protector --param=ssp-buffer-size=32 -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z -Wl,now -Wl,-z -Wl,relro -malign-data=abi -fno-semantic-interposition -ftree-vectorize -ftree-loop-vectorize -Wl,-sort-common -Wl,--enable-new-dtags" CFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -fstack-protector --param=ssp-buffer-size=32 -Wformat -Wformat-security -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z -Wl,now -Wl,-z -Wl,relro -fno-semantic-interposition -ffat-lto-objects -fno-trapping-math -Wl,-sort-common -Wl,--enable-new-dtags -mtune=skylake -Wa,-mbranches-within-32B-boundaries" THEANO_FLAGS="floatX=float32,openmp=true,gcc.cxxflags="-ftree-vectorize -mavx""
Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 Result Overview Phoronix Test Suite 100% 162% 224% 285% 347% NAS Parallel Benchmarks Apache Cassandra libgav1 x265 Kvazaar DaCapo Benchmark SVT-VP9 SVT-AV1 PJSIP SVT-HEVC Timed Apache Compilation libavif avifenc Tungsten Renderer Timed PHP Compilation Timed Linux Kernel Compilation Java Gradle Build PHPBench Liquid-DSP Node.js V8 Web Tooling Benchmark OpenVKL Intel Open Image Denoise PyBench Rodinia LAMMPS Molecular Dynamics Simulator BlogBench Xcompact3d Incompact3d TNN PostgreSQL pgbench oneDNN GROMACS Coremark Zstd Compression Timed MrBayes Analysis Embree OSPray Stockfish POV-Ray Chia Blockchain VDF Helsing Blender RELION asmFish High Performance Conjugate Gradient SecureMark Sysbench NAMD TensorFlow Lite
Ice Lake Ubuntu 20.04.2 / 20.10 / 21.04 Linux Benchmarks blogbench: Read java-gradle-perf: Reactor openvkl: vklBenchmarkUnstructuredVolume nwchem: C240 Buckyball openvkl: vklBenchmark relion: Basic - CPU cassandra: Writes incompact3d: X3D-benchmarking input.i3d securemark: SecureMark-TLS asmfish: 1024 Hash Memory, 26 Depth lammps: 20k Atoms tensorflow-lite: Mobilenet Quant compress-zstd: 8 - Decompression Speed compress-zstd: 3 - Decompression Speed hpcg: tensorflow-lite: NASNet Mobile tensorflow-lite: Mobilenet Float mrbayes: Primate Phylogeny Analysis keydb: helsing: 14 digit rodinia: OpenMP Leukocyte libgav1: Summer Nature 4K node-web-tooling: onednn: Recurrent Neural Network Training - bf16bf16bf16 - CPU onednn: Recurrent Neural Network Training - u8s8f32 - CPU compress-zstd: 8 - Compression Speed pjsip: INVITE compress-zstd: 19, Long Mode - Decompression Speed compress-zstd: 19, Long Mode - Compression Speed compress-zstd: 19, Long Mode - Compression Speed compress-zstd: 19 - Compression Speed pgbench: 100 - 250 - Read Only - Average Latency pgbench: 100 - 250 - Read Only tensorflow-lite: SqueezeNet compress-zstd: 19 - Decompression Speed blender: Barbershop - CPU-Only onednn: Recurrent Neural Network Training - f32 - CPU rodinia: OpenMP HotSpot3D onednn: Deconvolution Batch shapes_1d - f32 - CPU build-linux-kernel: Time To Compile sysbench: CPU blender: Pabellon Barcelona - CPU-Only compress-zstd: 3 - Compression Speed tnn: CPU - MobileNet v2 dacapobench: H2 stockfish: Total Time onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPU onednn: Recurrent Neural Network Inference - f32 - CPU onednn: Recurrent Neural Network Inference - u8s8f32 - CPU kvazaar: Bosphorus 4K - Medium blender: Classroom - CPU-Only tensorflow-lite: Inception V4 openvkl: vklBenchmarkVdbVolume tungsten: Volumetric Caustic pjsip: OPTIONS, Stateful x265: Bosphorus 4K tensorflow-lite: Inception ResNet V2 svt-av1: Preset 8 - Bosphorus 4K pjsip: OPTIONS, Stateless avifenc: 6 blender: Fishy Cat - CPU-Only compress-zstd: 19 - Decompression Speed compress-zstd: 19 - Compression Speed ospray: San Miguel - Path Tracer compress-zstd: 19, Long Mode - Decompression Speed rodinia: OpenMP LavaMD onednn: IP Shapes 1D - bf16bf16bf16 - CPU chia-vdf: Square Assembly Optimized dacapobench: Jython build-php: Time To Compile tungsten: Water Caustic kvazaar: Bosphorus 4K - Very Fast coremark: CoreMark Size 666 - Iterations Per Second chia-vdf: Square Plain C++ avifenc: 6, Lossless sysbench: RAM / Memory namd: ATPase Simulation - 327,506 Atoms build-apache: Time To Compile avifenc: 10, Lossless kvazaar: Bosphorus 4K - Ultra Fast dacapobench: Tradebeans gromacs: MPI CPU - water_GMX50_bare blender: BMW27 - CPU-Only ospray: San Miguel - SciVis phpbench: PHP Benchmark Suite tnn: CPU - SqueezeNet v1.1 ospray: XFrog Forest - Path Tracer onednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU pybench: Total For Average Test Times avifenc: 10 svt-hevc: 1 - Bosphorus 1080p onednn: Deconvolution Batch shapes_1d - bf16bf16bf16 - CPU onednn: Deconvolution Batch shapes_1d - u8s8f32 - CPU npb: LU.C liquid-dsp: 160 - 256 - 57 liquid-dsp: 128 - 256 - 57 liquid-dsp: 32 - 256 - 57 liquid-dsp: 16 - 256 - 57 x265: Bosphorus 1080p onednn: IP Shapes 3D - bf16bf16bf16 - CPU onednn: IP Shapes 1D - f32 - CPU ospray: XFrog Forest - SciVis tungsten: Hair ospray: Magnetic Reconnection - SciVis povray: Trace Time oidn: Memorial onednn: Matrix Multiply Batch Shapes Transformer - f32 - CPU embree: Pathtracer - Asian Dragon embree: Pathtracer ISPC - Asian Dragon incompact3d: input.i3d 193 Cells Per Direction onednn: Matrix Multiply Batch Shapes Transformer - bf16bf16bf16 - CPU onednn: Deconvolution Batch shapes_3d - u8s8f32 - CPU svt-vp9: PSNR/SSIM Optimized - Bosphorus 1080p embree: Pathtracer ISPC - Crown ospray: NASA Streamlines - Path Tracer npb: EP.C onednn: IP Shapes 3D - f32 - CPU svt-hevc: 7 - Bosphorus 1080p svt-hevc: 10 - Bosphorus 1080p onednn: Convolution Batch Shapes Auto - f32 - CPU onednn: Convolution Batch Shapes Auto - bf16bf16bf16 - CPU onednn: Deconvolution Batch shapes_3d - f32 - CPU lammps: Rhodopsin Protein tungsten: Non-Exponential ospray: NASA Streamlines - SciVis blogbench: Write Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 2253810 366.363 1776457 1875.8 669 348.838 106863 291.993968 230272 172711481 35.725 43074.5 39.8231 81319.3 41555.1 170.019 524178.09 82.465 62.044 19.39 10.79 671.541 684.271 2096.7 2531 2719.4 47.2 46.0 82.2 0.266 946634 47808.3 108.31 672.646 105.650 28.7517 24.813 213870.87 88.36 6148.4 443.547 10740 180493580 437.972 437.866 439.677 6.90 72.28 687019 21915837 13.4481 3815 12.92 569303 29.809 40082 15.383 45.72 2727.6 82.3 10.42 40.406 3.03516 147240 5320 40.207 31.2739 13.38 2347453.567360 138967 36.764 12176.80 0.27128 35.187 8.522 22.78 16729 9.004 29.61 90.91 715587 366.729 10.38 0.231483 995 5.050 29.57 3.27051 0.362841 187807.08 3080633333 3290766667 1631166667 826756667 28.33 1.82051 0.945450 18.87 6.52538 109.63 9.476 57.59 0.256555 81.2911 106.6858 11.3305505 0.615331 0.193198 204.86 67.0395 27.78 6259.88 1.37903 172.02 260.88 1.41084 2.10597 0.846330 23.866 5.23912 125 60768 2224145 382.988 1737714 1825 661 348.604 103051 319.487874 225195 171613950 36.300 46915.5 39.9669 90927.9 45998.8 178.773 421171.59 82.638 60.933 19.31 10.94 678.041 667.646 2128.7 1840 2782.7 43.6 44.8 83.0 0.263 954214 48816.5 109.07 671.557 104.315 32.6500 25.960 214228.62 88.16 4620.1 374.203 11235 173250319 433.426 431.304 433.741 6.93 71.92 716517 22077090 13.8745 3597 12.58 576988 28.139 40954 15.501 46.11 2740.7 84.0 10.42 39.522 3.01186 143600 5518 40.723 32.4833 13.33 2261054.029261 139400 38.524 12252.73 0.27083 35.987 8.967 23.16 18060 8.884 29.54 90.91 726623 367.799 10.38 0.218363 982 5.361 29.14 3.47588 0.353757 189606.14 3106666667 3316633333 1653866667 832983333 28.50 1.80328 0.942653 18.87 6.45646 110.19 9.451 49.87 0.249170 82.6069 106.1435 11.7113234 0.602936 0.190921 196.97 66.8866 27.78 6011.42 1.37432 157.78 234.92 1.39626 2.10694 0.850400 22.084 5.16631 125 63062 1908438 301.413 1828816 2209.4 815 358.316 312015 289.551473 229770 174596848 35.632 33677.2 39.4821 74734.9 32984.6 175.476 503991.58 79.118 40.815 54.59 13.06 660.198 663.896 2656.6 5296 2447.0 49.2 47.5 88.0 0.254 990608 46761.2 102.25 660.052 104.278 9.79872 20.736 212303.58 86.83 7166.7 354.298 4132 182083926 433.798 434.954 433.432 17.80 71.51 665666 29605565 13.8659 10360 29.05 572684 60.273 43880 10.237 43.83 2253.6 90.1 10.60 38.693 2.98572 151167 3590 31.104 18.1712 40.96 2452833.360945 143567 27.246 12670.82 0.27141 22.241 5.815 46.98 4282 9.201 28.23 100 900184 364.987 10.38 0.216048 1015 3.066 38.51 3.22981 0.361521 194386.02 3843066667 3970066667 1973100000 999833333 78.42 1.74481 0.921930 18.87 5.62201 125 8.952 59.98 0.247725 84.1301 107.7726 11.1637303 0.614468 0.188906 456.47 73.8370 28.57 5425.40 1.35679 315.80 592.99 1.58077 2.08771 0.862061 31.153 2.40790 142.86 56009 1979099 354.027 1813549 667 362.129 108941 323.879079 228894 168644528 35.586 41946.1 3118.5 3057.5 40.3877 80554.7 38365.8 167.322 79.610 62.211 19.00 11.04 676.539 679.936 2069.1 2491 2793.4 45.7 45.9 82.1 0.284 886858 47685.7 2698.6 108.27 677.855 104.766 30.7498 26.506 212714.19 88.89 6020.4 401.860 10878 183504987 440.632 442.350 442.700 6.95 73.35 679005 22243396 13.0865 3733 11.65 574742 28.370 41983 16.077 46.04 2781.7 82.5 10.42 2747.1 41.476 3.04815 148033 5088 42.735 31.4451 13.28 2391445.662566 131833 36.684 12185.51 0.27274 37.532 9.332 23.20 16983 8.428 29.55 90.91 721179 366.368 10.31 0.222234 1157 5.186 29.17 3.28960 0.367996 44055.39 3101166667 3302800000 1632900000 827833333 26.25 1.84199 0.957911 18.87 8.74867 109.63 9.089 54.83 0.254526 81.5024 106.0534 12.5811322 0.612234 0.203496 195.55 64.6630 27.78 2213.51 1.51260 159.70 240.54 1.88136 2.11134 0.854642 27.205 5.28732 125 52018 OpenBenchmarking.org
BlogBench BlogBench is designed to replicate the load of a real-world busy file server by stressing the file-system with multiple threads of random reads, writes, and rewrites. The behavior is mimicked of that of a blog by creating blogs with content and pictures, modifying blog posts, adding comments to these blogs, and then reading the content of the blogs. All of these blogs generated are created locally with fake content and pictures. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Final Score, More Is Better BlogBench 1.1 Test: Read Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 500K 1000K 1500K 2000K 2500K SE +/- 30037.66, N = 3 SE +/- 21799.22, N = 9 SE +/- 12916.51, N = 3 SE +/- 22175.10, N = 9 2253810 2224145 1908438 1979099 -O2 -O2 -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -O2 1. (CC) gcc options: -pthread
Java Gradle Build This test runs Java software project builds using the Gradle build system. It is intended to give developers an idea as to the build performance for development activities and build servers. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Java Gradle Build Gradle Build: Reactor Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 80 160 240 320 400 SE +/- 5.06, N = 9 SE +/- 10.71, N = 9 SE +/- 8.63, N = 6 SE +/- 8.29, N = 7 366.36 382.99 301.41 354.03
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: vklBenchmarkUnstructuredVolume Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 400K 800K 1200K 1600K 2000K SE +/- 7183.20, N = 3 SE +/- 17974.50, N = 3 SE +/- 13533.55, N = 3 SE +/- 7558.12, N = 3 1776457 1737714 1828816 1813549 MIN: 24424 / MAX: 5906521 MIN: 21419 / MAX: 5849413 MIN: 25882 / MAX: 5901670 MIN: 19659 / MAX: 5912498
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 Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 500 1000 1500 2000 2500 1875.8 1825.0 2209.4 -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
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 Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 200 400 600 800 1000 SE +/- 2.40, N = 3 SE +/- 5.81, N = 3 SE +/- 2.08, N = 3 SE +/- 2.67, N = 3 669 661 815 667 MIN: 1 / MAX: 2821 MIN: 1 / MAX: 2845 MIN: 1 / MAX: 3198 MIN: 1 / MAX: 2865
RELION RELION - REgularised LIkelihood OptimisatioN - is a stand-alone computer program for Maximum A Posteriori refinement of (multiple) 3D reconstructions or 2D class averages in cryo-electron microscopy (cryo-EM). It is developed in the research group of Sjors Scheres at the MRC Laboratory of Molecular Biology. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better RELION 3.1.1 Test: Basic - Device: CPU Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 80 160 240 320 400 SE +/- 1.61, N = 3 SE +/- 0.74, N = 3 SE +/- 0.17, N = 3 SE +/- 0.25, N = 3 348.84 348.60 358.32 362.13 -O3 -lmpi_cxx -O3 -lmpi_cxx -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -O2 -lmpi_cxx 1. (CXX) g++ options: -fopenmp -std=c++0x -rdynamic -ldl -ltiff -lfftw3f -lfftw3 -lpng -pthread -lmpi
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: X3D-benchmarking input.i3d Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 70 140 210 280 350 SE +/- 1.18, N = 3 SE +/- 3.10, N = 3 SE +/- 0.46, N = 3 SE +/- 0.15, N = 3 291.99 319.49 289.55 323.88 -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
SecureMark SecureMark is an objective, standardized benchmarking framework for measuring the efficiency of cryptographic processing solutions developed by EEMBC. SecureMark-TLS is benchmarking Transport Layer Security performance with a focus on IoT/edge computing. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org marks, More Is Better SecureMark 1.0.4 Benchmark: SecureMark-TLS Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 50K 100K 150K 200K 250K SE +/- 178.37, N = 3 SE +/- 124.15, N = 3 SE +/- 121.72, N = 3 SE +/- 359.29, N = 3 230272 225195 229770 228894 1. (CC) gcc options: -pedantic -O3
LAMMPS Molecular Dynamics Simulator LAMMPS is a classical molecular dynamics code, and an acronym for Large-scale Atomic/Molecular Massively Parallel Simulator. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ns/day, More Is Better LAMMPS Molecular Dynamics Simulator 29Oct2020 Model: 20k Atoms Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 8 16 24 32 40 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 35.73 36.30 35.63 35.59 -O3 -O3 -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -O2 1. (CXX) g++ options: -pthread -lm
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 Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 10K 20K 30K 40K 50K SE +/- 601.06, N = 15 SE +/- 706.39, N = 15 SE +/- 60.78, N = 3 SE +/- 623.47, N = 13 43074.5 46915.5 33677.2 41946.1
Zstd Compression This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 8 - Decompression Speed Fedora Server 34 700 1400 2100 2800 3500 SE +/- 8.89, N = 14 3118.5 1. (CC) gcc options: -O3 -pthread -lz -llzma
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 Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 9 18 27 36 45 SE +/- 0.03, N = 3 SE +/- 0.19, N = 3 SE +/- 0.01, N = 3 SE +/- 0.08, N = 3 39.82 39.97 39.48 40.39 -lmpi_cxx -lmpi_cxx -lmpi_cxx 1. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -pthread -lmpi
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: NASNet Mobile Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 20K 40K 60K 80K 100K SE +/- 768.19, N = 15 SE +/- 1128.79, N = 4 SE +/- 102.89, N = 3 SE +/- 755.90, N = 15 81319.3 90927.9 74734.9 80554.7
OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Mobilenet Float Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 10K 20K 30K 40K 50K SE +/- 612.15, N = 15 SE +/- 630.61, N = 15 SE +/- 68.45, N = 3 SE +/- 353.50, N = 3 41555.1 45998.8 32984.6 38365.8
Timed MrBayes Analysis This test performs a bayesian analysis of a set of primate genome sequences in order to estimate their phylogeny. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Timed MrBayes Analysis 3.2.7 Primate Phylogeny Analysis Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 40 80 120 160 200 SE +/- 0.83, N = 3 SE +/- 0.79, N = 3 SE +/- 1.06, N = 3 SE +/- 0.50, N = 3 170.02 178.77 175.48 167.32 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake 1. (CC) gcc options: -mmmx -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msha -maes -mavx -mfma -mavx2 -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi -mrdrnd -mbmi -mbmi2 -madx -mabm -O3 -std=c99 -pedantic -lm
KeyDB A benchmark of KeyDB as a multi-threaded fork of the Redis server. The KeyDB benchmark is conducted using memtier-benchmark. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Ops/sec, More Is Better KeyDB 6.0.16 Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 110K 220K 330K 440K 550K SE +/- 4128.37, N = 3 SE +/- 18099.02, N = 15 SE +/- 2367.62, N = 3 524178.09 421171.59 503991.58 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Helsing Helsing is an open-source POSIX vampire number generator. This test profile measures the time it takes to generate vampire numbers between varying numbers of digits. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Helsing 1.0-beta Digit Range: 14 digit Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 20 40 60 80 100 SE +/- 0.73, N = 15 SE +/- 0.11, N = 3 SE +/- 0.09, N = 3 SE +/- 0.15, N = 3 82.47 82.64 79.12 79.61 1. (CC) gcc options: -O2 -pthread
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 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 14 28 42 56 70 SE +/- 0.67, N = 3 SE +/- 1.30, N = 15 SE +/- 0.36, N = 15 SE +/- 0.49, N = 3 62.04 60.93 40.82 62.21 1. (CXX) g++ options: -O2 -lOpenCL
libgav1 Libgav1 is an AV1 decoder developed by Google for AV1 profile 0/1 compliance. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better libgav1 0.16.3 Video Input: Summer Nature 4K Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 12 24 36 48 60 SE +/- 0.15, N = 3 SE +/- 0.07, N = 3 SE +/- 0.06, N = 3 SE +/- 0.14, N = 3 19.39 19.31 54.59 19.00 -O3 -O3 -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -O2 1. (CXX) g++ options: -lpthread -lrt
Node.js V8 Web Tooling Benchmark Running the V8 project's Web-Tooling-Benchmark under Node.js. The Web-Tooling-Benchmark stresses JavaScript-related workloads common to web developers like Babel and TypeScript and Babylon. This test profile can test the system's JavaScript performance with Node.js. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org runs/s, More Is Better Node.js V8 Web Tooling Benchmark Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 3 6 9 12 15 SE +/- 0.07, N = 3 SE +/- 0.12, N = 15 SE +/- 0.01, N = 3 SE +/- 0.08, N = 3 10.79 10.94 13.06 11.04 1. Ubuntu 21.04: Nodejs
v12.21.0 2. Ubuntu 20.04.2 LTS: Nodejs
v10.19.0 3. Clear Linux 34630: Nodejs
v14.17.0 4. Fedora Server 34: Nodejs
v14.16.1
oneDNN This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 150 300 450 600 750 SE +/- 0.16, N = 3 SE +/- 4.59, N = 15 SE +/- 0.41, N = 3 SE +/- 0.57, N = 3 671.54 678.04 660.20 676.54 MIN: 647.67 MIN: 638.98 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 628.82 -O2 - MIN: 652.01 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 150 300 450 600 750 SE +/- 5.64, N = 15 SE +/- 1.50, N = 3 SE +/- 3.59, N = 3 SE +/- 2.47, N = 3 684.27 667.65 663.90 679.94 MIN: 645.4 MIN: 642.94 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 627.72 -O2 - MIN: 650 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
Zstd Compression This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 8 - Compression Speed Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 600 1200 1800 2400 3000 SE +/- 24.65, N = 3 SE +/- 25.03, N = 15 SE +/- 58.63, N = 12 SE +/- 30.33, N = 15 2096.7 2128.7 2656.6 2069.1 -llzma -llzma -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -llzma 1. (CC) gcc options: -O3 -pthread -lz
PJSIP PJSIP is a free and open source multimedia communication library written in C language implementing standard based protocols such as SIP, SDP, RTP, STUN, TURN, and ICE. It combines signaling protocol (SIP) with rich multimedia framework and NAT traversal functionality into high level API that is portable and suitable for almost any type of systems ranging from desktops, embedded systems, to mobile handsets. This test profile is making use of pjsip-perf with both the client/server on teh system. More details on the PJSIP benchmark at https://www.pjsip.org/high-performance-sip.htm Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Responses Per Second, More Is Better PJSIP 2.11 Method: INVITE Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 1100 2200 3300 4400 5500 SE +/- 22.31, N = 15 SE +/- 14.31, N = 3 SE +/- 20.58, N = 3 SE +/- 27.76, N = 5 2531 1840 5296 2491 -lSDL2 -lavformat -lavcodec -lswscale -lavutil -lasound -O2 -lSDL2 -lavformat -lavcodec -lswscale -lavutil -lasound -O2 -lSDL2 -lopus -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -O2 1. (CC) gcc options: -lstdc++ -lssl -lcrypto -luuid -lm -lrt -lpthread
Zstd Compression This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 19, Long Mode - Decompression Speed Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 600 1200 1800 2400 3000 SE +/- 1.06, N = 3 SE +/- 5.43, N = 15 SE +/- 7.42, N = 3 SE +/- 3.95, N = 15 2719.4 2782.7 2447.0 2793.4 -llzma -llzma -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -llzma 1. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 19, Long Mode - Compression Speed Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 11 22 33 44 55 SE +/- 0.33, N = 3 SE +/- 0.39, N = 15 SE +/- 0.18, N = 3 SE +/- 0.35, N = 15 47.2 43.6 49.2 45.7 -llzma -llzma -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -llzma 1. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19, Long Mode - Compression Speed Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 11 22 33 44 55 SE +/- 0.54, N = 15 SE +/- 0.61, N = 15 SE +/- 0.64, N = 3 SE +/- 0.55, N = 3 46.0 44.8 47.5 45.9 -llzma -llzma -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -llzma 1. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19 - Compression Speed Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 20 40 60 80 100 SE +/- 1.03, N = 15 SE +/- 0.70, N = 8 SE +/- 0.66, N = 3 SE +/- 0.74, N = 7 82.2 83.0 88.0 82.1 -llzma -llzma -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -llzma 1. (CC) gcc options: -O3 -pthread -lz
PostgreSQL pgbench This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average Latency Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 0.0639 0.1278 0.1917 0.2556 0.3195 SE +/- 0.003, N = 15 SE +/- 0.003, N = 4 SE +/- 0.005, N = 15 SE +/- 0.006, N = 13 0.266 0.263 0.254 0.284 -O2 -O2 -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -O2 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Only Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 200K 400K 600K 800K 1000K SE +/- 10755.01, N = 15 SE +/- 10643.51, N = 4 SE +/- 19682.88, N = 15 SE +/- 17861.91, N = 13 946634 954214 990608 886858 -O2 -O2 -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -O2 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
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: SqueezeNet Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 10K 20K 30K 40K 50K SE +/- 35.00, N = 3 SE +/- 510.23, N = 15 SE +/- 60.24, N = 3 SE +/- 31.53, N = 3 47808.3 48816.5 46761.2 47685.7
Zstd Compression This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19 - Decompression Speed Fedora Server 34 600 1200 1800 2400 3000 SE +/- 2.07, N = 7 2698.6 1. (CC) gcc options: -O3 -pthread -lz -llzma
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 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 20 40 60 80 100 SE +/- 0.26, N = 3 SE +/- 0.27, N = 3 SE +/- 0.12, N = 3 SE +/- 0.21, N = 3 108.31 109.07 102.25 108.27
oneDNN This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 150 300 450 600 750 SE +/- 1.73, N = 3 SE +/- 5.68, N = 8 SE +/- 2.16, N = 3 SE +/- 0.75, N = 3 672.65 671.56 660.05 677.86 MIN: 646.15 MIN: 639.68 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 626.35 -O2 - MIN: 653.3 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
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 HotSpot3D Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 20 40 60 80 100 SE +/- 0.57, N = 3 SE +/- 0.14, N = 3 SE +/- 0.11, N = 3 SE +/- 0.20, N = 3 105.65 104.32 104.28 104.77 1. (CXX) g++ options: -O2 -lOpenCL
oneDNN This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 8 16 24 32 40 SE +/- 0.28978, N = 15 SE +/- 0.49102, N = 15 SE +/- 0.09474, N = 15 SE +/- 0.34184, N = 12 28.75170 32.65000 9.79872 30.74980 MIN: 15.46 MIN: 9.3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 6.28 -O2 - MIN: 12.49 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
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 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 50K 100K 150K 200K 250K SE +/- 275.74, N = 3 SE +/- 252.80, N = 3 SE +/- 23.74, N = 3 SE +/- 276.88, N = 3 213870.87 214228.62 212303.58 212714.19 -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake 1. (CC) gcc options: -pthread -O2 -funroll-loops -rdynamic -ldl -laio -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: Pabellon Barcelona - Compute: CPU-Only Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 20 40 60 80 100 SE +/- 0.24, N = 3 SE +/- 0.21, N = 3 SE +/- 0.08, N = 3 SE +/- 0.12, N = 3 88.36 88.16 86.83 88.89
Zstd Compression This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 3 - Compression Speed Ubuntu 20.04.2 LTS Clear Linux 34630 Ubuntu 21.04 Fedora Server 34 1500 3000 4500 6000 7500 SE +/- 47.03, N = 3 SE +/- 48.29, N = 15 SE +/- 53.61, N = 3 SE +/- 54.04, N = 15 4576.8 7015.5 6148.4 6020.4 -llzma -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -llzma -llzma 1. (CC) gcc options: -O3 -pthread -lz
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 0.2.3 Target: CPU - Model: MobileNet v2 Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 100 200 300 400 500 SE +/- 9.40, N = 15 SE +/- 0.44, N = 3 SE +/- 0.15, N = 3 SE +/- 6.88, N = 15 443.55 374.20 354.30 401.86 -O3 - MIN: 367.81 / MAX: 808.75 -O3 - MIN: 371.48 / MAX: 419.18 -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 353.49 / MAX: 357.29 -O2 - MIN: 368.12 / MAX: 804.92 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -rdynamic -ldl
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 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 40M 80M 120M 160M 200M SE +/- 2129761.70, N = 15 SE +/- 1908422.73, N = 4 SE +/- 1887131.91, N = 3 SE +/- 1764312.05, N = 15 180493580 173250319 182083926 183504987 -pipe -fexceptions -fstack-protector -ffat-lto-objects -fno-trapping-math -mtune=skylake 1. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fprofile-use -fno-peel-loops -fno-tracer -pedantic -O3 -msse -msse3 -mpopcnt -mavx2 -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto=jobserver
oneDNN This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 100 200 300 400 500 SE +/- 0.96, N = 3 SE +/- 1.72, N = 3 SE +/- 1.50, N = 3 SE +/- 0.36, N = 3 437.97 433.43 433.80 440.63 MIN: 422.42 MIN: 414.41 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 414.44 -O2 - MIN: 424.84 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 100 200 300 400 500 SE +/- 0.63, N = 3 SE +/- 1.48, N = 3 SE +/- 1.15, N = 3 SE +/- 1.32, N = 3 437.87 431.30 434.95 442.35 MIN: 422.67 MIN: 414.55 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 417.43 -O2 - MIN: 425.26 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 100 200 300 400 500 SE +/- 0.53, N = 3 SE +/- 1.79, N = 3 SE +/- 2.18, N = 3 SE +/- 1.22, N = 3 439.68 433.74 433.43 442.70 MIN: 424.75 MIN: 416.67 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 414.35 -O2 - MIN: 423.41 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
Kvazaar This is a test of Kvazaar as a CPU-based H.265 video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 4K - Video Preset: Medium Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 4 8 12 16 20 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 6.90 6.93 17.80 6.95 -O2 -O2 -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -O2 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -lpthread -lm -lrt
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 Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 16 32 48 64 80 SE +/- 0.03, N = 3 SE +/- 0.10, N = 3 SE +/- 0.10, N = 3 SE +/- 0.69, N = 3 72.28 71.92 71.51 73.35
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 Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 150K 300K 450K 600K 750K SE +/- 7233.85, N = 5 SE +/- 2002.95, N = 3 SE +/- 6494.21, N = 3 SE +/- 3314.01, N = 3 687019 716517 665666 679005
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: vklBenchmarkVdbVolume Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 6M 12M 18M 24M 30M SE +/- 58341.71, N = 3 SE +/- 187763.97, N = 3 SE +/- 324102.01, N = 3 SE +/- 179975.75, N = 3 21915837 22077090 29605565 22243396 MIN: 1062215 / MAX: 153704880 MIN: 1030467 / MAX: 169859376 MIN: 1030715 / MAX: 177194520 MIN: 1023291 / MAX: 182220264
Tungsten Renderer Tungsten is a C++ physically based renderer that makes use of Intel's Embree ray tracing library. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Tungsten Renderer 0.2.2 Scene: Volumetric Caustic Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 4 8 12 16 20 SE +/- 0.44, N = 15 SE +/- 0.39, N = 15 SE +/- 0.48, N = 15 SE +/- 0.74, N = 12 13.45 13.87 13.87 13.09 -O3 -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz -O3 -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -O2 1. (CXX) g++ options: -std=c++0x -march=core2 -msse2 -msse3 -mssse3 -mno-sse4.1 -mno-sse4.2 -mno-sse4a -mno-avx -mno-fma -mno-bmi2 -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -rdynamic -ljpeg -lpthread -ldl
PJSIP PJSIP is a free and open source multimedia communication library written in C language implementing standard based protocols such as SIP, SDP, RTP, STUN, TURN, and ICE. It combines signaling protocol (SIP) with rich multimedia framework and NAT traversal functionality into high level API that is portable and suitable for almost any type of systems ranging from desktops, embedded systems, to mobile handsets. This test profile is making use of pjsip-perf with both the client/server on teh system. More details on the PJSIP benchmark at https://www.pjsip.org/high-performance-sip.htm Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Responses Per Second, More Is Better PJSIP 2.11 Method: OPTIONS, Stateful Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 2K 4K 6K 8K 10K SE +/- 6.89, N = 3 SE +/- 13.59, N = 3 SE +/- 1.53, N = 3 3815 3597 10360 3733 -lSDL2 -lavformat -lavcodec -lswscale -lavutil -lasound -O2 -lSDL2 -lavformat -lavcodec -lswscale -lavutil -lasound -O2 -lSDL2 -lopus -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -O2 1. (CC) gcc options: -lstdc++ -lssl -lcrypto -luuid -lm -lrt -lpthread
x265 This is a simple test of the x265 encoder run on the CPU with 1080p and 4K options for H.265 video encode performance with x265. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better x265 3.4 Video Input: Bosphorus 4K Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 7 14 21 28 35 SE +/- 0.09, N = 3 SE +/- 0.09, N = 3 SE +/- 0.40, N = 15 SE +/- 0.08, N = 3 12.92 12.58 29.05 11.65 -O3 -lnuma -O3 -lnuma -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -lnuma -O2 1. (CXX) g++ options: -rdynamic -lpthread -lrt -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 Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 120K 240K 360K 480K 600K SE +/- 790.57, N = 3 SE +/- 5213.69, N = 3 SE +/- 4180.58, N = 3 SE +/- 888.88, N = 3 569303 576988 572684 574742
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 Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 13 26 39 52 65 SE +/- 0.34, N = 3 SE +/- 0.34, N = 15 SE +/- 0.42, N = 3 SE +/- 0.29, N = 3 29.81 28.14 60.27 28.37 -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake 1. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
PJSIP PJSIP is a free and open source multimedia communication library written in C language implementing standard based protocols such as SIP, SDP, RTP, STUN, TURN, and ICE. It combines signaling protocol (SIP) with rich multimedia framework and NAT traversal functionality into high level API that is portable and suitable for almost any type of systems ranging from desktops, embedded systems, to mobile handsets. This test profile is making use of pjsip-perf with both the client/server on teh system. More details on the PJSIP benchmark at https://www.pjsip.org/high-performance-sip.htm Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Responses Per Second, More Is Better PJSIP 2.11 Method: OPTIONS, Stateless Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 9K 18K 27K 36K 45K SE +/- 533.56, N = 3 SE +/- 352.27, N = 3 SE +/- 270.37, N = 3 SE +/- 181.15, N = 3 40082 40954 43880 41983 -lSDL2 -lavformat -lavcodec -lswscale -lavutil -lasound -O2 -lSDL2 -lavformat -lavcodec -lswscale -lavutil -lasound -O2 -lSDL2 -lopus -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -O2 1. (CC) gcc options: -lstdc++ -lssl -lcrypto -luuid -lm -lrt -lpthread
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 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 4 8 12 16 20 SE +/- 0.19, N = 4 SE +/- 0.14, N = 15 SE +/- 0.03, N = 3 SE +/- 0.19, N = 15 15.38 15.50 10.24 16.08 1. (CXX) g++ options: -O3 -fPIC -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: Fishy Cat - Compute: CPU-Only Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 10 20 30 40 50 SE +/- 0.15, N = 3 SE +/- 0.17, N = 3 SE +/- 0.01, N = 3 SE +/- 0.08, N = 3 45.72 46.11 43.83 46.04
Zstd Compression This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 19 - Decompression Speed Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 600 1200 1800 2400 3000 SE +/- 12.48, N = 3 SE +/- 9.85, N = 3 SE +/- 4.09, N = 3 SE +/- 35.16, N = 3 2727.6 2740.7 2253.6 2781.7 -llzma -llzma -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -llzma 1. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 19 - Compression Speed Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 20 40 60 80 100 SE +/- 0.81, N = 3 SE +/- 0.68, N = 3 SE +/- 0.32, N = 3 SE +/- 0.72, N = 3 82.3 84.0 90.1 82.5 -llzma -llzma -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -llzma 1. (CC) gcc options: -O3 -pthread -lz
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 Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 3 6 9 12 15 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.04, N = 3 SE +/- 0.00, N = 3 10.42 10.42 10.60 10.42 MIN: 7.87 / MAX: 10.64 MIN: 7.94 / MAX: 10.53 MIN: 7.58 / MAX: 10.87 MIN: 7.81 / MAX: 10.53
Zstd Compression This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19, Long Mode - Decompression Speed Fedora Server 34 600 1200 1800 2400 3000 SE +/- 16.65, N = 3 2747.1 1. (CC) gcc options: -O3 -pthread -lz -llzma
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 LavaMD Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 9 18 27 36 45 SE +/- 0.15, N = 3 SE +/- 0.07, N = 3 SE +/- 0.46, N = 4 SE +/- 0.15, N = 3 40.41 39.52 38.69 41.48 1. (CXX) g++ options: -O2 -lOpenCL
oneDNN This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 0.6858 1.3716 2.0574 2.7432 3.429 SE +/- 0.02675, N = 12 SE +/- 0.03357, N = 3 SE +/- 0.00391, N = 3 SE +/- 0.02287, N = 14 3.03516 3.01186 2.98572 3.04815 MIN: 2.86 MIN: 2.84 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 2.85 -O2 - MIN: 2.87 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
Chia Blockchain VDF Chia is a blockchain and smart transaction platform based on proofs of space and time rather than proofs of work with other cryptocurrencies. This test profile is benchmarking the CPU performance for Chia VDF performance using the Chia VDF benchmark. The Chia VDF is for the Chia Verifiable Delay Function (Proof of Time). Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org IPS, More Is Better Chia Blockchain VDF 1.0.1 Test: Square Assembly Optimized Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 30K 60K 90K 120K 150K SE +/- 1568.63, N = 5 SE +/- 680.69, N = 3 SE +/- 240.37, N = 3 SE +/- 1369.10, N = 3 147240 143600 151167 148033 1. (CXX) g++ options: -flto -no-pie -lgmpxx -lgmp -lboost_system -pthread
Tungsten Renderer Tungsten is a C++ physically based renderer that makes use of Intel's Embree ray tracing library. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Tungsten Renderer 0.2.2 Scene: Water Caustic Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 8 16 24 32 40 SE +/- 0.27, N = 3 SE +/- 0.19, N = 3 SE +/- 0.04, N = 3 SE +/- 0.09, N = 3 31.27 32.48 18.17 31.45 -O3 -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz -O3 -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -O2 1. (CXX) g++ options: -std=c++0x -march=core2 -msse2 -msse3 -mssse3 -mno-sse4.1 -mno-sse4.2 -mno-sse4a -mno-avx -mno-fma -mno-bmi2 -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -rdynamic -ljpeg -lpthread -ldl
Kvazaar This is a test of Kvazaar as a CPU-based H.265 video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 4K - Video Preset: Very Fast Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 9 18 27 36 45 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.09, N = 3 SE +/- 0.03, N = 3 13.38 13.33 40.96 13.28 -O2 -O2 -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -O2 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -lpthread -lm -lrt
Coremark This is a test of EEMBC CoreMark processor benchmark. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Iterations/Sec, More Is Better Coremark 1.0 CoreMark Size 666 - Iterations Per Second Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 500K 1000K 1500K 2000K 2500K SE +/- 2872.35, N = 3 SE +/- 24473.66, N = 5 SE +/- 6737.83, N = 3 SE +/- 5456.02, N = 3 2347453.57 2261054.03 2452833.36 2391445.66 -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake 1. (CC) gcc options: -O2 -lrt" -lrt
Chia Blockchain VDF Chia is a blockchain and smart transaction platform based on proofs of space and time rather than proofs of work with other cryptocurrencies. This test profile is benchmarking the CPU performance for Chia VDF performance using the Chia VDF benchmark. The Chia VDF is for the Chia Verifiable Delay Function (Proof of Time). Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org IPS, More Is Better Chia Blockchain VDF 1.0.1 Test: Square Plain C++ Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 30K 60K 90K 120K 150K SE +/- 88.19, N = 3 SE +/- 585.95, N = 3 SE +/- 33.33, N = 3 SE +/- 589.73, N = 3 138967 139400 143567 131833 1. (CXX) g++ options: -flto -no-pie -lgmpxx -lgmp -lboost_system -pthread
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 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 9 18 27 36 45 SE +/- 0.47, N = 3 SE +/- 0.38, N = 3 SE +/- 0.11, N = 3 SE +/- 0.16, N = 3 36.76 38.52 27.25 36.68 1. (CXX) g++ options: -O3 -fPIC -lm
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 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 3K 6K 9K 12K 15K SE +/- 145.91, N = 15 SE +/- 138.52, N = 15 SE +/- 126.52, N = 3 SE +/- 101.00, N = 15 12176.80 12252.73 12670.82 12185.51 -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake 1. (CC) gcc options: -pthread -O2 -funroll-loops -rdynamic -ldl -laio -lm
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 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 0.0614 0.1228 0.1842 0.2456 0.307 SE +/- 0.00049, N = 3 SE +/- 0.00044, N = 3 SE +/- 0.00032, N = 3 SE +/- 0.00056, N = 3 0.27128 0.27083 0.27141 0.27274
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 Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 3 6 9 12 15 SE +/- 0.146, N = 15 SE +/- 0.118, N = 12 SE +/- 0.013, N = 3 SE +/- 0.100, N = 15 8.522 8.967 5.815 9.332 1. (CXX) g++ options: -O3 -fPIC -lm
Kvazaar This is a test of Kvazaar as a CPU-based H.265 video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 4K - Video Preset: Ultra Fast Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 11 22 33 44 55 SE +/- 0.11, N = 3 SE +/- 0.24, N = 3 SE +/- 0.34, N = 12 SE +/- 0.31, N = 3 22.78 23.16 46.98 23.20 -O2 -O2 -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -O2 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -lpthread -lm -lrt
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 Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 3 6 9 12 15 SE +/- 0.058, N = 3 SE +/- 0.033, N = 3 SE +/- 0.028, N = 3 SE +/- 0.014, N = 3 9.004 8.884 9.201 8.428 -O3 -O3 -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -O2 1. (CXX) g++ options: -pthread
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 Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 7 14 21 28 35 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.10, N = 3 SE +/- 0.15, N = 3 29.61 29.54 28.23 29.55
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 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 20 40 60 80 100 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 90.91 90.91 100.00 90.91 MIN: 55.56 / MAX: 100 MIN: 55.56 / MAX: 100 MIN: 52.63 / MAX: 111.11 MIN: 55.56 / MAX: 100
PHPBench PHPBench is a benchmark suite for PHP. It performs a large number of simple tests in order to bench various aspects of the PHP interpreter. PHPBench can be used to compare hardware, operating systems, PHP versions, PHP accelerators and caches, compiler options, etc. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Score, More Is Better PHPBench 0.8.1 PHP Benchmark Suite Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 200K 400K 600K 800K 1000K SE +/- 3328.66, N = 3 SE +/- 5472.66, N = 3 SE +/- 1642.74, N = 3 SE +/- 3881.00, N = 3 715587 726623 900184 721179
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 0.2.3 Target: CPU - Model: SqueezeNet v1.1 Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 80 160 240 320 400 SE +/- 0.08, N = 3 SE +/- 0.53, N = 3 SE +/- 0.04, N = 3 SE +/- 0.08, N = 3 366.73 367.80 364.99 366.37 -O3 - MIN: 365.95 / MAX: 373.2 -O3 - MIN: 367 / MAX: 370.11 -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 364.69 / MAX: 366.31 -O2 - MIN: 366.07 / MAX: 367.44 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -rdynamic -ldl
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 Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.00, N = 3 10.38 10.38 10.38 10.31 MIN: 7.58 / MAX: 10.75 MIN: 9.17 / MAX: 10.53 MIN: 8.13 / MAX: 10.75 MIN: 8.77 / MAX: 10.42
oneDNN This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 0.0521 0.1042 0.1563 0.2084 0.2605 SE +/- 0.002322, N = 6 SE +/- 0.001876, N = 8 SE +/- 0.001684, N = 3 SE +/- 0.002070, N = 7 0.231483 0.218363 0.216048 0.222234 MIN: 0.2 MIN: 0.19 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 0.19 -O2 - MIN: 0.19 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
PyBench This test profile reports the total time of the different average timed test results from PyBench. PyBench reports average test times for different functions such as BuiltinFunctionCalls and NestedForLoops, with this total result providing a rough estimate as to Python's average performance on a given system. This test profile runs PyBench each time for 20 rounds. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Milliseconds, Fewer Is Better PyBench 2018-02-16 Total For Average Test Times Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 200 400 600 800 1000 SE +/- 1.86, N = 3 SE +/- 0.88, N = 3 SE +/- 1.00, N = 3 SE +/- 0.58, N = 3 995 982 1015 1157
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 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 1.2062 2.4124 3.6186 4.8248 6.031 SE +/- 0.074, N = 15 SE +/- 0.099, N = 15 SE +/- 0.030, N = 15 SE +/- 0.070, N = 15 5.050 5.361 3.066 5.186 1. (CXX) g++ options: -O3 -fPIC -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: 1 - Input: Bosphorus 1080p Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 9 18 27 36 45 SE +/- 0.09, N = 3 SE +/- 0.33, N = 3 SE +/- 0.24, N = 3 SE +/- 0.31, N = 4 29.57 29.14 38.51 29.17 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
oneDNN This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 0.7821 1.5642 2.3463 3.1284 3.9105 SE +/- 0.00929, N = 3 SE +/- 0.00414, N = 3 SE +/- 0.00331, N = 3 SE +/- 0.01091, N = 3 3.27051 3.47588 3.22981 3.28960 MIN: 3.09 MIN: 3.31 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 3.02 -O2 - MIN: 3.12 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 0.0828 0.1656 0.2484 0.3312 0.414 SE +/- 0.004351, N = 3 SE +/- 0.003468, N = 3 SE +/- 0.001144, N = 3 SE +/- 0.004582, N = 3 0.362841 0.353757 0.361521 0.367996 MIN: 0.32 MIN: 0.31 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 0.32 -O2 - MIN: 0.32 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
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 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 40K 80K 120K 160K 200K SE +/- 419.66, N = 3 SE +/- 1295.33, N = 3 SE +/- 301.93, N = 3 SE +/- 204.64, N = 3 187807.08 189606.14 194386.02 44055.39 -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Ubuntu 21.04: Open MPI 4.1.0 3. Ubuntu 20.04.2 LTS: Open MPI 4.0.3 4. Clear Linux 34630: 3.2
Liquid-DSP LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 160 - Buffer Length: 256 - Filter Length: 57 Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 800M 1600M 2400M 3200M 4000M SE +/- 15087448.79, N = 3 SE +/- 11545032.60, N = 3 SE +/- 13074699.91, N = 3 SE +/- 13741098.13, N = 3 3080633333 3106666667 3843066667 3101166667 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 128 - Buffer Length: 256 - Filter Length: 57 Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 900M 1800M 2700M 3600M 4500M SE +/- 9583724.63, N = 3 SE +/- 8772368.23, N = 3 SE +/- 36096414.10, N = 3 SE +/- 6501025.56, N = 3 3290766667 3316633333 3970066667 3302800000 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 32 - Buffer Length: 256 - Filter Length: 57 Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 400M 800M 1200M 1600M 2000M SE +/- 768837.51, N = 3 SE +/- 5634516.64, N = 3 SE +/- 16877598.57, N = 3 SE +/- 2608320.02, N = 3 1631166667 1653866667 1973100000 1632900000 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 16 - Buffer Length: 256 - Filter Length: 57 Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 200M 400M 600M 800M 1000M SE +/- 702242.44, N = 3 SE +/- 5004752.19, N = 3 SE +/- 2729061.70, N = 3 SE +/- 1422279.08, N = 3 826756667 832983333 999833333 827833333 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
x265 This is a simple test of the x265 encoder run on the CPU with 1080p and 4K options for H.265 video encode performance with x265. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better x265 3.4 Video Input: Bosphorus 1080p Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 20 40 60 80 100 SE +/- 0.34, N = 3 SE +/- 0.25, N = 3 SE +/- 0.59, N = 3 SE +/- 0.15, N = 3 28.33 28.50 78.42 26.25 -O3 -lnuma -O3 -lnuma -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -lnuma -O2 1. (CXX) g++ options: -rdynamic -lpthread -lrt -ldl
oneDNN This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 0.4144 0.8288 1.2432 1.6576 2.072 SE +/- 0.01169, N = 14 SE +/- 0.00660, N = 3 SE +/- 0.00330, N = 3 SE +/- 0.01185, N = 3 1.82051 1.80328 1.74481 1.84199 MIN: 1.67 MIN: 1.67 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 1.61 -O2 - MIN: 1.69 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 0.2155 0.431 0.6465 0.862 1.0775 SE +/- 0.010679, N = 4 SE +/- 0.011491, N = 3 SE +/- 0.004580, N = 3 SE +/- 0.011811, N = 3 0.945450 0.942653 0.921930 0.957911 MIN: 0.86 MIN: 0.85 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 0.84 -O2 - MIN: 0.87 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
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: SciVis Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 5 10 15 20 25 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 18.87 18.87 18.87 18.87 MIN: 13.33 / MAX: 19.23 MIN: 12.82 / MAX: 19.23 MIN: 13.16 / MAX: 19.61 MIN: 12.05 / MAX: 19.23
Tungsten Renderer Tungsten is a C++ physically based renderer that makes use of Intel's Embree ray tracing library. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Tungsten Renderer 0.2.2 Scene: Hair Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 2 4 6 8 10 SE +/- 0.07388, N = 3 SE +/- 0.08029, N = 15 SE +/- 0.02021, N = 3 SE +/- 0.09718, N = 4 6.52538 6.45646 5.62201 8.74867 -O3 -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz -O3 -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -O2 1. (CXX) g++ options: -std=c++0x -march=core2 -msse2 -msse3 -mssse3 -mno-sse4.1 -mno-sse4.2 -mno-sse4a -mno-avx -mno-fma -mno-bmi2 -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -rdynamic -ljpeg -lpthread -ldl
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: SciVis Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 30 60 90 120 150 SE +/- 1.01, N = 15 SE +/- 0.93, N = 12 SE +/- 0.00, N = 3 SE +/- 1.01, N = 15 109.63 110.19 125.00 109.63 MIN: 20.83 / MAX: 125 MIN: 21.74 / MAX: 111.11 MIN: 90.91 MIN: 20 / MAX: 111.11
POV-Ray This is a test of POV-Ray, the Persistence of Vision Raytracer. POV-Ray is used to create 3D graphics using ray-tracing. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better POV-Ray 3.7.0.7 Trace Time Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 3 6 9 12 15 SE +/- 0.097, N = 5 SE +/- 0.084, N = 3 SE +/- 0.016, N = 3 SE +/- 0.090, N = 3 9.476 9.451 8.952 9.089 -lSM -lICE -lIlmImf -lIlmImf-2_5 -lImath-2_5 -lHalf-2_5 -lIex-2_5 -lIexMath-2_5 -lIlmThread-2_5 -lIlmThread -lSM -lICE -lIlmImf -lImath -lHalf -lIex -lIexMath -lIlmThread -lpthread -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -R/usr/lib -lSDL -lpthread -lSM -lICE -R/usr/lib 1. (CXX) g++ options: -pipe -O3 -ffast-math -march=native -pthread -lX11 -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system
oneDNN This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 0.0577 0.1154 0.1731 0.2308 0.2885 SE +/- 0.002948, N = 3 SE +/- 0.003241, N = 3 SE +/- 0.001913, N = 3 SE +/- 0.003140, N = 4 0.256555 0.249170 0.247725 0.254526 MIN: 0.23 MIN: 0.22 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 0.22 -O2 - MIN: 0.23 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
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 - Model: Asian Dragon Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 20 40 60 80 100 SE +/- 0.58, N = 3 SE +/- 0.68, N = 9 SE +/- 1.14, N = 3 SE +/- 0.76, N = 3 81.29 82.61 84.13 81.50 MIN: 67.06 / MAX: 91.79 MIN: 67 / MAX: 93.51 MIN: 68.3 / MAX: 93.51 MIN: 65.61 / MAX: 92.76
OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Asian Dragon Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 20 40 60 80 100 SE +/- 0.84, N = 10 SE +/- 0.91, N = 3 SE +/- 1.45, N = 3 SE +/- 1.03, N = 6 106.69 106.14 107.77 106.05 MIN: 85.33 / MAX: 112.78 MIN: 84.21 / MAX: 111.87 MIN: 85.87 / MAX: 112.96 MIN: 82.33 / MAX: 111.97
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 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 11.33 11.71 11.16 12.58 -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
oneDNN This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 0.1384 0.2768 0.4152 0.5536 0.692 SE +/- 0.004554, N = 3 SE +/- 0.002882, N = 3 SE +/- 0.001093, N = 3 SE +/- 0.006364, N = 3 0.615331 0.602936 0.614468 0.612234 MIN: 0.57 MIN: 0.56 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 0.56 -O2 - MIN: 0.56 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 0.0458 0.0916 0.1374 0.1832 0.229 SE +/- 0.001836, N = 13 SE +/- 0.001679, N = 14 SE +/- 0.000520, N = 3 SE +/- 0.001612, N = 15 0.193198 0.190921 0.188906 0.203496 MIN: 0.18 MIN: 0.18 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 0.18 -O2 - MIN: 0.18 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
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 Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 100 200 300 400 500 SE +/- 2.00, N = 15 SE +/- 1.73, N = 3 SE +/- 2.91, N = 3 SE +/- 2.71, N = 3 204.86 196.97 456.47 195.55 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -O2 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
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 Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 16 32 48 64 80 SE +/- 0.30, N = 3 SE +/- 0.70, N = 3 SE +/- 0.68, N = 3 SE +/- 0.40, N = 3 67.04 66.89 73.84 64.66 MIN: 59.72 / MAX: 87.99 MIN: 59.4 / MAX: 88.24 MIN: 64.62 / MAX: 94.03 MIN: 58.41 / MAX: 86.67
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 Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 7 14 21 28 35 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 27.78 27.78 28.57 27.78 MIN: 17.24 / MAX: 29.41 MIN: 16.67 / MAX: 29.41 MIN: 18.87 / MAX: 30.3 MIN: 16.39 / MAX: 29.41
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: EP.C Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 1300 2600 3900 5200 6500 SE +/- 51.84, N = 15 SE +/- 81.23, N = 15 SE +/- 165.45, N = 12 SE +/- 13.65, N = 3 6259.88 6011.42 5425.40 2213.51 -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Ubuntu 21.04: Open MPI 4.1.0 3. Ubuntu 20.04.2 LTS: Open MPI 4.0.3 4. Clear Linux 34630: 3.2
oneDNN This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 0.3403 0.6806 1.0209 1.3612 1.7015 SE +/- 0.01131, N = 3 SE +/- 0.01216, N = 3 SE +/- 0.00192, N = 3 SE +/- 0.00594, N = 3 1.37903 1.37432 1.35679 1.51260 MIN: 1.33 MIN: 1.32 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 1.31 -O2 - MIN: 1.46 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -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 Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 70 140 210 280 350 SE +/- 1.72, N = 3 SE +/- 1.68, N = 3 SE +/- 2.34, N = 15 SE +/- 1.49, N = 3 172.02 157.78 315.80 159.70 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 10 - Input: Bosphorus 1080p Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 130 260 390 520 650 SE +/- 2.49, N = 3 SE +/- 1.73, N = 3 SE +/- 5.64, N = 3 SE +/- 1.79, N = 15 260.88 234.92 592.99 240.54 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
oneDNN This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 0.4233 0.8466 1.2699 1.6932 2.1165 SE +/- 0.00589, N = 3 SE +/- 0.00638, N = 3 SE +/- 0.01755, N = 3 SE +/- 0.01180, N = 3 1.41084 1.39626 1.58077 1.88136 MIN: 1.27 MIN: 1.26 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 1.38 -O2 - MIN: 1.72 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 0.4751 0.9502 1.4253 1.9004 2.3755 SE +/- 0.01823, N = 3 SE +/- 0.01729, N = 3 SE +/- 0.00152, N = 3 SE +/- 0.01824, N = 3 2.10597 2.10694 2.08771 2.11134 MIN: 2.03 MIN: 2.03 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 2.03 -O2 - MIN: 2.03 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 0.194 0.388 0.582 0.776 0.97 SE +/- 0.008374, N = 6 SE +/- 0.008602, N = 6 SE +/- 0.000743, N = 3 SE +/- 0.008032, N = 6 0.846330 0.850400 0.862061 0.854642 MIN: 0.8 MIN: 0.8 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 0.81 -O2 - MIN: 0.8 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
LAMMPS Molecular Dynamics Simulator LAMMPS is a classical molecular dynamics code, and an acronym for Large-scale Atomic/Molecular Massively Parallel Simulator. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ns/day, More Is Better LAMMPS Molecular Dynamics Simulator 29Oct2020 Model: Rhodopsin Protein Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 7 14 21 28 35 SE +/- 0.02, N = 3 SE +/- 0.64, N = 12 SE +/- 0.47, N = 15 SE +/- 0.30, N = 4 23.87 22.08 31.15 27.21 -O3 -O3 -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -O2 1. (CXX) g++ options: -pthread -lm
Tungsten Renderer Tungsten is a C++ physically based renderer that makes use of Intel's Embree ray tracing library. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Tungsten Renderer 0.2.2 Scene: Non-Exponential Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 1.1896 2.3792 3.5688 4.7584 5.948 SE +/- 0.07466, N = 3 SE +/- 0.02249, N = 3 SE +/- 0.00072, N = 3 SE +/- 0.00702, N = 3 5.23912 5.16631 2.40790 5.28732 -O3 -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz -O3 -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -O2 1. (CXX) g++ options: -std=c++0x -march=core2 -msse2 -msse3 -mssse3 -mno-sse4.1 -mno-sse4.2 -mno-sse4a -mno-avx -mno-fma -mno-bmi2 -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -rdynamic -ljpeg -lpthread -ldl
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 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 30 60 90 120 150 SE +/- 0.00, N = 3 125.00 125.00 142.86 125.00 MIN: 31.25 / MAX: 142.86 MIN: 33.33 / MAX: 142.86 MIN: 41.67 MIN: 32.26 / MAX: 142.86
BlogBench BlogBench is designed to replicate the load of a real-world busy file server by stressing the file-system with multiple threads of random reads, writes, and rewrites. The behavior is mimicked of that of a blog by creating blogs with content and pictures, modifying blog posts, adding comments to these blogs, and then reading the content of the blogs. All of these blogs generated are created locally with fake content and pictures. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Final Score, More Is Better BlogBench 1.1 Test: Write Ubuntu 21.04 Ubuntu 20.04.2 LTS Clear Linux 34630 Fedora Server 34 14K 28K 42K 56K 70K SE +/- 717.36, N = 3 SE +/- 770.50, N = 3 SE +/- 74.61, N = 3 SE +/- 835.62, N = 3 60768 63062 56009 52018 -O2 -O2 -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -O2 1. (CC) gcc options: -pthread
Ubuntu 21.04 Processor: 2 x Intel Xeon Platinum 8380 @ 3.40GHz (80 Cores / 160 Threads), Motherboard: Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS), Chipset: Intel Device 0998, Memory: 504GB, Disk: 800GB INTEL SSDPF21Q800GB, Graphics: ASPEED, Monitor: VE228, Network: 2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP
OS: Ubuntu 21.04, Kernel: 5.11.0-17-generic (x86_64), Desktop: GNOME Shell 3.38.4, Display Server: X Server, 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 -vDisk Notes: NONE / errors=remount-ro,relatime,rw / Block Size: 4096Processor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd000270Java Notes: OpenJDK Runtime Environment (build 11.0.11+9-Ubuntu-0ubuntu2)Python Notes: Python 3.9.4Security 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 Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 13 May 2021 20:13 by user phoronix.
Ubuntu 20.04.2 LTS Processor: 2 x Intel Xeon Platinum 8380 @ 3.40GHz (80 Cores / 160 Threads), Motherboard: Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS), Chipset: Intel Device 0998, Memory: 504GB, Disk: 800GB INTEL SSDPF21Q800GB, Graphics: ASPEED, Monitor: VE228, Network: 2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP
OS: Ubuntu 20.04, Kernel: 5.8.0-53-generic (x86_64), Desktop: GNOME Shell 3.36.7, Display Server: X Server 1.20.9, 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 -vDisk Notes: NONE / errors=remount-ro,relatime,rw / Block Size: 4096Processor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd000270Java Notes: OpenJDK Runtime Environment (build 11.0.11+9-Ubuntu-0ubuntu2.20.04)Python 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 Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 17 May 2021 12:06 by user phoronix.
Clear Linux 34630 Processor: 2 x Intel Xeon Platinum 8380 @ 3.40GHz (80 Cores / 160 Threads), Motherboard: Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS), Chipset: Intel Device 0998, Memory: 504GB, Disk: 800GB INTEL SSDPF21Q800GB, Graphics: ASPEED, Monitor: VE228, Network: 2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP
OS: Clear Linux OS 34630, Kernel: 5.10.19-1032.native (x86_64), Desktop: GNOME Shell 40.0, Display Server: X Server, Compiler: GCC 11.1.1 20210517 releases/gcc-11.1.0-132-g7d91dd2efb + Clang 11.1.0 + LLVM 11.1.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: alwaysEnvironment Notes: FFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -fstack-protector --param=ssp-buffer-size=32 -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z -Wl,now -Wl,-z -Wl,relro -malign-data=abi -fno-semantic-interposition -ftree-vectorize -ftree-loop-vectorize -Wl,--enable-new-dtags -Wa,-mbranches-within-32B-boundaries" CXXFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -fstack-protector --param=ssp-buffer-size=32 -Wformat -Wformat-security -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z -Wl,now -Wl,-z -Wl,relro -fno-semantic-interposition -ffat-lto-objects -fno-trapping-math -Wl,-sort-common -Wl,--enable-new-dtags -mtune=skylake -Wa,-mbranches-within-32B-boundaries -fvisibility-inlines-hidden -Wl,--enable-new-dtags" FCFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -fstack-protector --param=ssp-buffer-size=32 -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z -Wl,now -Wl,-z -Wl,relro -malign-data=abi -fno-semantic-interposition -ftree-vectorize -ftree-loop-vectorize -Wl,-sort-common -Wl,--enable-new-dtags" CFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -fstack-protector --param=ssp-buffer-size=32 -Wformat -Wformat-security -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z -Wl,now -Wl,-z -Wl,relro -fno-semantic-interposition -ffat-lto-objects -fno-trapping-math -Wl,-sort-common -Wl,--enable-new-dtags -mtune=skylake -Wa,-mbranches-within-32B-boundaries" THEANO_FLAGS="floatX=float32,openmp=true,gcc.cxxflags="-ftree-vectorize -mavx""Compiler Notes: --build=x86_64-generic-linux --disable-libmpx --disable-libunwind-exceptions --disable-multiarch --disable-vtable-verify --disable-werror --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-clocale=gnu --enable-default-pie --enable-gnu-indirect-function --enable-languages=c,c++,fortran,go --enable-ld=default --enable-libstdcxx-pch --enable-lto --enable-multilib --enable-plugin --enable-shared --enable-threads=posix --exec-prefix=/usr --includedir=/usr/include --target=x86_64-generic-linux --with-arch=westmere --with-gcc-major-version-only --with-glibc-version=2.19 --with-gnu-ld --with-isl --with-ppl=yes --with-tune=skylake-avx512Disk Notes: MQ-DEADLINE / relatime,rw,stripe=256 / Block Size: 4096Processor Notes: Scaling Governor: intel_pstate performance - CPU Microcode: 0xd000270Java Notes: OpenJDK Runtime Environment (build 1.8.0-u252-ga-b00)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 Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 18 May 2021 22:01 by user phoronix.
Fedora Server 34 Processor: 2 x Intel Xeon Platinum 8380 @ 3.40GHz (80 Cores / 160 Threads), Motherboard: Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS), Chipset: Intel Device 0998, Memory: 504GB, Disk: 800GB INTEL SSDPF21Q800GB, Graphics: ASPEED, Monitor: VE228, Network: 2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP
OS: Fedora 34, Kernel: 5.11.20-300.fc34.x86_64 (x86_64), Compiler: GCC 11.1.1 20210428, 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-driverDisk Notes: NONE / attr2,inode64,logbsize=32k,logbufs=8,noquota,relatime,rw,seclabel / Block Size: 4096Processor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd000270Java Notes: OpenJDK Runtime Environment 18.9 (build 11.0.11+9)Python 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 Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 19 May 2021 07:16 by user .